Wide and thick plate water cooling intelligent control method and system model establishment method

Abstract

The invention provides a wide and thick plate water cooling intelligent control method and a system model establishing method, and belongs to the technical field of steel rolling process production. The technical problem that in the prior art, wide and thick plate water cooling mechanism models under different marks and thickness specifications are prone to losing efficacy under the conditions that the production technology is changed, equipment conditions are changed or the marks and the specifications are newly added is solved. According to the technical scheme, the method comprises the following steps: S1, processing a process rule; s2, establishing a data set; s3, creating a conventional water cooling control model; s4, creating a continuous same-specification water cooling control model; s5, before the new steel plate enters the water cooling area, a corresponding water cooling control model is selected, and control parameters are issued to an operation picture; s6, operating the picture by an operator to modify the control parameters; and S7, when the process rule changes or new data exist, the actions S1-S4 are repeated. The method has the beneficial effects that the stability of water cooling control and the hit rate of the final cooling temperature are improved, and manual input errors of multiple control parameters can be avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of steel rolling process production, and in particular to a method for intelligently controlling water cooling of wide and thick plates and a method for establishing a system model. Background Art

[0002] Wide and thick plates are indispensable and important materials in the fields of ships, pressure vessels, boilers, engineering machinery, large bridges, etc. In recent years, with the development of the economy, the demand for wide and thick plates has also increased. Cooling is an important part of the production of wide and thick plates. By effectively controlling the cooling rate and final cooling temperature of the steel plate, the structure and performance of the steel plate can be improved, the strength and toughness of the steel plate can be increased, and the unevenness and residual stress of the steel plate can be reduced.

[0003] Water cooling is a common cooling method in the production of wide and thick plates, and is suitable for cooling thick plates with high temperature and high power. In traditional production, operators usually manually set the roller speed and the amount of water in the upper and lower nozzles of multiple water cooling areas based on their own experience each time, thereby controlling the final cooling temperature of the current steel plate. As the number of brands and specifications increases, the requirements for the final cooling temperature range control are becoming more and more stringent, and the production pace is also getting faster and faster. Under different brands, thickness specifications and cooling water temperature conditions, the requirements for the final cooling temperature of steel plates are also different. At the same time, operators also need to dynamically adjust the control parameters according to the temperature of the steel plate to be water-cooled, the air temperature (season) and the equipment status. Therefore, it is difficult to quickly adapt to the above changes by adjusting the water cooling control parameters only by manual experience, especially for inexperienced operators.

[0004] In order to solve the above problems, it is an important direction to build a water cooling mechanism model for wide and thick plates of different grades and thickness specifications, and realize the automatic distribution of water cooling control parameters. However, the mechanism model is easy to fail when the production process changes, equipment conditions change, or new grades and specifications are added, and it often needs to be rebuilt, which often occurs in actual production. Therefore, it is necessary to use modern information technology based on big data analysis, machine learning, and other in-depth integration with water cooling process knowledge to build a water cooling intelligent control model with self-learning ability and dynamic optimization of control parameters according to actual conditions. Summary of the invention

[0005] The purpose of the present invention is to overcome the problems in the background technology and provide a method for intelligent control of water cooling of wide and thick plates and a method for establishing a system model. The intelligent control method can effectively avoid manual input of multiple control parameters, which is conducive to improving work efficiency and reducing quality problems caused by errors in manual control parameter input.

[0006] In order to achieve the above-mentioned invention object, the technical solution adopted by the present invention is specifically: a method for intelligent control of water cooling of wide and thick plates, characterized in that it includes the following steps:

[0007] S1: Process rule processing, merging, logically processing and integrating various original process rules;

[0008] S2: Establishing a data set, the data set includes an electronic process rule data set, a historical water cooling control parameter data set and a data set of related process data, wherein the data set of related process data includes a conventional process data set and a continuous process data set of the same specification;

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

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

[0011] S5: According to the initial conditions of the current steel plate, the corresponding water cooling control model is selected, and the control parameters are sent to the operation screen;

[0012] S6: The operator operates the screen to modify the control parameters.

[0013] Furthermore, in step S1, the original process rules include temperature requirements for different grades, different thicknesses, different water temperatures, different final rolling conditions, final cooling temperature requirements and roller speed requirements.

[0014] Furthermore, in step S2, the historical water cooling control parameter data set and the data set of related process data both include the water volume of each nozzle, roller speed, actual grade, actual water temperature, actual thickness, final rolling temperature, start cooling temperature and final cooling temperature.

[0015] Furthermore, in steps S3 and S4, the set values ​​include the water volume of each nozzle and the roller speed.

[0016] Furthermore, in step S5, the initial conditions of the current steel plate include brand, thickness, cooling temperature, whether it is continuous specification and water temperature.

[0017] The present invention also provides a system model establishment method, comprising the following steps:

[0018] Step 1: Establish a process rule processing module. According to the water cooling process requirements, based on external steel grades, internal steel grades and original rules, process according to the matching rules to obtain the processed process rules;

[0019] Step 2: Establish a data set module, the data set includes a process rule data set, a historical water cooling control parameter data set, a conventional process data set and a continuous same-specification process data set;

[0020] Step 3: Establish a conventional water cooling control model, and obtain a set of optimal weighted values ​​for multiple parameter control settings of steel plates of different grades, specifications and cooling water temperatures according to the process rule data set, historical water cooling control parameter data set and conventional process data set processed in the first and second steps through an optimization algorithm, and obtain a set of optimal weighted values ​​through the model parameter adjustment rules, and weight the set value model 1 to obtain the optimal recommended value model 1 under the current grade, specification and water temperature;

[0021] Step 4: Establish a continuous water cooling control model for the same specification. When the cooling start temperature of two continuously produced slabs of the same specification is the same, the current steel plate uses the cooling start temperature of the previous steel plate of the same grade and specification. According to the process rule data set processed in the second step, the historical water cooling control parameter data set and the continuous process data data of the same specification, a set of parameter control setting value model 2 for steel plates of different grades, different thicknesses, different cooling water temperatures and different steel plate cooling start temperatures is obtained through the model algorithm. A set of optimal weighted values ​​is calculated through the model parameter adjustment rules, and the setting value model 2 is weighted to obtain the optimal recommended value model 2.

[0022] Step 5: Automatic water cooling, control parameters of the steel plate to be water-cooled are issued in advance, and the head of the steel plate to be water-cooled leaves the rolling mill or the Nth pass from the end is used as a trigger signal. When the system detects the trigger signal, it first determines whether the steel plate meets the conditions for automatic issuance, and then determines whether the steel plate is continuous with the same grade and similar specifications. Then, according to the model of the third or fourth step, the water volume of each nozzle and the roller speed are calculated, and the water cooling control parameters are issued to the operation screen according to the manual / automatic mode selected by the user;

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

[0024] Furthermore, 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.

[0025] Furthermore, in the first step, in the process rules after the treatment, according to the requirements of different brands, the thickness is between 10 and 120 mm, with 3 to 5 mm as an interval, the cooling water temperature is 2 to 3°C as an interval, and the cooling water temperature is distributed between 10 and 35°C.

[0026] Furthermore, in the second step, the process rule data set is obtained by processing the external steel seed data set, the internal steel seed data set and the original rule sub-data set, and is manually added or modified in the corresponding sub-data set, and the system automatically processes and updates the data set according to the rules.

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

[0028] Compared with the prior art, the present invention has the following beneficial effects:

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

[0030] 2. The present invention provides a method for establishing a water-cooling intelligent control system model. This model can quickly adjust the control parameters when the equipment conditions or process conditions change, thereby avoiding fluctuations in the water-cooling control effect caused by operators' untimely adjustment of control parameters or experience differences 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 defective products due to substandard water cooling temperature. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

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

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

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

[0035] Figure 4 : The water cooling parameters of the present invention are automatically sent down the flow chart. DETAILED DESCRIPTION

[0036] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. Of course, the specific embodiments described here are only used to explain the present invention and are not used to limit the present invention.

[0037] Example: Figure 1-Figure 4As shown, the present invention provides a method for intelligent water cooling control of wide and thick plates that can dynamically adjust control parameters based on actual production conditions. After obtaining initial condition data, water cooling control parameters are suggested through a dynamic data model and multiple control parameters are sent to a primary operation screen. The present invention is beneficial to the stability of water cooling control and the hit rate of final cooling temperature, can avoid manual input errors of multiple control parameters, and is beneficial to reducing the number of performance defectives caused by substandard water cooling temperature. The method is specifically implemented as follows:

[0038] S1. Processing of process rules: merging, logically processing and integrating various original process rules. The process rules include requirements for final rolling temperature, final cooling temperature and roller speed under different grades, thicknesses and water temperatures.

[0039] S2. Establish a data set, which includes a computerized process rule data set, a historical water cooling control parameter data set, and a data set of related process data, etc. There are two data sets of related process data: a conventional process data data set and a continuous process data data set of the same specification. The historical water cooling control parameter data set and the data set of related process data include the water volume of each nozzle, roller speed, actual grade, actual water temperature, actual thickness, final rolling temperature, start cooling temperature, and final cooling temperature, etc.

[0040] S3, conventional water cooling control model, according to the process rule data set, historical water cooling control parameter data set, and conventional process data set processed in the above steps, according to the model algorithm, obtain the optimal parameter setting value of the current specification steel plate under normal conditions. The setting value includes the water volume and roller speed of each nozzle. The initial conditions of the current steel plate include brand, thickness, whether it is continuous specification and water temperature.

[0041] S4, continuous same specification water cooling control model, according to the process rule data set, historical water cooling control parameter data set, and continuous process data set processed in the above steps, according to the model algorithm, obtain the optimal parameter setting value of the current specification steel plate under normal circumstances, the setting value includes the water volume and roller speed of each nozzle, the setting value includes the water volume and roller speed of each nozzle.

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

[0043] S6. For the automatically issued control parameters, the operator 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 meet the actual situation, they will be used. If they do not meet the actual situation, they will be modified manually. There are two aspects of not meeting the actual situation: first, the parameters are indeed wrong, especially for grades and specifications that have not been produced for a long time. For example, if the control parameters are suitable for production in winter, and then production resumes in summer, the parameters may need to be adjusted; or the equipment situation has changed and needs to be adjusted. Second, even if the grade and specification are the same, but some steel plates have special process requirements, the water cooling parameters will also be adjusted.

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

[0045] In order to better achieve the above-mentioned invention effects, the present invention also provides a system model establishment method, and the specific implementation steps are as follows:

[0046] The first step is to establish a process rule processing module. According to the water cooling process requirements, based on the external steel type, internal steel type, and original rules, the process is processed according to the matching rules to obtain the final process rules. Among them, in the processed rules, according to the requirements of different grades, the thickness is divided into 10-120mm, with 3-5mm as an interval, and the cooling water temperature is 2-3℃ as an interval. The above specific values ​​need to be determined according to the original rules of each steel plate; according to historical data, the cooling water temperature is distributed between 10 and 35℃, and the original rules include thickness, final rolling temperature range requirements, cooling water temperature and final cooling temperature range requirements, and roller speed range requirements; the thickness and water temperature range requirements are relatively broad.

[0047] The second step is to establish a data set, which includes a process rule data set, a historical water cooling control parameter data set, a conventional process data data set, and a continuous process data set of the same specification. Among them, the process rule data set is obtained through processing the external steel seed data set, the internal steel seed data set, and the original rule sub-data set. Manual additions or modifications are made in the corresponding sub-data set, and the system automatically processes and updates the data set according to the rules. The historical water cooling control parameter data set and the process data data set are automatically updated according to the rules. The above data are taken from the most recent year and are updated dynamically.

[0048] The third step is to establish a conventional water cooling control model. According to the process rule data set, historical water cooling control parameter data set and conventional process data set processed in the second step, a set of parameter control setting value models for steel plates of different grades, thicknesses and specifications at different cooling water temperatures are obtained according to the model algorithm, namely, the water volume and roller speed of 18 nozzles in 4 zones. A set of optimal weighted values ​​is calculated using the model parameter adjustment rules, and the above set of control parameter setting value models are weighted to obtain the optimal recommended value model.

[0049] The fourth step is to establish a continuous water-cooling control model for the same specification. Normally, the steel plate is water-cooled after rolling. Due to the long length of the steel plate and the compact layout of the production line, when the front half of the steel plate is water-cooled, the back half is still in the rolling mill area. Therefore, the current cooling temperature of the steel plate is difficult to obtain before the cooling, and can only be calculated after the water cooling is completed. However, in fact, the cooling temperature has a direct impact on the final cooling temperature, including the selection of control parameters. According to actual production experience and data analysis, the cooling temperatures of two consecutive steel plates of the same grade, same specification or similar specifications produced continuously are relatively close. In order to improve the accuracy of the final cooling temperature, it is assumed that the continuous The cooling start temperature of two slabs of the same specification produced successively is the same, so the current steel plate can use the cooling start temperature of the previous steel plate of the same grade and specification. According to the process rule data set processed in the second step, the historical water cooling control parameter data set, and the continuous process data set of the same specification, a set of parameter control setting value models for steel plates of different grades, thicknesses, specifications, cooling water temperatures, and cooling start temperatures are obtained according to the model algorithm, namely, the water volume and roller speed of 18 nozzles in 4 zones. A set of optimal weighted values ​​are calculated using the model parameter adjustment rules, and the above set of control parameter setting value models are weighted to obtain the optimal recommended value model.

[0050] The fifth step is the automatic water-cooling distribution function. In actual production, the control parameters of the steel plate to be water-cooled need to be distributed in advance. According to the actual situation, the third pass from the head of the steel plate to be water-cooled out of the rolling mill can be used as a trigger signal. When the system detects the trigger signal, it first determines whether the steel plate meets the conditions for automatic distribution, and then determines whether the steel plate is a continuous grade with similar specifications. Then, according to the model of the third or fourth step, the water volume of each nozzle and the roller speed are calculated, and the water cooling control parameters are distributed 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 principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for intelligent control of water cooling of wide and thick plates, characterized in that: The steps include: S1: Process rule processing, merging, logically processing and integrating various original process rules; S2: Establishing a data set, the data set includes an electronic process rule data set, a historical water cooling control parameter data set and a data set of related process data, wherein the data set of related process data includes a conventional process data set and a continuous process data set of the same specification; S3: conventional water cooling control model, according to the process rule data set, historical water cooling control parameter data set and conventional process data set processed in steps S1 and S2, the optimal parameter setting value of the current specification steel plate is obtained through the model algorithm; S4: a continuous same-specification water cooling control model, which obtains the optimal parameter setting value of the current specification steel plate through a model algorithm according to the process rule data set processed in steps S1 and S2, the historical water cooling control parameter data set and the continuous same-specification process data set; S5: According to the initial conditions of the current steel plate, the corresponding water cooling control model is selected, and the control parameters are sent to the operation screen; S6: The operator operates the screen to modify the control parameters.

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

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

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

6. A system model building method, the system model building method is based on the method for intelligent control of water cooling of wide and thick plates according to any one of claims 1 to 5, characterized in that: The steps include: Step 1: Establish a process rule processing module. According to the water cooling process requirements, based on external steel grades, internal steel grades and original rules, process according to the matching rules to obtain the processed process rules; Step 2: Establish a data set module, the data set includes a process rule data set, a historical water cooling control parameter data set, a conventional process data set and a continuous same-specification process data set; Step 3: Establish a conventional water cooling control model, and obtain a set of optimal weighted values ​​for multiple parameter control settings of steel plates of different grades, specifications and cooling water temperatures according to the process rule data set, historical water cooling control parameter data set and conventional process data set processed in the first and second steps through an optimization algorithm, and obtain a set of optimal weighted values ​​through the model parameter adjustment rules, and weight the set value model 1 to obtain the optimal recommended value model 1 under the current grade, specification and water temperature; Step 4: Establish a continuous water cooling control model for the same specification. When the cooling start temperature of two continuously produced slabs of the same specification is the same, the current steel plate uses the cooling start temperature of the previous steel plate of the same grade and specification. According to the process rule data set processed in the second step, the historical water cooling control parameter data set and the continuous process data data of the same specification, a set of parameter control setting value model 2 for steel plates of different grades, different thicknesses, different cooling water temperatures and different steel plate cooling start temperatures is obtained through the model algorithm. A set of optimal weighted values ​​is calculated through the model parameter adjustment rules, and the setting value model 2 is weighted to obtain the optimal recommended value model 2. Step 5: Automatic water cooling, control parameters of the steel plate to be water-cooled are issued in advance, and the head of the steel plate to be water-cooled leaves the rolling mill or the Nth pass from the end is used as a trigger signal. When the system detects the trigger signal, it first determines whether the steel plate meets the conditions for automatic issuance, and then determines whether the steel plate is continuous with the same grade and similar specifications. Then, according to the model of the third or fourth step, the water volume of each nozzle and the roller speed are calculated, and the water cooling control parameters are issued to the operation screen according to the manual / automatic mode selected by the user; Step 6: The operator chooses to use or modify the control parameters.

7. The method for establishing a wide and thick plate water cooling intelligent control model 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 method for establishing a water-cooling intelligent control model for thick and wide plates according to claim 7 is characterized in that: In the first step, in the process rules after treatment, according to the requirements of different brands, the thickness is between 10 and 120 mm, with 3 to 5 mm as an interval, the cooling water temperature is 2 to 3°C as an interval, and the cooling water temperature is distributed between 10 and 35°C.

9. The method for establishing a wide and thick plate water cooling intelligent control model according to claim 6, characterized in that: In the second step, the process rule data set is obtained by processing the external steel seed data set, the internal steel seed data set and the original rule sub-data set, and is manually added or modified in the corresponding sub-data set. The system automatically processes and updates the data set according to the rules.

10. The method for establishing a wide and thick plate water cooling intelligent control model according to claim 9, characterized in that: In the second step, the historical water cooling control parameter data set and the process data data set are automatically updated according to the rules.

Images