A control method and system for a tension straightening machine

Abstract

This application relates to the field of control technology for tension bending straightening machines, and more particularly to a control method and system for a tension bending straightening machine. The method includes: acquiring an inlet stress distribution cloud map of the sheet material and converting it into an inlet stress matrix; acquiring the target stress value of the sheet material, and calculating an inlet stress deviation matrix based on the inlet stress matrix and the target stress value; using the inlet stress deviation matrix as model input and the pressure adjustment sequence of the straightening roller group as optimization variables, calling a pre-trained stress evolution prediction model for rolling optimization to obtain the optimal pressure adjustment sequence; and controlling the straightening roller group to adjust the pressure based on the optimal pressure adjustment sequence. This application can effectively eliminate residual stress in the sheet material.

Description

Technical Field

[0001] This application relates to the field of control technology for tension bending straightening machines, and in particular to a control method and system for tension bending straightening machines. Background Technology

[0002] In the field of sheet metal processing, the tension straightening machine is the core equipment for eliminating residual stress and improving the flatness of the sheet metal. Its control precision directly determines the processing quality of the sheet metal. Precise control of residual stress in the sheet metal has become a key requirement for improving the yield of high-end sheet metal products in the industry.

[0003] In related technologies, the pressure control of the straightening roller group of the bending straightening machine is mostly based on the fixed parameter setting method based on the specifications of the plate, or simply based on the stress detection data of a single point of the plate for simple pressure compensation adjustment. That is, the fixed pressure value of the straightening roller group is set in advance according to the basic properties of the plate such as material and thickness, or the pressure adjustment amount is calculated through the stress data of a single detection point and applied to the entire straightening roller group simultaneously.

[0004] However, this control method does not take into account the uneven distribution of in-plane stress in the actual material, and cannot make targeted adjustments to the roller pressure according to the actual stress deviation at different locations of the material. This can easily lead to situations where the material still has excessive residual stress and unsatisfactory flatness after straightening, making it difficult to meet the process requirements for precise elimination of residual stress in high-end material processing. Summary of the Invention

[0005] To address the problem of excessive residual stress in localized areas of sheet metal after straightening in existing technologies, this application provides a control method and system for a tension bending straightening machine.

[0006] Firstly, this application provides a control method for a tension straightening machine, employing the following technical solution: A control method for a tension bending straightening machine is provided, applied to a control system of the tension bending straightening machine, the system including a main controller and a tension bending straightening machine, the method being executed by the main controller, the method comprising: Obtain the inlet stress distribution cloud map of the plate and convert the inlet stress distribution cloud map into an inlet stress matrix; Obtain the target stress value of the plate, and calculate the inlet stress deviation matrix based on the inlet stress matrix and the target stress value; Using the inlet stress deviation matrix as the model input and the pressure adjustment sequence of the straightening roller group as the optimization variable, the pre-trained stress evolution prediction model is called to perform rolling optimization and solve for the optimal pressure adjustment sequence. Based on the optimal pressure adjustment sequence, the pressure of the straightening roller group is adjusted.

[0007] By adopting the above technical solution, the inlet stress distribution cloud map of the plate is obtained and quantified into an inlet stress matrix. Combined with the target stress value, the deviation matrix is ​​calculated. With the deviation matrix as input and the roller pressure adjustment sequence as variable, the optimal adjustment amount is obtained by rolling optimization with the help of a pre-trained stress evolution prediction model and the roller group is controlled to execute. This achieves precise quantification and targeted control of plate stress, breaks through the limitations of traditional experience-based control, significantly improves the accuracy and flatness of residual stress elimination in the plate, and adapts to the plate processing needs under different working conditions.

[0008] In a preferred embodiment, this application can be further configured as follows: The step of using the inlet stress deviation matrix as model input and the pressure adjustment sequence of the straightening roller group as optimization variables, calling a pre-trained stress evolution prediction model for rolling optimization, and solving for the optimal pressure adjustment sequence includes: Obtain the current process parameters and the initial pressure setting sequence of the straightening roller group. The current process parameters include the actual value of the process tension, the plate travel speed, and the plate property parameters. The inlet stress deviation matrix, the current process parameters, and the initial pressure setting sequence are input into the stress evolution prediction model to obtain the predicted outlet stress matrix; Define the objective function as minimizing the sum of squared deviations between the predicted outlet stress matrix and the target stress value, use the pressure adjustment sequence as the optimization variable, and define the constraints. Based on the objective function and the optimization variables, and under the constraints, the optimal pressure adjustment sequence is obtained by solving the problem through an iterative optimization algorithm.

[0009] By adopting the above technical solution, the current process parameters and the initial pressure setting sequence of the roller group are integrated, and the predicted outlet stress matrix is ​​obtained by coordinating the input stress evolution prediction model. The objective function is to minimize the sum of squared deviations and set constraints. The optimal adjustment amount is solved by iterative algorithm, which realizes the coupled optimization of process parameters, roller pressure setting and stress evolution. This ensures that the optimization process fits the actual working conditions, improves the reliability and adaptability of the optimal solution, and ensures that the outlet stress of the plate approaches the target value.

[0010] In a preferred embodiment, this application can be further configured as follows: the step of obtaining the optimal pressure adjustment sequence by solving an iterative optimization algorithm based on the objective function and the optimization variables, under the constraints of the conditions, includes: Initialize the optimization variables as a zero vector; During the iteration process, the following steps are performed: The pressure adjustment sequence of the current iteration step is superimposed with the initial pressure setting sequence to generate the current target pressure setting sequence; The current target pressure setting sequence, the inlet stress deviation matrix, and the current process parameters are input into the stress evolution prediction model to obtain the current predicted outlet stress matrix; Based on the current predicted outlet stress matrix and the target stress value, the objective function is invoked to calculate the current objective function value; Determine whether the current objective function value satisfies the preset convergence condition; If the conditions are met, the current pressure adjustment sequence is determined as the optimal pressure adjustment sequence and the iteration is terminated. If the conditions are not met, update the pressure adjustment sequence and continue to the next iteration.

[0011] By adopting the above technical solution, the optimization variables are initialized as zero vectors, the adjustment amount and the initial pressure setting sequence are iteratively superimposed, the outlet stress is predicted, the objective function value is calculated and the convergence is judged. If the convergence is not satisfied, the variables are updated and the iteration continues, which effectively avoids local optima and ensures that the pressure adjustment amount sequence obtained is optimal.

[0012] In a preferred embodiment, this application can be further configured such that the defined constraints include: Based on the plate travel speed, the pressure change rate constraint, the inter-roller pressure difference constraint, and the total load gradient constraint are dynamically determined. The pressure change rate constraint, the inter-roller pressure difference constraint, and the total load gradient constraint are combined into the constraint conditions.

[0013] By adopting the above technical solution, the three types of constraints—pressure change rate, inter-roller pressure difference, and total load gradient—are dynamically determined and combined based on the sheet material's traveling speed. This allows the constraint conditions to adapt to the sheet material's traveling rhythm, avoiding sudden changes in roller pressure that could lead to sheet material deformation, equipment impact, or deviation. It also takes into account the rationality of single-roller adjustment, the stability of roller group coordination, and the safety of equipment load-bearing capacity.

[0014] In a preferred embodiment, this application can be further configured such that: obtaining the inlet stress distribution cloud map of the plate includes: The system receives echo signals from a stress detection array located after the inlet tension roller group of the bending straightener, the stress detection array comprising multi-channel electromagnetic ultrasonic transducers arranged along the width direction of the plate. Acoustic feature parameters are extracted from the echo signal, including transit time and center frequency offset; Based on the acoustic characteristic parameters, the one-dimensional stress distribution at the width position of each channel is determined, and the plates are spliced ​​together according to the width direction of the plate to form a transverse stress distribution line; The position encoder signal and the traveling speed of the plate are acquired. Based on the position encoder signal and the traveling speed of the plate, the acquisition timestamp and longitudinal position coordinates of each transverse stress distribution line are determined. Multiple transverse stress distribution lines collected in a time sequence are meshed and integrated in a two-dimensional plane according to the corresponding collection timestamps and longitudinal position coordinates to obtain the inlet stress distribution cloud map.

[0015] By adopting the above technical solution, the echo signal is collected by a multi-channel electromagnetic ultrasonic transducer, the acoustic feature parameters are extracted and converted into a transverse stress distribution line, and the spatiotemporal coordinates are determined by combining the position encoder signal and the travel speed. The mesh is then integrated into an inlet stress distribution cloud map, realizing non-contact, full-area, dynamic and accurate acquisition of the inlet stress of the plate, and can clearly capture the stress concentration area at the edge.

[0016] In a preferred embodiment, this application can be further configured such that: each instruction in the target pressure setting sequence corresponds to a straightening roller to be controlled; the step of controlling the straightening roller group to adjust the pressure based on the optimal pressure adjustment sequence includes: Based on the traveling speed of the sheet material and the mechanical position of each straightening roller in the straightening roller group, calculate the arrival time of each grid unit on the sheet material to each straightening roller. Each adjustment value in the optimal pressure adjustment sequence is associated with its corresponding arrival time; Based on the arrival time of the binding, a pressure adjustment command based on the corresponding adjustment amount is sent to the pressure actuator of the corresponding straightening roller.

[0017] By adopting the above technical solution, the time when the plate grid unit arrives at each straightening roller is calculated, the optimal adjustment amount is bound to the arrival time, and the pressure command is sent on time. This achieves precise temporal and spatial synchronization between roller pressure adjustment and plate movement, ensuring that the adjustment pressure is accurately applied to the target plate area, avoiding uneven stress correction caused by timing misalignment, and improving the pertinence and effectiveness of roller group pressure control.

[0018] In a preferred embodiment, this application can be further configured such that the method also includes: The vibration signals of the bending straightening machine are collected in real time, and vibration characteristics are extracted from the vibration signals; Based on the vibration characteristics, an active vibration cancellation signal is generated; The active vibration cancellation signal is converted into a control command, which drives the actuator installed in the transmission part of the bending straightening machine to perform the action to suppress vibration.

[0019] By adopting the above technical solution, the vibration signal of the equipment is collected and its features are extracted. Dynamically adapted active vibration cancellation signals are generated according to the principle of equal amplitude and opposite phase. These signals are converted into control commands to drive the actuator to perform closed-loop suppression, effectively canceling the interference of vibration of the transmission part on the rolling accuracy, avoiding stress elimination deviation and plate processing defects caused by vibration, and protecting the transmission parts of the equipment, thereby improving the stability and service life of the equipment.

[0020] Secondly, this application provides a control system for a tension bending straightening machine, which adopts the following technical solution: A control system for a tension bending straightening machine includes a main controller and a tension bending straightening machine, wherein the tension bending straightening machine includes a straightening roller group and a stress detection array; The stress detection array is used to scan the plate entering the tension straightening machine and acquire echo signals, and send the echo signals to the main controller; The main controller is used to execute the control method of the tension straightening machine as described in any of the first aspects; The straightening roller group is used to receive and execute the target pressure setting sequence sent by the main controller to eliminate the residual stress of the plate.

[0021] In a preferred embodiment, this application can be further configured such that the main controller includes: At least one processor; Memory; At least one application, wherein the at least one application is stored in memory and configured to be executed by at least one processor, the at least one application being configured to: execute the control method of the tension straightening machine as described in any of the first aspects.

[0022] In summary, this application includes the following beneficial technical effects: This application obtains the inlet stress distribution cloud map of the sheet material and quantifies it into an inlet stress matrix. Combined with the target stress value, a deviation matrix is ​​calculated. Using the deviation matrix as input and the roller pressure adjustment sequence as variables, the optimal adjustment amount is obtained through rolling optimization using a pre-trained stress evolution prediction model, and the roller group is controlled to execute. This achieves precise quantification and targeted control of sheet material stress, breaks through the limitations of traditional experience-based control, significantly improves the accuracy and flatness of residual stress elimination in the sheet material, and adapts to the sheet material processing needs under different working conditions. Attached Figure Description

[0023] Figure 1 This is a flowchart illustrating a control method for a tension straightening machine provided in an embodiment of this application; Figure 2 This is a schematic diagram of the control system of a tension straightening machine provided in an embodiment of this application; Figure 3This is a schematic diagram of the structure of a main controller provided in an embodiment of this application. Detailed Implementation

[0024] The following is in conjunction with the appendix Figure 1 To be continued Figure 3 This application will be described in further detail.

[0025] This specific embodiment is merely an explanation of this application and is not intended to limit it. After reading this specification, those skilled in the art can make modifications to this embodiment without contributing any inventive step, but such modifications are protected by patent law as long as they fall within the scope of the claims of this application.

[0026] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0027] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article, unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.

[0028] It should be noted that all data interaction processes involved in this application have corresponding transmission protocols, including authorized data collection and use, and both parties involved in the data interaction have completed data authorization through the execution of the protocol.

[0029] This application provides a control method for a tension bending straightening machine, such as... Figure 1 As shown, the method provided in this embodiment is executed by a main controller, which can be a server or a terminal device. The server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smartphone, tablet, laptop, desktop computer, etc., but is not limited to these. The terminal device and the server can be directly or indirectly connected via wired or wireless communication. This embodiment does not impose any limitations on this connection. The method includes steps S101-S104, wherein: S101. Obtain the inlet stress distribution cloud map of the plate and convert the inlet stress distribution cloud map into an inlet stress matrix.

[0030] Specifically, a stress detection array is deployed after the tension roller group at the inlet of the bending straightener. This array includes multi-channel electromagnetic ultrasonic transducers evenly arranged along the width of the sheet material. The transducers synchronously emit electromagnetic ultrasonic signals to the sheet material and receive echo signals. The stress detection array scans along the width direction, and as the sheet material moves, the main controller receives and analyzes the echo signals to obtain a series of continuous transverse stress line distribution data.

[0031] The main controller segments the continuously collected, timestamped transverse stress distribution line data according to a preset fixed cycle. Within each cycle, several transverse stress distribution lines are integrated and visualized in a two-dimensional plane based on their respective collection timestamps and the longitudinal coordinates corresponding to the material's movement, ultimately generating a complete inlet stress distribution cloud map. The inlet stress distribution cloud map is a two-dimensional image where the horizontal axis (X-axis) represents the width of the material, and the vertical axis (Y-axis) represents the length (movement) of the material. The color or value of each pixel in the image represents the magnitude and direction of the residual stress within the material at that point; tensile stress is positive, and compressive stress is negative.

[0032] The core control concept of this embodiment is segmented control. Each inlet stress distribution cloud map precisely corresponds to a new plate segment of fixed length. This fixed length is the product of a preset period and the plate's traveling speed, i.e., the distance the plate travels within the preset period. Each newly generated inlet stress distribution cloud map corresponds to a newly digitized plate segment about to enter the straightening rollers. The control system will initiate a complete control process for this specific plate segment; that is, the control method for the bending straightener provided in this embodiment is a control process for any given plate segment.

[0033] The main controller directly reads the stress values ​​of the regularized mesh from the inlet stress distribution cloud map and stores them in a two-dimensional floating-point array, namely the inlet stress matrix.

[0034] S102. Obtain the target stress value of the plate, and calculate the inlet stress deviation matrix based on the inlet stress matrix and the target stress value.

[0035] The target stress value is an ideal stress state value set according to the requirements of the sheet metal processing technology. The ideal straightening goal is to make the residual stress inside the sheet metal zero, that is, to completely eliminate it. However, in actual industry, the target value can be set to a small allowable range close to zero. In this embodiment, the target stress value can be set according to actual needs, and this embodiment does not limit it.

[0036] The difference between the inlet stress matrix and the target stress value is calculated element by element to obtain the inlet stress deviation matrix. The dimension of the inlet stress deviation matrix is ​​completely consistent with that of the inlet stress matrix. The value of each element in the inlet stress deviation matrix is ​​equal to the value of the corresponding element in the inlet stress matrix minus the target stress value.

[0037] S103. Using the inlet stress deviation matrix as the model input and the pressure adjustment sequence of the straightening roller group as the optimization variable, the pre-trained stress evolution prediction model is called to perform rolling optimization and solve for the optimal pressure adjustment sequence.

[0038] Specifically, the stress evolution prediction model is a machine learning model pre-trained using a large amount of historical processing data. It can accurately predict the stress variation of the sheet metal under different roller pressure adjustments. The training set includes data such as inlet stress, process parameters, roller pressure, and outlet stress. The trained model is used as input for the inlet stress deviation matrix, process parameters, and the pressure setting sequence of the straightening roller group, and outputs the predicted outlet stress matrix. The pressure adjustment sequence contains the same number of elements as the number of straightening rollers in the straightening roller group; each element represents the amount by which the pressure of the corresponding straightening roller needs to be adjusted from the current baseline setting.

[0039] Rolling optimization is an online optimization. Whenever a new section of plate enters (corresponding to a new inlet stress deviation matrix), the control system initiates an optimization calculation to determine the optimal pressure adjustment sequence for this section of plate.

[0040] S104. Based on the optimal pressure adjustment sequence, control the straightening roller group to adjust the pressure.

[0041] Specifically, the main controller sends pressure commands with precise timestamps to the pressure actuators of each straightening roller, such as servo valves or electric cylinders. The actuators dynamically adjust the pressure according to the command time points, thereby applying customized straightening forces to areas with specific stress characteristics on the board, ultimately achieving the uniform elimination of residual stress across the entire board.

[0042] This embodiment obtains the inlet stress distribution cloud map of the plate and quantifies it into an inlet stress matrix. Combined with the target stress value, a deviation matrix is ​​calculated. Using the deviation matrix as input and the roller pressure adjustment sequence as variables, the optimal adjustment amount is obtained by rolling optimization with the help of a pre-trained stress evolution prediction model, and the roller group is controlled to execute. This achieves precise quantification and targeted control of plate stress, breaks through the limitations of traditional experience-based control, significantly improves the accuracy and flatness of residual stress elimination in the plate, and adapts to the plate processing needs under different working conditions.

[0043] One possible implementation of this application embodiment involves using the inlet stress deviation matrix as the model input and the pressure adjustment sequence of the straightening roller group as the optimization variable. A pre-trained stress evolution prediction model is invoked for rolling optimization to obtain the optimal pressure adjustment sequence, including: Obtain the current process parameters and the initial pressure setting sequence of the straightening roller group. The current process parameters include the actual value of the process tension, the sheet travel speed, and the sheet property parameters. Input the inlet stress deviation matrix, current process parameters, and initial pressure setting sequence into the stress evolution prediction model to obtain the predicted outlet stress matrix; The objective function is defined as minimizing the sum of squared deviations between the predicted outlet stress matrix and the target stress value, with the pressure adjustment sequence as the optimization variable, and constraints are defined. Based on the objective function and optimization variables, and under the constraints, the optimal pressure adjustment sequence is obtained by solving the problem through an iterative optimization algorithm.

[0044] The training process of the stress evolution prediction model includes: collecting historical processing data of different specifications of plates from a tension bending straightening machine, and classifying and organizing it according to the input feature set and output label set; the input feature set includes the inlet stress deviation matrix, process parameters (actual values ​​of process tension, plate travel speed, plate property parameters), and straightening roller pressure setting sequence during historical processing; the output label set is the plate outlet stress matrix actually collected by stress detection equipment under the corresponding input working conditions; simultaneously, the dataset is preprocessed, including outlier removal, data standardization, and matrix dimension unification. It is divided into training set, validation set, and test set. Based on the dimensions of the input and output data, a deep neural network model is built. The input layer adapts to the splicing format of multi-dimensional features, the hidden layers are set with multiple convolutional and fully connected layers, and the output layer outputs the predicted value with the same dimensions as the outlet stress matrix. The training set is input into the pre-built network model. The mean square error between the predicted and actual exit stress matrices is used as the loss function, and optimizers such as Adam and SGD are used to iteratively update the model parameters. During training, the validation set is input into the model at fixed intervals to verify the model's generalization ability. If overfitting occurs, optimization is performed using dropout, regularization, etc. The test set is input into the trained model, and evaluation indicators such as the correlation coefficient and mean absolute error between the model's predicted and actual values ​​are calculated. If the indicators meet the preset prediction accuracy requirements, the model training is complete; otherwise, the network structure and training hyperparameters are adjusted, and retraining is performed. The trained stress evolution prediction model is deployed to the main controller of the tension bending straightening machine. At the same time, an online model update mechanism is set up. The main controller collects new processing data in real time, performs incremental training on the model periodically, and continuously optimizes the model parameters to ensure the model's prediction accuracy for different working conditions and different plates, adapting to the changes in actual production processes.

[0045] The straightening machine is equipped with various sensors, including tension sensors and speed encoders. Tension sensors detect the actual process tension in real time, representing the magnitude of the longitudinal tension applied during the straightening process, measured in MPa. The speed encoder collects the real-time speed of the sheet material passing through the straightening rollers, i.e., the sheet's travel speed, measured in m / s. The main controller receives the actual process tension and sheet travel speed collected by the sensors in real time. The main controller also has a process database to store attribute parameters for different types of sheet materials, including inherent physical parameters such as material type, thickness, elastic modulus, and Poisson's ratio. Based on the type of sheet material currently being straightened, the corresponding sheet attribute parameters are retrieved from the process database. The initial pressure setting sequence for the straightening rollers is an ordered set of pre-calibrated reference pressure values ​​for each straightening roller, specific to the current sheet material specifications. Each element in the sequence corresponds one-to-one with the arrangement order of the rollers in the straightening roller group.

[0046] The main controller standardizes the acquired inlet stress deviation matrix, current process parameters, and initial pressure setting sequence, and then inputs them into the pre-trained stress evolution prediction model according to the preset input format. The model performs feature extraction and nonlinear calculation on the input data based on the internal training mapping relationship, and finally outputs the predicted outlet stress matrix. This matrix is ​​a two-dimensional numerical matrix with the same dimension as the inlet stress deviation matrix. Each element corresponds to the predicted stress value at a specific two-dimensional position of the plate after passing through the straightening roller group, which intuitively reflects the outlet stress distribution state of the plate under the roller pressure setting.

[0047] The expression for the objective function is: ,in, To predict the value of the element in the i-th row and j-th column of the outlet stress matrix, T represents the target stress value of the plate. The smaller the sum of squared deviations, the closer the outlet stress of the plate is to the ideal target stress state. The optimization direction is to minimize the objective function value. The pressure adjustment sequence of the straightening roller group is set as the optimization variable. This sequence is a one-dimensional numerical sequence, where each element corresponds to the pressure adjustment increment / decrement of one roller in the straightening roller group. Positive values ​​indicate pressure increase, and negative values ​​indicate pressure decrease. The sequence order is consistent with the arrangement order of the straightening rollers. The optimization process involves iteratively adjusting the values ​​of each element in the sequence.

[0048] This embodiment integrates the current process parameters and the initial pressure setting sequence of the roller group, and collaboratively inputs the stress evolution prediction model to obtain the predicted outlet stress matrix. With minimizing the sum of squared deviations as the objective function and setting constraints, the optimal adjustment amount is solved through an iterative algorithm. This achieves coupled optimization of process parameters, roller pressure setting and stress evolution, ensuring that the optimization process fits the actual working conditions, improving the reliability and adaptability of the optimal solution, and ensuring that the outlet stress of the plate approaches the target value.

[0049] One possible implementation of this application involves obtaining the optimal pressure adjustment sequence through an iterative optimization algorithm based on an objective function and optimization variables, under constraints. This includes: Initialize the optimization variables as a zero vector; During the iteration process, the following steps are performed: The pressure adjustment sequence of the current iteration step is superimposed with the initial pressure setting sequence to generate the current target pressure setting sequence; Input the current target pressure setting sequence, inlet stress deviation matrix and current process parameters into the stress evolution prediction model to obtain the current predicted outlet stress matrix; Based on the current predicted outlet stress matrix and the target stress value, the objective function is called to calculate the current objective function value; Determine whether the current objective function value satisfies the preset convergence condition; If the conditions are met, the current pressure adjustment sequence is determined as the optimal pressure adjustment sequence and the iteration is terminated; If the conditions are not met, update the pressure adjustment sequence and continue to the next iteration.

[0050] In this embodiment, the objective function is used as the optimization guide and the constraints are used as the boundaries. The values ​​of the optimization variables (pressure adjustment sequence) are continuously adjusted through an iterative optimization algorithm. The values ​​are repeatedly substituted into the stress evolution prediction model to verify the prediction effect until the objective function value meets the preset convergence condition. At this time, the pressure adjustment sequence is the optimal solution.

[0051] Specifically, the main controller initiates iterative optimization calculations, first initializing the optimization variables (pressure adjustment sequence) as a zero vector, meaning the initial state does not adjust the reference pressure of the straightening roller group; after entering the iterative loop, it performs the following operations sequentially: element-wise superposition of the pressure adjustment sequence of the current iteration step with the initial pressure setting sequence generates the current pressure setting sequence of the straightening roller group; the current pressure setting sequence, the inlet stress deviation matrix, and the current process parameters are input again into the stress evolution prediction model to obtain the predicted outlet stress matrix for this iteration; the predicted outlet stress matrix for this iteration is substituted into the predefined objective function to calculate the current... The objective function value is compared with the preset convergence threshold, and it is also determined whether the number of iterations has reached the preset upper limit. If the current objective function value meets the convergence condition, or the number of iterations has reached the upper limit, the preset convergence condition is met, the iteration is terminated, and the current pressure adjustment sequence is determined as the optimal pressure adjustment sequence. If the convergence condition is not met, the elements of the pressure adjustment sequence are updated according to the gradient change of the objective function, such as along the direction of decreasing objective function value when using gradient descent, combined with the constraint conditions. The iteration returns to the first step of the current iteration and starts the next loop until the optimal solution is obtained.

[0052] This embodiment initializes the optimization variables as a zero vector, iteratively superimposes the adjustment amount and the initial pressure setting sequence, predicts the outlet stress, calculates the objective function value and judges the convergence. If the convergence is not satisfied, the variables are updated and the iteration continues, effectively avoiding local optima and ensuring that the pressure adjustment amount sequence obtained is optimal.

[0053] One possible implementation of this application embodiment defines constraints, including: Based on the sheet material travel speed, the pressure change rate constraint, the inter-roller pressure difference constraint, and the total load gradient constraint are dynamically determined. The pressure change rate constraint, the inter-roller pressure difference constraint, and the total load gradient constraint are combined into a set of constraints.

[0054] Specifically, the sheet material's travel speed is a key dynamic factor affecting straightening stability. The faster the speed, the shorter the dwell time of the sheet material at each straightening roller, requiring smoother roller pressure adjustments; otherwise, sheet material deformation, misalignment, or equipment impact damage can easily occur. The pressure change rate constraint refers to the upper limit of pressure adjustment amplitude per unit time for a single straightening roller (unit: MPa / s), used to avoid sudden roller pressure changes impacting the sheet material and equipment. The faster the sheet material travels, the smaller the pressure change rate should be. The inter-roller pressure difference constraint refers to the upper limit of the pressure difference between two adjacent straightening rollers (unit: MPa), used to prevent uneven force distribution on the roller group, leading to sheet material misalignment and edge wrinkling, especially suitable for the need to eliminate edge stress in new sheet materials. The faster the sheet material travels, the higher the risk of misalignment. The total load gradient constraint refers to the upper limit of the overall load variation amplitude of the straightening roller group over time (unit: kN / s), used to ensure the operational stability of the equipment's transmission and hydraulic systems, avoiding sudden changes in total load that could cause equipment failure. The faster the sheet material travels, the smoother the total load adjustment needs to be.

[0055] The correspondence between the board's travel speed and various constraint thresholds is pre-set based on the board's process requirements and production experience. The corresponding constraint thresholds are directly retrieved based on the current board travel speed to form constraint conditions. Specifically, for each element in the pressure adjustment sequence, the adjustment amount of its corresponding single straightening roll is limited to a ratio of its adjustment amount to the adjustment time (i.e., the pressure change rate) not exceeding a constraint threshold. The formula is |ΔPn / Δt|≤K1, where ΔPn is the pressure adjustment amount of the nth straightening roll, Δt is the adjustment time, and K1 is the pressure change rate threshold. For adjacent elements in the pressure adjustment sequence, the actual pressure difference after superimposing the initial pressure setting value (i.e., the inter-roller pressure difference) is limited to not exceeding a constraint threshold. The formula is |(ΔP0n+ΔPn)-(ΔP0(n+1)+ΔP(n+1))|≤K2, where ΔP0n is the initial reference pressure value of the nth straightening roll, and K2 is the inter-roller pressure difference threshold. The total load change rate (i.e., the total load gradient) after superimposing the pressure adjustments of all straightening rolls is limited to not exceeding a constraint threshold. The formula is |∑(ΔPn×S) / Δt|≤K3, where S is the force-bearing area of ​​the nth straightening roll, and K3 is the total load gradient threshold.

[0056] This embodiment dynamically determines and combines three types of constraints based on the sheet material's traveling speed: pressure change rate, inter-roller pressure difference, and total load gradient. This ensures that the constraints are adapted to the sheet material's traveling rhythm, preventing sudden changes in roll pressure that could lead to sheet material deformation, equipment impact, or deviation. It also takes into account the rationality of single-roller adjustments, the coordinated stability of roll groups, and the safety of equipment load-bearing capacity.

[0057] One possible implementation of this application embodiment involves obtaining an inlet stress distribution cloud map of the plate material, including: The system receives echo signals from a stress detection array located after the inlet tension roller group of the tension straightener. The stress detection array includes multi-channel electromagnetic ultrasonic transducers arranged along the width of the plate. Acoustic feature parameters are extracted from the echo signal, including transit time and center frequency offset. Based on acoustic characteristic parameters, the one-dimensional stress distribution at the corresponding width position of each channel is determined, and the plates are spliced ​​together along the width direction to form a transverse stress distribution line. The position encoder signal and the traveling speed of the plate are acquired. Based on the position encoder signal and the traveling speed of the plate, the acquisition timestamp and longitudinal position coordinates of each transverse stress distribution line are determined. Multiple transverse stress distribution lines collected in a time sequence are meshed and integrated in a two-dimensional plane according to the corresponding collection timestamps and longitudinal position coordinates to obtain an inlet stress distribution cloud map.

[0058] In this embodiment, a stress detection array is fixedly deployed on the plate transport path behind the tension roller group at the inlet of the bending straightener. This array includes multi-channel electromagnetic ultrasonic transducers arranged at equal intervals along the width of the plate. The number of channels is adapted to the maximum processing width of the plate, ensuring coverage of the entire width and edge areas of the plate. The transducers maintain a preset non-contact distance from the plate. When the plate passes through the detection area at a constant speed, the multi-channel electromagnetic ultrasonic transducers synchronously emit high-frequency electromagnetic ultrasonic signals to the plate. The signals propagate through the interior of the plate and are reflected at the stress interface to form echo signals. After receiving the echo signals, the transducers send them to the main controller in real time via the data transmission bus. The main controller opens the data receiving port and performs buffering and preliminary noise reduction processing on the echo signals.

[0059] The transit time and center frequency offset are core acoustic features that have a quantitative mapping relationship with stress values. The transit time is the time difference between the ultrasonic wave transmission and reception, and the center frequency offset is the offset of the echo signal's center frequency relative to the transmitted signal. The main controller calls a preset acoustic feature extraction algorithm to filter the buffered echo signal to remove signal noise caused by environmental electromagnetic interference and equipment vibration, restoring the original waveform of the echo signal. The transit time of the ultrasonic wave transmission and reception is calculated through time-domain analysis, and the center frequency of the echo signal is extracted through frequency-domain Fourier transform. The center frequency offset is obtained by comparing it with the center frequency of the transmitted signal.

[0060] Through preliminary process calibration, a quantitative calibration model is established for transit time, center frequency offset, and actual stress value of the board. Using this model, the acoustic characteristic parameters of each channel are converted into stress values ​​at the corresponding width position. Then, by splicing the channels in the width direction, the transverse stress distribution line of a single cross section can be obtained, which intuitively reflects the stress distribution state in the width direction at a certain longitudinal position of the board.

[0061] The main controller retrieves the pre-stored electromagnetic ultrasonic stress calibration model, substitutes the acoustic characteristic parameters of each channel into the model, calculates the single-point stress data at the corresponding plate width position, and performs linear interpolation and splicing on the single-point stress data according to the arrangement order of the transducers along the plate width direction to form a continuous transverse stress distribution line. Its horizontal axis is the plate width position coordinate, and the vertical axis is the stress value at the corresponding position.

[0062] The main controller synchronously acquires the position encoder signal and the sheet material's traveling speed. The position encoder is installed on the conveyor roller system and outputs a sheet material traveling displacement pulse signal. After synchronous calibration, a unique acquisition timestamp is assigned to each transverse stress distribution line. Taking the initial detection position of the stress detection array as the origin of the longitudinal coordinate system, and combining the position encoder displacement signal and the sheet material's traveling speed, the longitudinal position coordinates corresponding to each transverse stress distribution line are calculated. The longitudinal position coordinates take the initial detection position of the stress detection array as the origin of the longitudinal coordinate system, with the traveling direction of the sheet material as the positive direction. Finally, the main controller establishes a correlated dataset of transverse stress distribution lines, acquisition timestamps, and longitudinal position coordinates, and arranges the transverse stress distribution lines in an orderly manner according to the acquisition timestamps.

[0063] The main controller divides the detection area into a two-dimensional grid according to a preset grid precision. Horizontal nodes correspond to the width of the sheet metal, and vertical nodes correspond to the vertical coordinates. Multiple ordered horizontal stress distribution lines are retrieved, and stress data is mapped to corresponding grid nodes based on the vertical coordinates. Interpolation is used to ensure each grid cell corresponds to a unique stress value, forming a mapping relationship between two-dimensional grid cells and stress values. A cloud map generation algorithm is then invoked to visualize the stress values ​​according to a preset color gradient. Coordinate scales, stress color bars, and units are added to generate a stress distribution cloud map at the sheet metal inlet, visually presenting the overall stress distribution at the inlet.

[0064] This embodiment utilizes a multi-channel electromagnetic ultrasonic transducer to collect echo signals, extracts acoustic feature parameters and converts them into transverse stress distribution lines, combines position encoder signals and travel speed to determine spatiotemporal coordinates, and integrates them into a gridded inlet stress distribution cloud map, achieving non-contact, full-area, dynamic and accurate acquisition of inlet stress of the plate material, and can clearly capture the stress concentration area at the edge.

[0065] One possible implementation of this application embodiment is that each instruction in the target pressure setting sequence corresponds to a straightening roller to be controlled; based on the optimal pressure adjustment sequence, controlling the straightening roller group to adjust the pressure includes: Based on the sheet material's travel speed and the mechanical position of each straightening roller in the straightening roller group, calculate the arrival time of each grid cell on the sheet material to each straightening roller. Each adjustment value in the optimal pressure adjustment sequence is linked to its corresponding arrival time; Based on the arrival time of the binding, a pressure adjustment command based on the corresponding adjustment amount is sent to the pressure actuator of the corresponding straightening roller.

[0066] Specifically, the optimal pressure adjustment sequence is a one-dimensional ordered dataset, where each element corresponds to the pressure increment or decrement of a straightening roller to be controlled, and corresponds one-to-one with the arrangement order of the rollers in the straightening roller group. The sheet material moves continuously at a constant speed, and it is necessary to establish the correspondence between the sheet material grid cells (corresponding to the two-dimensional grid nodes of the inlet stress distribution cloud map) and each straightening roller through spatiotemporal coordinate conversion to ensure that the roller pressure adjustment is accurately applied to the target sheet material area.

[0067] The main controller retrieves the collected sheet material traveling speed and the pre-stored mechanical position coordinates of each straightening roller in the straightening roller group. Using the location of the stress detection array as a reference, it sets longitudinal coordinates along the sheet material's traveling direction and records the center longitudinal coordinates of each straightening roller as its mechanical position coordinates. It extracts the longitudinal position coordinates of each grid cell in the inlet stress distribution cloud map and calculates the longitudinal distance between each grid cell and each straightening roller. Based on the uniform motion formula (time = distance / velocity), it calculates the accurate arrival time of each grid cell to the center position of the corresponding straightening roller.

[0068] The main controller clearly defines the correspondence between the optimal pressure adjustment sequence and the straightening rolls, i.e., the nth adjustment in the sequence corresponds to the nth straightening roll in the straightening roll group. The arrival times of all corresponding grid cells are extracted according to the straightening roll number, and the start time of the arrival times of all corresponding grid cells for the same straightening roll is taken as the trigger time for pressure adjustment of that roll. Each adjustment in the optimal pressure adjustment sequence is bound to the corresponding straightening roll's pressure adjustment trigger time, generating a command dataset with timestamped straightening roll number, optimal adjustment amount, and arrival time, ensuring that each pressure adjustment command contains a clearly defined execution target, adjustment range, and trigger time.

[0069] The main controller has a built-in timing module that synchronizes with the system time in real time and monitors the countdown to the pressure adjustment trigger time of each straightening roller. When the system time reaches the arrival time corresponding to a certain straightening roller, the main controller immediately extracts the optimal pressure adjustment amount for that straightening roller from the instruction dataset, combines it with the pre-stored initial pressure setpoint, calculates the target pressure value for that straightening roller, and generates the corresponding pressure adjustment command. The command is sent to the pressure actuator of the corresponding straightening roller, such as a hydraulic actuator or servo pressure controller, via the control bus. After receiving the command, the actuator adjusts the pressure of the straightening roller precisely to the target value through feedback adjustment using its built-in pressure sensor, and maintains that pressure until the adjustment command for the next section of the sheet material is triggered, thus completing the precise control of the roller pressure for the entire section of the sheet material.

[0070] This embodiment calculates the arrival time of the plate grid unit at each straightening roller, binds the optimal adjustment amount with the arrival time, and sends pressure commands on time to achieve precise temporal and spatial synchronization between roller pressure adjustment and plate movement. This ensures that the adjustment pressure is accurately applied to the target plate area, avoids uneven stress correction caused by timing misalignment, and improves the pertinence and effectiveness of roller group pressure control.

[0071] One possible implementation of this application embodiment includes: The vibration signals of the tension bending straightening machine are collected in real time, and vibration characteristics are extracted from the vibration signals; Based on vibration characteristics, an active vibration cancellation signal is generated; The active vibration cancellation signal is converted into a control command, which drives the actuator installed on the transmission part of the bending straightening machine to perform the action to suppress vibration.

[0072] Specifically, high-frequency vibration sensors are fixedly installed at the motor output end, roller coupling, and straightening roller bearing housing of the bending straightening machine. These sensors collect vibration signals from each part in real time and transmit them synchronously to the main controller via shielded transmission lines to avoid signal interference. The main controller then calls a vibration signal processing algorithm to first filter and de-trend the original vibration signal, eliminating environmental noise. Next, it uses Fourier transform to convert the time-domain signal into a frequency-domain signal, extracting vibration characteristic parameters, including the dominant frequency, amplitude, phase, and harmonic components.

[0073] The main controller uses the dominant vibration frequency, amplitude, and phase as core inputs. Following the principle of equal amplitude and opposite phase (180° out of phase), it generates an active vibration cancellation signal that complements the characteristics of the original vibration signal. For complex vibrations with multiple superimposed frequencies, the algorithm generates corresponding cancellation sub-signals for each harmonic component, which are then synthesized to obtain a composite cancellation signal. Simultaneously, it monitors changes in vibration characteristic parameters in real time and dynamically adjusts the amplitude and phase of the cancellation signal to ensure real-time adaptation between the cancellation signal and the original vibration signal, avoiding vibration suppression lag.

[0074] The main controller converts the generated active vibration cancellation signal into analog control commands adapted to the actuators via a digital-to-analog converter module. The actuators are installed at adjacent fixed structures at each vibration acquisition point and flexibly connected to the transmission components. Based on real-time changes in vibration characteristics, the main controller sends control commands to the corresponding actuators via a control bus. Upon receiving the commands, the actuators quickly respond and output a mechanical force opposite to the original vibration, thus canceling the vibration of the transmission components through force interference.

[0075] This embodiment collects equipment vibration signals and extracts features, generates dynamically adapted active vibration cancellation signals according to the principle of equal amplitude and opposite phase, converts them into control commands to drive the actuator to perform closed-loop suppression, effectively cancels the interference of vibration of the transmission part on the rolling accuracy, avoids stress elimination deviation and plate processing defects caused by vibration, and protects the transmission components of the equipment, improving the stability and service life of the equipment.

[0076] This application provides a control system for a tension bending straightening machine, such as... Figure 2 As shown, system 200 includes a main controller 201 and a tension bending straightener 202. The tension bending straightener 202 includes a straightening roller group and a stress detection array. The stress detection array is used to scan the sheet material entering the tension bending straightener and acquire echo signals, and send the echo signals to the main controller. The straightening roller group is used to receive and execute the target pressure setting sequence sent by the main controller to eliminate residual stress in the sheet material.

[0077] This application provides a main controller in its embodiments, such as... Figure 3 As shown, Figure 3 The main controller 201 shown includes a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, for example, via a bus 302. Optionally, the main controller 201 may also include a transceiver 304. It should be noted that in practical applications, the transceiver 304 is not limited to one, and the structure of this main controller 201 does not constitute a limitation on the embodiments of this application.

[0078] Processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 301 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0079] Bus 302 may include a pathway for transmitting information between the aforementioned components. Bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 302 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 3 The symbol is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0080] The memory 303 may be a ROM (Read Only Memory) or other type of static storage device capable of storing static information and instructions, RAM (Random Access Memory) or other type of dynamic storage device capable of storing information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0081] The memory 303 is used to store the application code for executing the scheme of this application, and the processor 301 controls its execution. The processor 301 is used to execute the application code stored in the memory 303 to implement the content shown in the aforementioned embodiment of the control method for the tension straightening machine.

[0082] Figure 3 The main controller shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0083] This application provides a computer-readable storage medium storing a computer program that, when run on a computer, enables the computer to execute the contents shown in the aforementioned embodiment of the control method for a tension straightening machine.

[0084] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0085] This application provides a computer program product, including a computer program that, when executed by a processor, implements the content shown in the aforementioned embodiment of the control method for a tension straightening machine.

[0086] The above are only some embodiments of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A control method for a tension straightening machine, characterized in that, A control system for a tension bending straightening machine, the system comprising a main controller and a tension bending straightening machine, wherein the method is executed by the main controller, the method comprising: Obtain the inlet stress distribution cloud map of the plate and convert the inlet stress distribution cloud map into an inlet stress matrix; Obtain the target stress value of the plate, and calculate the inlet stress deviation matrix based on the inlet stress matrix and the target stress value; Using the inlet stress deviation matrix as the model input and the pressure adjustment sequence of the straightening roller group as the optimization variable, the pre-trained stress evolution prediction model is called to perform rolling optimization and solve for the optimal pressure adjustment sequence. Based on the optimal pressure adjustment sequence, the pressure of the straightening roller group is controlled to be adjusted.

2. The control method for the tension bending straightening machine according to claim 1, characterized in that, The process involves using the inlet stress deviation matrix as the model input and the pressure adjustment sequence of the straightening roller group as the optimization variable, calling a pre-trained stress evolution prediction model for rolling optimization, and solving for the optimal pressure adjustment sequence, including: Obtain the current process parameters and the initial pressure setting sequence of the straightening roller group. The current process parameters include the actual value of the process tension, the plate travel speed, and the plate property parameters. The inlet stress deviation matrix, the current process parameters, and the initial pressure setting sequence are input into the stress evolution prediction model to obtain the predicted outlet stress matrix; Define the objective function as minimizing the sum of squared deviations between the predicted outlet stress matrix and the target stress value, use the pressure adjustment sequence as the optimization variable, and define the constraints. Based on the objective function and the optimization variables, and under the constraints, the optimal pressure adjustment sequence is obtained by solving the problem through an iterative optimization algorithm.

3. The control method for the tension bending straightening machine according to claim 2, characterized in that, The process of obtaining the optimal pressure adjustment sequence by solving an iterative optimization algorithm based on the objective function and the optimization variables, under the constraints of the conditions, includes: Initialize the optimization variables as a zero vector; During the iteration process, the following steps are performed: The pressure adjustment sequence of the current iteration step is superimposed with the initial pressure setting sequence to generate the current target pressure setting sequence; The current target pressure setting sequence, the inlet stress deviation matrix, and the current process parameters are input into the stress evolution prediction model to obtain the current predicted outlet stress matrix; Based on the current predicted outlet stress matrix and the target stress value, the objective function is invoked to calculate the current objective function value; Determine whether the current objective function value satisfies the preset convergence condition; If the conditions are met, the current pressure adjustment sequence is determined as the optimal pressure adjustment sequence and the iteration is terminated. If the conditions are not met, update the pressure adjustment sequence and continue to the next iteration.

4. The control method for the tension bending straightening machine according to claim 2, characterized in that, The defined constraints include: Based on the plate travel speed, the pressure change rate constraint, the inter-roller pressure difference constraint, and the total load gradient constraint are dynamically determined. The pressure change rate constraint, the inter-roller pressure difference constraint, and the total load gradient constraint are combined into the constraint conditions.

5. The control method for the tension bending straightening machine according to claim 1, characterized in that, The process of obtaining the inlet stress distribution cloud map of the plate includes: The system receives echo signals from a stress detection array located after the inlet tension roller group of the bending straightener, the stress detection array comprising multi-channel electromagnetic ultrasonic transducers arranged along the width direction of the plate. Acoustic feature parameters are extracted from the echo signal, including transit time and center frequency offset; Based on the acoustic characteristic parameters, the one-dimensional stress distribution at the width position of each channel is determined, and the plates are spliced ​​together according to the width direction of the plate to form a transverse stress distribution line; The position encoder signal and the traveling speed of the plate are acquired. Based on the position encoder signal and the traveling speed of the plate, the acquisition timestamp and longitudinal position coordinates of each transverse stress distribution line are determined. Multiple transverse stress distribution lines collected in a time sequence are meshed and integrated in a two-dimensional plane according to the corresponding collection timestamps and longitudinal position coordinates to obtain the inlet stress distribution cloud map.

6. The control method for the tension bending straightening machine according to claim 1, characterized in that, Each instruction in the target pressure setting sequence corresponds to a straightening roller to be controlled; the step of controlling the straightening roller group to adjust the pressure based on the optimal pressure adjustment sequence includes: Based on the traveling speed of the sheet material and the mechanical position of each straightening roller in the straightening roller group, calculate the arrival time of each grid unit on the sheet material to each straightening roller. Each adjustment value in the optimal pressure adjustment sequence is associated with its corresponding arrival time; Based on the arrival time of the binding, a pressure adjustment command based on the corresponding adjustment amount is sent to the pressure actuator of the corresponding straightening roller.

7. The control method for the tension bending straightening machine according to claim 1, characterized in that, The method further includes: The vibration signals of the bending straightening machine are collected in real time, and vibration characteristics are extracted from the vibration signals; Based on the vibration characteristics, an active vibration cancellation signal is generated; The active vibration cancellation signal is converted into a control command, which drives the actuator installed in the transmission part of the bending straightening machine to perform the action to suppress vibration.

8. A control system for a tension bending straightening machine, characterized in that, It includes a main controller and a tension bending straightener, wherein the tension bending straightener includes a straightening roller group and a stress detection array; The stress detection array is used to scan the plate entering the tension straightening machine and acquire echo signals, and send the echo signals to the main controller; The main controller is used to execute the control method of the tension straightening machine according to any one of claims 1-7; The straightening roller group is used to receive and execute the target pressure setting sequence sent by the main controller to eliminate the residual stress of the plate.

9. The control system of the tension bending straightening machine according to claim 8, characterized in that, The main controller includes: At least one processor; Memory; At least one application, wherein the at least one application is stored in memory and configured to be executed by at least one processor, said at least one application being configured to: perform the control method of the tension straightening machine according to any one of claims 1-7.

Images