Claims:

1. A processor implemented method (300) for monitoring and forecasting of catalyst degradation of a selective catalytic reduction (SCR) equipment, the method comprising:

receiving, via one or more hardware processors, a plurality of data related to the SCR equipment from a plurality of data sources, wherein the SCR equipment comprises a plurality of catalyst layers (302);
preprocessing, via the one or more hardware processors, the received plurality of data, wherein the preprocessed plurality of data is synchronized in a data repository regularly at periodic time intervals (304);
predicting, via the one or more hardware processors, a catalyst degradation index for each catalyst layer of the plurality of catalyst layers using a catalyst degradation model, wherein the inputs for the catalyst degradation model comprise measured values of a first set of parameters and measured values of a second set of parameters from the plurality of preprocessed data (306);
predicting, via the one or more hardware processors, a second set of parameters for each catalyst layer of the plurality of catalyst layers using a chemical reaction model wherein the inputs to the chemical reaction model comprise predicted catalyst degradation index of respective layers and measured values of the first set of parameters from the plurality of preprocessed data (308);
estimating, via the one or more hardware processors, the first set of parameters for a first catalyst layer of the plurality of catalyst layers over a predefined forecast time period using an estimator model for the first catalyst layer and the preprocessed plurality of data (310);
forecasting, via the one or more hardware processors, the catalyst degradation index for the first catalyst layer over the predefined forecast time using a degradation forecast model of the first catalyst layer, estimated values of the first set of parameters for the first catalyst layer, and the preprocessed plurality of data (312);
forecasting, via the one or more hardware processors, the second set of parameters for the first catalyst layer over the predefined forecast time using the estimated first set of parameters for the first catalyst layer, the forecasted catalyst degradation index for the first catalyst layer and the plurality of processed data using a chemical reaction model (314);
forecasting, via the one or more hardware processors, the catalyst degradation index for each catalyst layer of the plurality of catalyst layers successively over the predefined forecast time using the degradation forecast model of the respective catalyst layer, the forecasted second set of parameters from the previous catalyst layer of the plurality of catalyst layers and the plurality of processed data (316);
forecasting, via the one or more hardware processors, the second set of parameters of the each catalyst layer of the plurality of catalyst layers successively over the predefined forecast time using the forecasted second set of parameters of the previous catalyst layer and the forecasted catalyst degradation index of the current catalyst layer (318);
providing, via the one or more hardware processors, a set of recommendations for optimal maintenance and scheduling for each catalyst layer and the SCR equipment based on the forecasted catalyst degradation index of the last catalyst layer and the forecasted second set of parameters for the last catalyst layer (320).

2. The method as claimed in claim 1, further comprising simulating configured to simulate the what-if and if-what scenario analysis in at least one of an online and an offline.

3. The method as claimed in claim 1, further comprising:
periodically checking a performance of a catalyst monitor and the degradation forecasting models against an actual plant data obtained at that time;
generating an alarm, if the accuracy of the degradation forecasting models moves out of a predefined limit;
triggering an auto-update loop configured to re-tune the degradation forecasting models based on the preprocessed plurality of data.

4. The method as claimed in claim 1, wherein the first set of parameters for the catalyst layer comprises conditions at an upstream of the catalyst layer, wherein the conditions comprise a concentration of NOx, a concentration of ammonia, a concentration of Sulphur oxides and a temperature and a pressure of a flue gas.

5. The method as claimed in claim 1, wherein the second set of parameters for the catalyst layer comprises conditions at a downstream of the catalyst layer, wherein the conditions comprise of the concentration of NOx, the concentration of ammonia, the concentration of Sulphur oxides and the temperature, and the pressure of the flue gas.

6. The method as claimed in claim 1, wherein the plurality of data comprises one or more of data received from distributed control system (DCS), data received from installed sensors, data received from historian, data received from laboratory information management system (LIMS), data received from a plurality of external sources, manual input data received from a plurality of digital systems present in a power plant, design and maintenance information, catalyst degradation information, a plurality of domain parameters, and predicted values from a plurality of data models.

7. The method as claimed in claim 1, wherein the preprocessing comprises:
checking erroneous data in the plurality of data,
removing outliers in the plurality of data,
imputing new values in place of missing values,
transforming the plurality of data into different shape, size and frequency based on the SCR design specifications, forecasting horizon and the available plant data.

8. The method as claimed in claim 1, wherein the catalyst degradation index comprise a function of a voidage fraction and an available surface area of an SCR catalyst bed, wherein the voidage fraction indicates the area available for flow for gas and the surface area available indicates the surfaces where components of the SCR equipment interact with a catalyst for an NOx reduction reaction to take place.

9. The method as claimed in claim 1, further comprising generating an alarm if the forecasted catalyst degradation index of the last layer and the estimated second set of parameters of the last layer moves out of a predefined limit.

10. The method as claimed in claim 1, wherein the catalyst degradation model, the chemical reaction model, the degradation forecast model comprise first-principle based models, data-driven models, knowledge-based models and combination thereof.

11. The method as claimed in claim 1, wherein recommendations comprise of optimal operating set points on SCR and upstream equipment, catalyst maintenance schedule and actions, plant maintenance scheduling suggestions.

12. The method as claimed in claim 1, wherein the first set and the second set of parameters for catalyst layers could be measured by installation of permanent or temporary sensors inside or on the SCR equipment.

13. A system for monitoring and forecasting of catalyst degradation of a selective catalytic reduction (SCR) equipment, the system comprises:

an input/output interface for a plurality of data related to the SCR equipment from a plurality of data sources, wherein the SCR equipment comprises a plurality of catalyst layers;
one or more hardware processors;
a memory in communication with the one or more hardware processors, wherein the one or more first hardware processors are configured to execute programmed instructions stored in the one or more first memories, to:
preprocess the received plurality of data, wherein the preprocessed plurality of data is synchronized in a data repository regularly at periodic time intervals;
predict a catalyst degradation index for each catalyst layer of the plurality of catalyst layers using a catalyst degradation model, wherein the inputs for the catalyst degradation model comprise measured values of a first set of parameters and measured values of a second set of parameters from the plurality of preprocessed data;
predict the second set of parameters for each catalyst layer of the plurality of catalyst layers using a chemical reaction model wherein the inputs to the chemical reaction model comprise predicted catalyst degradation index and measured values of the first set of parameters from the plurality of preprocessed data;
estimate, the first set of parameters for a first catalyst layer of the plurality of catalyst layers over a predefined forecast time period using an estimator model for the first catalyst layer and the preprocessed plurality of data;
forecast, the catalyst degradation index for the first catalyst layer over the predefined forecast time using a degradation forecast model of the first catalyst layer, estimated values of the first set of parameters for the first catalyst layer, and the preprocessed plurality of data;
forecast, the second set of parameters for the first catalyst layer over the predefined forecast time using the estimated first set of parameters for the first catalyst layer, the forecasted catalyst degradation index for the first catalyst layer and the plurality of processed data using a chemical reaction model;
forecast, the catalyst degradation index for each catalyst layer of the plurality of catalyst layers over the predefined forecast time using the degradation forecast model of the respective catalyst layer, the forecasted second set of parameters from the previous catalyst layer of the plurality of catalyst layers and the plurality of processed data;
forecast, the second set of parameters of the each catalyst layer of the plurality of catalyst layers over the predefined forecast time using the forecasted second set of parameters of the previous catalyst layer and the forecasted catalyst degradation index of the current catalyst layer; and
provide, a set of recommendations for optimal maintenance and scheduling for each catalyst layer and the SCR equipment based on the forecasted catalyst degradation index of the last catalyst layer and the forecasted second set of parameters for the last catalyst layer.

14. The system of claim 13 further configured to display the provided set of recommendations.
, Description:FORM 2

THE PATENTS ACT, 1970
(39 of 1970)
&
THE PATENT RULES, 2003

COMPLETE SPECIFICATION
(See Section 10 and Rule 13)

Title of invention:
METHOD AND SYSTEM FOR MONITORING AND FORECASTING OF CATALYST DEGRADATION OF SELECTIVE CATALYTIC REDUCTION EQUIPMENT

Applicant:
Tata Consultancy Services Limited
A company Incorporated in India under the Companies Act, 1956
Having address:
Nirmal Building, 9th Floor,
Nariman Point, Mumbai 400021,
Maharashtra, India

The following specification particularly describes the invention and the manner in which it is to be performed.
TECHNICAL FIELD

[001] The disclosure herein generally relates to the field of a selective catalytic reduction (SCR) equipment and, more particularly, to a method and system for real time online monitoring and forecasting the performance of selective catalytic reduction (SCR) equipment by utilizing a digital replica of the selective catalytic reduction equipment.

BACKGROUND
[002] The process of power generation in a thermal power plant involves combustion of coal inside a boiler resulting in production of hot flue gases. Nitrous oxides or NOx is one of the most harmful constituents of these flue gases and need to be maintained under certain level as mandated by the environmental regulations. Selective catalytic reduction (SCR) technology is one of the main drivers of today’s NOx reduction efforts across the world. SCR is a massive reactor where a series of catalyst beds facilitate a chemical reaction between incoming NOx from boiler flue gases and injected reagent such as ammonia to produce nitrogen and water. Typically, SCRs successfully remove close to 90-95% of the NOx.
[003] There are several challenges with respect to operation and maintenance of SCR equipment, specifically in a thermal power plant. Operation of SCR equipment is expensive because of the demand of expensive reducing agent like Ammonia. Secondly, the catalyst beds need periodic replacement / replenishment due to catalyst poisoning, clogging, which adds to the maintenance costs. Further, performance of SCR equipment degrades over time both in terms of operating efficiency and catalytic effectiveness. Requirement of reducing agent gradually increases over time due to deterioration / poisoning of catalyst, for removing a set amount of NOx. This is compounded by the clogging of the catalyst pores with ash. The clogging also increases resistance to flow, in turn increasing the demand on fans and hence the cost. One more important problem is the leaking of Ammonia into the downstream equipment. Ammonia that goes off unreacted (called Ammonia slip) from the SCR equipment combines with Sulphur oxides in the gas stream from the boiler to form deposits that settle in downstream equipment such as air preheaters and force unplanned maintenance.
[004] The NOx removal efficiency and ammonia slip are typically used as indicators of SCR catalyst condition, however highly unpredictable nature of catalyst degradation and lack of enough sensors make it difficult even for an experienced operator to take appropriate decisions.
[005] Few control systems exist in the prior art, but most of them cater to automobile SCRs where the problems like ash deposition are not very relevant. The existing technologies do not satisfactorily account for ash deposition due to coal in thermal power plants. In addition, the SCRs in thermal power plants comprise of multiple layers of catalyst beds, which undergo uneven degradation. The existing means of managing SCR performance rely heavily on the catalyst management plan provided by the manufacturer as well as on the heuristics and experience, but these fail to address above issues, even in a state-of-the-art plant.

SUMMARY
[006] Embodiments of the present disclosure present technological improvements as solutions to one or more of the above-mentioned technical problems recognized by the inventors in conventional systems. For example, in one embodiment, a system for monitoring and forecasting of catalyst degradation of a selective catalytic reduction (SCR) equipment is provided. The system comprises an input/ output interface, one or more hardware processors and a memory. The input/output interface provides a plurality of data related to the SCR equipment from a plurality of data sources, wherein the SCR equipment having a plurality of catalyst layers. The memory is in communication with the one or more hardware processors, wherein the one or more first hardware processors are configured to execute programmed instructions stored in the one or more first memories, to: preprocess the received plurality of data, wherein the preprocessed plurality of data is synchronized in a data repository regularly at a regular time interval; predict a catalyst degradation index for each catalyst layer of the plurality of catalyst layers using a catalyst degradation model, wherein the inputs for catalyst degradation model comprise of measured values of a first set of parameters and measured values of a second set of parameters from the plurality of preprocessed data; predict the second set of parameters for each catalyst layer of the plurality of catalyst layers using a chemical reaction model wherein the inputs to the chemical reaction model comprise of predicted catalyst degradation index and measured values of the first set of parameters from the plurality of preprocessed data; estimate, the first set of parameters for a first catalyst layer of the plurality of catalyst layers over a predefined forecast time period using an estimator model for the first catalyst layer and the preprocessed plurality of data; forecast, the catalyst degradation index for the first catalyst layer over the predefined forecast time using a degradation forecast model of the first catalyst layer, estimated values of the first set of parameters for the first catalyst layer, and the preprocessed plurality of data; forecast, the second set of parameters for the first catalyst layer over the predefined forecast time using the estimated first set of parameters for the first catalyst layer, the forecasted catalyst degradation index for the first catalyst layer and the plurality of processed data using a chemical reaction model; forecast, the catalyst degradation index for each catalyst layer of the plurality of catalyst layers over the predefined forecast time using the degradation forecast model of the respective catalyst layer, the forecasted second set of parameters from the previous catalyst layer of the plurality of catalyst layers and the plurality of processed data; forecast, the second set of parameters of the each catalyst layer of the plurality of catalyst layers over the predefined forecast time using the forecasted second set of parameters of the previous catalyst layer and the forecasted catalyst degradation index of the current catalyst layer; and provide, a set of recommendations for optimal maintenance and scheduling for each catalyst layer and the SCR equipment based on the forecasted catalyst degradation index of the last catalyst layer and the forecasted second set of parameters for the last catalyst layer.
[007] In another aspect, a method for monitoring and forecasting of catalyst degradation of a selective catalytic reduction (SCR) equipment is provided. Initially, a plurality of data related to the SCR equipment is received from a plurality of data sources, wherein the SCR equipment having a plurality of catalyst layers. The received plurality of data is then preprocessed, wherein the preprocessed plurality of data is synchronized in a data repository regularly at a regular time interval. In the next step, a catalyst degradation index is predicted for each catalyst layer of the plurality of catalyst layers using a catalyst degradation model, wherein the inputs for catalyst degradation model comprise of measured values of a first set of parameters and measured values of a second set of parameters from the plurality of preprocessed data. Further, a second set of parameters is predicted for each catalyst layer of the plurality of catalyst layers using a chemical reaction model wherein the inputs to the chemical reaction model comprise of predicted catalyst degradation index of respective layers and measured values of the first set of parameters from the plurality of preprocessed data. In the next step, the first set of parameters is predicted for a first catalyst layer of the plurality of catalyst layers over a predefined forecast time period using an estimator model for the first catalyst layer and the preprocessed plurality of data. Further the catalyst degradation index is forecasted for the first catalyst layer over the predefined forecast time using a degradation forecast model of the first catalyst layer, estimated values of the first set of parameters for the first catalyst layer, and the preprocessed plurality of data. The second set of parameters is also forecasted for the first catalyst layer over the predefined forecast time using the estimated first set of parameters for the first catalyst layer, the forecasted catalyst degradation index for the first catalyst layer and the plurality of processed data using a chemical reaction model. Further, the catalyst degradation index id forecasted for each catalyst layer of the plurality of catalyst layers successively over the predefined forecast time using the degradation forecast model of the respective catalyst layer, the forecasted second set of parameters from the previous catalyst layer of the plurality of catalyst layers and the plurality of processed data. In the next step, the second set of parameters is forecasted of the each catalyst layer of the plurality of catalyst layers successively over the predefined forecast time using the forecasted second set of parameters of the previous catalyst layer and the forecasted catalyst degradation index of the current catalyst layer. And finally, a set of recommendations is provided for optimal maintenance and scheduling for each catalyst layer and the SCR equipment based on the forecasted catalyst degradation index of the last catalyst layer and the forecasted second set of parameters for the last catalyst layer.
[008] In yet another aspect, a non-transitory computer readable medium for monitoring and forecasting of catalyst degradation of a selective catalytic reduction (SCR) equipment is provided. Initially, a plurality of data related to the SCR equipment is received from a plurality of data sources, wherein the SCR equipment having a plurality of catalyst layers. The received plurality of data is then preprocessed, wherein the preprocessed plurality of data is synchronized in a data repository regularly at a regular time interval. In the next step, a catalyst degradation index is predicted for each catalyst layer of the plurality of catalyst layers using a catalyst degradation model, wherein the inputs for catalyst degradation model comprise of measured values of a first set of parameters and measured values of a second set of parameters from the plurality of preprocessed data. Further, a second set of parameters is predicted for each catalyst layer of the plurality of catalyst layers using a chemical reaction model wherein the inputs to the chemical reaction model comprise of predicted catalyst degradation index of respective layers and measured values of the first set of parameters from the plurality of preprocessed data. In the next step, the first set of parameters is predicted for a first catalyst layer of the plurality of catalyst layers over a predefined forecast time period using an estimator model for the first catalyst layer and the preprocessed plurality of data. Further the catalyst degradation index is forecasted for the first catalyst layer over the predefined forecast time using a degradation forecast model of the first catalyst layer, estimated values of the first set of parameters for the first catalyst layer, and the preprocessed plurality of data. The second set of parameters is also forecasted for the first catalyst layer over the predefined forecast time using the estimated first set of parameters for the first catalyst layer, the forecasted catalyst degradation index for the first catalyst layer and the plurality of processed data using a chemical reaction model. Further, the catalyst degradation index id forecasted for each catalyst layer of the plurality of catalyst layers successively over the predefined forecast time using the degradation forecast model of the respective catalyst layer, the forecasted second set of parameters from the previous catalyst layer of the plurality of catalyst layers and the plurality of processed data. In the next step, the second set of parameters is forecasted of the each catalyst layer of the plurality of catalyst layers successively over the predefined forecast time using the forecasted second set of parameters of the previous catalyst layer and the forecasted catalyst degradation index of the current catalyst layer. And finally, a set of recommendations is provided for optimal maintenance and scheduling for each catalyst layer and the SCR equipment based on the forecasted catalyst degradation index of the last catalyst layer and the forecasted second set of parameters for the last catalyst layer.
[009] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.

BRIEF DESCRIPTION OF THE DRAWINGS

[010] The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate exemplary embodiments and, together with the description, serve to explain the disclosed principles:
[011] FIG. 1 illustrates a network diagram of a system for monitoring and forecasting of catalyst degradation of a selective catalytic reduction (SCR) equipment according to some embodiments of the present disclosure.
[012] FIG. 2 illustrates an architecture of the system for monitoring and forecasting of catalyst degradation of the selective catalytic reduction (SCR) equipment according to some embodiments of the present disclosure.
[013] FIG. 3 is a flowchart illustrating steps involved in real-time online monitoring, optimization and forecasting output of selective catalytic reduction equipment according to some embodiments of the present disclosure.
[014] FIG. 4 shows flowchart illustrating steps involved in real-time monitoring of catalyst degradation of the selective catalytic reduction equipment according to some embodiments of the present disclosure.
[015] FIG. 5 shows inputs and outputs for the chemical reaction model in the degradation monitor unit according to some embodiments of the present disclosure.
[016] FIG. 6 shows flowchart illustrating steps involved in monitoring and forecasting of catalyst degradation of the selective catalytic reduction (SCR) equipment according to some embodiments of the present disclosure.
[017] FIG. 7 shows inputs and outputs for the degradation forecast model in predictor unit for a first layer of the SCR according to some embodiments of the present disclosure.
[018] FIG. 8 shows inputs and outputs for the degradation forecast model in a predictor unit for layer n (n >1, layer 2 onwards) of the SCR according to some embodiments of the present disclosure.

DETAILED DESCRIPTION OF EMBODIMENTS
[019] Exemplary embodiments are described with reference to the accompanying drawings. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. Wherever convenient, the same reference numbers are used throughout the drawings to refer to the same or like parts. While examples and features of disclosed principles are described herein, modifications, adaptations, and other implementations are possible without departing from the scope of the disclosed embodiments.
[020] Selective catalytic reduction (SCR) technology used mainly for NOx reduction. There are several challenges with respect to operation and maintenance of SCR equipment, specifically in a thermal power plant. The NOx removal efficiency and ammonia slip are typically used as indicators of SCR catalyst condition, however highly unpredictable nature of catalyst degradation and lack of enough sensors make it difficult even for an experienced operator to take appropriate decisions.
[021] Few control systems exist in the prior art for the monitoring the performance of SCR equipment, but most of them cater to automobile SCRs where the problems like ash deposition are not very relevant. There are no comprehensive systems available in the prior art for online monitoring and forecast of SCR health in terms of operating efficiency, fouling/clogging conditions, Ammonia (NH3) slip prediction and forecast. Further, the existing approaches either use data based approach or purely empirical based approach. This may not be sufficient to provide a comprehensive solution to SCR related issues. Data based systems will not be able to work when the SCR is new and does not have any past operation data. The empirical systems are either not accurate or lack the speed of calculation to be useful in real-time applications.
[022] Referring now to the drawings, and more particularly to FIG. 1 through FIG. 8, where similar reference characters denote corresponding features consistently throughout the figures, there are shown preferred embodiments and these embodiments are described in the context of the following exemplary system and/or method.
[023] According to an embodiment of the disclosure, a system 100 for real-time monitoring, optimization and forecasting output and health of selective catalytic reduction (SCR) equipment in a thermal power plant 102 is shown in the network diagram of Fig. 1 and an architecture diagram of FIG. 2. The system 100 is utilizing a digital replica of the SCR equipment used in the thermal power plant 102. The digital replica is used for monitoring and advance forecast of the condition of SCR equipment. The condition may be represented by NOx conversion efficiency, differential pressure or catalyst activity levels. The system 100 is configured to diagnose the causes of current SCR equipment conditions. In addition, the system 100 provides an advisory system to improve the life of SCR catalyst. The advisory system provides recommendation to improve the life of SCR equipment. Alternatively, the system 100 also provides a way to improve the overall operation in view of degrading catalyst activity.
[024] The system, 100 also provides a solution to account for the effect of ash deposition and its effect on catalyst deactivation. The system 100 also provides long term forecast of future requirement and leaking of reducing agent. This helps the operators in making right decisions in just the right time.
[025] Although the present disclosure is explained considering that the system 100 is implemented on a server, it may also be present elsewhere such as a local machine or an edge or cloud. It may be understood that the system 100 comprises one or more computing devices 104, such as a laptop computer, a desktop computer, a notebook, a workstation, a cloud-based computing environment and the like. It will be understood that the system 100 may be accessed through one or more input/output interfaces 106, collectively referred to as I/O interface 106. Examples of the I/O interface 106 may include, but are not limited to, a user interface, a portable computer, a personal digital assistant, a handheld device, a smartphone, a tablet computer, a workstation and the like. The I/O interface 106 is communicatively coupled to the system 100 through a network 108.
[026] In an embodiment, the network 108 may be a wireless or a wired network, or a combination thereof. In an example, the network 108 can be implemented as a computer network, as one of the different types of networks, such as virtual private network (VPN), intranet, local area network (LAN), wide area network (WAN), the internet, and such. The network 108 may either be a dedicated network or a shared network, which represents an association of the different types of networks that use a variety of protocols, for example, Hypertext Transfer Protocol (HTTP), Transmission Control Protocol/Internet Protocol (TCP/IP), and Wireless Application Protocol (WAP), to communicate with each other. Further, the network 108 may include a variety of network devices, including routers, bridges, servers, computing devices, storage devices. The network devices within the network 108 may interact with the system 100 through communication links.
[027] The system 100 may be implemented in a workstation, a mainframe computer, a server, and a network server. In an embodiment, the computing device 104 further comprises one or more hardware processors 110, one or more memory 112, hereinafter referred as a memory 112 and a data repository 114, for example, a repository 114. The memory 112 is in communication with the one or more hardware processors 110, wherein the one or more hardware processors 110 are configured to execute programmed instructions stored in the memory 112, to perform various functions as explained in the later part of the disclosure. The repository 114 may store data processed, received, and generated by the system 100.
[028] The system 100 supports various connectivity options such as BLUETOOTH®, USB, ZigBee and other cellular services. The network environment enables connection of various components of the system 100 using any communication link including Internet, WAN, MAN, and so on. In an exemplary embodiment, the system 100 is implemented to operate as a stand-alone device. In another embodiment, the system 100 may be implemented to work as a loosely coupled device to a smart computing environment. The components and functionalities of the system 100 are described further in detail.
[029] According to an embodiment of the disclosure, the memory 112 further comprises a plurality of units. The plurality of units are configured to perform various functions. The plurality of units comprises a preprocessing unit 116, a predictor unit 118, a simulator unit 120, a recommender unit 122, a model upgrade unit 124, and a catalyst monitor unit 126.
[030] The system 100 is a digital system 100 connected to a one or more sources 104. The one or more sources 104 may include the thermal power plant’s data recording, retrieval and control systems. For example, the plant distributed control system (DCS), Laboratory information management system (LIMS), historian and other systems are connected to the system 100 through a two-way communication channel via a data acquisition and communication unit 130. The system 100 receives real-time data from a thermal power plant 102 which is stored in a data repository 108 or a database 108. The system 100 provides real-time monitoring, forecast and recommendations, which is communicated back to a control system of the thermal power plant 102 and the operator through a graphic user interface 110. There is also a way of entering manual data or information through the system 100.
[031] The system 100 receives the real-time data from a plurality of data sources 128. The plurality of data sources like data repository 118, distributed control system (DCS), Laboratory information management system (LIMS), MES and other digital systems from the plant. Data can also be collected from advanced sensors installed for sensing specific operating conditions. The data may also be collected from external sources and manual input. This data and the historical data accumulated in a data historian is connected to the digital twin (on edge/cloud) through a communication interface. According to an embodiment of the disclosure, the data repository 118 may comprise of information/data related to materials, operational data, maintenance information, design information, equipment information, predictive models, optimization models, operation data, processed data, recommendations/ decisions from the system, environmental parameters and expert knowledge among others.
[032] According to an embodiment of the disclosure, the I/O interface 106 or a graphic user interface (GUI) 106 is the user interface of the system 100 which is used by a user or an operator of the system 100. The GUI 106 works as interactive mode to exchange information between the system 100, the data repository 114 and the user. The GUI 106 is also configured to display the thermal power plant operation in real time, shows the trends of the plurality of key variables. The user interacts with the system 100 via the GUI 106 where the user can perform simulation for detailed analysis. The GUI 106 is accessible to the user via smartphones, laptop or desktop configuration thus giving the user the freedom to interact with the system 100 from anywhere anytime. The graphic user interface 106 may include a variety of software and hardware interfaces, for example, interfaces for peripheral device(s), such as a keyboard, a mouse, an external memory, a camera device, and a printer. The interfaces 106 can facilitate multiple communications within a wide variety of networks and protocol types, including wired networks, for example, local area network (LAN), cable, etc., and wireless networks, such as Wireless LAN (WLAN), cellular, or satellite.
[033] According to an embodiment of the disclosure, the key parameters at the entry of the SCR catalyst layers are referred to as a first set of parameters and parameters at the exit of the SCR catalyst layer are referred to as the second set of parameters. The first set of parameters for the catalyst layer comprises conditions at an upstream of the catalyst layer, wherein the conditions comprise a concentration of NOx, a concentration of ammonia, a concentration of Sulphur oxides and a temperature and a pressure of a flue gas. The second set of parameters for the catalyst layer comprises conditions at a downstream of the catalyst layer, wherein the conditions comprise the concentration of NOx, the concentration of ammonia, the concentration of Sulphur oxides and the temperature, and the pressure of the flue gas. The conditions can be measured using set of permanent or temporary sensors.
[034] According to an embodiment of the disclosure, the memory 112 comprises the preprocessing unit 116. The preprocessing unit 116 is configured to preprocess the received plurality of data to remove erroneous data and fill missing data. The preprocessing unit 116 also imputes new values in place of missing values, and transforms the plurality of data into different shape, size and frequency based on the SCR design specifications, forecasting horizon and the available plant data.
[035] The processing unit 116 receives the real-time data from the plant DCS, LIMS and other connected supplementary equipment via a communication device. It merges the data coming from different sources at different frequency such as operation data from sensors received every minute and LIMS data updated every hour/shift. It is connected to the cloud or database and keeps track of both operational and real-time data. Furthermore, depending upon the need of the predictor unit 118 and the catalyst monitor unit 126, the preprocessing unit 116 transform the data appropriately and save it in the data repository 114 for future use. As an example, the preprocessing unit 116 smoothen out data or do pattern based selection of data for various units. The preprocessing unit 116 also comprise identification of operating regimes such as steady and transient. The preprocessing unit 116 may also separate the data based on maintenance cycle of SCR and other equipment.
[036] According to an embodiment of the disclosure, the memory 112 further comprises the predictor unit 118. The predictor unit 118 forecasts the first set of parameters and the second set of parameters that comprise of inlet NOx, inlet NH3, inlet SO2, catalyst degradation index, outlet NOx, NH3 slip, outlet SO3 at each catalyst layer of the SCR over a predefined forecasting horizon or a predefined forecast time tf. The predictor unit 118 makes use of degradation forecast models that comprise of a chemical reaction model, an estimator model and degrade forecast models, prebuilt into the database 114.
[037] According to an embodiment of the disclosure, the system 100 is configured to also act as a simulator. For that purpose, the system 100 comprises the simulator unit 120. The simulator unit 120 allows the operator to do an online “what-if” scenario analysis. The simulator unit 120 receives the real-time processed data from the plant and predicts/ forecasts the parameters comprising of catalyst degradation index, NH3 slip. The difference of the simulator unit 120 from the predictor unit 118 is that, here the operator has an option to change the value of inputs and its trends. The system 100 may be connected to external sources and databases such as weather forecast and coal property databases.
[038] According to an embodiment of the disclosure, the system 100 also comprises the recommender unit 122. The recommender unit 122 provides operation set points and recommendations to the operator for improving the performance and maintenance of the SCR. The recommendations can be based on the operation settings of SCR equipment such as soot-blowing time/frequency/intensity and allowable NOx set-point or they can be from more global perspective such as coal usage advisory (ash and other elements content in coal), boiler operation settings, addition/removal of process characteristic measuring device, addition/removal of process equipment, design changes for process improvement (addition of NH3 at various locations). The recommender unit 122 also includes advice on maintenance activities such as when to change the catalyst layer and which one to change. It may provide a schedule for replacement / maintenance of catalyst layers based on real-time forecasting and monitoring.
[039] The system 100 is driven by the predictive and forecast models based on a combination of first principles based modelling, data science and artificial intelligence based on domain knowledge. The advisory may be supported by various optimization algorithms. According to an embodiment of the disclosure, the system 100 also comprises the model upgrade unit 124. The model upgrade unit 124 periodically checks the performance of the catalyst monitor and degradation forecasting models against the actual plant data obtained at that time. If the accuracy of the model does not match pre-defined accuracy constraint/criteria/band, the model update alarm is generated. This triggers the auto-update loop that rebuilds/re-tunes the predictive models based on the processed data of the plant. The models updated with latest data representing recent behavior of SCR equipment are then used as soft sensors and forecasters.
[040] FIG. 3 illustrates an example flow chart of a method 300 for monitoring and forecasting of catalyst degradation of a selective catalytic reduction (SCR) equipment, in accordance with an example embodiment of the present disclosure. The method 300 depicted in the flow chart may be executed by a system, for example, the system 100 of FIG. 1. In an example embodiment, the system 100 may be embodied in the computing device.
[041] Operations of the flowchart, and combinations of operations in the flowchart, may be implemented by various means, such as hardware, firmware, processor, circuitry and/or other device associated with execution of software including one or more computer program instructions. For example, one or more of the procedures described in various embodiments may be embodied by computer program instructions. In an example embodiment, the computer program instructions, which embody the procedures, described in various embodiments may be stored by at least one memory device of a system and executed by at least one processor in the system. Any such computer program instructions may be loaded onto a computer or other programmable system (for example, hardware) to produce a machine, such that the resulting computer or other programmable system embody means for implementing the operations specified in the flowchart. It will be noted herein that the operations of the method 300 are described with help of system 100. However, the operations of the method 300 can be described and/or practiced by using any other system.
[042] Initially at step 302 of the method 300, a plurality of data related to the SCR equipment is received from a plurality of data sources 128, wherein the SCR equipment having a plurality of catalyst layers. The plurality of data comprises one or more of data received from distributed control system (DCS), data received from historian, data received from laboratory information management system (LIMS), data received from a plurality of external sources, manual input data received from a plurality of digital systems present in the in a power plant, design and maintenance information, catalyst degradation information, a plurality of domain parameters, and predicted values from a plurality of data models.
[043] At step 304, the received plurality of data is then preprocessed, wherein the preprocessed plurality of data is synchronized in a data repository regularly at a regular time interval. At step 306, a catalyst degradation index is predicted for each catalyst layer of the plurality of catalyst layers using a catalyst degradation model, wherein the inputs for catalyst degradation model comprise of measured values of the first set of parameters and measured values of the second set of parameters from the plurality of preprocessed data. In this step the first set of parameters and the second set of parameters may be measured using various permanent and temporary sensors installed in the thermal power plant.
[044] At step 308, a second set of parameters is predicted for each catalyst layer of the plurality of catalyst layers using a chemical reaction model wherein the inputs to the chemical reaction model comprise of predicted catalyst degradation index and measured values of the first set of parameters from the plurality of preprocessed data.
[045] At step 310, the first set of parameters for a first catalyst layer of the plurality of catalyst layers is estimated over a predefined forecast time period (tf) using an estimator model for the first catalyst layer and the preprocessed plurality of data.
[046] Further, at step 312, the catalyst degradation index is forecasted for the first catalyst layer over the predefined forecast time tf period using a degradation forecast model of the first catalyst layer, estimated values of the first set of parameters for the first catalyst layer, and the preprocessed plurality of data.
[047] At step 314, the second set of parameters for the first catalyst layer is forecasted over the predefined forecast time using the estimated first set of parameters for the first catalyst layer, the forecasted catalyst degradation index for the first catalyst layer and the plurality of processed data using a chemical reaction model. At step 316, the catalyst degradation index for each catalyst layer of the plurality of catalyst layers is forecasted over the predefined forecast time using the degradation forecast model of the respective catalyst layer, the forecasted second set of parameters from the previous catalyst layer of the plurality of catalyst layers and the plurality of processed data.
[048] Further at step 318, the second set of parameters of the each catalyst layer of the plurality of catalyst layers is forecasted over the predefined forecast time using the forecasted second set of parameters of the previous catalyst layer and the forecasted catalyst degradation index of the current catalyst layer. And finally at step 320 a set of recommendations is provided for optimal maintenance and scheduling for each catalyst layer and the SCR equipment based on the forecasted catalyst degradation index of the last catalyst layer and the forecasted second set of parameters for the last catalyst layer.
[049] FIG. 4 shows the flowchart 400 illustrating steps involved in real-time monitoring of catalyst degradation and key parameters comprising NH3 slip according to some embodiments of the present disclosure. The preprocessed data arrived from the preprocessing unit 116 is utilized for this purpose. The data may comprise of flue gas flow rate, gas temperatures, gas pressures, gas chemical composition (NOx, SO2), reagent (NH3) flow rate, ambient conditions and so on. Alternatively, temporary sensors could be used for measuring NOx at the entry and exit of each layer of catalyst. This is required so that the health of catalyst can be effectively tracked for each layer of SCR independently. At step 402, this data is first used by the catalyst degradation model and the chemical reaction model to predict catalyst degradation index in real-time for each layer separately. Once the catalyst degradation is identified for each layer, at step 404, the chemical reaction models are used to predict the second set of parameters comprising concentrations of NH3 slip, NOx and SO3 at the exit of each layer, the pressure drop (indicating the ash clogging) across each layer. The second set of parameters are then given to the predictor unit 118.
[050] The schematic illustrating the chemical reaction model 500 is shown in FIG. 5. The chemical reaction model 500 comprises of combination of first principles based model and the data driven models. As one embodiment of this disclosure, the chemical reaction model may comprise of a physics-informed neural network model that finds a solution to differential equations representing the flow, heat transfer and the chemical reactions involved in the SCR process. The model uses the first set of parameters (real-time sensor data comprising of gas flow, gas temperature, gas composition, gas pressure at the entry of each layer), design information of SCR, ash content from the coal properties, the domain parameters such as heat transfer coefficients, chemical kinetic constants, reaction rates and the catalyst degradation index to predict the second set of parameters (key parameters at the exit of SCR layer). The predicted second set of parameters comprise of gas composition (NOx, SO3, NH3), gas temperature, gas pressure. The chemical reaction model 500 is pre-built and validated using the historical data of the plant for each layer of SCR separately. The catalyst degradation index may be represented as a function of physics based parameters or weights of neural network model.
[051] According to an embodiment of present disclosure, the catalyst degradation index is represented as a function of voidage fraction and available surface area of an SCR catalyst bed. The voidage fraction indicates the area available for flow for gas and the surface area available indicates the surfaces where the components interact with a catalyst for the NOx reduction reaction to take place.
[052] The catalyst degradation model comprises of parameters estimation loop over the chemical reaction model. The catalyst degradation model uses the chemical reaction model iteratively so as to identify the optimum value of catalyst degradation index. The value of catalyst degradation index is considered to be optimum when the difference between the key parameters comprising NOx, predicted by the internal chemical reaction model and the actual sensor value is below the set error threshold. The set error threshold could be modified by the user as per the need.
[053] The catalyst degradation model could be used in parallel for all layers of the SCR when at least a NOx sensor is available at the exit of each layer of the SCR. Alternatively, the catalyst degradation models can be used in series when the limited number of sensors are available at the exit of SCR layers. In that case, the catalyst degradation index for all the layers are identified together by tuning the SCR exit NOx predicted by the series of chemical reaction models, against the actual NOX measured at the exit of SCR.
[054] Fig. 6A-6B is a flowchart 600 illustrating steps in forecasting catalyst degradation and other key parameters comprising NH3 slip over the predefined forecast time tf. At step 602. the preprocessed data from the preprocessing unit 116 are first transformed appropriately to feed them to the degradation forecast model. This transformation comprises merging data, down-sampling of the data, appropriate scaling, removing outliers and cleaning the data. At step 604, the processed data is used to estimate trends in the first set of parameters over the forecast horizon tf using the estimator model in the degradation forecast models. At step 606, forecast models in catalyst degradation forecast models are used to forecast the trends in catalyst degradation index over the forecast horizon tf, using the preprocessed data at step 602 and the estimated values of the first set of parameters at step 604. At step 608, the chemical reaction models in catalyst degradation forecast models are used in a repetitive manner at predefined interval h over the forecast horizon tf, to forecast the trends in the second set of parameters. The second set of parameters may comprise of gas composition (NOx, NH3, SO3, mercury), gas temperature, gas pressures at the exit of given SCR layer. All the values forecasted are stored in the database. At step 610, the next catalyst layer is chosen. At step 612, it is checked if there are more layers in SCR. If no, then the process stops. If yes, at step 614, the catalyst degradation forecast model for next layer (n=2) is used to forecast trends in catalyst degradation index for the next layer (n=2), using the forecast of the second set of parameters from step 608 (n=1) and the preprocessed data at step 602. At step 616, the forecast of catalyst degradation index for next layer (n=2) and the forecast of the second set of parameters from step 608 (n=1) are used by the chemical reaction model for next layer (n=2) to forecast the second set of parameters for next layer (n=2). Steps 612 to 616 are repeated for every successive layer until all layers of SCR are accounted for. The final forecasts for each layer are stored in the database.
[055] Fig. 7 illustrates the input output structure of the catalyst degradation forecast models for layer 1 of the SCR. The catalyst degradation forecast models for layer 1 comprises of estimator models, forecast model and chemical reaction model.
[056] As one embodiment of this disclosure, the estimator model comprises of machine/deep learning time series models that receive the past data and external inputs to estimate the trends of the first set of parameters over forecasting horizon Tf. The inputs for estimator models comprise of synchronized historical data from catalyst monitor unit and predictor unit. This may comprise previously stored data for design, maintenance, LIMS, predicted catalyst degradation index, the first set of parameters and the second set of parameters for layer 1 of SCR. These estimator models could be univariate time series models or detailed multivariate time series models incorporating downstream/connected equipment parameters. For example, estimator sub-model for NOx at inlet of SCR layer 1 may comprise of a deep learning based time series model that uses the past data of the first set of parameters, historical soft sensed values of catalyst degradation index of layer 1, past and anticipated future coal usage and properties to predict the expected NOx at the inlet of SCR layer 1 over forecasting horizon tf.
[057] The forecasting model for layer 1 comprises of a neural network model that forecasts the trend of catalyst degradation for layer 1 over forecasting horizon tf. The forecasting model could be a hybrid model comprising of a deep learning network embedded with a physics. The model may use inputs that comprise of output from estimator model for layer 1 as well as synchronized historical data from catalyst monitor unit and predictor unit for layer 1. In addition, the forecast model may use design and maintenance information for layer 1 and the domain parameters such as heat transfer coefficients, chemical kinetics for layer 1 (stored in the database). The forecasting model can be used in a repetitive loop in order to extend its forecast capability.
[058] The chemical reaction model in the degradation forecast model for layer 1 uses the output from estimator model, output from forecast model, design-maintenance information and the domain parameters for layer 1 to forecast the values of the second set of parameters for layer 1 over forecasting horizon tf. The chemical reaction model may do this forecast at specified intervals of duration h, which could be preset or provided by the operator. The forecast occurs at every time interval of h until the forecast horizon is reached.
[059] Fig. 8 shows the catalyst degradation forecast models for SCR layers other than the first layer. The forecast model for layer n utilizes synchronized historical data from catalyst monitor unit and predictor unit comprising of previously stored data for design, maintenance, LIMS, predicted catalyst degradation index, the first set of parameters and the second set of parameters for layer n. In addition, it may use estimated/ forecasted values of the second set of parameters for layer n-1 over forecasting horizon tf (equivalent to the first set of parameters for layer n). The forecast model then predicts the trend in catalyst degradation index over the forecasting horizon tf for layer n. For instance, degradation index of layer 2 could be predicted over forecasting horizon tf by using the forecasted values of the second set of parameters for layer 1 (which is nothing but estimated the first set of parameters for layer 2) along with all the previously stored from the database.
[060] The forecasted values of degradation index for layer 2 are then used by chemical reaction model of layer 2 along with design, maintenance and domain parameters information to predict the second set of parameters for layer 2 over forecasting horizon tf. This forecast may also comprise of repeated predictions at time interval h until the forecasting horizon is reached.
[061] The forecasts done by the catalyst degradation forecast model could be utilized for providing alerts and notifications to the user regarding upcoming operating and maintenance issues. In addition, outputs from catalyst monitor and predictor units could be used to provide the operation and maintenance recommendations to the operator.
[062] All the models in the units – catalyst degradation model, chemical reaction model, estimator model and forecast model may comprise of a combination of first-principles based models (heat transfer, fluid flow, chemical kinetics, deposition), data-driven models (machine learning, deep learning, reinforcement learning) and knowledge driven models (expert knowledge rules, heuristics, industry guidelines, Original equipment manufacturer handbooks).
[063] According to an embodiment of the disclosure, the system 100 can be installed at the thermal power plant location or on a distributed (cloud) platform. The system 100 can be used in another thermal power plant by adjusting the characteristic parameter values of predictive models. For example, model characteristic parameters like design of SCR, operating load of power plant, ambient conditions, fuel and its usage pattern, emission control norms of the region (in which power plant is located), power plant operational history (newly commissioned/ old plant). The system 100 could also be installed at any other plant with a selective catalytic reduction unit.
[064] The written description describes the subject matter herein to enable any person skilled in the art to make and use the embodiments. The scope of the subject matter embodiments is defined by the claims and may include other modifications that occur to those skilled in the art. Such other modifications are intended to be within the scope of the claims if they have similar elements that do not differ from the literal language of the claims or if they include equivalent elements with insubstantial differences from the literal language of the claims.
[065] The embodiments of present disclosure herein addresses unresolved problems related to monitoring of the catalyst layer present in the SCR equipment. The embodiment, thus provides a method and system for monitoring and forecasting of catalyst degradation of a selective catalytic reduction (SCR) equipment.
[066] It is to be understood that the scope of the protection is extended to such a program and in addition to a computer-readable means having a message therein; such computer-readable storage means contain program-code means for implementation of one or more steps of the method, when the program runs on a server or mobile device or any suitable programmable device. The hardware device can be any kind of device which can be programmed including e.g., any kind of computer like a server or a personal computer, or the like, or any combination thereof. The device may also include means which could be e.g., hardware means like e.g., an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a combination of hardware and software means, e.g., an ASIC and an FPGA, or at least one microprocessor and at least one memory with software processing components located therein. Thus, the means can include both hardware means and software means. The method embodiments described herein could be implemented in hardware and software. The device may also include software means. Alternatively, the embodiments may be implemented on different hardware devices, e.g., using a plurality of CPUs.
[067] The embodiments herein can comprise hardware and software elements. The embodiments that are implemented in software include but are not limited to, firmware, resident software, microcode, etc. The functions performed by various components described herein may be implemented in other components or combinations of other components. For the purposes of this description, a computer-usable or computer readable medium can be any apparatus that can comprise, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
[068] The illustrated steps are set out to explain the exemplary embodiments shown, and it should be anticipated that ongoing technological development will change the manner in which particular functions are performed. These examples are presented herein for purposes of illustration, and not limitation. Further, the boundaries of the functional building blocks have been arbitrarily defined herein for the convenience of the description. Alternative boundaries can be defined so long as the specified functions and relationships thereof are appropriately performed. Alternatives (including equivalents, extensions, variations, deviations, etc., of those described herein) will be apparent to persons skilled in the relevant art(s) based on the teachings contained herein. Such alternatives fall within the scope of the disclosed embodiments. Also, the words “comprising,” “having,” “containing,” and “including,” and other similar forms are intended to be equivalent in meaning and be open ended in that an item or items following any one of these words is not meant to be an exhaustive listing of such item or items, or meant to be limited to only the listed item or items. It must also be noted that as used herein and in the appended claims, the singular forms “a,” “an,” and “the” include plural references unless the context clearly dictates otherwise.
[069] Furthermore, one or more computer-readable storage media may be utilized in implementing embodiments consistent with the present disclosure. 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., be non-transitory. Examples include random access memory (RAM), read-only memory (ROM), volatile memory, nonvolatile memory, hard drives, CD ROMs, DVDs, flash drives, disks, and any other known physical storage media.
[070] It is intended that the disclosure and examples be considered as exemplary only, with a true scope of disclosed embodiments being indicated by the following claims.