A method and system model establishment method for intelligent control of water cooling of wide and thick plates

Abstract

The application provides a wide and thick plate water cooling intelligent control method and a system model establishment method, and belongs to the technical field of steel rolling process production. The technical problems that the water cooling mechanism model of the wide and thick plate under different brands and thickness specifications is easy to fail under the conditions of production process change, equipment condition change or new brand specification addition in the prior art are solved. The technical scheme is as follows: including the following steps, S1: process rule processing; S2: establishing a data set; S3: creating a conventional water cooling control model; S4: creating a continuous same-specification water cooling control model; S5: when a new steel plate enters the water cooling area, selecting the corresponding water cooling control model and issuing the control parameters to the operation picture; S6: the operation personnel modifies the control parameters in the operation picture; S7: when the process rule changes or there is new data, repeating the actions S1-S4. The application has the beneficial effects that the application is beneficial to improving the stability of the water cooling control and the final cooling temperature hit rate, and can avoid the manual input error of multiple control parameters.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of steel rolling process, in particular to a method for intelligent control of water cooling of wide and heavy plate and a system model establishing method. BACKGROUND

[0002] Wide and heavy plate is an important material indispensable in the fields of ship, pressure vessel, boiler, engineering machinery, large bridge, etc. In recent years, with the development of economy, the demand for wide and heavy plate is also increasing. Cooling is an important part of wide and heavy plate production, and by effectively controlling the cooling speed and final cooling temperature of the steel plate, the organization and performance of the steel plate can be improved, the strength and toughness of the steel plate can be improved, and the unevenness and residual stress of the steel plate can be reduced.

[0003] Water cooling is a common cooling method in wide and heavy plate production, which is suitable for high temperature and high power thick plate cooling. In traditional production, the operator usually manually sets the roller speed and the water flow of the upper and lower nozzles in multiple water cooling areas according to his own experience, so as to control the final cooling temperature of the current steel plate. As the number of grades and specifications increases, the requirement for the control of the final cooling temperature interval is becoming more and more strict, and the production rhythm is also becoming faster. Under different grades, thickness specifications and cooling water temperature conditions, the requirements for the final cooling temperature of the steel plate are also different, and at the same time, the operator also needs to dynamically adjust the control parameters according to the temperature of the steel plate to be water cooled, air temperature (season) and equipment state, etc. Therefore, it is difficult to quickly adapt to the above changes by relying on manual experience to adjust the water cooling control parameters, especially for operators with insufficient experience.

[0004] To solve the above problems, it is an important direction to build a water cooling mechanism model of wide and heavy plate of different grades and thickness specifications, and to realize automatic issuance of water cooling control parameters. However, the mechanism model is easy to fail under the conditions of change of production process, change of equipment condition or addition of new grades and specifications, and often needs to be rebuilt, and the above conditions will frequently occur in actual production. Therefore, it is necessary to use modern information technology based on big data analysis, machine learning and deep integration with water cooling process knowledge to build a water cooling intelligent control model with self-learning ability and dynamically optimized control parameters according to actual conditions. SUMMARY

[0005] The purpose of the present application is to overcome the problems in the background art, and to provide a method for intelligent control of water cooling of wide and heavy plate and a system model establishing method. The intelligent control method can effectively avoid manual input of multiple control parameters, which is beneficial to improve work efficiency and reduce quality problems caused by manual control parameter input errors.

[0006] In order to achieve the above application purpose, the technical scheme adopted by the present application is specifically as follows: a method for intelligent control of water cooling of wide and heavy plate, characterized in that it comprises the following steps:

[0007] S1: process rule processing, merging, logical processing and integration of various original process rules;

[0008] S2: establishing a data set, the data set including an electronicized process rule data set, a historical water cooling control parameter data set and a related process data data set, the related process data data set including a conventional process data set and a continuous same specification process data set;

[0009] S3: conventional water cooling control model, according to the process rule data set, the historical water cooling control parameter data set and the conventional process data set processed in steps S1 and S2, through model algorithm, the optimal parameter setting value of the current specification steel plate is obtained;

[0010] S4: continuous same specification water cooling control model, according to the process rule data set, the historical water cooling control parameter data set and the continuous same specification process data set processed in steps S1 and S2, through model algorithm, the optimal parameter setting value of the current specification steel plate is obtained;

[0011] S5: according to the initial condition of the current steel plate, the corresponding water cooling control model is selected, and the control parameter is issued to the operation picture;

[0012] S6: the operator modifies the control parameter in the operation picture.

[0013] Further, in step S1, the original process rules include different grades, different thicknesses, different water temperatures, temperature requirements under different finish rolling, finish cooling temperature requirements and roller speed requirements.

[0014] Further, in step S2, the historical water cooling control parameter data set and the related process data data set both include the water quantity of each nozzle, the roller speed, the actual grade, the actual water temperature, the actual thickness, the finish rolling temperature, the open cooling temperature and the finish cooling temperature.

[0015] Further, in steps S3 and S4, the setting value includes the water quantity of each nozzle and the roller speed.

[0016] Further, in step S5, the initial condition of the current steel plate includes the grade, the thickness, the open cooling temperature, whether it is a continuous specification and the water temperature.

[0017] The application also provides a system model establishing method, comprising the following steps:

[0018] First step: establishing a process rule processing module, according to the water cooling process requirement, based on the external steel grade, the internal steel grade and the original rule, the processed process rule is obtained by processing according to the matching rule;

[0019] Step 2: Establish the dataset module. The dataset includes process rule dataset, historical water cooling control parameter dataset, conventional process data dataset, and continuous process data dataset of the same specification.

[0020] Step 3: Establish a conventional water cooling control model. Based on the process rule dataset, historical water cooling control parameter dataset, and conventional process data dataset processed in Step 1 and Step 2, obtain multiple parameter control setpoint models for steel plates of different grades, specifications, and cooling water temperatures through an optimization algorithm. Obtain a set of optimal weighted values ​​through model parameter tuning rules. Weight the setpoint models to obtain the optimal suggested value model for the current grade, specification, and water temperature.

[0021] Step 4: Establish a continuous water-cooling control model of the same specification. When the starting cooling temperature of two slabs of the same specification produced in succession is the same, the current steel plate uses the starting cooling temperature of the previous steel plate of the same grade and specification. Based on the process rule dataset processed in Step 2, the historical water-cooling control parameter dataset, and the continuous process data dataset of the same specification, a set of parameter control setpoints model 2 for steel plates of different grades, thicknesses, specifications, cooling water temperatures, and starting cooling temperatures is obtained through the model algorithm. Through the model parameter tuning rules, a set of optimal weighted values ​​is calculated. The setpoints model 2 are weighted to obtain the optimal suggested value model 2.

[0022] Step 5: Automatic water cooling control parameters are sent out in advance. The start of the water cooling process is the head of the steel plate exiting the mill or the Nth pass from the end. When the system detects the trigger signal, it first determines whether the steel plate meets the conditions for automatic control, then determines whether the steel plate is a continuous series of similar grades and specifications. Then, based on the model in Step 3 or Step 4, it calculates the water flow rate of each nozzle and the speed of the roller table, and sends the water cooling control parameters to the operation screen according to the manual / automatic mode selected by the user.

[0023] Step 6: The operator selects to use or modify the control parameters.

[0024] Furthermore, in the first step, the original rules include requirements for thickness, final rolling temperature range, cooling water temperature range, final cooling temperature range, and roller speed range.

[0025] Furthermore, in the first step, in the process rules after processing, the thickness is between 10 and 120 mm, with 3 to 5 mm as a range, and the cooling water temperature is between 2 and 3℃ as a range, with the cooling water temperature distribution between 10 and 35℃, depending on the requirements of different grades.

[0026] Furthermore, in the second step, the process rule dataset is obtained by processing the external steel seed dataset, the internal steel seed dataset, and the original rule sub-dataset. Manual additions or modifications are made to the corresponding sub-datasets, and the system automatically processes and updates the dataset according to the rules.

[0027] Furthermore, in the second step, the historical water-cooling control parameter dataset and process data dataset are automatically updated according to rules.

[0028] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0029] 1. The water-cooling intelligent control method provided by the present invention can effectively avoid manually inputting multiple control parameters, which is conducive to improving work efficiency and reducing quality problems caused by errors in manual control parameter input.

[0030] 2. This invention provides a method for establishing a water-cooled intelligent control system model. This model can quickly adjust control parameters when equipment or process conditions change, avoiding fluctuations in water-cooling control effects caused by operators' untimely adjustment of control parameters or differences in experience in similar situations. At the same time, compared with manual operation, this model has a higher final cooling temperature hit rate, reducing the number of performance defects caused by substandard water-cooling temperatures. Attached Figure Description

[0031] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used together with the embodiments of the invention to explain the invention and do not constitute a limitation thereof.

[0032] Figure 1 : Process flow chart of the present invention.

[0033] Figure 2 : A conventional water-cooling control model diagram of the present invention.

[0034] Figure 3 Flowchart of the continuous specification water cooling control model of the present invention.

[0035] Figure 4 The flowchart of the automatic distribution of water cooling parameters in this invention. Detailed Implementation

[0036] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. Of course, the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0037] Example: Figures 1-4As shown, this invention provides a method for intelligent water-cooling control of thick plates that can dynamically adjust control parameters based on actual production conditions. After obtaining initial condition data, the method suggests water-cooling control parameters through a dynamic data model and sends multiple control parameters to the primary operation screen. This invention improves the stability of water-cooling control and the hit rate of final cooling temperature, avoids manual input errors of multiple control parameters, and helps reduce the number of defective products caused by substandard water-cooling temperatures. The specific implementation of the method is as follows:

[0038] S1. Process rule processing: Merging, logically processing, and integrating various original process rules. Process rules include final rolling temperature requirements, final cooling temperature requirements, and roller speed requirements for different grades, thicknesses, and water temperatures.

[0039] S2. Establish a dataset, which includes an electronic process rule dataset, a historical water-cooling control parameter dataset, and a dataset of relevant process data. Among them, there are two datasets of relevant process data: a regular process data dataset and a continuous process data dataset of the same specification. The historical water-cooling control parameter dataset and the dataset of relevant process data contain the water flow rate of each nozzle, roller speed, actual grade, actual water temperature, actual thickness, final rolling temperature, start-up cooling temperature, and final cooling temperature.

[0040] S3. Conventional water cooling control model: Based on the process rule dataset, historical water cooling control parameter dataset, and conventional process data dataset processed in the above steps, the model algorithm obtains the optimal parameter settings for the current specification steel plate under normal conditions. The settings include the water volume of each nozzle and the roller speed. The initial conditions of the current steel plate include grade, thickness, whether it is a continuous specification, and water temperature.

[0041] S4. Continuous same-specification water cooling control model: Based on the process rule dataset, historical water cooling control parameter dataset, and continuous process data dataset processed in the above steps, the optimal parameter settings for the current specification steel plate are obtained under normal circumstances according to the model algorithm. The settings include the water volume of each nozzle and the roller speed.

[0042] S5. Based on the initial conditions of the current steel plate, including grade, thickness, cooling start temperature, whether it is a continuous specification, water temperature, etc., select the corresponding water cooling control model and send the control parameters to the operation screen.

[0043] S6. For automatically issued control parameters, operators can modify or use the control parameters on the operation screen according to the actual situation. The actual situation is determined by the operator. If the parameters match the actual situation, they should be used; otherwise, they should be manually modified. There are two aspects to not matching the actual situation: First, the parameters are indeed incorrect, especially for grades and specifications that have not been produced for a long time. For example, if the control parameters are suitable for winter production, then the parameters may need to be adjusted if production resumes in summer; or the equipment conditions may have changed, requiring adjustment. Second, even for the same grade and specification, some steel plates have special process requirements, and the water cooling parameters will also be adjusted.

[0044] S7. When the process rules change or new data is available, repeat actions S1-S4.

[0045] To better achieve the aforementioned effects, this invention also provides a method for establishing a system model, the specific implementation steps of which are as follows:

[0046] The first step is to establish a process rule processing module. Based on the water cooling process requirements, external steel grades, internal steel grades, and original rules, the module processes the data according to matching rules to obtain the final process rules. In the processed rules, the thickness is divided into zones of 10–120 mm, with each zone ranging from 3–5 mm, and the cooling water temperature is divided into zones of 2–3 °C. The specific values ​​need to be determined based on the original rules for each steel plate. According to historical data, the cooling water temperature range is between 10–35 °C. The original rules include requirements for thickness, final rolling temperature range, cooling water temperature and final cooling temperature range, and roller speed range. The thickness and water temperature range requirements are relatively broad.

[0047] The second step is to establish datasets, which include process rule datasets, historical water-cooling control parameter datasets, conventional process data datasets, and continuous process data datasets of the same specifications. The process rule dataset is obtained by processing external steel seed datasets, internal steel seed datasets, and original rule sub-datasets. Users can manually add or modify data in the corresponding sub-datasets, and the system will automatically process and update the datasets according to the rules. The historical water-cooling control parameter dataset and process data dataset are automatically updated according to the rules. The above data are taken from the most recent year and are dynamically updated.

[0048] The third step is to establish a conventional water cooling control model. Based on the process rule dataset, historical water cooling control parameter dataset, and conventional process data dataset processed in the second step, a set of parameter control setpoint models for steel plates of different grades, thicknesses, and cooling water temperatures are obtained according to the model algorithm. These setpoints include the water volume of 18 nozzles in 4 zones and the speed of the roller conveyor. Using the model parameter tuning rules, a set of optimal weighted values ​​are calculated. These weighted values ​​are then applied to the above set of control parameter setpoint models to obtain the optimal suggested value model.

[0049] Step 4: Establish a continuous water-cooling control model for the same specifications. Typically, steel plates are water-cooled after rolling. Due to the long length of the steel plates and the compact layout of the production line, when the first half of the steel plate is water-cooled, the second half is still in the rolling mill area. Therefore, the initial cooling temperature of the current steel plate is difficult to obtain before the initial cooling and can only be calculated after the current water-cooling is completed. However, in reality, the initial cooling temperature directly affects the final cooling temperature, including the selection of control parameters. Based on actual production experience and data analysis, for continuously produced steel plates of the same grade and specification or with similar specifications, the initial cooling temperatures of two consecutive plates are relatively close. To improve the accuracy of the final cooling temperature, it is assumed that the continuous cooling... Since the starting cooling temperature of the two slabs of the same specification produced in the next step is the same, the starting cooling temperature of the previous slab of the same grade and specification can be used for the current steel plate. Based on the process rule dataset after the second step, the historical water cooling control parameter dataset, and the dataset of continuous process data of the same specification, a set of parameter control setpoint models for steel plates of different grades, thicknesses, specifications, cooling water temperatures, and starting cooling temperatures are obtained according to the model algorithm. That is, the water volume of 18 nozzles in 4 zones and the speed of the roller conveyor. Using the model parameter tuning rules, a set of optimal weighted values ​​are calculated. The above set of control parameter setpoint models are weighted to obtain the optimal suggested value model.

[0050] Step 5: Automatic water cooling parameter distribution function. In actual production, the control parameters of the steel plate to be water-cooled need to be distributed in advance. The third to last pass can be used as the trigger signal. When the system detects the trigger signal, it first determines whether the steel plate meets the conditions for automatic distribution, then determines whether the steel plate is a continuous series of similar specifications of the same grade. Then, based on the model in Step 3 or Step 4, it calculates the water volume of each nozzle and the speed of the roller conveyor, and distributes the water cooling control parameters to the operation screen according to the manual / automatic mode selected by the user.

[0051] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for intelligent control of water cooling in thick plates, characterized in that, Includes the following steps: S1: Process rule processing, which involves merging, logically processing, and integrating various original process rules; S2: Establish a dataset, which includes an electronic process rule dataset, a historical water-cooling control parameter dataset, and a dataset of relevant process data. The dataset of relevant process data includes a conventional process dataset and a continuous process dataset of the same specification. S3: Conventional water cooling control model. Based on the process rule dataset, historical water cooling control parameter dataset, and conventional process dataset processed in steps S1 and S2, the model algorithm obtains the optimal parameter settings for the current specification steel plate. S4: Continuous same specification water cooling control model. Based on the process rule dataset, historical water cooling control parameter dataset and continuous same specification process dataset after processing in steps S1 and S2, the optimal parameter setting value of the current specification steel plate is obtained through model algorithm. S5: Based on the initial conditions of the current steel plate, select the corresponding water-cooling control model and send the control parameters to the operation screen; S6: Operators can modify control parameters via the control screen.

2. The method for intelligent control of water cooling of thick plates according to claim 1, characterized in that, In step S1, the original process rules include temperature requirements for different grades, different thicknesses, different water temperatures, different final rolling temperatures, final cooling temperature requirements, and roller speed requirements.

3. The method for intelligent control of water cooling of thick plates according to claim 1, characterized in that, In step S2, the historical water-cooling control parameter dataset and the related process data dataset both include the water volume of each nozzle, roller speed, actual grade, actual water temperature, actual thickness, final rolling temperature, start-up cooling temperature, and final cooling temperature.

4. The method for intelligent control of water cooling of thick plates according to claim 1, characterized in that, In steps S3 and S4, the set values ​​include the water volume of each nozzle and the roller speed.

5. The method for intelligent control of water cooling of thick plates according to claim 1, characterized in that, In step S5, the initial conditions of the current steel plate include grade, thickness, cooling start temperature, whether it is a continuous specification, and water temperature.

6. A system model establishment method, the system model establishment method being based on the intelligent control method for water cooling of thick plates as described in any one of claims 1-5, characterized in that, Includes the following steps: Step 1: Establish a process rule processing module. Based on the water cooling process requirements, external steel type, internal steel type, and original rules, process the rules according to the matching rules to obtain the processed process rules. Step 2: Establish the dataset module. The dataset includes process rule dataset, historical water cooling control parameter dataset, conventional process data dataset, and continuous process data dataset of the same specification. Step 3: Establish a conventional water cooling control model. Based on the process rule dataset, historical water cooling control parameter dataset, and conventional process data dataset processed in Step 1 and Step 2, obtain multiple parameter control setpoint models for steel plates of different grades, specifications, and cooling water temperatures through an optimization algorithm. Obtain a set of optimal weighted values ​​through model parameter tuning rules. Weight the setpoint models to obtain the optimal suggested value model for the current grade, specification, and water temperature. Step 4: Establish a continuous water-cooling control model of the same specification. When the starting cooling temperature of two slabs of the same specification produced in succession is the same, the current steel plate uses the starting cooling temperature of the previous steel plate of the same grade and specification. Based on the process rule dataset processed in Step 2, the historical water-cooling control parameter dataset, and the continuous process data dataset of the same specification, a set of parameter control setpoints model 2 for steel plates of different grades, thicknesses, specifications, cooling water temperatures, and starting cooling temperatures is obtained through the model algorithm. Through the model parameter tuning rules, a set of optimal weighted values ​​is calculated. The setpoints model 2 are weighted to obtain the optimal suggested value model 2. Step 5: Automatic water cooling control parameters are sent out in advance. The start of the water cooling process is the head of the steel plate exiting the mill or the Nth pass from the end. When the system detects the trigger signal, it first determines whether the steel plate meets the conditions for automatic control, then determines whether the steel plate is a continuous series of similar grades and specifications. Then, based on the model in Step 3 or Step 4, it calculates the water flow rate of each nozzle and the speed of the roller table, and sends the water cooling control parameters to the operation screen according to the manual / automatic mode selected by the user. Step 6: The operator selects to use or modify the control parameters.

7. The system model establishment method according to claim 6, characterized in that, In the first step, the original rules include thickness requirements, final rolling temperature range requirements, cooling water temperature range requirements, final cooling temperature range requirements, and roller speed range requirements.

8. The system model establishment method according to claim 7, characterized in that, In the first step, the processed process rules stipulate that, according to the requirements of different grades, the thickness is between 10 and 120 mm, with 3 to 5 mm as one interval, the cooling water temperature is in the range of 2 to 3℃, and the cooling water temperature is distributed between 10 and 35℃.

9. A system model establishment method according to claim 6, characterized in that, In the second step, the process rule dataset is obtained by processing the external steel seed dataset, the internal steel seed dataset, and the original rule sub-dataset. Manual additions or modifications are made to the corresponding sub-datasets, and the system automatically processes and updates the dataset according to the rules.

10. A system model establishment method according to claim 9, characterized in that, In the second step, the historical water-cooling control parameter dataset and process rule dataset are automatically updated according to the rules.

Images