A deformation-preventing self-adaptive bracket system for large steel plate heat treatment

Abstract

The application discloses a kind of anti-deformation adaptive bracket systems for large steel plate heat treatment, belong to metal heat treatment technical field;Through data acquisition module, steel plate basic parameters and heat treatment process data are collected, digital twin construction module is based on steel plate basic parameters and heat treatment process data to construct and real-time update digital twin model, data analysis module is based on digital twin model analysis steel plate in heating, heat preservation and quenching stage deformation and shape deviation, strategy generation module is based on the analysis result of data analysis module to generate high-precision control strategy to drive adaptive bracket to carry out dynamic adjustment, system has self-learning optimization ability, through error feedback, continuously calibrates digital twin model parameters, improves prediction accuracy, auxiliary repair module carries out multi-point high-precision correction and local heat treatment repair to deformed steel plate, effectively suppresses deformation problem in heat treatment process, improves product quality and production stability.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of metal heat treatment, and specifically discloses a deformation-preventing self-adaptive bracket system for heat treatment of large steel plates. BACKGROUND

[0002] In the heat treatment process of large steel plates, plastic deformation such as warping, concave, and twisting is prone to occur due to uneven heating, phase transformation stress, self-weight, and other factors, which seriously affects the flatness and dimensional accuracy of the product, and even leads to workpiece scrap. Traditional heat treatment brackets mostly adopt rigid support or simple adjustable structure, lack real-time monitoring and dynamic response capability for the shape change of the steel plate in the heat treatment process, and cannot effectively inhibit or compensate for the deformation.

[0003] At present, the industry relies on experience to set process parameters and repairs deformation through subsequent mechanical correction, but this method is low in efficiency and high in cost, and is strict in technical requirements for operators. Although some individual research attempts to introduce sensors to monitor temperature or deformation, it still lacks systematic digital modeling, real-time prediction, and closed-loop control capability, and it is difficult to achieve precise deformation prevention and self-adaptive adjustment. The pain points of the prior art are:

[0004] Passive support: the traditional bracket is a rigid fixed structure, which cannot cope with the complex internal stress changes of the steel plate due to thermal expansion and contraction and phase transformation in the heat treatment process, resulting in uncontrollable deformation;

[0005] Deformation is unpredictable: deformation is the result of heat treatment, which cannot be intervened in the process, and can only be corrected or scrapped afterwards, which is high in cost;

[0006] Multi-factor coupling: deformation is the result of the coupling of multiple factors such as the composition of the steel plate, heating / cooling rate, and temperature uniformity, which cannot be quantitatively analyzed by traditional experience;

[0007] Poor consistency: the heat treatment deformation of steel plates of different batches and different furnace times fluctuates greatly, and the product quality is unstable;

[0008] Therefore, it is necessary to invent a deformation-preventing self-adaptive bracket system for heat treatment of large steel plates to solve the above problems. SUMMARY

[0009] In order to overcome the prior art defects mentioned above, the present application provides a deformation prevention self-adaptive bracket system for large steel plate heat treatment, which collects steel plate basic parameters and heat treatment process data through a data acquisition module, constructs and updates a digital twin model in real time based on the steel plate basic parameters and heat treatment process data through a digital twin construction module, analyzes the deformation trend and shape deviation of the steel plate in the heating, holding and quenching stages based on the digital twin model through a data analysis module, generates a high-precision control strategy to drive the self-adaptive bracket to make dynamic adjustments based on the analysis results of the data analysis module through a strategy generation module, and has self-learning optimization capability, continuously calibrates the digital twin model parameters through error feedback, improves the prediction accuracy, and assists the repair module to perform multi-point high-precision correction and local heat treatment repair on the deformed steel plate, effectively solving the problems mentioned in the background art.

[0010] To achieve the above object, the present application provides the following technical scheme: a deformation prevention self-adaptive bracket system for large steel plate heat treatment, comprising a data acquisition module, a data analysis module, a self-adaptive array bracket, a digital twin construction module, a strategy generation module, a self-learning optimization module and an auxiliary repair module.

[0011] The data acquisition module collects steel plate basic parameters and heat treatment process data.

[0012] The digital twin construction module generates a digital twin model dynamically mapped with the steel plate based on the steel plate basic parameters and synchronously integrated heat treatment process preset parameters, receives heat treatment process data in real time during the heat treatment process, updates the temperature distribution and shape simulation results of the model, and outputs predicted shape data of the steel plate according to the heat treatment process data.

[0013] The data analysis module analyzes the deformation amount and shape deviation of the steel plate during the heat treatment process based on the digital twin model and the heat treatment process data, and outputs the analysis results.

[0014] The analysis method of the shape deviation is to compare the shape data collected by the data acquisition module in real time with the expected shape, and calculate the local bulging or concave deviation.

[0015] The analysis method of the deformation amount is to subtract the real-time deformation amount obtained by the difference between the shape data collected by the data acquisition module in real time and the predicted shape data output by the digital twin model.

[0016] The strategy generation module generates a control strategy of the self-adaptive array bracket according to the analysis results of the data analysis module.

[0017] The self-adaptive array bracket is composed of a support matrix of m*n high-precision electric servo cylinders, each cylinder body can be independently controlled to rise and fall, and is used to receive and execute the control strategy generated by other modules.

[0018] Self-learning optimization module: compare the shape data of the discharged steel plate predicted by the digital twin model with the actual shape data of the discharged steel plate, calculate the error value; feed the key process parameters and the error value to the digital twin construction module to automatically calibrate the model parameters in the digital twin model; accumulate the heat treatment process data of the same type of steel plate, and iteratively optimize the fitting accuracy of the function f(C, AT, G, t) in the deviation mathematical model;

[0019] The key process parameters include the carbon content of the steel plate and the heat treatment process data; the function f in the deviation mathematical model is an empirical fitting function for predicting the maximum deformation of the steel plate under a specific process, where C represents the carbon content of the steel plate, AT represents the characteristic temperature difference, G represents the thickness ratio of the steel plate, and t represents the duration of a specific stage;

[0020] Auxiliary repair module: based on the shape deviation of the heat treatment process data and the steel plate, generate the optimal correction control strategy for the deformed steel plate; perform multi-point adjustment on the deformation area through the self-adaptive array bracket, and realize repair combined with multiple local heat treatments.

[0021] Preferably, the steel plate basic parameters include the material composition, geometric size and initial flatness of the steel plate; the heat treatment process data includes temperature field distribution data, shape data and heating / cooling rate data; the shape data includes steel plate surface three-dimensional point cloud data.

[0022] Preferably, the analysis method of the deformation amount is to subtract the real-time deformation amount obtained by subtracting the real-time shape data collected by the data acquisition module from the predicted shape data output by the digital twin model.

[0023] Preferably, the generation steps of the control strategy are as follows:

[0024] Calculate the feedforward control amount based on the predicted deformation amount;

[0025] Calculate the feedback control amount based on the shape deviation;

[0026] Combine the feedforward control amount and the feedback control amount to generate the total control amount.

[0027] Preferably, the feedforward control amount is obtained by multiplying the predicted deformation amount by a feedforward gain coefficient K ff ; and the feedback control amount is obtained by multiplying the difference between the real-time shape deviation and the target shape deviation by a feedback gain coefficient K fb .

[0028] Preferably, the generation method of the optimal correction control strategy is to inversely solve the support force distribution and heat treatment parameters to be applied based on the shape deviation data and the deviation mathematical model, generate adjustment instructions with the goal of minimizing residual stress, and the heat treatment parameters include heating power and heating coordinates.

[0029] Technical effects and advantages of the present application:

[0030] 1. The system makes real-time prediction through digital twin model and performs high-precision multi-point adjustment with adaptive array bracket, realizing a revolutionary change from "passive support" to "active orthopedic", which can actively offset the deformation caused by thermal stress and phase change during heat treatment; through the feedforward-feedback composite control strategy and auxiliary repair function, it can effectively prevent irreversible excessive deformation of large steel plates during heat treatment, minimize waste rate and subsequent correction cost, and directly improve production yield and economic benefits;

[0031] 2. The multi-physics field coupled digital twin model can accurately simulate the dynamic changes of temperature, stress and deformation of steel plates during heat treatment, providing a scientific basis for prediction and control, and reducing the dependence on traditional "trial and error" experience; based on comprehensive data collection and real-time morphology analysis, all control strategies and repair schemes are data-driven, making the decision-making process more objective, accurate and reliable;

[0032] 3. The self-learning optimization module can automatically calibrate the key physical parameters in the digital twin model using the error between actual production data and predicted data, making the model more accurate as production data accumulates, with the feature of "getting smarter the more you use it"; by continuously iterating and optimizing the deviation mathematical model f(C, ΔT, G, t), the system will continuously deposit and solidify the process knowledge of processing similar steel plates, forming an enterprise's unique, continuously optimized intelligent process database, and improving the overall process level;

[0033] 4. The system not only focuses on preventing deformation, but also provides backup solutions for deformation management. For the existing deviation, online repair can be performed through precise mechanical adjustment and controlled local heat treatment to maximize product recovery, providing double protection; from monitoring and analysis to control and optimization, the whole process is highly automated, reducing the over-reliance on operator experience, reducing quality fluctuations caused by human factors, and improving the stability and consistency of the production process; the online repair capability can reduce the time required for offline processing due to deformation unqualified steel plates, speed up the production process, and improve equipment utilization and capacity. BRIEF DESCRIPTION OF DRAWINGS

[0034] The present application is further illustrated by the accompanying drawings, but the embodiments in the drawings do not constitute any limitation on the present application. For ordinary skilled in the art, other drawings can be obtained without creative labor on the basis of the following drawings.

[0035] Figure 1 The overall structure module and data interaction diagram of the present application.

[0036] Figure 2 The overall step flowchart of the present application. DETAILED DESCRIPTION

[0037] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0038] The present application provides a kind of for large steel plate heat treatment as shown in Figure 1 The anti-deformation adaptive bracket system for large steel plate heat treatment includes a data acquisition module, a data analysis module, an adaptive array bracket, a digital twin construction module, a strategy generation module, a self-learning optimization module and an auxiliary repair module.

[0039] As shown in Figure 2 The overall step flowchart of the present application is as follows:

[0040] The data acquisition module acquires steel plate basic parameters and heat treatment process data;

[0041] Further, in the above technical solution, the steel plate basic parameters include the material composition, geometric size and initial flatness of the steel plate; the heat treatment process data includes temperature field distribution data, shape data and heating / cooling rate data; the shape data includes steel plate surface three-dimensional point cloud data.

[0042] Further, the material composition and geometric size of the steel plate are obtained through an upstream production system interface, specifically, the material composition of the steel plate can be analyzed by a spectrometer, and the geometric size of the steel plate can be acquired by a laser range finder; the shape data is acquired by using a three-dimensional laser scanner to acquire steel plate surface point cloud data, and the data of each point includes its three-dimensional coordinates (xi, yi, zi); the initial flatness is calculated by a point cloud processing algorithm; the temperature field distribution data is monitored in real time by arranging an infrared thermal imager to monitor the steel plate surface temperature; and the heating / cooling rate data, i.e., the temperature change rate with time, is recorded by a high-frequency temperature sensor.

[0043] Further, the calculation process of the initial flatness is as follows:

[0044] The least square method is used to perform plane fitting on the preprocessed point cloud data to obtain a "best fitting plane" that best represents the overall inclination state of the steel plate, and the equation of the reference plane can be expressed as Ax+By+Cz+D=0, wherein A, B and C are normal vectors, and D is a constant;

[0045] The distance of each point in the point cloud to the reference plane is calculated, i.e., the deviation value di of the point, and the calculation formula is: ;

[0046] The standard deviation of all point deviation values di is calculated using the formula: The standard deviation of all point deviation values di is calculated using the formula:

[0047] The digital twin construction module synchronously integrates the heat treatment process preset parameters based on the steel plate basic parameters to generate a digital twin model dynamically mapped with the steel plate, and in the heat treatment process, the digital twin model updates the temperature distribution and shape simulation results of the model by real-time receiving heat treatment process data, and outputs the predicted shape data of the steel plate according to the heat treatment process data.

[0048] Further, in the above technical solution, the heat treatment process preset parameters include target temperature, holding time, heating rate, cooling medium type and its flow rate, and positioning data for describing the initial position of the steel plate on the carrier.

[0049] Further, the construction process of the digital twin model is as follows:

[0050] Based on the steel plate basic parameters and process preset parameters, an initial digital twin model is constructed by using multi-physical field coupling simulation technology, such as finite element analysis (FEA); the model covers physical processes such as heat conduction, phase change, thermal stress, and elastic-plastic deformation.

[0051] In the heat treatment process, temperature field and shape data are real-time received; the temperature distribution and predicted shape of the model are dynamically updated to keep synchronization with the physical entity; and the predicted shape data of the steel plate is real-time output to provide data support for subsequent analysis and control modules.

[0052] The data analysis module analyzes the deformation amount and shape deviation of the steel plate in the heat treatment process based on the digital twin model and heat treatment process data, and outputs the analysis results.

[0053] Further, in the above technical solution, the analysis method of the shape deviation is: by comparing the shape data collected by the data acquisition module in real time with the expected shape, the local bulge or depression deviation is calculated; the expected shape is the ideal shape of the steel plate at the current time in the standard heat treatment process.

[0054] Further, the specific analysis process of the shape deviation is as follows:

[0055] The corresponding points of the key points are found in the actual point cloud and the expected point cloud, respectively.

[0056] The difference between the actual height and the expected height of each key point in the normal direction is calculated, and the calculation formula is δi=zia−ziw; δi>0 indicates that the actual position of the point is higher than the expected position, and δi<0 indicates that the actual position of the point is lower than the expected position; in the formula, zia represents the actual height of key point i in the z-axis direction, and ziw represents the expected height of key point i in the z-axis direction;

[0057] It should be further pointed out that the key point is the position of the electric servo cylinder of the adaptive array bracket, and zia, ziw and zip are all derived from the shape data, i.e. the z coordinate of the point cloud data corresponding to the key point;

[0058] Further, in the above technical solution, the analysis method of the deformation amount is: the difference between the shape data collected by the data acquisition module in real time and the predicted shape data output by the digital twin model is obtained, and the real-time deformation amount is obtained.

[0059] Further, the specific analysis process of the deformation amount is as follows:

[0060] The real-time collected shape data and the predicted shape data are compared point by point, the deformation value ΔS of each key point is calculated, a deformation amount matrix is obtained, and the deformation amount is obtained by summarizing each deformation value ΔS in the deformation amount matrix, and the calculation formula is S=∑|ΔS|; in the formula, ΔS=zia−zip, and zip represents the predicted height of key point i in the z-axis direction;

[0061] The strategy generation module generates a control strategy for the adaptive array bracket according to the analysis result of the data analysis module;

[0062] Further, in the above technical solution, the generation steps of the control strategy are as follows:

[0063] The feedforward control amount is calculated based on the predicted deformation amount;

[0064] Further, the calculation formula of the feedforward control amount Uff of the key point is: Uff=Kff×ΔS, and in the formula, Kff is a feedforward gain coefficient, which is pre-calibrated according to material characteristics and process parameters;

[0065] The feedback control amount is calculated based on the shape deviation;

[0066] Further, the calculation formula of the feedback control amount Ufb of the key point is: Ufb=Kfb(δa−δt), and in the formula, Kfb is a feedback gain coefficient, which is determined by a fuzzy control algorithm, δa is an actual shape deviation, and δt is a target shape deviation, which is usually 0, i.e. no deviation.

[0067] The total control amount is generated by combining the feedforward control amount and the feedback control amount.

[0068] The calculation formula of the total control amount Ut of the further key point is: Ut=Uff+Ufb;

[0069] The adaptive array bracket receives and executes the control strategy generated by other modules;

[0070] The self-learning optimization module compares the shape data of the discharged steel plate predicted by the digital twin model with the actual shape data of the discharged steel plate, calculates the error value, feeds the key process parameters and the error value back to the digital twin construction module, automatically calibrates the model parameters in the digital twin model, accumulates the heat treatment process data of the same type of steel plate, iteratively optimizes the fitting precision of the function f in the deviation mathematical model, and reduces the subsequent prediction deviation;

[0071] Further, in the above technical solution, the key process parameters include: heat treatment process data in the steel plate heat treatment process and carbon content of the steel plate.

[0072] Further, the function f in the deviation mathematical model is an empirical fitting function for predicting the maximum deformation of the steel plate under a specific process, and the mathematical expression is f(C, ΔT, G, t), wherein C represents the carbon content of the steel plate, which is a key factor affecting the phase change behavior and hardenability; ΔT represents the characteristic temperature difference, which can be defined as the maximum temperature difference between the surface and the core of the steel plate during heating or cooling, or the maximum temperature difference between the two ends in the length direction, which is the main driving source of thermal stress; G represents the thickness-span ratio of the steel plate, i.e. the ratio of the thickness to the maximum supporting span, which is used to quantify the bending stiffness of the steel plate under the action of gravity and thermal stress; t represents the duration of a specific stage, such as the heating stage, the holding stage, and the quenching stage; the initial form of the function can be preset as a linear polynomial, for example: f=w C ·C+w b ·ΔT+w G ·G+w d ·t+e, wherein w C , w b , w G , w d and e are initial weight coefficients, and the goal of the self-learning optimization module is to continuously adjust these coefficients through regression analysis, and possibly introduce cross terms such as C*ΔT or higher order terms, to improve the prediction accuracy of the function on the final deformation.

[0073] Further, the definition of the same type of steel plate is that the carbon content deviation ∈ [-0.02, 0.02]% and the geometric size deviation ∈ [-5, 5]%; the geometric size includes length, width and thickness.

[0074] Further, the least squares method or the gradient descent method is used to calibrate the model parameters in the digital twin model, and the error back propagation mechanism is used to gradually reduce the prediction error; the optimization process of the model parameters is as follows:

[0075] Error calculation and quantification: the shape data of the steel plate after being discharged predicted by the digital twin model and the actual shape data of the steel plate after being discharged are calculated point by point for height deviation at the same key points, and the root mean square error is used as the quantification index of the overall error, that is, the error value;

[0076] Determination of parameters to be calibrated: select the key physical parameters sensitive to the prediction results and with high uncertainty as the parameters to be calibrated, which usually include: thermal expansion coefficient, phase transition plasticity coefficient and phase transition expansion coefficient;

[0077] Example:

[0078] If the system finds that the predicted deformation is generally smaller than the actual deformation, it may indicate that the thermal expansion coefficient or the phase transition expansion coefficient in the model is underestimated, and these two parameters should be prioritized as parameters to be calibrated.

[0079] Construction of loss function and optimization problem: usually directly use the root mean square error as the loss function, and take minimizing the error between the prediction output of the model and the actual data as the optimization goal, and use the Bayesian optimization algorithm to find the optimal value of the parameters to be calibrated;

[0080] Further, the optimization deviation mathematical model is realized through an iterative cycle of data-driven: the system continuously collects the heat treatment process parameters of the same type of steel plate, such as carbon content, heating rate, geometric size and actual deformation result data, after cleaning and feature engineering, using machine learning algorithms such as random forest or gradient boosting tree, to minimize the error between the predicted deformation and the actual deformation, to train and optimize the prediction function f; The new model after training is deployed for real-time prediction, its performance is continuously monitored, and the data of the same type of steel plate accumulated in production is used to trigger a new round of training regularly, so that the prediction accuracy of the model is continuously evolving, and eventually form a self-learning intelligent system that encapsulates the core process knowledge of the enterprise.

[0081] The auxiliary repair module generates the optimal correction control strategy for the deformed steel plate based on the heat treatment process data and the shape deviation of the steel plate; through the self-adaptive array bracket, multi-point adjustment with ±0.01mm precision is performed on the deformation area, and combined with multiple local heat treatments to realize repair.

[0082] Further, in the above technical solution, the generation method of the optimal correction control strategy is: based on the shape deviation data and the deviation mathematical model, the support force distribution and the heat treatment parameters to be applied are reversely solved to generate adjustment instructions with the goal of minimizing residual stress, and the heat treatment parameters include heating power and heating coordinates.

[0083] Further, the reverse solving is a mathematical optimization process with the goal of "minimizing residual stress", and the core is to perform inversion calculation based on the established digital twin model or deviation mathematical model;

[0084] The specific manner is as follows:

[0085] Optimization variables: the action force of each support point to be applied and the parameters of local heat treatment;

[0086] Objective function: the primary goal is to minimize the overall residual stress of the corrected workpiece, and at the same time, the minimum shape deviation can be considered;

[0087] Constraint condition: the variable needs to be within the physical limit of the system, and at the same time, the shape of the corrected steel plate needs to meet the flatness tolerance requirement;

[0088] Solving process: the system uses the digital twin model as a surrogate model, runs an iterative optimization algorithm for solving, such as gradient descent method, genetic algorithm or sequential quadratic programming method, and the algorithm automatically generates multiple sets of candidate support force distribution and heat treatment parameter combinations within the constraint range of the variable, inputs each set of candidate combination into the digital twin model, and quickly simulates and calculates the residual stress and final shape of the steel plate after applying the parameter set; according to the simulation result, the objective function value is calculated, and the algorithm is updated and generates a better parameter combination accordingly, until the optimal solution that minimizes the objective function is found.

[0089] Further, the local heat treatment refers to a non-uniform, precise and controllable heating and cooling process for the specific area that has been deformed.

[0090] Finally, it should be pointed out that the above only describes the preferred embodiments of the present application and is not used to limit the present application, although the present application has been described in detail with reference to the foregoing embodiments, for those skilled in the art, the technical solutions recorded in the foregoing embodiments can still be modified, or some technical features can be replaced, and any modification, equivalent replacement, improvement, etc. within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A deformation prevention self-adaptive bracket system for heat treatment of large steel plates, characterized in that, The system comprises a data acquisition module, a data analysis module, an adaptive array bracket, a digital twin construction module, a strategy generation module, a self-learning optimization module, and an auxiliary repair module. The data acquisition module acquires steel plate basic parameters and heat treatment process data. The digital twin construction module generates a digital twin model dynamically mapped to the steel plate based on the steel plate basic parameters and the preset heat treatment process parameters, and updates the temperature distribution and shape simulation results of the model in real time during the heat treatment process. The data analysis module analyzes the deformation and shape deviation of the steel plate during the heat treatment process based on the digital twin model and the heat treatment process data, and outputs the analysis results. The shape deviation is analyzed by comparing the real-time shape data collected by the data acquisition module with the expected shape. The deformation is analyzed by subtracting the real-time shape data collected by the data acquisition module from the predicted shape data output by the digital twin model. The strategy generation module generates a control strategy for the adaptive array bracket based on the analysis results of the data analysis module. The adaptive array bracket comprises a support matrix composed of m x n high-precision electric servo cylinders, each cylinder can be independently controlled to rise and fall, and is used to receive and execute the control strategy generated by other modules. The self-learning optimization module compares the shape data of the steel plate after being discharged predicted by the digital twin model with the actual shape data of the steel plate after being discharged, calculates the error value, feeds back the key process parameters and error value to the digital twin construction module, automatically calibrates the model parameters in the digital twin model, accumulates the heat treatment process data of similar steel plates, and iteratively optimizes the fitting precision of the function f(C, ΔT, G, t) in the deviation mathematical model. The key process parameters include the carbon content of the steel plate and the heat treatment process data. The function f in the deviation mathematical model is an empirical fitting function for predicting the maximum deformation of the steel plate under a specific process, where C represents the carbon content of the steel plate, ΔT represents the characteristic temperature difference, G represents the thickness-span ratio of the steel plate, and t represents the duration of a specific stage.

2. A self-adaptive deformation-prevention cradle system for heat treatment of large steel plates as claimed in claim 1, characterized in that: The auxiliary repair module generates an optimal correction control strategy for the deformed steel plate based on the heat treatment process data and the shape deviation of the steel plate, and performs multi-point adjustment on the deformed area through the adaptive array bracket and combines multiple local heat treatments to achieve repair.

3. A self-adaptive cradle system for preventing deformation of a large steel plate during heat treatment according to claim 1, wherein: The steel plate basic parameters include the material composition, geometric size, and initial flatness of the steel plate.

4. A self-adaptive cradle system for preventing deformation of a large steel plate during heat treatment according to claim 1, wherein: The heat treatment process preset parameters include the target temperature, holding time, heating rate, cooling medium type and its flow rate, and positioning data for describing the initial position of the steel plate on the bracket. The generation steps of the control strategy are as follows: Calculate the feedforward control amount based on the predicted deformation amount. Calculate the feedback control amount based on the shape deviation. Combine the feedforward control amount and the feedback control amount to generate the total control amount.

5. A self-adapting cradle system for preventing deformation of large steel plates during heat treatment as claimed in claim 4, wherein: The feedforward control amount is obtained by multiplying the predicted deformation amount by a feedforward gain coefficient K ff The feedback control amount is obtained by multiplying the difference between the real-time shape deviation and the target shape deviation by a feedback gain coefficient K fb .

6. A self-adapting cradle system for preventing deformation of large steel plates during heat treatment as claimed in claim 1, wherein: The optimal correction control strategy is generated in the following manner: based on the shape deviation data and the deviation mathematical model, the support force distribution and the heat treatment parameters to be applied are reversely solved, adjustment instructions are generated with the objective of minimizing residual stress, and the heat treatment parameters include heating power and heating coordinates.

Images