Abstract: The present invention relates to operation and control of hot strip mill rolling process using a model based web-portal. The web-portal consisting of a mathematical-artificial neural network based model calculates optimized gap (7) and speed reference values (8) using mathematical theory of plastic deformation, heat transfer and microstructure evolution during hot rolling process. The model uses on-line data (1, 2, 3, 4) collected from mill automation system to train itself using artificial neural network technique. The portal sends the calculated optimized references values (7, 8) to the mill through mill automation system. The model also needs fine-tuning of its calibration parameters (5) which is generally done by model experts. The portal provides platform for fine-tuning of process parameters from a remote location eliminating the requirement of physical presence of the experts at the site. The present invention is particularly helpful in improving operation practice and control of a hot strip mill.
CLIAMS:1. A Web-portal based automation system for setting of roll gap and speed references in a hot strip mill from a remote location comprising:
- plurality of finishing stands;
- plurality of mill sensors;
- plurality of mill actuators;
- at least two PLC systems for acquiring process data of the rolling from mill sensors and sending the calculated gap and speed reference to the mill actuators;
- at least one VAX system for acquiring primary data; and
- at least one ERP system for acquiring chemical composition data of the rolled material;
wherein one of the said PLC system records mill operating data consists of gap setup values and roll force values from said finishing stand(s) for each and every coil processed in the hot strip mill and other said PLC system records speed reference, actual speed, temperature, strip thickness, looper tension and looper angle data;
wherein at least one L2-Web Server comprising mathematical-artificial neural network based model for calculating the optimized values of gap and speed based on the acquired data; and
wherein said L2-Web Server operatively connected with the PLC system, the VAX system and the ERP system for receiving the process data and sending the calculated gap and speed schedule to the said mill through the PLC system.
2. The system as claimed in claim 1, wherein said L2-Web Server comprises L1-L2 Database, L2-database, L2-L1 Database to store all the input data of each and every coil for post-process analysis.
3. The system as claimed in claim 2, wherein said L1-L2 Database, L2-database, L2-L1 Database are Relational Database Management Systems (RDBMS).
4. The system as claimed in claim 1, wherein core unit of said L2-Web Server comprises:
- L1-L2 data communication system (L1-CCS) unit to receive data from PLCs, VAX, ERP and store in a L1-L2 Database;
- Model Control System (MCS) to calculate the optimized gap and speed schedule and stores these values in a L2-database based on mathematical-Artificial Neural Network (ANN) model;
- Auto-Calibration System (ACS) to train the ANN model and stores the updated values of weights and bias in L2-Database;
- Developer Control System (DCS) to receive the fine-tuned model calibration values and store in L2-Database;
- Operator Control System (OCS) to switch between Model-mode to Operator-mode;
- L2-L1 Communication System (L2-CCS) system to send the model calculated gap and speed reference stored in L2-L1 Database to the mill through PLC system.
5. The system as claimed in claim 4, wherein said L2-L1 Communication System (L2-CCS) system comprises SDataWinCC Module and ABB-BB module:
wherein said SDataWinCC Module gets the (Automatic Gauge Control) AGC operator selection in Model-Mode or Operator-mode; and
ABB-BB module checks some safety limits and sends the speed reference data to mill.
6. The system as claimed in claim 5, wherein said SDataWinCC comprises of:
- GDataL2DB sub-module to obtain gets the model predicted Gap and Speed reference values from the L2-L1 Database using ADO protocol;
- SL2SpeedData sub-module to send the model calculated speed schedule to the mill using OPC program; and
- SL2GapData sub-module to send the model calculated gap reference to the mill through L2-Web Server.
7. The system as claimed in claim 4, wherein said Model-mode is mathematical-Artificial Neural Network (ANN) model mode.
8. The system as claimed in claim 4, wherein said Operator-mode is manual mode.
9. The system as claimed in claim 4, wherein said Developer Control System (DCS) fine-tunes the model from far remote location.
10. The system as claimed in claim 1, wherein said primary data comprises diameter of work rolls, grade of steel, target thickness, target width.
11. The system as claimed in claim 1 wherein said system self-trains the artificial-neural network module and stores the updated values of weight and bias in the database for use of the model for predicting parameters in the next coil.
12. The system as claimed in claim 1 wherein the said system sends the online calculated roll gap speed gap references to the respective PLC system as output through the database.
,TagSPECI:FIELD OF THE INVENTION
The present invention relates to operation and control of hot strip mill rolling process using a model based web-portal. More particularly, the present invention provides platform for fine-tuning of process parameters from a remote location eliminating the requirement of physical presence of the experts at the site.
BACKGROUND OF THE INVENTION
The present invention is intended to be applied to a hot strip mill. The present invention relates to a rolling control method, in particular to a method for controlling the rolling gap, etc., belong to the technical field of metallurgy. Rolling is classified according to the temperature of work piece rolled. If the temperature of the metal is above its recrystallization temperature, then the process is termed as hot rolling. For hot working processes, large deformation can be successively repeated, as the metal remains soft and ductile. The metal stock is subjected to high compressive stresses as a result of the friction between the rolls and the metal surface. Rolling involves passing the material between two rolls revolving more or less at the same peripheral speed but in opposite directions, i.e., clockwise and counterclockwise. The distance between them is spaced, which is somewhat less than the height of the metal stock entering them. These rolls can either be flat or grooved (contoured) for the hot rolling of rods or shapes.
US 3733866 A discloses a method of controlling a continuous hot rolling mill and more particularly to a method of controlling the acceleration of a continuous hot rolling mill wherein the roll gap and the roll peripheral speed of each mill stand is controlled according to a predetermined pattern in order to maintain the gauge of the finished plates at a constant value and to eliminate off-gauge products when accelerating the rolling mill.
US 6227021 B1 teaches a control apparatus for a hot rolling mill having a plurality of rolling stands, including a roll gap tension controller configured to control a roll gap of one of the rolling stands so that a detected interstand tension value of a rolled material positioned between the adjacent rolling stands accords with a target interstand tension value thereof; and a tension width controller configured to control a width of the rolled material by correcting the target interstand tension value.
The earlier practice of determining roll gap and speed references to the mill was manually by mill operators. The operator had to decide the roll gap and speed references based on his skill and experience. In the present invention, these reference values are calculated by a mathematical-artificial neural network model based web-portal and selected in the mill automatically through mill automation system. The web-based portal is also used to fine-tune the model calibration from a remote location (generally from a different city where the model experts are located)
The web-portal of the present invention consisting of a mathematical-artificial neural network based model calculates optimized gap and speed reference values using mathematical theory of plastic deformation, heat transfer and microstructure evolution during hot rolling process. The model of the present invention uses on-line data collected from mill automation system to train itself using artificial neural network technique. The portal sends the calculated optimized references values to the mill through mill automation system. The model also needs fine-tuning of its calibration parameters which is generally done by model experts. The present invention is particularly helpful in improving operation practice and control of a hot strip mill.
OBJECTS OF THE INVENTION
The prime object of the present invention is to overcome one or more of the drawbacks of the related prior art.
It is an object of the present invention is to develop a model based web-portal which calculates the gap and speed reference values of a hot rolling mill using a mathematical-artificial neural network model based on the input data received from the mill automation system.
Another object of the invention is that the web-portal sends the calculated gap and speed schedules to the mill through mill automation system.
Yet another object of the present invention is to develop a platform in the web-portal through which the mill expert can fine-tune the model from a remote location.
Yet another object of the invention is that the mill operators can visualize the model calculated gap and speed schedules through the web-portal and change the mode from model-mode to manual-mode as per their convenience.
These and other objects of the present invention will become readily apparent from the following detailed description read in conjunction with the accompanying drawings.
SUMMARY OF THE INVENTION
The following presents a simplified summary of the invention in order to provide a basic understanding of some aspects of the invention.
Thus according to one of the aspect of the present invention, there is provided a mill automation system for facilitating automatic rolling of steel strips in a hot rolling mill comprising:
PLC system for acquiring process data of the rolling including roll gap, entry temperature of the steel strips, roll diameter, rolling speed, looper angle, looper tension, roll force, motor current from mill sensors and also sending the calculated gap and speed reference to the mill actuators;
VAX system for acquiring primary data including diameter of work rolls, grade of steel, target thickness, target width;
ERP system for chemical composition of the rolled material;
L2-Web Server operatively connected with the PLC system, the VAX system and the ERP system for receiving the process data and sending the calculated gap and speed schedule to the mill through PLC system. The L2-Webserver also hosts web-portal of the mathematical-artificial neural network based model which calculates the optimized values of gap and speed based on the input data.
According to non-limiting aspect of the invention there is provided a Web-portal based automation system for setting of roll gap and speed references in a hot strip mill from a remote location comprising:
plurality of finishing stands;
plurality of mill sensors;
plurality of mill actuators;
at least two PLC systems for acquiring process data of the rolling from mill sensors and sending the calculated gap and speed reference to the mill actuators;
at least one VAX system for acquiring primary data; and
at least one ERP system for acquiring chemical composition data of the rolled material;
wherein one of the said PLC system records mill operating data consists of gap setup values and roll force values from said finishing stand(s) for each and every coil processed in the hot strip mill and other said PLC system records speed reference, actual speed, temperature, strip thickness, looper tension and looper angle data;
wherein at least one L2-Web Server comprising mathematical-artificial neural network based model for calculating the optimized values of gap and speed based on the acquired data; and
wherein said L2-Web Server operatively connected with the PLC system, the VAX system and the ERP system for receiving the process data and sending the calculated gap and speed schedule to the said mill through the PLC system.
In another non-limiting aspect of the invention core unit of said L2-Web Server comprises:
L1-L2 data communication system (L1-CCS) unit to receive data from PLCs, VAX, ERP and store in a L1-L2 Database;
Model Control System (MCS) to calculate the optimized gap and speed schedule and stores these values in a L2-database based on mathematical-Artificial Neural Network (ANN) model;
Auto-Calibration System (ACS) to train the ANN model and stores the updated values of weights and bias in L2-Database;
Developer Control System (DCS) to receive the fine-tuned model calibration values and store in L2-Database;
Operator Control System (OCS) to switch between Model-mode to Operator-mode;
L2-L1 Communication System (L2-CCS) system to send the model calculated gap and speed reference stored in L2-L1 Database to the mill through PLC system.
Another aspect of the invention is that the web-portal sends the calculated gap and speed schedules to the mill through mill automation system.
Yet another aspect of the invention is that the web-portal stores all the input data of each and every coil in a database for post-process analysis and sends the online calculated roll gap speed gap references to the respective PLC system as output through the database.
Yet another aspect of the invention is that the web-portal self-trains the artificial-neural network module and stores the updated values of weight and bias in the database for use of the model for predicting parameters in the next coil.
Yet another aspect of the present invention is that the web-portal has a developer control system platform through which the mill expert can fine-tune the model from a remote location (may be from a different city).
Yet another aspect of the present invention is that the web-portal has facilitate the mill engineers/managers to supervise the mill operation from any remote terminal from the steel plant.
Yet another aspect of the invention is that the web-portal enables the mill operators to visualize the model calculated gap and speed schedules through the web-portal and change the mode from model-mode to manual-mode as per their convenience
To enable the invention to be more clearly understood and carried into practice, reference is now made to the accompanying drawing in which like references denote like parts throughout the description
BRIEF DESCRIPTION OF THE ACCOMPANYING FIGURES
The different preferred embodiments of the invention will now be described, by way of example with reference to the accompanying drawings, in which:
Figure 1 shows a schematic illustration of hardware associated with a hot strip rolling mill.
Figure 2 shows Context Diagram of the interaction of various hardware for which the model based portal receives the data and sends the output.
Figure 3 shows various sub-units of model based portal of present invention.
Figure 4 shows methodology of taking data input from system by the portal.
Figure 5 shows the data flow diagram of portal output between the model output database and mill actuators through PLC systems.
Figure 6 shows data flow diagram within the output communication unit.
Persons skilled in the art will appreciate that elements in the figures are illustrated for simplicity and clarity and may have not been drawn to scale. For example, the dimensions of some of the elements in the figure may be exaggerated relative to other elements to help to improve understanding of various exemplary embodiments of the present disclosure.
Throughout the drawings, it should be noted that like reference numbers are used to depict the same or similar elements, features, and structures.
DETAILED DESCRIPTION OF THE INVENTION
The following description with reference to the accompanying drawings is provided to assist in a comprehensive understanding of exemplary embodiments of the invention as defined by the claims and their equivalents. It includes various specific details to assist in that understanding but these are to be regarded as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. In addition, descriptions of well-known functions, symbols, abbreviation and constructions are omitted for clarity and conciseness.
The terms and words used in the following description and claims are not limited to the bibliographical meanings, but, are merely used by the inventor to enable a clear and consistent understanding of the invention. Accordingly, it should be apparent to those skilled in the art that the following description of exemplary embodiments of the present invention are provided for illustration purpose only and not for the purpose of limiting the invention as defined by the appended claims and their equivalents.
It is to be understood that the singular forms “a,” “an,” and “the” include plural referents unless the context clearly dictates otherwise.
By the term “substantially” it is meant that the recited characteristic, parameter, or value need not be achieved exactly, but that deviations or variations, including for example, tolerances, measurement error, measurement accuracy limitations and other factors known to those of skill in the art, may occur in amounts that do not preclude the effect the characteristic is intended to provide.
Features that are described and/or illustrated with respect to one embodiment may be used in the same way or in a similar way in one or more other embodiments and/or in combination with or instead of the features of the other embodiments.
It should be emphasized that the term “comprises/comprising” when used in this specification is taken to specify the presence of stated features, integers, steps or components but does not preclude the presence or addition of one or more other features, integers, steps, components or groups thereof.
The advantages, nature, and various additional features of the invention will appear more fully upon consideration of the illustrative experiment now to be described in detail in connection with accompanying drawings.
Figure 1 shows a schematic diagram of a hot strip mill. Strips of different steel grades, thickness and width are rolled from slab in a hot strip mill. The typical conventional Hot Strip Mill shown in the figure comprises 3 Roughing stands and 6 Finishing stands. The first roughing stand (R0/V0) is a combination horizontal stand and a vertical stand. The other two roughing stands (R1 and R2) are 4 high horizontal stands. There is a delay table after R2 stand, one coil box and a crop shear at the end of the delay table. There are six numbers of 4 high finishing stands (F1 to F6) and two hydraulic down coilers. These mills are manual operated and the draft and speed schedules for different stands are set by the operator. The values of roll gap for draft schedule and the values of speed for speed schedule at different stands are calculated by the operators based on their experience and skill.
Figure 2 shows context diagram of the web-portal with the detailed description of each data label in Table 1. Table 1 provides details of reference ID used in Figure 2. Figure 2 shows that the flow of data from mill automation system to model and vice-versa. The figure 2 shows that different mill operating data (1) received from a PLC system (S7-400 PLC system of Siemens make). This data consists of gap setup values and roll force values from six finishing stands recorded by the PLC for each and every coil processed in the mill. Similarly speed reference, actual speed, temperature, strip thickness, looper tension and looper angle data (2) are received from another PLC system (800 PEC PLC of ABB make). The primary data input (3) including grade of steel, diameter of work rolls, target width and target thickness are received from VAX system. The chemical composition data (4) of steel are received from ERP system.
Table 1
The mode (6) selection (model-mode or manual-mode) signals are received from the mill operators through the portal itself. The model calibration parameters (5) also come to the model through the portal itself whenever the model is fine tuned by the model experts. The outputs of the Web-portal to various units are also shown in the figure. The Gap Reference (7) calculated by the portal is sent to the same Siemens S7-400 PLC system when model-mode is selected by the operator. Similarly the speed Reference data (8) is also sent to the mill through ABB 800 PEC PLC system when model-mode is selected by the operator. The operating performance data (9) are shown to mill operation engineers at any remote location. The model performance data like model error level (10) are shown to model developers at their remote location through the portal so that they can fine-tune the model in case of high errors. The model calculated gap and speed reference values (11) are also displayed to mill operators at their cabin (generally known as speed cabin of the mill).
Figure 3 depicts various sub-units of model based portal and the corresponding description of L-Web Server is provided in Table 2. The core unit of the portal consists of six numbers of sub-units. The L1-L2 data communication system (L1-CCS) unit is the communication program (P1) which receives data from PLCs, VAX, ERP (combined referred to as Level-1 Automation system) and stores in a Relational Database Management System (RDBMS). The name L1-L2 database in Figure 3 is the database where the all the input data is stored. The Model Control System (MCS) is the part of the portal in which the mathematical-Artificial Neural Network (ANN) model (called here as Level-2 Automation System) program (P2). This program (P2) runs automatically when the signal of discharge of a coil from the furnace is received to the portal, calculates the optimized gap and speed schedule and stores these values in a separate RDBMS called here as L2-Database. Table 2 illustrates the function of various sub-units of Figure 3.
Table 2
The Auto-Calibration System (ACS) runs automatically (P3) and trains the ANN program of the model and stores the updated values of weights and bias in L2-Database. The Developer Control System (DCS) is the platform of the Portal which receives the fine-tuned model calibration values and stores in L2-Database (P4). The fifth unit of the Portal is Operator Control System (OCS) which allows operators to switch between Model-mode to Operator-mode. Once the model-mode is selected, the model calculated gap and speed settings are sent to another RDBMS called L2-L1 database (P5). The last unit of the model is L2-L1 Communication System (L2-CCS) system which sends the model calculated gap and speed reference from the L2-L1 Database to the mill through PLC system (P6).
Figure 4 shows the methodology of taking data input from Mill Automation System by the portal. The communication between the PLC and portal takes place through a software called WinCC Server (of Siemens make). The data from the WinCC server is received by the model through OLE for Process Control (OPC) communication protocol. Similarly data from VAX system and ERP system are received using file transfer protocol (ftp) of communication. The data is stored in the database using ActiveX Data Objects (ADO) protocol of data communication between a program and RDCBMS. The L1-CCS program (P1) as described in Figure 3 has three sub-components. The GDataS7 program (P1.1) gets data from S7 PLC, the GDataABB (P1.2) gets data from 800 PEC PLC and GDataVAX program (P1.3) gets data from VAX and ERP systems.
Figure 5 shows the methodology of data transfer from L2-L1 Database to Mill through PLC systems. There are two sub-modules of L2-CCS module as described in Figure-3. Those sub-modules are SDataWinCC Module and ABB-BB module. Table 3 provides the description of the references used in Figure 5.
Table 3
There are basically two operators at operator cabin (called speed cabin) for controlling the mill. The operator which sets speed reference is called Speed Operator and the Operator which sets roll gap is called (Automatic Gauge Control) AGC Operator. SDataWinCC gets the AGC operator selection Model-Mode or Manual Mode (Operator-mode). If Model Mode is selected, then it fetches the model calculated Gap and Speed reference values from the database and sends to the mill through WinCC servers. The roll gap data is changed to model predicted calculations. The ABB-BB checks some safety limits and sends the speed reference data to mill.
Figure 6 shows the data flow within the output communication unit (Referred as SDataWinCC in figure-5). This unit has three sub-modules. The first submodule (GDataL2DB) gets the model predicted Gap and Speed reference values from the L2-L1 Database using ADO protocol (6.1.1). The second module (SL2SpeedData) send the model calculated speed schedule to the mill using OPC program (6.1.2). The third module (SL2GapData) module sends the model calculated gap reference to the mill through WinCC Server (6.1.3).
Although the invention has been described with reference to particular examples of the invention, it should be appreciated that it may be exemplified in other forms. The invention qualifies to be adopted in a variety of other embodiments such modifications and alternatives obtaining the advantages and the benefits of the present invention will be apparent to those skilled in the art. All such modifications and alternatives will be obvious to a person skilled in art. Further the present invention has been described with respect to certain specific embodiments, it will be clear to those skilled in the art that the inventive features of the present invention are applicable to other embodiments as well, all of which are intended to fall within the scope of the present invention.
The description herein contains many specifics; these should not be construed as limiting the scope of the invention, but as merely providing illustrations of some of the embodiments of the invention. One of ordinary skill in the art will appreciate that elements and materials other than those specifically exemplified can be employed in the practice of the invention without resort to undue experimentation. All art-known functional equivalents, of any such elements and materials are intended to be included in this invention. Numerous variations, changes and substitutions may be made without departing from the invention herein.
| # | Name | Date |
|---|---|---|
| 1 | FORM 3.pdf ONLINE | 2015-02-13 |
| 2 | Form 2 with complete specification as filed.pdf ONLINE | 2015-02-13 |
| 3 | Drawing as filed.pdf ONLINE | 2015-02-13 |
| 4 | FORM 3.pdf | 2015-03-13 |
| 5 | Form 2 with complete specification as filed.pdf | 2015-03-13 |
| 6 | Drawing as filed.pdf | 2015-03-13 |
| 7 | 173-KOL-2015-(16-04-2015)-PA.pdf | 2015-04-16 |
| 8 | 173-KOL-2015-(16-04-2015)-FORM-1.pdf | 2015-04-16 |
| 9 | 173-KOL-2015-(16-04-2015)-CORRESPONDENCE.pdf | 2015-04-16 |
| 10 | Form 13 [01-10-2016(online)].pdf | 2016-10-01 |
| 11 | Form 26 [24-10-2016(online)].pdf | 2016-10-24 |
| 12 | Form 18 [12-12-2016(online)].pdf | 2016-12-12 |
| 13 | 173-KOL-2015-FER.pdf | 2020-02-13 |
| 14 | 173-KOL-2015-FER_SER_REPLY [07-08-2020(online)].pdf | 2020-08-07 |
| 15 | 173-KOL-2015-DRAWING [07-08-2020(online)].pdf | 2020-08-07 |
| 16 | 173-KOL-2015-CORRESPONDENCE [07-08-2020(online)].pdf | 2020-08-07 |
| 17 | 173-KOL-2015-CLAIMS [07-08-2020(online)].pdf | 2020-08-07 |
| 18 | 173-KOL-2015-PatentCertificate06-09-2022.pdf | 2022-09-06 |
| 19 | 173-KOL-2015-IntimationOfGrant06-09-2022.pdf | 2022-09-06 |
| 1 | searchstrategy_13-02-2020.pdf |