Multi-scale quality control system and method for intelligent hot rolling of large-size slabs

Abstract

The invention belongs to the technical field of metal rolling, and particularly relates to a multi-scale quality control system and method for intelligent hot rolling of large-size slabs. In order to realize quality abnormity control and working procedure coordination optimization control in the plate and strip rolling process, a microstructure model based on a crystallography principle and a physical principle is established, required material parameters are obtained by utilizing experiments, and the rolling process structure prediction is realized by virtue of computer simulation calculation. By establishing a casting blank rolling macro-micro evolution model, the model is embedded into an intelligent control system, and process optimization based on structure prediction is achieved. The reliable model and system can further broaden the application range of the prediction model, improve the prediction accuracy and reliability, provide powerful data support for intelligent production of the rolling process, and provide thinking and methods for intelligent development of plates and strips.

Description

Technical Field

[0001] The present invention belongs to the technical field of metal rolling, and in particular relates to a multi-scale quality control system and method for intelligent hot rolling of large-size slabs. Background Art

[0002] Plate and strip materials are important products in the steel industry, which to a certain extent reflect the degree of production continuity and scale effect of enterprises. In recent years, driven by the "dual carbon" goals, plate and strip rolling technology has developed in the direction of high-end product performance, advanced production technology and green and intelligent production lines. The hot rolling process of plate and strip materials involves heating and thermal deformation, which realizes the shape change of the slab on a macro scale and involves thermal stress of the material and microstructural transformation on a micro scale. The nonlinearity, time-varying nature and complex thermal-mechanical coupling of the hot rolling process pose huge challenges to the diagnosis of abnormal product quality and the stability of hot rolling production.

[0003] Research on integrated intelligent control of plate and strip rolling quality is the development direction for realizing intelligent production. According to the requirements of process autonomy, collaborative diagnosis and optimization, principle and data association operation, and virtual-real collaborative control, relevant material databases, process model databases, and geometric model databases must be established. The quality of plate and strip products is inseparable from the characteristics of the microstructure. The performance of the product can be improved by regulating the microstructure and grain refinement. In traditional microstructure observation and analysis, it is often carried out through experimental research, which is generally time-consuming, costly, and difficult to cover all process conditions.

[0004] Improve the accuracy of the model and the dynamic adaptation to complex working conditions, and achieve coordinated optimization of all levels of the process, so as to improve product quality and production efficiency, reduce costs and emissions. Therefore, the quality abnormality control and process coordination optimization control of the plate and strip rolling process are urgent problems to be solved. Summary of the invention

[0005] In response to the above problems, the present invention provides a multi-scale quality control system and method for intelligent hot rolling of large-size slabs. By integrating the digital twins of macroscopic deformation conditions and microscopic scale models and comparing production data, production quality control, abnormality diagnosis and reverse optimization of hot rolling process parameters can be achieved.

[0006] To achieve the above object, the present invention adopts the following technical solutions:

[0007] The present invention provides a multi-scale quality control system for large-size slab intelligent hot rolling, comprising:

[0008] Virtual calculation module, which performs numerical simulation calculation on the slab rolling process based on numerical simulation software and outputs simulation calculation results;

[0009] The quality control module records the technical parameters of the slab rolling production process and compares them with the simulation calculation results of the virtual calculation module;

[0010] The quality anomaly diagnosis module analyzes the quality status differences based on the process parameters of the slab rolling process, the simulation calculation results of the virtual calculation module and the comparison results of the quality control module, optimizes the process parameters, and feeds the optimized process parameters back to the slab rolling process for regulation.

[0011] Furthermore, the process parameters of the slab rolling process include material parameters, slab size, hot rolling process parameters and hot rolling equipment parameters.

[0012] Furthermore, the virtual calculation module is based on the finite element analysis software ABAQUS, and the process parameters of the slab rolling process are imported through the pre-processing module of the finite element analysis software ABAQUS, wherein the thermal deformation stress model of the slab material and the average grain size model of the microstructure are written by ABAQUSPython;

[0013] The thermal deformation stress model is updated as follows:

[0014]

[0015] Among them, α(ε,T), and n(ε,T) are the material parameters of the casting billet, is the thermal deformation activation energy, R is the ideal gas constant, and T is the absolute temperature;

[0016] The microstructure average grain size model is updated as follows:

[0017]

[0018] Where d0 is the initial grain size, d t is the average grain size after t seconds, t is the holding time, K, n are material-related constants, Q b is the activation energy of grain boundary self-diffusion.

[0019] Furthermore, the quality abnormality diagnosis module is specifically:

[0020] The slab thickness b, temperature T, rolling force F and rolling speed v during the slab rolling process are collected as parameters, and differential operation is performed with the results of the virtual calculation module to calculate the slab thickness change Δb, temperature change ΔT, rolling force change ΔF and rolling speed Δv;

[0021] The differential parameters p = [Δb, ΔT, ΔF, Δv] are standardized as follows:

[0022]

[0023] Among them, p' is the parameter after standardization;

[0024] The standardized parameters p'=[Δb', ΔT', ΔF', Δv'] are input into the quality anomaly diagnosis model, and the rolling temperature anomaly, pressure anomaly, speed anomaly and equipment vibration are output, and then the rolling process parameters are reversely optimized, and the optimized process parameters are fed back to the slab rolling process; the quality anomaly diagnosis model adopts a BP neural network, which includes an input layer, a hidden layer and an output layer, wherein the transfer equation of the hidden layer is f1(·), and the output of the hidden layer is:

[0025]

[0026] The transfer equation of the output layer is f2(·), then the output of the output layer is:

[0027]

[0028] Where i is 1, 2, 3, or 4, that is, x1 = Δb', x2 = ΔT', x3 = ΔF', x4 = Δv', n is the number of input layer nodes, q is the number of hidden layer nodes, m is the number of output layer nodes, and v ki is the weight from input layer node i to hidden layer node k, w jk is the weight from hidden layer node k to output layer node j.

[0029] The present invention also provides a multi-scale quality control method for large-size slab intelligent hot rolling, comprising the following steps:

[0030] Step 1, real-time acquisition of process parameters of slab rolling process;

[0031] Step 2, based on the process parameters of the billet rolling process collected in real time, numerical simulation calculation is performed on the process parameters;

[0032] Step 3, comparing the process parameters of the billet rolling process collected in real time with the results of the simulation calculation in step 2;

[0033] Step 4: Based on the real-time collection of process parameters of the slab rolling process, the results of the simulation calculation in step 2 and the comparison results in step 3, quality status difference analysis is performed to optimize the process parameters. The optimized process parameters are fed back to the slab rolling process for regulation.

[0034] Furthermore, the process parameters of the slab rolling process in step 1 include material parameters, slab size, hot rolling process parameters and hot rolling equipment parameters.

[0035] Further, the step 2 is specifically as follows:

[0036] With the help of finite element analysis software ABAQUS, the process parameters of the slab rolling process are imported through the pre-processing module of the finite element analysis software ABAQUS, and the thermal deformation stress model and the microstructure average grain size model are written by ABAQUSPython;

[0037] The thermal deformation stress model is updated as follows:

[0038]

[0039] Among them, α(ε,T), and n(ε,T) are the material parameters of the casting billet, is the thermal deformation activation energy, R is the ideal gas constant, and T is the absolute temperature;

[0040] The microstructure average grain size model is updated as follows:

[0041]

[0042] Where d0 is the initial grain size, d t is the average grain size after t seconds, t is the holding time, K, n are material-related constants, Q b is the activation energy of grain boundary self-diffusion.

[0043] Further, the step 4 is specifically as follows:

[0044] The slab thickness b, temperature T, rolling force F and rolling speed v during the slab rolling process are collected as parameters, and the difference operation is performed with the result of the simulation calculation in step 1 to calculate the slab thickness change Δb, temperature change ΔT, rolling force change ΔF and rolling speed Δv;

[0045] The differential parameters p = [Δb, ΔT, ΔF, Δv] are standardized as follows:

[0046]

[0047] Among them, p' is the parameter after standardization;

[0048] The standardized parameters p'=[Δb', ΔT', ΔF', Δv'] are input into the quality anomaly diagnosis model, and the rolling temperature anomaly, pressure anomaly, speed anomaly and equipment vibration are output, and then the rolling process parameters are reversely optimized, and the optimized process parameters are fed back to the slab rolling process; the quality anomaly diagnosis model adopts a BP neural network, which includes an input layer, a hidden layer and an output layer, wherein the transfer equation of the hidden layer is f1(·), and the output of the hidden layer is:

[0049]

[0050] The transfer equation of the output layer is f2(·), then the output of the output layer is:

[0051]

[0052] Where i is 1, 2, 3, or 4, that is, x1 = Δb', x2 = ΔT', x3 = ΔF', x4 = Δv', n is the number of input layer nodes, q is the number of hidden layer nodes, m is the number of output layer nodes, and v ki is the weight from input layer node i to hidden layer node k, w jk is the weight from hidden layer node k to output layer node j.

[0053] Compared with the prior art, the present invention has the following advantages:

[0054] 1) By establishing a microstructure model based on crystallographic and physical principles, obtaining the required material parameters through experiments, and using computer simulation calculations, the organization prediction of the rolling process can be achieved. By establishing a macro-micro evolution model of billet rolling, the model is embedded in the intelligent control system to achieve process optimization based on organization prediction. Reliable models and systems can further broaden the scope of application of prediction models, improve the accuracy and reliability of predictions, and provide strong data support for the intelligent production of rolling processes, and provide ideas and methods for the intelligent development of plate and strip materials.

[0055] 2) The quality control system and method of the present invention can realize the micro-scale visualization of the slab during the rolling process. By using digital twins, the stress field, strain field, and average grain size of the rolling process can be visualized in real time, so as to intuitively understand the rolling process and timely predict slab quality problems.

[0056] 3) In the system of the present invention, the database has a wide range of industrial samples, the sources of production samples and simulation samples are reliable, the calculation in the quality abnormality diagnosis module is simple, and the convergence speed is fast, so as to achieve the purpose of realizing effective quality control with a few key rules. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 It is a schematic structural diagram of a multi-scale quality control system for intelligent hot rolling of large-size slabs according to the present invention;

[0058] Figure 2 Schematic diagram of BP neural network. DETAILED DESCRIPTION

[0059] In order to further illustrate the technical solution of the present invention, the present invention is further described below through embodiments.

[0060] like Figure 1As shown, a multi-scale quality control system for intelligent hot rolling of large-size slabs in this embodiment is mainly divided into three parts: virtual computing module, quality control module and quality anomaly diagnosis module. The production process data is provided to three parts, namely, production data of the macro production process, micro crystallographic principle and physical principle thermal deformation stress model, and microstructure model. Combined with the data-driven quality anomaly diagnosis model, the prediction, quality feedback and process reverse optimization of large-size slabs in the rolling process are realized, providing strong data support for the intelligent production of rolling process and providing ideas and methods for the intelligent development of plate and strip materials.

[0061] Among them, 1) virtual calculation module: performs numerical simulation calculation on the slab rolling process based on numerical simulation software and outputs simulation calculation results;

[0062] The process parameters of the slab rolling process in this embodiment include material parameters, slab size, hot rolling process parameters and hot rolling equipment parameters. The material parameters include thermophysical parameters, thermal deformation constitutive model, thermal deformation grain model, etc.

[0063] The virtual calculation module uses the finite element analysis software ABAQUS. The process parameters of the slab rolling process are imported through the pre-processing module of the finite element analysis software ABAQUS. The thermal deformation stress model of the slab material and the average grain size model of the microstructure are written by ABAQUSPython.

[0064] The thermal deformation stress model is updated as follows:

[0065]

[0066] Among them, α(ε,T), and n(ε,T) are the material parameters of the casting billet, obtained by experimental calculation, is the thermal deformation activation energy, R is the ideal gas constant, and T is the absolute temperature;

[0067] The microstructure average grain size model is updated as follows:

[0068]

[0069] Where d0 is the initial grain size, d t is the average grain size after t seconds, t is the holding time, K, n are material-related constants, Q b is the activation energy of grain boundary self-diffusion.

[0070] 2) Quality control module: records the technical parameters of the slab rolling production process and compares them with the simulation calculation results of the virtual calculation module;

[0071] The quality control module of this embodiment is implemented based on the existing online comprehensive quality control system, and the quality control system contains quality judgment rules, quality evaluation methods, rolling process weight table, and slab and equipment characteristic parameter identification.

[0072] 3) Quality abnormality diagnosis module: Based on the process parameters of the slab rolling process, the simulation calculation results of the virtual calculation module and the comparison results of the quality control module, the quality status difference analysis is carried out to optimize the process parameters. The optimized process parameters are fed back to the slab rolling process for regulation;

[0073] The quality abnormality diagnosis module of this embodiment collects the slab thickness b, temperature T, rolling force F and rolling speed v during the slab rolling process as parameters, performs differential operation with the results of the virtual calculation module, and calculates the slab thickness change Δb, temperature change ΔT, rolling force change ΔF and rolling speed Δv;

[0074] The differential parameters p = [Δb, ΔT, ΔF, Δv] are standardized as follows:

[0075]

[0076] Among them, p' is the parameter after standardization;

[0077] The standardized parameters p'=[Δb', ΔT', ΔF', Δv'] are input into the quality abnormality diagnosis model, and the rolling temperature abnormality, pressure abnormality, speed abnormality and equipment vibration are output, and then the rolling process parameters are reversely optimized, and the optimized process parameters are fed back to the slab rolling process; the quality abnormality diagnosis model adopts BP neural network (such as Figure 2 As shown in Figure 2), it includes input layer, hidden layer and output layer. The transfer equation of the hidden layer is f1(·), then the output of the hidden layer is:

[0078]

[0079] The transfer equation of the output layer is f2(·), then the output of the output layer is:

[0080]

[0081] Where i is 1, 2, 3, or 4, that is, x1 = Δb', x2 = ΔT', x3 = ΔF', x4 = Δv', n is the number of input layer nodes, q is the number of hidden layer nodes, m is the number of output layer nodes, and v ki is the weight from input layer node i to hidden layer node k, w jk is the weight from hidden layer node k to output layer node j.

[0082] A multi-scale quality control method for large-size slab intelligent hot rolling in this embodiment includes the following steps:

[0083] Step 1: collect the process parameters of the slab rolling process in real time. The process parameters of the slab rolling process include material parameters, slab size, hot rolling process parameters and hot rolling equipment parameters. The material parameters include thermophysical parameters, thermal deformation constitutive model, thermal deformation grain model, etc.

[0084] Step 2, based on the process parameters of the billet rolling process collected in real time, numerical simulation calculation is performed on the process parameters;

[0085] The numerical simulation calculation is carried out with the help of finite element analysis software ABAQUS. The process parameters of the slab rolling process are imported through the pre-processing module of the finite element analysis software ABAQUS. The thermal deformation stress model and the microstructure average grain size model are written by ABAQUSPython.

[0086] The thermal deformation stress model is updated as follows:

[0087]

[0088] Among them, α(ε,T), and n(ε,T) are the material parameters of the casting billet, is the thermal deformation activation energy, R is the ideal gas constant, and T is the absolute temperature;

[0089] The microstructure average grain size model is updated as follows:

[0090]

[0091] Where d0 is the initial grain size, d t is the average grain size after t seconds, t is the holding time, K, n are material-related constants, Q b is the activation energy of grain boundary self-diffusion.

[0092] Step 3, comparing the process parameters of the billet rolling process collected in real time with the results of the simulation calculation in step 2;

[0093] Step 4: Based on the real-time acquisition of the process parameters of the slab rolling process, the results of the simulation calculation in step 2 and the results of the comparison in step 3, the quality status difference analysis is performed to optimize the process parameters, and the optimized process parameters are fed back to the slab rolling process for regulation;

[0094] First, the slab thickness b, temperature T, rolling force F and rolling speed v during the slab rolling process are collected as parameters, and the difference operation is performed with the results of the simulation calculation in step 1 to calculate the slab thickness change Δb, temperature change ΔT, rolling force change ΔF and rolling speed Δv;

[0095] Then the differential parameters p = [Δb, ΔT, ΔF, Δv] are standardized as follows:

[0096]

[0097] Among them, p' is the parameter after standardization;

[0098] Finally, the standardized parameters p'=[Δb', ΔT', ΔF', Δv'] are input into the quality anomaly diagnosis model, and the rolling temperature anomaly, pressure anomaly, speed anomaly and equipment vibration are output, and then the rolling process parameters are reversely optimized. The optimized process parameters are fed back to the slab rolling process; the quality anomaly diagnosis model adopts a BP neural network, which includes an input layer, a hidden layer and an output layer. The transfer equation of the hidden layer is f1(·), and the output of the hidden layer is:

[0099]

[0100] The transfer equation of the output layer is f2(·), then the output of the output layer is:

[0101]

[0102] Where i is 1, 2, 3, or 4, that is, x1 = Δb', x2 = ΔT', x3 = ΔF', x4 = Δv', n is the number of input layer nodes (n = 4), q is the number of hidden layer nodes (q = 6), m is the number of output layer nodes (m = 4), and v ki is the weight from input layer node i to hidden layer node k, w jk is the weight from hidden layer node k to output layer node j.

[0103] The above shows and describes the main features and advantages of the present invention. It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential features of the present invention. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the appended claims rather than the above description, and it is intended that all changes that fall within the meaning and scope of the equivalent elements of the claims are included in the present invention.

[0104] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

Claims

1. A multi-scale quality control system for large-size slab intelligent hot rolling, characterized in that: include: Virtual calculation module, which performs numerical simulation calculation on the slab rolling process based on numerical simulation software and outputs simulation calculation results; The quality control module records the technical parameters of the slab rolling production process and compares them with the simulation calculation results of the virtual calculation module; The quality anomaly diagnosis module analyzes the quality status differences based on the process parameters of the slab rolling process, the simulation calculation results of the virtual calculation module and the comparison results of the quality control module, optimizes the process parameters, and feeds the optimized process parameters back to the slab rolling process for regulation.

2. A multi-scale quality control system for large-size slab intelligent hot rolling according to claim 1, characterized in that: The process parameters of the slab rolling process include material parameters, slab size, hot rolling process parameters and hot rolling equipment parameters.

3. A multi-scale quality control system for large-size slab intelligent hot rolling according to claim 2, characterized in that: The virtual calculation module is based on the finite element analysis software ABAQUS, and the process parameters of the slab rolling process are imported through the pre-processing module of the finite element analysis software ABAQUS, wherein the slab material thermal deformation stress model and the microstructure average grain size model are written by ABAQUSPython; The thermal deformation stress model is updated as follows: Among them, α(ε,T), and n(ε,T) are the material parameters of the casting billet, is the thermal deformation activation energy, R is the ideal gas constant, and T is the absolute temperature; The microstructure average grain size model is updated as follows: Where d0 is the initial grain size, d t is the average grain size after t seconds, t is the holding time, K, n are material-related constants, Q b is the activation energy of grain boundary self-diffusion.

4. A multi-scale quality control system for large-size slab intelligent hot rolling according to claim 3, characterized in that: The quality abnormality diagnosis module is specifically: The slab thickness b, temperature T, rolling force F and rolling speed v during the slab rolling process are collected as parameters, and differential operation is performed with the results of the virtual calculation module to calculate the slab thickness change Δb, temperature change ΔT, rolling force change ΔF and rolling speed Δv; The differential parameters p = [Δb, ΔT, ΔF, Δv] are standardized as follows: Among them, p' is the parameter after standardization; The standardized parameters p'=[Δb', ΔT', ΔF', Δv'] are input into the quality anomaly diagnosis model, and the rolling temperature anomaly, pressure anomaly, speed anomaly and equipment vibration are output, and then the rolling process parameters are reversely optimized, and the optimized process parameters are fed back to the slab rolling process; the quality anomaly diagnosis model adopts a BP neural network, which includes an input layer, a hidden layer and an output layer, wherein the transfer equation of the hidden layer is f1(·), and the output of the hidden layer is: The transfer equation of the output layer is f2(·), then the output of the output layer is: Where i is 1, 2, 3, or 4, that is, x1 = Δb', x2 = ΔT', x3 = ΔF', x4 = Δv', n is the number of input layer nodes, q is the number of hidden layer nodes, m is the number of output layer nodes, and v ki is the weight from input layer node i to hidden layer node k, w jk is the weight from hidden layer node k to output layer node j.

5. A multi-scale quality control method for large-size slab intelligent hot rolling, characterized in that: The following steps are involved: Step 1, real-time acquisition of process parameters of slab rolling process; Step 2, based on the process parameters of the billet rolling process collected in real time, numerical simulation calculation is performed on the process parameters; Step 3, comparing the process parameters of the billet rolling process collected in real time with the results of the simulation calculation in step 2; Step 4: Based on the real-time collection of process parameters of the slab rolling process, the results of the simulation calculation in step 2 and the comparison results in step 3, quality status difference analysis is performed to optimize the process parameters. The optimized process parameters are fed back to the slab rolling process for regulation.

6. The multi-scale quality control method for large-size slab intelligent hot rolling according to claim 5, characterized in that: The process parameters of the slab rolling process in step 1 include material parameters, slab size, hot rolling process parameters and hot rolling equipment parameters.

7. A multi-scale quality control method for large-size slab intelligent hot rolling according to claim 6, characterized in that: The step 2 is specifically as follows: With the help of finite element analysis software ABAQUS, the process parameters of the slab rolling process are imported through the pre-processing module of the finite element analysis software ABAQUS, and the thermal deformation stress model and the microstructure average grain size model are written by ABAQUSPython; The thermal deformation stress model is updated as follows: Among them, α(ε,T), and n(ε,T) are the material parameters of the casting billet, is the thermal deformation activation energy, R is the ideal gas constant, and T is the absolute temperature; The microstructure average grain size model is updated as follows: Where d0 is the initial grain size, d t is the average grain size after t seconds, t is the holding time, K, n are material-related constants, Q b is the activation energy of grain boundary self-diffusion.

8. The multi-scale quality control method for large-size slab intelligent hot rolling according to claim 7, characterized in that: The specific steps of step 4 are as follows: The slab thickness b, temperature T, rolling force F and rolling speed v during the slab rolling process are collected as parameters, and the difference operation is performed with the result of the simulation calculation in step 1 to calculate the slab thickness change Δb, temperature change ΔT, rolling force change ΔF and rolling speed Δv; The differential parameters p = [Δb, ΔT, ΔF, Δv] are standardized as follows: Among them, p' is the parameter after standardization; The standardized parameters p'=[Δb', ΔT', ΔF', Δv'] are input into the quality anomaly diagnosis model, and the rolling temperature anomaly, pressure anomaly, speed anomaly and equipment vibration are output, and then the rolling process parameters are reversely optimized, and the optimized process parameters are fed back to the slab rolling process; the quality anomaly diagnosis model adopts a BP neural network, which includes an input layer, a hidden layer and an output layer, wherein the transfer equation of the hidden layer is f1(·), and the output of the hidden layer is: The transfer equation of the output layer is f2(·), then the output of the output layer is: Where i is 1, 2, 3, or 4, that is, x1 = Δb', x2 = ΔT', x3 = ΔF', x4 = Δv', n is the number of input layer nodes, q is the number of hidden layer nodes, m is the number of output layer nodes, and v ki is the weight from input layer node i to hidden layer node k, w jk is the weight from hidden layer node k to output layer node j.

Images