Claims:We claim:
1. A method for controlling lime quality in real-time during lime calcination process, the method comprising:
receiving, by a lime quality control system 107 associated with each of one or more Parallel Flow Regenerative (PFR) kilns 101, data 105 from one or more computing units 103 corresponding to the one or more PFR kilns 101, wherein the data 105 is of one or more process parameters 2071 associated with lime calcination process, in the one or more PFR kilns 101;
predicting, using a predictive model 215 of the lime quality control system 107, a first lime quality value 2072 for each of the one or more PFR kilns 101 based on the received data 105 at a first predetermined time 2073;
determining, by the lime quality control system 107, a correction factor 2074 for each of the one or more PFR kilns 101 based on the predicted first lime quality value 2072 and an output indicative of actual lime quality value 2075 from each of the one or more PFR kilns 101;
predicting, using a prescriptive model 219 of the lime quality control system 107, a second lime quality value 2076, at a second predetermined time 2077, for each of the one or more PFR kilns 101 for current data associated with the one or more process parameters 2071 of the lime calcination process in the one or more PFR kilns 101 using the correction factor 2074; and
recommending, by the lime quality control system 107, one or more corrective actions 109 for each of the one or more PFR kilns 101 after the second predetermined time 2077 on a display interface 111 of the lime quality control system 107, based on the second lime quality value 2076 predicted for each of the one or more PFR kilns 101, wherein the one or more corrective actions 109 are adopted for controlling the lime quality of each of the one or more PFR kilns 101.

2. The method as claimed in claim 1, wherein the one or more corrective actions 109 correspond to varying the one or more process parameters 2071 of each of the one or more PFR kilns 101.

3. The method as claimed in claim 1, wherein the data 105 is obtained at predefined time intervals from the one or more computing units 103 corresponding to the one or more PFR kilns 101.

4. The method as claimed in claim 1, wherein each of the first lime quality value 2072 and the second lime quality value 2076 are percentage composition of Calcium Oxide (CaO) from each of the one or more PFR kilns 101.

5. The method as claimed in claim 1, wherein the first predetermined time 2073 corresponds to a time instant when burnt lime enters into a cooling zone 229 in the lime calcination process.

6. The method as claimed in claim 1, wherein the predictive model 215 implements Multiple Linear Regression (MLR) technique for predicting the first lime quality value 2072.

7. The method as claimed in claim 1, wherein the process parameters 2071 of the one or more PFR kilns 101 comprises time tagged heat input to the PFR kiln 101, gas flow in the PFR kiln 101, percentage of excess air in the PFR kiln 101, waste gas temperature inside the PFR kiln 101, pyrometric kiln temperature, and pressure inside the PFR kiln 101.

8. The method as claimed in claim 1, wherein the one or more corrective actions 109 for each of the one or more PFR kilns 101 are displayed on the display interface 111 of the lime quality control system 107 for facilitating an operator 113 of the lime quality control system 107 for performing the one or more corrective actions 109.

9. The method as claimed in claim 1, wherein the correction factor 2074 is sum of weighted difference between the predicted first lime quality value 2072 and the output indicative of the actual lime quality value 2075 from each of the one or more PFR kilns 101.

10. The method as claimed in claim 1, wherein the second predetermined time 2077 corresponds to a time instant when limestone (CaCO3) is in a burning zone 227 in the lime calcination process.
11. The method as claimed in claim 1, wherein predicting the second lime quality value 2076 comprises:
obtaining the current data associated with the one or more process parameters 2071 of lime calcination process when limestone (CaCO3) is in a preheating zone 225 and burning zone 227 in the lime calcination process;
associating the current data of the one or more process parameters 2071 with corresponding predefined regression coefficients 2078; and
determining the second lime quality value 2076 by combining the current data associated with the one or more process parameters 2071 with the corresponding predefined regression coefficients 2078.

12. A lime quality control system 107 for controlling lime quality in real-time during lime calcination process, the lime quality control system 107 comprises:
a display interface 111;
a predictive model 215;
a prescriptive model 219;
one or more processors 203; and
one or more memory devices communicatively coupled to the one or more processors 203, wherein the one or more memory devices store the processor-executable instructions, which, on execution, cause the one or more processors 203 to:
receive data 105 from one or more computing units 103 corresponding to one or more Parallel Flow Regenerative (PFR) kilns 101, wherein the data 105 is of one or more process parameters 2071 associated with lime calcination process, in the one or more PFR kilns 101;
predict using the predictive model 215, a first lime quality value 2072 for each of the one or more PFR kilns 101 based on the received data 105 at a first predetermined time 2073;
determine a correction factor 2074 for each of the one or more PFR kilns 101 based on the predicted first lime quality value 2072 and an output indicative of actual lime quality value 2075 from each of the one or more PFR kilns 101;
predict using the prescriptive model 219, a second lime quality value 2076, at a second predetermined time 2077, for each of the one or more PFR kilns 101 for current data associated with the one or more process parameters 2071 of the lime calcination process in the one or more PFR kilns 101 using the correction factor 2074; and
recommend one or more corrective actions 109 for each of the one or more PFR kilns 101 after the second predetermined time 2077 on the display interface 111, based on the second lime quality value 2076 predicted for each of the one or more PFR kilns 101, wherein the one or more corrective actions 109 are adopted for controlling the lime quality of each of the one or more PFR kilns 101.
13. The lime quality control system 107 as claimed in claim 12, wherein the one or more corrective actions 109 correspond to varying the one or more process parameters 2071 of each of the one or more PFR kilns 101.

14. The lime quality control system 107 as claimed in claim 12, wherein the one or more processors 203 are configured to obtain the data 105 at predefined time intervals from the one or more computing units 103 corresponding to the one or more PFR kilns 101.

15. The lime quality control system 107 as claimed in claim 12, wherein each of the first lime quality value 2072 and the second lime quality value 2076 are percentage composition of Calcium Oxide (CaO) from each of the one or more PFR kilns 101.

16. The lime quality control system 107 as claimed in claim 12, wherein the first predetermined time 2073 corresponds to a time instant when burnt lime enters into a cooling zone 229 in the lime calcination process.

17. The lime quality control system 107 as claimed in claim 12, wherein the predictive model 215 implements Multiple Linear Regression (MLR) technique for predicting the first lime quality value 2072.

18. The lime quality control system 107 as claimed in claim 12, wherein the process parameters 2071 of the one or more PFR kilns 101 comprises time tagged heat input to the PFR kiln 101, gas flow in the PFR kiln 101, percentage of excess air in the PFR kiln 101, waste gas temperature inside the PFR kiln 101, pyrometric kiln temperature, and pressure inside the PFR kiln 101.

19. The lime quality control system 107 as claimed in claim 12, wherein the one or more processors 203 are configured to display the one or more corrective actions 109 for each of the one or more PFR kilns 101 on the display interface 111 for facilitating an operator 113 of the lime quality control system 107 for performing the one or more corrective actions 109.

20. The lime quality control system 107 as claimed in claim 12, wherein the correction factor 2074 is sum of weighted difference between the predicted first lime quality value 2072 and the output indicative of the actual lime quality value 2075 from each of the one or more PFR kilns 101.

21. The lime quality control system 107 as claimed in claim 12, wherein the second predetermined time 2077 corresponds to a time instant when limestone (CaCO3) is in a burning zone 227 in the lime calcination process.

22. The lime quality control system 107 as claimed in claim 12, wherein the one or more processors 203 are configured to:
obtain the current data of the one or more process parameters 2071 associated with the lime calcination process when limestone (CaCO3) is in a preheating zone 225 and burning zone 227 in the lime calcination process;
associate the current data of the one or more process parameters 2071 with corresponding predefined regression coefficients 2078; and
determine the second lime quality value 2076 by combining the current data associated with the one or more process parameters 2071 with the corresponding predefined regression coefficients 2078.
, Description:TECHNICAL FIELD
The present subject matter is generally related to lime quality control through process automation and more particularly, but not exclusively, to a method and system for controlling lime quality in real-time during lime calcination process.
BACKGROUND
In steel production industries, lime is added for removal of silica and phosphorus, after performing oxygen blow. More particularly, in basic oxygen furnace of the steel production industries, the lime reacts with impurities primarily silica and phosphorus to form a slag, which is later removed. Here, quality of steel produced is significantly affected by quality of lime produced during lime calcination process of steel making process. Hence, obtaining good quality of lime with higher composition of Calcium Oxide (CaO) is desirable.
Generally, lime calcination process takes almost 24 hours’ time duration to produce quicklime from the raw limestone. During the lime calcination process, the raw limestones/Calcium Carbonate (CaCO3) are heated up to a dissociation temperature in Parallel Flow Regenerative (PFR) kilns for decomposition into the quicklime as follows:
CaCO3 + 42.5 kcal of heat = CaO + CO2 (?)
Conventionally, for quality testing of the quicklime, sample of the quicklime produced from the PFR kilns is sent to a laboratory for determining percentage composition of CaO in the sample. Thus, conventional lime quality testing requires at least 24 hours of duration for determining percentage composition of CaO in the lime from the PFR kilns. As a result, it becomes time consuming for an operator to determine subsequent corrective actions to be performed for modifying process parameters of the PFR kilns to control future lime quality of the PFR kilns. In scenarios, where multiple PFR kilns are in operation and quality of lime produced from each of the PFR kilns are different, the operator adjusts process parameters of each of the PFR kilns to attain a desirable lime quality. This becomes cumbersome if the number of PFR kilns is large, which in turn limits taking prompt decisions by the operator. In scenarios, where the quicklime produced has a lower percentage composition of CaO due to an abnormal operating regime, the quality of steel produced gets deteriorated and may not be utilised for intended purpose. This results in wasteful utilization of resources and cost ineffective.

The information disclosed in this background of the disclosure section is only for enhancement of understanding of the general background of the invention and should not be taken as an acknowledgement or any form of suggestion that this information forms the prior art already known to a person skilled in the art.

SUMMARY

Disclosed herein is a method for controlling lime quality in real-time during lime calcination process. The method comprises receiving, by a lime quality control system associated with each of one or more Parallel Flow Regenerative (PFR) kilns, data from one or more computing units corresponding to one or more PFR kilns. Here, the data is of one or more process parameters associated with lime calcination process, in the one or more PFR kilns. Further, the method comprises predicting, using a predictive model of the lime quality control system, a first lime quality value for each of the one or more PFR kilns based on the received data at a first predetermined time. Thereafter, the method comprises determining, by the lime quality control system, a correction factor for each of the one or more PFR kilns based on the predicted first lime quality value and an output indicative of actual lime quality value from each of the one or more PFR kilns. Further, the method comprises predicting, using a prescriptive model of the lime quality control system, a second lime quality value, at a second predetermined time, for each of the one or more PFR kilns for current data associated with the one or more process parameters of the lime calcination process in the one or more PFR kilns using the correction factor. Thereafter, the method comprises recommending, by the lime quality control system, one or more corrective actions for each of the one or more PFR kilns after the second predetermined time on a display interface of the lime quality control system, based on the second lime quality value predicted for each of the one or more PFR kilns. Here, the one or more corrective actions are adopted for controlling the lime quality of each of the one or more PFR kilns.

Further, the present disclosure discloses a lime quality control system for controlling lime quality in real-time during lime calcination process. The lime quality control system comprises a display interface, a predictive model, a prescriptive model, one or more processors, and one or more memory devices communicatively coupled to the one or more processors. The one or more processors receive data from one or more computing units corresponding to one or more Parallel Flow Regenerative (PFR) kilns. Here, the data is of one or more process parameters associated with lime calcination process, in the one or more PFR kilns. Based on the received data at a first predetermined time, the one or more processors predict a first lime quality value for each of the one or more PFR kilns at a first predetermined time using the predictive model. Further, based on the predicted first lime quality value and an output indicative of actual lime quality value from each of the one or more PFR kilns, the one or more processors determine a correction factor for each of the one or more PFR kilns. Using the correction factor, the one or more processors predict a second lime quality value, at a second predetermined time, for each of the one or more PFR kilns for current data associated with the one or more process parameters of the lime calcination process in the one or more PFR kilns, using the prescriptive model. Thereafter, the one or more processors recommend one or more corrective actions for each of the one or more PFR kilns after the second predetermined time on the display interface, based on the second lime quality value predicted for each of the one or more PFR kilns. Here, the one or more corrective actions are adopted for controlling the lime quality of each of the one or more PFR kilns.

The foregoing summary is illustrative only and is not intended to be in any way limiting. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features will become apparent by reference to the drawings and the following detailed description.

BRIEF DESCRIPTION OF THE ACCOMPANYING DRAWINGS
The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate exemplary embodiments and, together with the description, explain the disclosed principles. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. The same numbers are used throughout the figures to reference like features and components. Some embodiments of system and/or methods in accordance with embodiments of the present subject matter are now described, by way of example only, and regarding the accompanying figures, in which:

Fig.1 shows exemplary architecture for controlling lime quality in real-time during lime calcination process in accordance with some embodiments of the present disclosure.

Fig.2a shows a block diagram of a lime quality control system in accordance with some embodiments of the present disclosure.
Fig.2b shows working of a predictive model and a prescriptive model of a control module in a lime quality control system in accordance with some embodiments of the present disclosure.

Fig.2c shows an exemplary display interface of a lime quality control system in accordance with some embodiments of the present disclosure.

Fig.3 shows a flowchart illustrating method for controlling lime quality in real-time during lime calcination process in accordance with some embodiments of the present disclosure.
Fig.4 shows a block diagram of an exemplary computer system for implementing embodiments consistent with the present disclosure.
It should be appreciated by those skilled in the art that any block diagrams herein represent conceptual views of illustrative systems embodying the principles of the present subject matter. Similarly, it will be appreciated that any flow charts, flow diagrams, state transition diagrams, pseudo code, and the like represent various processes which may be substantially represented in computer readable medium and executed by a computer or processor, whether such computer or processor is explicitly shown.

DETAILED DESCRIPTION
In the present document, the word "exemplary" is used herein to mean "serving as an example, instance, or illustration." Any embodiment or implementation of the present subject matter described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.
While the disclosure is susceptible to various modifications and alternative forms, specific embodiment thereof has been shown by way of example in the drawings and will be described in detail below. It should be understood, however that it is not intended to limit the disclosure to the specific forms disclosed, but on the contrary, the disclosure is to cover all modifications, equivalents, and alternative falling within the scope of the disclosure.
The terms “comprises”, “comprising”, “includes”, “including” or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a setup, device, or method that comprises a list of components or steps does not include only those components or steps but may include other components or steps not expressly listed or inherent to such setup or device or method. In other words, one or more elements in a system or apparatus proceeded by “comprises… a” does not, without more constraints, preclude the existence of other elements or additional elements in the system or method.
The present disclosure relates to a method and a system for controlling lime quality in real-time during lime calcination process. During steel making process, one or more Parallel Flow Regenerative (PFR) kilns may be used for the lime calcination process. In each of the one or more PFR kilns, limestone may be processed sequentially at a pre-heating zone, a burning zone and a cooling zone of the PFR kiln. Each of the one or more PFR kilns may be communicatively coupled with corresponding one or more computing units, which may monitor one or more process parameters associated with each of the one or more PFR kilns at various time instants. The one or more process parameters may be measured through corresponding one or more industrial sensors configured in the one or more PFR kilns. Thereafter, time-tagging may be performed on the monitored one or more process parameters by the one or more computing units. Here, the time tagging may correspond to monitoring the one or more process parameters at different time intervals and associating the one or more process parameters with corresponding time instants. The time tagged one or more process parameters may constitute data associated with the lime calcination process for each of the one or more PFR kilns. Further, the data may be sent from the one or more computing units to a lime quality control system for further processing.

The data may be obtained by the lime quality control system at predefined time intervals from the one or more computing units corresponding to the one or more PFR kilns. Further, the lime quality control system may predict a first lime quality value at a first predetermined time for each of the one or more PFR kilns. The first predetermined time may correspond to a time instant when burnt lime enters into a cooling zone in the lime calcination process. Here, the lime quality control system may use a predictive model, for predicting the first lime quality value. The predictive model may implement for example, Multiple Linear Regression (MLR) technique for predicting the first lime quality value. The predictive model may predict the first lime quality values for the one or more PFR kilns based on the received data that may comprise time tagged heat inputs to the PFR kilns, amount of gas flows in the PFR kilns, percentages of excess air in the PFR kilns, waste gas temperatures inside the PFR kilns, pyrometric kiln temperatures, and pressures inside the PFR kilns. Each first lime quality value may be a percentage composition of Calcium Oxide (CaO) from each of the one or more PFR kilns.

Once the first lime quality values are predicted, the lime quality control system may determine a correction factor for each of the one or more PFR kilns. The lime quality control system may determine the correction factor for each of the one or more PFR kilns based on the predicted first lime quality value and an output indicative of actual lime quality value from each of the one or more PFR kilns. Particularly, the correction factor may be sum of weighted difference between the predicted first lime quality value and an output indicative of the actual lime quality value from each of the one or more PFR kilns.

Further, the lime quality control system may predict a second lime quality value at a second predetermined time, for each of the one or more PFR kilns. The second predetermined time may correspond to a time instant when limestone (CaCO3) is in a burning zone in the lime calcination process. Particularly, the lime quality control system may obtain the current data associated with the one or more process parameters of lime calcination process when limestone (CaCO3) is in a preheating zone and burning zone in the lime calcination process. Further, the lime quality control system may associate the current data of the one or more process parameters with corresponding predefined regression coefficients. Thereafter, the lime quality control system may determine the second lime quality value by combining the current data associated with the one or more process parameters with the corresponding predefined regression coefficients. Here, lime quality control system may utilize a prescriptive model for predicting the second lime quality value for each of the one or more PFR kilns using the corresponding determined correction factor.

Further, the lime quality control system may recommend one or more corrective actions for each of the one or more PFR kilns after the second predetermined time. The one or more corrective actions may correspond to varying the one or more process parameters of each of the one or more PFR kilns. The lime quality control system may recommend the one or more corrective actions to an operator on a display interface of the lime quality control system. The one or more corrective actions may be recommended based on the second lime quality value predicted for each of the one or more PFR kilns. The one or more corrective actions may be adopted for controlling the lime quality of each of the one or more PFR kilns.

The disclosed lime quality control system may predict the percentage lime quality value (CaO%) on an hourly basis at the end of the lime-production cycle such as at sixteenth hour of the lime calcination process, using data associated with the one or more PFR kilns (plant data). Further, the lime quality control system may provide recommendation to the operator for dynamically controlling the lime quality of the one or more PFR kilns in the current lime calcination process by performing the one or more corrective actions. Thus, the operator may be facilitated to take prompt decisions for performing the one or more corrective actions on the one or more process parameters at least twelve hours in advance before the final production of lime from the one or more PFR kilns. In this manner, the present disclosure ensures efficient controlling of the one or more process parameters to achieve improved lime quality at the output of the one or more PFR kilns.

Fig.1 shows exemplary architecture for controlling lime quality in real-time during lime calcination process in accordance with some embodiments of the present disclosure.

As shown in Fig.1, the architecture 100 may include one or more PFR kilns 101, such as a PFR kiln 1011 to PFR kiln 101N [alternatively referred as one or more PFR kilns or PFR kilns 101], one or more computing units 103, such as a computing unit 1031 to a computing unit 101N [alternatively referred as one or more computing units or computing units 103], a lime quality control system 107, a display interface 111, and an operator 113. Here, the computing unit 1031 may be associated with the PFR kiln 1011, the computing unit 1032 may be associated with the PFR kiln 1012, the computing unit 1033 may be associated with the PFR kiln 1013 and the computing unit 103N may be associated with the PFR kiln 101N. Alternatively, the computing units 1031, 1032, 1033, 103N may be associated with any one of the PFR kilns 1011, 1012, 1013, and 101N. In an embodiment, the lime quality control system 107 may be configured inside a mainframe computer system (not shown in figure). In another embodiment, the lime quality control system 107 may be a server to which the one or more computing units 103 corresponding to the one or more PFR kilns 101 may be associated with. As an example, the computing units 103 may include, but not limited to, Programmable Logic Controller (PLCs), Distributed Control System (DCS), and Supervisory Control and Data Acquisition (SCADA). In the illustrated architecture 100, the data 105 such as data 1051, 1052, 1053, 105N may be sent from the computing units 1031, 1032, 1033, 103N to lime quality control system 107 respectively. The data 105 may be processed by the lime quality control system 107 to recommend one or more corrective actions 109 such as corrective actions 1091, 1092, 1093, 109N for the one or more PFR kilns 1011, 1012, 1013, and 101N respectively. The recommended one or more corrective actions 1091, 1092, 1093, 109N may be displayed on the display interface 111 for controlling lime quality of the one or more PFR kilns 1011, 1012, 1013, and 101N in real-time during lime calcination process respectively.
In an exemplary scenario (not shown in figure), the PFR kiln 1011 may be associated with the PLCs 1031, 1032, and 1033. The process parameters 2071 may be measured through various types of industrial sensors such as temperature sensors, pressure sensors, and air flow meters. The measured process parameters 2071 may be monitored along with corresponding time instant in the PLCs 1031, 1032, and 1033. Further, the time tagged process parameters 2071 may be received at the lime quality control system 107 from the PLCs 1031, 1032, and 1033. Data 105 comprising the time tagged process parameters 2071 received at the lime quality control system 107 may include heat input to the PFR kiln 1011, gas flow in the PFR kiln 1011, percentage of excess air in the PFR kiln 1011, waste gas temperature inside the PFR kiln 1011, pyrometric kiln temperature, and pressure inside the PFR kiln 1011. As an example, the data 105 may be obtained at 24 hours of time interval at the lime quality control system 107 from the PLCs 1031, 1032, and 1033 corresponding to the PFR kiln 1011. Further, a predictive model of the lime quality control system 107 may predict a first lime quality value such as 89% of CaO, for the PFR kiln 1011 at 16th hour of a lime-production cycle of 24 hours. Here, 16th hour may represent a time instant when burnt lime enters into a cooling zone in the lime calcination process. Further, the lime quality control system 107 may determine a correction factor for the PFR kiln 1011 based on the predicted first lime quality value (89% of CaO) and an output indicative of actual lime quality value (94% of CaO) from the PFR kiln 1011. As an example, the correction factor may be determined as 4 for first time instant t1. Further, a prescriptive model of the lime quality control system 107 may predict a second lime quality value such as 93% of CaO, for the PFR kiln 1011 at 12th hour of the lime-production cycle of 24 hours. Here, 12th hour may represent a time instant when limestone (CaCO3) is in a burning zone in the lime calcination process. The prescriptive model may add the correction factor of 4 with a previously predicted lime quality value of 89% CaO to obtain final predicted lime quality value as 93% of CaO. Further, the lime quality control system 107 may recommend one or more corrective actions 109 for each of the one or more PFR kilns 1011 after 12th hour of the lime-production cycle of 24 hours based on the final predicted lime quality value as 93% of CaO. The one or more corrective actions 109 may be displayed on a Human Machine Interface (HMI) of the lime quality control system 107. The one or more corrective actions 109 may correspond to modifying the process parameters 2071 from the current set point to a new set point. As an example, the lime quality control system 107 may recommend an operator 113 to increase waste gas temperature by 0.15 degrees and decrease kiln pressure by 6.28 bar. Accordingly, the operator 113 may control the setpoints of the one or more process parameters 2071 associated with the lime calcination process to obtain 94% or above of CaO in the output quicklime from the PFR kiln 1011.

Fig.2a shows a block diagram of a lime quality control system in accordance with some embodiments of the present disclosure.

In some implementations, the lime quality control system 107 may include an I/O interface 201, at least a processor 203, and at least a memory device 205. The I/O interface 201 may be configured to receive data 105 comprising one or more process parameters 2071 associated with lime calcination process in one or more PFR kilns 101, from corresponding one or more computing units 103. Further, the I/O interface 201 may be configured to receive desirable percentage value of CaO in quicklime to be produced from the one or more PFR kilns 101 during steel making process. In other words, an operator 113 of the lime quality control system 107 may preset the desirable lime quality value for the one or more kilns through the I/O interface 201. The processor 203 may be configured to receive the data 105 associated with lime calcination process through the I/O interface 201. The processor 203 may retrieve some data 207 from the memory device 205 and interact with the modules 209 for further processing of the received data 105. The processor 203 further may provide one or more corrective actions 109 for each of the one or more PFR kilns 101 to control lime quality in real-time during the lime calcination process using Multivariate Linear Regression (MLR) based machine learning based model. In the lime quality control system 107, the memory device 205 may store data 207 received through the I/O interface 201, modules 209 and the processor 203. In one embodiment, the data 207 may also include process parameters 2071, first lime quality values 2072, first predetermined time 2073, correction factors 2074, actual lime quality value 2075, second lime quality values 2076, second predetermined time 2077, predefined regression coefficients 2078, weight factors 2079, and other data 20710. The other data 20710 may store data, including temporary data and temporary files, generated by the modules 209 for performing the various functions of the lime quality control system 107.
In some embodiments, the data 207 stored in the memory device 205 may be processed by the modules 209 of the lime quality control system 107. In an example, the modules 209 may be communicatively coupled to the processor 203 configured in the lime quality control system 107. The modules 209 may be present outside the memory device 205 as shown in Fig.2a and implemented as hardware. As used herein, the term modules 209 may refer to an Application Specific Integrated Circuit (ASIC), an electronic circuit, a processor (shared, dedicated, or group) and memory that execute one or more software or firmware programs, a combinational logic circuit, and/or other suitable components that provide the described functionality.
In some embodiments, the modules 209 may include, for example, a data acquisition module 211, a control module 213, a display interface 221 and other modules 223. The other modules 223 may be used to perform various miscellaneous functionalities of the lime quality control system 107. It will be appreciated that aforementioned modules 209 may be represented as a single module or a combination of different modules. Furthermore, a person of ordinary skill in the art will appreciate that in an implementation, the one or more modules 209 may be stored in the memory device 205, without limiting the scope of the disclosure. The said modules 209 when configured with the functionality defined in the present disclosure will result in a novel hardware.
In an embodiment, the data acquisition module 211 may be configured to fetch data 105 from a level#1 automation system and may send to a level#2 automation system. More particularly, the data 105 comprising one or more process parameters 2071 associated with the lime calcination process for the one or more kilns may be monitored by the one or more computing units 103, where the data 105 may be time tagged. Based on the tagging, the data 105 may be transmitted from the one or more computing units 103 to an external server for process data acquisition and analysis. Here, the server may constitute the level#1 automation system. From the server, the data acquisition module 211 may fetch the data 105 to a database, which may constitute the level#2 automation system. Further, the database may receive the data 105 from the interface module and may store the data 105 in appropriate format for further use by the lime quality control system 107. In the database, the data 105 comprising the time tagged process parameters 2071 may be stored batch wise along with sequence numbers of the one or more PFR kilns 101. As an example, each batch may comprise the data 105 of the one or more PFR kilns 101 of past 24 hours.
In an embodiment, the control module 213 may control lime quality in real-time during lime calcination process based on the data 105 comprising one or more process parameters 2071 associated with the lime calcination process. The control module 213 may comprise a predictive model 215, a determination module 217, and a prescriptive model 219. Fig.2b shows working of the predictive model 215 and the prescriptive model 219 of the control module 213 in the lime quality control system 107 in accordance with some embodiments of the present disclosure. As illustrated in Fig.2b, the predictive model 215 may predict a first lime quality value 2072 for each of the one or more PFR kilns 101 based on the received data 105. The first lime quality value 2072 may be a percentage composition of Calcium Oxide (CaO) from each of the one or more PFR kilns 101. The first lime quality value 2072 may be predicted at a first predetermined time 2073. The first predetermined time 2073 may correspond to a time instant when burnt lime enters into a cooling zone 229 in the lime calcination process. As an example, obtaining quicklime from the limestone in the one or more PFR kilns 101 through the lime calcination process may take up to 24 hours of time duration. The limestone may be processed in a preheating zone 225, a burning zone 227 and a cooling zone 229 sequentially for producing the quicklime. The predictive model 215 may predict the first lime quality value 2072 after 16th hour, when the limestone enters the cooling zone 229 in the lime calcination process as illustrated in Fig. 2b.
In the lime quality control system 107, the predictive model 215 may perform predictive analysis by utilizing Multiple Linear Regression (MLR). Generally, in the MLR based predictive analysis, target variable may be predicted based on one or more feature variables. In the present disclosure, the percentage composition of Calcium Oxide (CaO) may be considered as the target variable, and the one or more received process parameters 2071 associated with the lime calcination process in the one or more PFR kilns 101 may be considered as feature variables. The first lime quality value 2072 Cp may be predicted as follows using the MLR:
Cp =??0+??1????1+ ??2????2……………+??????????

where,
????1, ????2, ……………????n may represent process parameters associated with the lime calcination process in the one or more PFR kilns at ith time instant;
??1, ??2, …… ??n may represent predefined regression coefficients for the process parameters ????1, ????2, ……………????n respectively;
??0 may represent a constant value associated with an intercept of a regression line;

The predictive model 215 may retrieve the process parameters 2071 associated with the one or more PFR kilns 101 and corresponding predefined regression coefficients 2078 from the memory device 205 as illustrated in Fig. 2a. The retrieved process parameters 2071 may comprise heat input to the PFR kiln 101, gas flow in the PFR kiln 101, percentage of excess air in the PFR kiln 101, waste gas temperature inside the PFR kiln 101, pyrometric kiln temperature, and pressure inside the PFR kiln 101. The heat input may represent the heat input required per kg of lime for burning the raw lime inside each of the one or more kilns. The gas flow may be associated with burning gas used to burn the lime inside the kiln. Mostly coke oven gas and mixed gas may be used in the burning zone 227 of the one or more PFR kilns 101 for lime calcination process. Further, excess air percentage may represent how much percentage of air may be supplied in excess as compared to the standard quantity of air for burning the limestone. The waste gas temperature may be the temperature of gas coming out of the non-burning shaft after burning the lime in the burning-shaft. The pyrometric kiln temperature may represent the temperature of channel which links two shafts of the PFR kilns 101. This may provide the necessary temperature of burning zone 227 and may be measured using a pyrometer. Further, kiln pressure may be pressure inside the PFR kiln 101 generated by the solid-gas flow inside the PFR kiln 101.

As an example, the predictive model 215 may assign the retrieved process parameters 2071 as follows:
X1 = Heat input to the PFR kiln 101; X2 = Gas flow in the PFR kiln 101;
X3 = Percentage of excess air in the PFR kiln 101; X4 = Pressure inside the PFR kiln 101;
X5 = Pyrometric kiln temperature; and X6 = Waste gas temperature inside the PFR kiln 101.
As an example, the retrieved predefined regression coefficients 2078 may be represented as follows:
??1 = -0.000273, ??2 = 0.001451, ??3 = -0.070650,
??4 = 0.006365, ??5 = -0.012468, ??6 = -0.003941.
Further, ??0 =104.5017165533906
Hence, the predictive model 215 may predict the first lime quality value 2072 Cp as follows:
Cp = 104.5017165533906+(-0.000273)X1+(0.001451)X2+(-0.070650)X3
+(0.006365)X4+(-0.012468)X5+(-0.003941)X6

Here, the predefined regression coefficients 2078 may be positive or negative. The positive value of the predefined regression coefficients 2078 may indicate that when the process parameter associated with the positive predefined regression coefficient increases, the lime quality may be increased. In other words, the positive predefined regression coefficient may have increasing effect on the lime quality. Further, the negative value of the predefined regression coefficients 2078 may indicate that when the process parameter associated with the negative predefined regression coefficient increases, the lime quality may be decreased. In other words, the negative predefined regression coefficient may have decreasing effect on the lime quality.

In an embodiment, the determination module 217 may determine a correction factor 2074 for each of the one or more PFR kilns 101. The determination module 217 may retrieve output indicative of actual lime quality value 2075 for each of the one or more PFR kilns 101 from the memory device 205. Thereafter, the determination module 217 may determine the correction factor 2074 based on the predicted first lime quality value 2072 and the retrieved actual lime quality value 2075. More particularly, the determination module 217 may determine sum of weighted difference between the predicted first lime quality value 2072 and the retrieved actual lime quality value 2075 from each of the one or more PFR kilns 101 for determining the correction factor 2074. Here, the determination module 217 may utilize exponential time series technique for determining the correction factor 2074. The correction factor 2074 may be represented as follows:
Cf = W1 (Ca1-Cp1) + W2 (Ca2-Cp2) + ……………...+ Wn (Can-Cpn)
(or) Cf = W1 e1 + W2e2 + ……………...+ Wnen
Here, en = Can-Cpn
Cf may represent the correction factor 2074 for the PFR kiln 101;
e1, e2,……………….en may represent predicted error at nth time instant;
W1, W2, …….Wn may represent weights or correction coefficients for corresponding errors at nth time instant, such that W1 > W2 > …….> Wn

The determination module 217 may prioritize the recently predicated error with respect to other predicted errors in a descending order. The prioritizing of the predicted errors may be achieved by multiplying the predicted errors with corresponding correction coefficients 2079, in which the correction coefficients 2079 may be assigned predefined values in the descending order. As an example, the predicted error (e1) at 1st time instant may be given higher priority with respect to the predicted error (e2) at 2nd time instant, by multiplying the predicted error (e1) with the correction coefficient W1 and which may have higher positive integer value in comparison to the correction coefficient W2 of the predicted error (e2). In an embodiment, the determination module 217 may be implemented as separate module. Alternatively, the functionalities of the determination module 217 may be implemented in the predictive module.

In an embodiment, the prescriptive model 219 may receive the correction factor 2074 from the determination module 217. The prescriptive model 219 may predict a second lime quality value 2076 for each of the one or more PFR kilns 101 for current data associated with the one or more process parameters 2071 of the lime calcination process in the one or more PFR kilns 101 using the correction factor 2074. The second lime quality value 2076 may be a percentage composition of Calcium Oxide (CaO) from each of the one or more PFR kilns 101. The second lime quality value 2076 may be predicted at a second predetermined time 2077. The second predetermined time 2077 may correspond to a time instant when the limestone (CaCO3) is in the burning zone 227 in the lime calcination process. As an example, the prescriptive model 219 may predict the second lime quality value 2076 after 12th hour of the lime calcination process duration (which may take up to 24 hours duration), when the limestone is in the burning zone 227 in the lime calcination process as illustrated in Fig. 2b.

To predict the second lime quality value 2076, the prescriptive model 219 may retrieve from the memory device 205, the current data associated with the one or more process parameters 2071 of lime calcination process when limestone (CaCO3) is in a preheating zone 225 and burning zone 227 in the lime calcination process. Further, the prescriptive model 219 may associate the current data of the one or more process parameters 2071 with corresponding predefined regression coefficients 2078. Further, the prescriptive model 219 may combine the current data associated with the one or more process parameters 2071 with the corresponding predefined regression coefficients 2078 for determining the second lime quality value 2076. In an embodiment, the prescriptive model 219 may implement MLR technique for predicting the second lime quality value 2076. As an example, the prescriptive model 219 may predict the second lime quality value 2076 Cpt as follows:

Cpt = 104.5017165533906+(-0.000273)X1+(0.001451)X2+(-0.070650)X3
+(0.006365)X4+(-0.012468)X5+(-0.003941)X6
Further, the prescriptive model 219 may recommend one or more corrective actions 109 for each of the one or more PFR kilns 101 after the second predetermined time 2077 on a display interface 111 of the lime quality control system 107 as illustrated in Fig. 1. The prescriptive model 219 may recommend the one or more corrective actions 109 based on the second lime quality value 2076 predicted for each of the one or more PFR kilns 101 as illustrated in Fig. 2b. More particularly, upon determining the second lime quality value 2076, the prescriptive model 219 may predict a final lime quality value Cpt+1 based on the correction factor 2074 Cf and the second lime quality value 2076 Cpt, as follows:
Cpt+1 = Cpt + Cf

Based on the determined final lime quality value Cpt+1 , the prescriptive model 219 may determine which of the one or more process parameters 2071 needs to be controlled for achieving the actual lime quality value 2075. Accordingly, the prescriptive model 219 may recommend the operator 113 of the lime quality control system 107 to modify current setpoints of the process parameters 2071 to new setpoints by controlling industrial actuators or industrial valves associated with the one or more process parameters 2071 of the one or PFR kilns 101.

As an example, the prescriptive model 219 may determine that final lime quality value Cpt+1 for the PFR kiln 1011 may be 93%. The prescriptive model 219 may determine that the final lime quality value is poor in comparison to the actual desirable lime quality value of 94%. Hence, the prescriptive model 219 may prioritize which of the process parameters 2071 of the PFR kiln 1011 needs to be modified by increasing or decreasing the setpoints of the process parameters 2071. Here, the prescriptive model 219 may recommend the operator 113 for increasing the heat input to the PFR kiln 1011 by 10.18 degrees first followed by decreasing pressure inside the PFR kiln 1011 by 6.66 bar.

In an embodiment, the prescriptive model 219 may display the one or more corrective actions 109 to be performed by the operator 113 in terms of the color indications to distinguish priorities of the corrective actions 109 recommended. As an example, the prescriptive model 219 may display red color for the corrective actions 109 to indicate highest priority and green color for the corrective actions 109 to indicate lowest priority. Particularly, from the display interface 111, the operator 113 may clearly visualize which of the PFR kilns 101 need to be addressed on urgent basis in comparison to the other PFR kilns 101, and which of the process parameters 2071 of the respective PFR kilns 101 need to be controlled immediately for maintaining a good lime quality value in the quicklime to be produced from the PFR kilns 101.

In an embodiment, the display interface 111 may be configured to display one or more entities on a display screen of the lime quality control system 107. As an example, the one or more entities may be displayed as one or more column entities or row entities. As an example, the one or more entities may include Prescription, Actions taken by the operator 113, date_time, kiln_no, PRES_CAO, ACT_CAO, CAO_DIFF (Act – pres), Heat input, and Gas_flow as shown in Fig.2c. As an example, prescription may display one or more corrective actions 109 to be taken by the operator 113. Green color may be shown to indicate that the corrective action has been taken. Red color may be shown to indicate that the corrective action has not been taken. As an example, action taken may be shown by box, which may be clicked by the operator 113 after performing the one or more corrective actions 109. As an example, the date_time may show the time instant at which the prescriptive model 219 is providing the recommendations for the one or more corrective actions 109. As an example, kiln_no may show the numbering of kilns. As an example, PRES_CAO may be final output lime quality predicted by the prescriptive model 219. As an example, ACT_CAO may represent the actual quality of lime to be produced in the future. As an example, CAO_DIFF (Act – pres) may be the difference between actual lime quality (ACT_CAO) and prescribed lime quality (PRES_CAO). As an example, heat input may represent heat input per kg of lime provided to burn the raw limestone inside the PFR kiln 101. As an example, gas_flow may be related to the burning gas used to burn the limestone inside the PFR kiln 101. Mostly coke oven gas and mixed gas may be used in the PFR kilns 101.

Fig.3 shows a flowchart illustrating method for controlling lime quality in real-time during lime calcination process in accordance with some embodiments of the present disclosure.

As illustrated in Fig.3, the method 300 includes one or more blocks illustrating a method for controlling lime quality in real-time during lime calcination process. The order in which the method 300 is described is not intended to be construed as a limitation, and any number of the described method blocks can be combined in any order to implement the method. Additionally, individual blocks may be deleted from the methods without departing from the spirit and scope of the subject matter described herein. Furthermore, the method can be implemented in any suitable hardware, software, firmware, or combination thereof.

At block 301, the method may include receiving, by a lime quality control system 107 associated with each of one or more PFR kilns 101, data 105 from one or more computing units 103 corresponding to the one or more PFR kilns 101. The data 105 may comprise one or more process parameters 2071 associated with lime calcination process, in the one or more PFR kilns 101. The process parameters 2071 of the one or more PFR kilns 101 may comprise time tagged heat input to the PFR kiln 101, gas flow in the PFR kiln 101, percentage of excess air in the PFR kiln 101, waste gas temperature inside the PFR kiln 101, pyrometric kiln temperature, and pressure inside the PFR kiln 101. Here, the one or more process parameters 2071 associated with lime calcination process may be obtained at predefined time intervals, from the one or more computing units 103.
At block 303, the method may include predicting, using a predictive model 215 of the lime quality control system 107, a first lime quality value 2072 for each of the one or more PFR kilns 101 based on the received data 105 at a first predetermined time 2073. Upon receiving the data 105 from the one or more computing units 103 corresponding to the one or more PFR kilns 101, the predictive model 215 may predict the first lime quality value 2072 which corresponds to a percentage composition of Calcium Oxide (CaO) from each of the one or more PFR kilns 101. The first lime quality value 2072 may be predicted at the first predetermined time 2073 which corresponds to a time instant when burnt lime enters into a cooling zone 229 in the lime calcination process. For predicting the first lime quality value 2072, Multiple Linear Regression (MLR) technique may be implemented by the predictive model 215.
At block 305, the method may include determining, by the lime quality control system 107, a correction factor 2074 for each of the one or more PFR kilns 101 based on the predicted first lime quality value 2072 and an output indicative of actual lime quality value 2075 from each of the one or more PFR kilns 101. The correction factor 2074 may be sum of weighted difference between the predicted first lime quality value 2072 and the output indicative of the actual lime quality value 2075 from each of the one or more PFR kilns 101.
At block 307, the method may include predicting, using a prescriptive model 219 of the lime quality control system 107, a second lime quality value 2076, at a second predetermined time 2077, for each of the one or more PFR kilns 101 for current data associated with the one or more process parameters 2071 of the lime calcination process in the one or more PFR kilns 101 using the correction factor 2074. The prescriptive model 219 may predict at the second predetermined time 2077, the second lime quality value 2076 which corresponds to a percentage composition of Calcium Oxide (CaO) from each of the one or more PFR kilns 101. The second predetermined time 2077 may correspond to a time instant when limestone (CaCO3) is in a burning zone 227 in the lime calcination process. More particularly, the current data associated with the one or more process parameters 2071 of lime calcination process may be obtained, when limestone (CaCO3) is in a preheating zone 225 and burning zone 227 in the lime calcination process. Further, the current data of the one or more process parameters 2071 may be associated with corresponding predefined regression coefficients 2078. Further, the second lime quality value 2076 may be determined by combining the current data associated with the one or more process parameters 2071 with the corresponding predefined regression coefficients 2078.
At block 309, the method may include recommending, by the lime quality control system 107, one or more corrective actions 109 for each of the one or more PFR kilns 101 after the second predetermined time 2077 on a display interface 111 of the lime quality control system 107, based on the second lime quality value 2076 predicted for each of the one or more PFR kilns 101. The one or more corrective actions 109 may be adopted for controlling the lime quality of each of the one or more PFR kilns 101. The one or more corrective actions 109 may correspond to varying the one or more process parameters 2071 of each of the one or more PFR kilns 101. The one or more corrective actions 109 for each of the one or more PFR kilns 101 may be displayed on the display interface 111 of the lime quality control system 107. The displayed one or more corrective actions 109 may facilitate an operator 113 of the lime quality control system 107 performing the one or more corrective actions 109 promptly.
Fig.4 shows a block diagram of an exemplary computer system for implementing embodiments consistent with the present disclosure.
Computer System

Fig.4 illustrates a block diagram of an exemplary computer system 400 for implementing embodiments consistent with the present disclosure. In an embodiment, the computer system 400 may be a system for controlling lime quality in real-time during lime calcination process. The computer system 400 may include a central processing unit (“CPU” or “processor”) 402. The processor 402 may comprise at least one data processor for executing program components for executing user or system-generated business processes. The processor 402 may include specialized processing units such as integrated system (bus) controllers, memory management control units, floating point units, graphics processing units, digital signal processing units, etc.
The processor 402 may be disposed in communication with one or more input/output (I/O) devices (411 and 412) via I/O interface 401. The I/O interface 401 may employ communication protocols/methods such as, without limitation, audio, analog, digital, stereo, IEEE-1394, serial bus, Universal Serial Bus (USB), infrared, PS/2, BNC, coaxial, component, composite, Digital Visual Interface (DVI), high-definition multimedia interface (HDMI), Radio Frequency (RF) antennas, S-Video, Video Graphics Array (VGA), IEEE 802.n /b/g/n/x, Bluetooth, cellular (e.g., Code-Division Multiple Access (CDMA), High-Speed Packet Access (HSPA+), Global System For Mobile Communications (GSM), Long-Term Evolution (LTE) or the like), etc. Using the I/O interface 401, the computer system 400 may communicate with one or more I/O devices 411 and 412.
In some embodiments, the processor 402 may be disposed in communication with a communication network 409 via a network interface 403. The network interface 403 may communicate with the communication network 409. The network interface 403 may employ connection protocols including, without limitation, direct connect, Ethernet (e.g., twisted pair 10/100/1000 Base T), Transmission Control Protocol/Internet Protocol (TCP/IP), token ring, IEEE 802.11a/b/g/n/x, etc.
The communication network 409 can be implemented as one of the several types of networks, such as intranet or Local Area Network (LAN) and such within the organization. The communication network 409 may either be a dedicated network or a shared network, which represents an association of several types of networks that use a variety of protocols, for example, Hypertext Transfer Protocol (HTTP), Transmission Control Protocol/Internet Protocol (TCP/IP), Wireless Application Protocol (WAP), etc., to communicate with each other. Further, the communication network 409 may include a variety of network devices, including routers, bridges, servers, computing devices, storage devices, etc.
In some embodiments, the processor 402 may be disposed in communication with a memory 405 (e.g., RAM 413, ROM 414, etc. as shown in Fig. 4) via a storage interface 404. The storage interface 404 may connect to memory 405 including, without limitation, memory drives, removable disc drives, etc., employing connection protocols such as Serial Advanced Technology Attachment (SATA), Integrated Drive Electronics (IDE), IEEE-1394, Universal Serial Bus (USB), fiber channel, Small Computer Systems Interface (SCSI), etc. The memory drives may further include a drum, magnetic disc drive, magneto-optical drive, optical drive, Redundant Array of Independent Discs (RAID), solid-state memory devices, solid-state drives, etc.
The memory 405 may store a collection of program or database components, including, without limitation, user /application 406, an operating system 407, a web browser 408, mail client 415, mail server 416, web server 417 and the like. In some embodiments, computer system 400 may store user /application data 406, such as the data, variables, records, etc. as described in this invention. Such databases may be implemented as fault-tolerant, relational, scalable, secure databases such as OracleR or SybaseR.
The operating system 407 may facilitate resource management and operation of the computer system 400. Examples of operating systems include, without limitation, APPLE MACINTOSHR OS X, UNIXR, UNIX-like system distributions (E.G., BERKELEY SOFTWARE DISTRIBUTIONTM (BSD), FREEBSDTM, NETBSDTM, OPENBSDTM, etc.), LINUX DISTRIBUTIONSTM (E.G., RED HATTM, UBUNTUTM, KUBUNTUTM, etc.), IBMTM OS/2, MICROSOFTTM WINDOWSTM (XPTM, VISTATM/7/8, 10 etc.), APPLER IOSTM, GOOGLER ANDROIDTM, BLACKBERRYR OS, or the like. A user interface may facilitate display, execution, interaction, manipulation, or operation of program components through textual or graphical facilities. For example, user interfaces may provide computer interaction interface elements on a display system operatively connected to the computer system 400, such as cursors, icons, check boxes, menus, windows, widgets, etc. Graphical User Interfaces (GUIs) may be employed, including, without limitation, APPLE MACINTOSHR operating systems, IBMTM OS/2, MICROSOFTTM WINDOWSTM (XPTM, VISTATM/7/8, 10 etc.), UnixR X-Windows, web interface libraries (e.g., AJAXTM, DHTMLTM, ADOBE® FLASHTM, JAVASCRIPTTM, JAVATM, etc.), or the like.
Furthermore, one or more computer-readable storage media may be utilized in implementing embodiments consistent with the present invention. A computer-readable storage medium refers to any type of physical memory on which information or data readable by a processor may be stored. Thus, a computer-readable storage medium may store instructions for execution by one or more processors, including instructions for causing the processor(s) to perform steps or stages consistent with the embodiments described herein. The term “computer-readable medium” should be understood to include tangible items and exclude carrier waves and transient signals, i.e., non-transitory. Examples include Random Access Memory (RAM), Read-Only Memory (ROM), volatile memory, nonvolatile memory, hard drives, Compact Disc (CD) ROMs, Digital Video Disc (DVDs), flash drives, disks, and any other known physical storage media.
Advantages of the embodiment of the present disclosure are illustrated herein.
In an embodiment, the present disclosure provides a method and a system for controlling lime quality in real-time during lime calcination process.

In an embodiment, the present disclosure provides a lime quality control system which utilizes machine learning techniques for improving CaO content in output lime produced by PFR kilns during lime calcination process of steel making process.

In an embodiment, the present disclosure provides a lime quality control system that avoids manual intervention of an operator for determining appropriate process parameters of the PFR kilns that needs to be modified or adjusted during calcination process to ensure whether a desired composition of Calcium Oxide (CaO) is obtained in output lime from the one or more PFR kilns or not.

In an embodiment, the present disclosure provides a predictive model which predicts a first lime quality value for each of the one or more PFR kilns based on the received process parameters at a time instant when burnt lime enters into a cooling zone in the lime calcination process. This prevents long waiting time duration for determining the lime quality of the final quicklime produced from the PFR kilns. Conventionally, the sample of the quicklime produced after end of the lime production cycle (24 hours) is tested in the laboratory to know the percentage composition of the CaO in the sample. The disclosed predictive model reduces this long waiting duration to a first predetermined time (16th hour) from the end of the lime production cycle (24 hours), thereby increasing effective utilization of time and resources for a next lime calcination process.

In an embodiment, the present disclosure provides a prescriptive model which provides second lime quality value for each of the one or more PFR kilns at a time instant when limestone (CaCO3) is in a burning zone in the lime calcination process. This enables the operator to control the lime quality of the quicklime to be produced from the PFR kiln in the current lime calcination batch. In other words, as the second lime quality is predicted when the limestone (CaCO3) is in the burning zone, the operator has the flexibility to dynamically modify process parameters settings which needs to be reflected in the current lime calcination process for maintaining a good lime quality at the output of the PFR kilns. Thus, the prescriptive model further cuts down the waiting time duration from the first predetermined time (16th hour) to the second predetermined time (12th hour) to control quality of the lime to be produced in the ongoing lime calcination process, instead of controlling quality of the lime to be produced in the next lime calcination process. This improves performance of the PFR kilns in terms of producing good quality of quicklime with higher percentage composition of CaO.

The terms "an embodiment", "embodiment", "embodiments", "the embodiment", "the embodiments", "one or more embodiments", "some embodiments", and "one embodiment" mean "one or more (but not all) embodiments of the invention(s)" unless expressly specified otherwise.

The terms "including", "comprising", “having” and variations thereof mean "including but not limited to", unless expressly specified otherwise. The enumerated listing of items does not imply that any or all the items are mutually exclusive, unless expressly specified otherwise.

The terms "a", "an" and "the" mean "one or more", unless expressly specified otherwise.
A description of an embodiment with several components in communication with each other does not imply that all such components are required. On the contrary, a variety of optional components are described to illustrate the wide variety of possible embodiments of the invention.

When a single device or article is described herein, it will be clear that more than one device/article (whether they cooperate) may be used in place of a single device/article. Similarly, where more than one device or article is described herein (whether they cooperate), it will be clear that a single device/article may be used in place of the more than one device or article or a different number of devices/articles may be used instead of the shown number of devices or programs. The functionality and/or the features of a device may be alternatively embodied by one or more other devices which are not explicitly described as having such functionality/features. Thus, other embodiments of the invention need not include the device itself.

Finally, the language used in the specification has been principally selected for readability and instructional purposes, and it may not have been selected to delineate or circumscribe the inventive subject matter. It is therefore intended that the scope of the invention be limited not by this detailed description, but rather by any claims that issue on an application based here on. Accordingly, the embodiments of the present invention are intended to be illustrative, but not limiting, of the scope of the invention, which is set forth in the following claims.

While various aspects and embodiments have been disclosed herein, other aspects and embodiments will be apparent to those skilled in the art. The various aspects and embodiments disclosed herein are for purposes of illustration and are not intended to be limiting, with the true scope and spirit being indicated by the following claims.

Referral Numerals:
Reference Number Description
100 Architecture
101, 1011, 1012, 1013, 101N PFR Kiln
103, 1031, 1032, 1033, 103N Computing unit
105, 1051, 1052, 1053, 105N Data
107 Lime quality control system
109, 1091, 1092, 1093, 109N Corrective actions
111 Display interface
113 Operator
201 I/O interface
203 Processor
205 Memory device
207 Data
2071 Process parameters
2072 First lime quality values
2073 First predetermined time
2074 Correction factors
2075 Actual lime quality value
2076 Second lime quality values
2077 Second predetermined time
2078 Predefined regression coefficients
2079 Weight factors/correction coefficients
20710 Other data
209 Modules
211 Data acquisition module
213 Control module
215 Predictive model
217 Determination module
219 Prescriptive model
221 Display interface
223 Other modules
225 Preheating zone
227 Burning zone
229 Cooling zone
400 Computer system
401 I/O Interface
402 Processor
403 Network interface
404 Storage interface
405 Memory
406 User/Application
407 Operating system
408 Web browser
409 Communication network
411 Input device
412 Output device
413 RAM
414 ROM
415 Mail client
416 Mail server
417 Web server