Stretch bending equipment operation control method and system based on big data analysis

Abstract

The invention relates to the technical field of equipment operation control, in particular to a stretch bending equipment operation control method and system based on big data analysis, and the method comprises the steps: S1, collecting profile material data and profile section data, and collecting contact surface contour data and contact surface pressure data of a profile and a mold; s2, the stretch bending performance of the profile and the distortion degree of the section of the profile in the stretch bending forming process are evaluated through the profile material data and the profile section data; s3, the contour difference degree of the profile and the mold and the contact surface pressure distribution uniformity in the stretch bending forming process are evaluated through the contact surface contour data and the contact surface pressure data; and S4, constructing a stretch bending equipment operation control model, and inputting the evaluation results of the step S2 and the step S3 into the stretch bending equipment operation control model to obtain optimal operation control parameters of the stretch bending equipment. According to the method, the characteristics of the profile and the characteristics of the die are quantitatively evaluated, so that the stretch bending process is precisely regulated and controlled, and the forming precision and forming quality of the profile are improved.

Description

Technical Field

[0001] The present application relates to the technical field of equipment operation control, and in particular to a method and system for controlling the operation of a stretch bending equipment based on big data analysis. Background Art

[0002] With the rapid development of industries such as aerospace, automobiles and high-speed trains, there is a clear trend towards large-scale and integrated parts, and the use of large-profile parts is increasing. The process methods for preparing hollow curved profiles include press bending, roll bending, winding and stretch bending. Among them, stretch bending has significant advantages such as low process cost and simple operation and is widely used.

[0003] Profile bending refers to the bending process in which the profile is pre-stretched to the material yield limit, loaded and bent while maintaining a certain axial tension, and pressed into the mold to form. In the process of stretch bending, according to the different loading sequences of axial tension and bending moment, the loading methods can be divided into the following three types: stretching first and then bending (PM), bending first and then stretching (MP), and stretching first, bending and then stretching (PMP).

[0004] During the profile bending process, the operating parameters of the bending equipment, including the stretching speed, pre-stretching amount and supplementary stretching amount, have a great influence on the profile forming quality. Among them, a reasonable stretching speed can ensure that the profile is evenly stressed during the deformation process, and avoid surface defects or internal stress concentration caused by too fast or too slow speed. The setting of the pre-stretching amount is directly related to the deformation of the profile in the initial stage. Too high or too low will lead to reduced profile forming accuracy, and even cause breakage or inability to accurately match the mold contour. The adjustment of the supplementary stretching amount helps to correct the local uneven deformation that may occur during the forming process, and ensure that the final profile geometry is more closely aligned with the mold contour. The existing bending equipment operation control method usually relies on experience when setting the bending equipment operating parameters such as the stretching speed, pre-stretching amount and supplementary stretching amount, and fails to fully consider the impact of changes in different profile materials, cross-sectional shapes and mold contours on the profile forming quality, resulting in low profile forming accuracy. Summary of the invention

[0005] In order to overcome the defects and shortcomings of the prior art, the present application provides a stretch-bending equipment operation control method and system based on big data analysis, which realizes precise control of the stretch-bending process by quantitatively evaluating the profile characteristics and mold characteristics, thereby improving the profile forming accuracy and forming quality.

[0006] In order to achieve the above objectives, this application adopts the following technical solutions: In a first aspect, the present application provides a method for controlling the operation of a stretch bending device based on big data analysis, comprising the following steps: S1: Collect profile material data and profile cross-section data, and collect profile data and contact surface pressure data between the profile and the mold; S2: Evaluate the bending performance of the profile and the degree of cross-section distortion of the profile during the bending process through the profile material data and profile cross-section data; S3: Evaluate the difference between the profile and the die and the uniformity of the contact surface pressure distribution during the stretch bending process through the contact surface profile data and contact surface pressure data; S4: constructing a bending equipment operation control model, and inputting the evaluation results of step S2 and step S3 into the bending equipment operation control model to obtain the optimal operation control parameters of the bending equipment.

[0007] Optionally, evaluating the bending performance of the profile in step S2 includes: S21: Obtaining profile material data and profile cross-section data, where the profile material data includes profile material thickness, material density, and material hardness; S22: Calculate the profile section symmetry index based on the profile section data; S23: Calculate the profile material distribution uniformity index based on the profile material data. The profile material distribution uniformity index calculation formula is: ; In the formula Indicates The first material monitoring point measured Type of material parameter value, Indicates The average value of material parameters of each type, Indicates the number of profile material monitoring points, Indicates the type number of material parameters, Indicates the profile material distribution uniformity index; S24: The profile bending performance index is calculated by the profile cross-section symmetry index and the profile material distribution uniformity index. The profile bending performance index is used to evaluate the profile bending performance. The calculation formula of the profile bending performance index is: ; In the formula Represents the cross-section symmetry index of the profile, Indicates the profile material distribution uniformity index, represents the adjustment factor, Indicates the profile bending performance index.

[0008] Optionally, the step S22 includes: S221: Obtaining the initial profile cross-section image in the profile cross-section data, preprocessing the initial profile cross-section image and calculating the centroid coordinates of the initial profile cross-section ,Preprocessing includes grayscale and binarization; S222: The upper and lower symmetry deviations and the left and right symmetry deviations of the profile section are calculated by the centroid coordinates, and then the profile section symmetry index is calculated. The calculation formula of the profile section symmetry index is: ; In the formula Indicates the upper and lower symmetry deviation of the profile section. Indicates the profile cross-section image The pixel value at position, represents the ordinate of the centroid coordinate, Indicates the left-right symmetry deviation of the profile section. represents the abscissa of the centroid coordinates, The profile cross-section image is The number of pixels on the axis, The profile cross-section image is The number of pixels on the axis, Represents the symmetry index of the profile section.

[0009] Optionally, evaluating the degree of cross-sectional distortion of the profile in step S2 includes: S25: Obtaining profile cross-section point cloud data from the profile cross-section data, where the profile cross-section point cloud data includes profile standard cross-section point cloud data and profile bending cross-section point cloud data during the bending forming process; S26: Encode the profile standard section point cloud data and the profile bending section point cloud data into ordered contour point sets respectively to obtain a first profile section contour point set and the second profile cross-section contour point set ; S27: Through the first profile section contour point set and the second profile cross-section contour point set Calculate from arrive One-way Hausdorff distance and from arrive One-way Hausdorff distance , and then calculate the profile section distortion index, which is used to evaluate the degree of profile section distortion during the stretch bending process. The profile section distortion index calculation formula is: ; In the formula Represents the point set from the first profile section contour To the second profile section contour point set The one-way Hausdorff distance of Represents the set of points from the second profile section contour To the first profile section contour point set The one-way Hausdorff distance of represents the maximum value function, represents the maximum value of Hausdorff distance, Represents the profile section distortion index.

[0010] Optionally, evaluating the degree of contour difference in step S3 includes: S31: Acquire contact surface contour data, where the contact surface contour data includes an initial profile contact surface contour image and a mold contact surface contour image; S32: using an edge detection algorithm to respectively extract pixels of each point of the contact surface contour in the initial profile contact surface contour image and the mold contact surface contour image, to obtain a first contact surface contour pixel set and a second contact surface contour pixel set; S33: Calculate the minimum Euclidean distance between each pixel in the first contact surface contour pixel set and the pixel in the second contact surface contour pixel set and calculate the contour difference index between the profile and the mold. The contour difference index is used to evaluate the degree of difference between the profile and the mold. The calculation formula of the contour difference index is: ; In the formula Represents the first contact surface contour pixel set The Euclidean distance between a pixel and the nearest neighbor pixel in the second contact surface contour pixel set, represents the number of pixels in the first contact surface contour pixel set, represents the maximum value of the Euclidean distance between the pixels in the first contact surface contour pixel set and the pixels in the second contact surface contour pixel set, Represents the contour difference index.

[0011] Optionally, evaluating the uniformity of the pressure distribution on the contact surface in step S3 includes: S34: Acquiring contact surface pressure data; S35: The contact surface pressure distribution uniformity index during the stretch bending forming process is calculated using the contact surface pressure data. The contact surface pressure distribution uniformity index is used to evaluate the contact surface pressure distribution uniformity during the stretch bending forming process. The calculation formula for the contact surface pressure distribution uniformity index is: ; In the formula Indicates The contact surface pressure monitored by a pressure sensor, Indicates the maximum contact surface pressure detected by the pressure sensor. Indicates the minimum contact surface pressure detected by the pressure sensor. Indicates the number of pressure sensors, Represents the uniformity index of contact surface pressure distribution.

[0012] Optionally, the bending equipment operation control model in step S4 is constructed based on a BP neural network, and the bending equipment operation control model comprises an input layer with 4 nodes, a hidden layer with 7 nodes, and an output layer with 3 nodes. , Profile section distortion index , Contour Difference Index , contact surface pressure distribution uniformity index The optimal operating control parameters of the bending equipment are input as the input layer, and the optimal operating control parameters of the bending equipment include the bending speed, the pre-stretching force and the supplementary stretching force.

[0013] It should be noted that the adjustment factor is obtained as follows: 5000 sets of profile material data and profile cross-section data are collected to distinguish whether the profile bending performance meets the production requirements, the profile material data and profile cross-section data are substituted into the calculation formula of the profile bending performance index for calculation, the calculated profile bending performance index and the distinction result are simultaneously imported into the fitting software, and the optimal adjustment factor that meets the distinction accuracy of the distinction result is output.

[0014] In the second aspect, the present application provides a stretch bending equipment operation control system based on big data analysis, including: A data acquisition module is used to collect profile material data and profile cross-section data, and to collect profile data and contact surface pressure data between the profile and the mold; The first evaluation module is used to evaluate the bending performance of the profile and the degree of cross-section distortion of the profile during the bending forming process through the profile material data and the profile cross-section data; The second evaluation module is used to evaluate the difference between the profile of the profile and the die and the uniformity of the contact surface pressure distribution during the stretch bending forming process through the contact surface profile data and the contact surface pressure data; The control model building module is used to build a bending equipment operation control model, and input the evaluation results of the first evaluation module and the second evaluation module into the bending equipment operation control model to obtain the optimal operation control parameters of the bending equipment.

[0015] In a third aspect, the present application provides an electronic device, comprising: a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes a stretch bending equipment operation control method based on big data analysis by calling the computer program stored in the memory.

[0016] In a fourth aspect, the present application provides a computer-readable storage medium storing instructions, which, when executed on a computer, enables the computer to execute a method for controlling the operation of a stretch bending equipment based on big data analysis.

[0017] Compared with the prior art, this application has the following advantages and beneficial effects: The present application provides comprehensive basic information for the operation control of the stretch-bending equipment by collecting profile material data, profile cross-section data, and the contact surface contour and pressure data between the profile and the die. The profile stretch-bending performance is evaluated by analyzing the profile cross-section symmetry and the uniformity of profile material distribution, and the degree of profile cross-section distortion during the stretch-bending forming process is evaluated based on the profile cross-section data. At the same time, the degree of contour difference between the profile and the die and the uniformity of contact surface pressure distribution are evaluated based on the contact surface contour and pressure data. Finally, an operation control model for the stretch-bending equipment is constructed, and the evaluation results are input into the model to obtain the optimal operation control parameters of the stretch-bending equipment, thereby achieving precise control of the stretch-bending process, effectively optimizing the equipment operation parameters, and thus improving the forming accuracy and forming quality of the profile. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings: Figure 1 It is a schematic diagram of the overall process of the stretch bending equipment operation control method based on big data analysis provided in an embodiment of the present application; Figure 2 This is a schematic diagram of a mold-fixed profile bending process provided in an embodiment of the present application; Figure 3 It is a schematic diagram of the structure of the operation control model of the stretch bending equipment provided in the embodiment of the present application; Figure 4 It is a structural schematic diagram of a stretch bending equipment operation control system based on big data analysis provided in an embodiment of the present application; Figure 5 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0019] The technical solution of the present application is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical solution of the present application, rather than limitations on the technical solution of the present application. In the absence of conflict, the embodiments of the present application and the technical features in the embodiments can be combined with each other.

[0020] See also Figure 1 , Figure 1 It is a schematic diagram of the overall process of the stretch bending equipment operation control method based on big data analysis provided in the embodiment of the present application, which specifically includes the following steps: S1: Collect profile material data and profile cross-section data, and collect profile data and contact surface pressure data between the profile and the mold.

[0021] S2: Evaluate the bending performance of the profile and the degree of cross-section distortion of the profile during the bending process through the profile material data and profile cross-section data; The cross-sectional symmetry of the profile will directly affect the uniform deformation ability of the profile during the bending process. If the cross-section is asymmetrical, it may lead to uneven bending stress, thus affecting the final forming quality. At the same time, the uniformity of the profile material distribution determines the difference in material response of different parts of the profile during the bending process. If the material distribution is uneven, it may cause local over-stretching or insufficient deformation of the profile. Therefore, accurate evaluation of the cross-sectional symmetry and material distribution uniformity of the profile is helpful to determine the optimal bending speed, pre-stretching force, supplementary stretching force and other equipment operating parameters to ensure that the profile is uniformly stressed during the entire bending process, thereby improving the forming accuracy and optimizing the forming quality. Evaluate the bending performance of the profile, including: S21: Obtaining profile material data and profile cross-section data, where the profile material data includes profile material thickness, material density, and material hardness; S22: Calculate the profile section symmetry index based on the profile section data; S23: Calculate the profile material distribution uniformity index based on the profile material data. The profile material distribution uniformity index calculation formula is: ; In the formula Indicates The first material monitoring point measured Type of material parameter value, Indicates The average value of material parameters of each type, Indicates the number of profile material monitoring points, Indicates the type number of material parameters, Indicates the profile material distribution uniformity index; S24: The profile bending performance index is calculated by the profile cross-section symmetry index and the profile material distribution uniformity index. The profile bending performance index is used to evaluate the profile bending performance. The calculation formula of the profile bending performance index is: ; In the formula Represents the cross-section symmetry index of the profile, Indicates the profile material distribution uniformity index, represents the adjustment factor, Indicates the bending performance index of profiles; Asymmetric cross-section profiles refer to profiles whose cross-sectional shapes are asymmetric within the cross section. During the bending process of this type of profile, the stress inside the cross section will produce an additional bending moment, causing the profile to bend lateral, which in turn affects the forming accuracy. Profiles with high symmetry can ensure that the stress distribution of the profile is uniform during bending, thereby reducing defects such as distortion, deformation and cracks caused by uneven stress. In addition, profiles with high symmetry are easier to achieve precise control during the bending process, which helps to improve the bending efficiency of the profile. The calculation of the profile cross-section symmetry index includes: S221: Obtaining the initial profile cross-section image in the profile cross-section data, preprocessing the initial profile cross-section image and calculating the centroid coordinates of the initial profile cross-section ,The preprocessing includes gray scale and binarization. The profile cross section image is converted into a gray scale image by gray scale ,and then the image is converted into a black and white image by binarization. ,The pixel value of the profile cross section is 255 and the pixel value of the background is 0; S222: The upper and lower symmetry deviations and the left and right symmetry deviations of the profile section are calculated by the centroid coordinates, and then the profile section symmetry index is calculated. The calculation formula of the profile section symmetry index is: ; In the formula Indicates the upper and lower symmetry deviation of the profile section. For each pixel The vertical symmetry deviation is obtained by calculating the difference between the pixel value of the pixel and the pixel at the vertical symmetric position. Indicates the profile cross-section image The pixel value at position, represents the ordinate of the centroid coordinate, Indicates the left-right symmetry deviation of the profile section. The left-right symmetry deviation is used to measure whether the left and right parts of the profile section image are symmetrical. represents the abscissa of the centroid coordinates, The profile cross-section image is The number of pixels on the axis, The profile cross-section image is The number of pixels on the axis, Indicates the symmetry index of the profile section; During the bending process, the cross section of the profile will inevitably deform, which is called cross-sectional distortion. This phenomenon often occurs in hollow thin-walled profiles or bent profiles with large forming curvature. The main reason for cross-sectional distortion is that during the bending process, the profile is subjected to different longitudinal, tangential and radial forces. Different tensile and compressive forces produce different compressive strains and tensile strains, which are manifested macroscopically as changes in geometric shapes such as longitudinal contraction, radial thickening, axial elongation or compression, that is, cross-sectional distortion of each surface. The degree of cross-sectional distortion of the profile is evaluated, including: S25: Obtaining profile cross-section point cloud data from the profile cross-section data, where the profile cross-section point cloud data includes profile standard cross-section point cloud data and profile bending cross-section point cloud data during the bending forming process; S26: Encode the profile standard section point cloud data and the profile bending section point cloud data into ordered contour point sets respectively to obtain a first profile section contour point set and the second profile cross-section contour point set ; S27: Through the first profile section contour point set and the second profile cross-section contour point set Calculate from arrive One-way Hausdorff distance and from arrive One-way Hausdorff distance , and then calculate the profile section distortion index, which is used to evaluate the degree of profile section distortion during the stretch bending process. The profile section distortion index calculation formula is: ; In the formula Represents the point set from the first profile section contour To the second profile section contour point set The one-way Hausdorff distance of Represents the point set from the second profile section contour To the first profile section contour point set The one-way Hausdorff distance of represents the maximum value function, represents the maximum value of Hausdorff distance, Used to normalize the final calculation results, Represents the profile section distortion index, if The closer the value is to 0, the smaller the cross-sectional deformation of the profile is and the higher the forming accuracy is. The closer the value is to 1, the greater the cross-sectional deformation of the profile is, and the more significant the distortion is.

[0022] S3: Evaluate the difference between the profile and the die and the uniformity of the contact surface pressure distribution during the stretch bending process through the contact surface profile data and contact surface pressure data; Accurate assessment of profile differences helps adjust the tensile force, bending speed and die positioning of the bending equipment to ensure that the profile fits tightly with the die during the bending process, reduce springback and forming errors, thereby improving the dimensional accuracy of the product, avoiding over-stretching and profile damage, and assessing the degree of profile differences, including: S31: Acquire contact surface contour data, where the contact surface contour data includes an initial profile contact surface contour image and a mold contact surface contour image; S32: using an edge detection algorithm to respectively extract pixels of each point of the contact surface contour in the initial profile contact surface contour image and the mold contact surface contour image, to obtain a first contact surface contour pixel set and a second contact surface contour pixel set, wherein the edge detection algorithm may use a Canny edge detection algorithm, which can capture fine edges and has a strong ability to suppress noise; S33: Calculate the minimum Euclidean distance between each pixel in the first contact surface contour pixel set and the pixel in the second contact surface contour pixel set and calculate the contour difference index between the profile and the mold. The contour difference index is used to evaluate the degree of difference between the profile and the mold. The calculation formula of the contour difference index is: ; In the formula Represents the first contact surface contour pixel set The Euclidean distance between a pixel and the nearest neighbor pixel in the second contact surface contour pixel set, To quantify the The distance difference between the profile contact surface contour pixel and the closest pixel in the mold contact surface contour, represents the number of pixels in the first contact surface contour pixel set, represents the maximum value of the Euclidean distance between the pixels in the first contact surface contour pixel set and the pixels in the second contact surface contour pixel set, Used to normalize the contour difference index calculation results to make the difference metrics more comparable. represents the contour difference index; See also Figure 2 , Figure 2 : is a schematic diagram of a mold-fixed profile bending process provided in an embodiment of the present application. A fixed mold is used to tighten the profile through rotatable clamps on both sides and rotate it around the bending mold. During this process, the profile will gradually fit completely with the mold, thereby achieving the goal of bending. During the profile bending process, the uniform pressure distribution on the contact surface between the profile and the mold can ensure that the profile is uniformly stressed during the bending process, avoiding local excessive deformation or stress concentration, thereby improving the forming accuracy and mechanical properties of the profile, and at the same time helping to reduce the rebound after bending, ensuring the consistency of the profile size, preventing surface scratches and internal cracks, and improving the final profile forming quality. The uniformity of the contact surface pressure distribution is evaluated, including: S34: Acquiring contact surface pressure data; S35: The contact surface pressure distribution uniformity index during the stretch bending forming process is calculated using the contact surface pressure data. The contact surface pressure distribution uniformity index is used to evaluate the contact surface pressure distribution uniformity during the stretch bending forming process. The calculation formula for the contact surface pressure distribution uniformity index is: ; In the formula Indicates The contact surface pressure monitored by a pressure sensor, Indicates the maximum contact surface pressure detected by the pressure sensor. Indicates the minimum contact surface pressure detected by the pressure sensor. Indicates the number of pressure sensors, Represents the uniformity index of contact surface pressure distribution.

[0023] S4: constructing a bending equipment operation control model, and inputting the evaluation results of step S2 and step S3 into the bending equipment operation control model to obtain optimal operation control parameters of the bending equipment; See also Figure 3 , Figure 3 The structure diagram of the bending equipment operation control model provided in the embodiment of the present application is a schematic diagram of the bending equipment operation control model. The bending equipment operation control model is constructed based on the BP neural network. The bending equipment operation control model includes an input layer with 4 nodes, a hidden layer with 7 nodes, and an output layer with 3 nodes. , Profile section distortion index , Contour Difference Index , contact surface pressure distribution uniformity index As the input layer input, the optimal operation control parameters of the bending equipment are output as the output layer output. The optimal operation control parameters of the bending equipment include bending speed, pre-stretching force and supplementary stretching force. The training steps of the bending equipment operation control model are as follows: (1) Initialize the network, set the number of input layer nodes to 4, the corresponding input variables are the profile bending performance index, profile cross-section distortion index, contour difference index, and contact surface pressure distribution uniformity index, set the number of hidden layer nodes to 7, which is used to calculate the weighted sum of the input variables of the input layer and activate through the activation function, set the number of output layer nodes to 3, corresponding to the bending speed, pre-stretching force, and supplementary stretching force, respectively, and at the same time, initialize the weights and biases for the connections from the input layer to the hidden layer and from the hidden layer to the output layer. The weights and biases are the parameters to be optimized in the network; (2) Calculate the hidden layer output by taking the weighted sum of the input variables of the input layer and adding the bias term, and then calculate the hidden layer output through the activation function. The output of each node in the hidden layer is: ; In the formula represents the hidden layer The output of the node, , Represents the input layer nodes to the hidden layer The weight of the node, Represents the input layer The input variables of the nodes, represents the hidden layer The bias of the node, Represents the Sigmoid activation function of the hidden layer; (3) Calculate the output layer output. The output of the hidden layer is passed to the output layer. Similarly, the output of each output node is the weighted sum of the hidden layer output plus the bias, and then processed by the output layer activation function to obtain the output layer output. The output layer activation function is the Softmax activation function. (4) Construct a loss function. The loss function is defined as minimizing the profile section distortion index and maximizing the contact surface pressure distribution uniformity index. The calculation formula of the loss function is as follows: ; In the formula Represents the profile section distortion index, Represents the contact surface pressure distribution uniformity index, represents the profile section distortion weight, Indicates the uniformity weight of the contact surface pressure distribution. , represents the loss value; (5) Update weights and biases, use the back propagation algorithm to calculate the gradient of the loss function for each weight and bias in the network. The gradient is the partial derivative of the loss function with respect to each weight and bias, and then use the Adam optimization algorithm to update the weights and biases; (6) Determine the training stop condition: when the loss value of the loss function is lower than the threshold or changes very little after multiple iterations, indicating that the network has converged, the training is stopped. Otherwise, return to step (2) and continue iterative training.

[0024] See also Figure 4 , Figure 4 : is a structural diagram of a bending equipment operation control system based on big data analysis provided in an embodiment of the present application. This embodiment provides a bending equipment operation control system based on big data analysis, including: The data acquisition module 210 is used to acquire profile material data and profile cross-section data, and acquire profile data and contact surface pressure data of the profile and the mold; A first evaluation module 220, for evaluating the bending performance of the profile and the degree of cross-sectional distortion of the profile during the bending forming process according to the profile material data and the profile cross-sectional data; A second evaluation module 230 is used to evaluate the difference between the profile of the profile and the die and the uniformity of the contact surface pressure distribution during the stretch bending forming process through the contact surface profile data and the contact surface pressure data; The control model building module 240 is used to build a bending equipment operation control model, and input the evaluation results of the first evaluation module and the second evaluation module into the bending equipment operation control model to obtain the optimal operation control parameters of the bending equipment.

[0025] In the embodiment of the present application, the first evaluation module 220 is used to evaluate the bending performance of the profile and the degree of cross-sectional distortion of the profile during the bending forming process through the profile material data and the profile cross-sectional data, and the bending performance of the profile is evaluated, including: Obtaining profile material data and profile cross-section data, where the profile material data includes profile material thickness, material density and material hardness; Calculate the profile section symmetry index through the profile section data; The profile material distribution uniformity index is calculated through the profile material data. The profile material distribution uniformity index calculation formula is: ; In the formula Indicates The first material monitoring point measured Type of material parameter value, Indicates The average value of material parameters of each type, Indicates the number of profile material monitoring points, Indicates the type number of material parameters, Indicates the profile material distribution uniformity index; The profile bending performance index is calculated by the profile cross-section symmetry index and the profile material distribution uniformity index. The profile bending performance index is used to evaluate the profile bending performance. The calculation formula of the profile bending performance index is: ; In the formula Represents the cross-section symmetry index of the profile, Indicates the profile material distribution uniformity index, represents the adjustment factor, Indicates the bending performance index of profiles; Calculate the profile cross-section symmetry index, including: Obtain the initial profile cross-section image from the profile cross-section data, pre-process the initial profile cross-section image and calculate the centroid coordinates of the initial profile cross-section ,Preprocessing includes grayscale and binarization; The upper and lower symmetry deviations and left and right symmetry deviations of the profile section are calculated by the centroid coordinates, and then the profile section symmetry index is calculated. The calculation formula of the profile section symmetry index is: ; In the formula Indicates the upper and lower symmetry deviation of the profile section. Indicates the profile cross-section image The pixel value at position, represents the ordinate of the centroid coordinate, Indicates the left-right symmetry deviation of the profile section. represents the abscissa of the centroid coordinates, The profile cross-section image is The number of pixels on the axis, The profile cross-section image is The number of pixels on the axis, Indicates the symmetry index of the profile section; Evaluate the degree of cross-section distortion of profiles, including: Obtaining profile cross-section point cloud data from the profile cross-section data, where the profile cross-section point cloud data includes profile standard cross-section point cloud data and profile bending cross-section point cloud data during the bending forming process; Encode the standard section point cloud data of the profile and the bending section point cloud data of the profile into ordered contour point sets respectively to obtain the first profile section contour point set and the second profile cross-section contour point set ; Through the first profile section contour point set and the second profile cross-section contour point set Calculate from arrive One-way Hausdorff distance and from arrive One-way Hausdorff distance , and then calculate the profile section distortion index, which is used to evaluate the degree of profile section distortion during the stretch bending process. The profile section distortion index calculation formula is: ; In the formula Represents the point set from the first profile section contour To the second profile section contour point set The one-way Hausdorff distance of Represents the point set from the second profile section contour To the first profile section contour point set The one-way Hausdorff distance of represents the maximum value function, represents the maximum value of Hausdorff distance, Represents the profile section distortion index.

[0026] In the embodiment of the present application, the second evaluation module 230 is used to evaluate the degree of difference between the profile and the die and the uniformity of the contact surface pressure distribution during the stretch bending forming process through the contact surface profile data and the contact surface pressure data, and the degree of profile difference is evaluated, including: Acquiring contact surface contour data, the contact surface contour data comprising an initial profile contact surface contour image and a mold contact surface contour image; Using an edge detection algorithm, pixels of each point of the contact surface contour in the initial profile contact surface contour image and the mold contact surface contour image are respectively extracted to obtain a first contact surface contour pixel set and a second contact surface contour pixel set; The minimum Euclidean distance between each pixel in the first contact surface contour pixel set and the pixel in the second contact surface contour pixel set is calculated, and the contour difference index between the profile and the mold is calculated. The contour difference index is used to evaluate the degree of difference between the profile and the mold. The calculation formula of the contour difference index is: ; In the formula Represents the first contact surface contour pixel set The Euclidean distance between a pixel and the nearest neighbor pixel in the second contact surface contour pixel set, represents the number of pixels in the first contact surface contour pixel set, represents the maximum value of the Euclidean distance between the pixels in the first contact surface contour pixel set and the pixels in the second contact surface contour pixel set, represents the contour difference index; Evaluate the uniformity of contact surface pressure distribution, including: Obtain contact surface pressure data; The contact surface pressure distribution uniformity index during the stretch bending process is calculated using the contact surface pressure data. The contact surface pressure distribution uniformity index is used to evaluate the contact surface pressure distribution uniformity during the stretch bending process. The calculation formula for the contact surface pressure distribution uniformity index is: ; In the formula Indicates The contact surface pressure monitored by a pressure sensor, Indicates the maximum contact surface pressure detected by the pressure sensor. Indicates the minimum contact surface pressure detected by the pressure sensor. Indicates the number of pressure sensors, Represents the uniformity index of contact surface pressure distribution.

[0027] In the embodiment of the present application, the control model construction module 240 is used to construct the bending equipment operation control model, and the evaluation results of the first evaluation module 220 and the second evaluation module 230 are input into the bending equipment operation control model to obtain the optimal operation control parameters of the bending equipment. The bending equipment operation control model is constructed based on the BP neural network. The bending equipment operation control model includes an input layer with 4 nodes, a hidden layer with 7 nodes, and an output layer with 3 nodes. The profile bending performance index , Profile section distortion index , Contour Difference Index , contact surface pressure distribution uniformity index The optimal operating control parameters of the bending equipment are input as the input layer, and the optimal operating control parameters of the bending equipment include the bending speed, the pre-stretching force and the supplementary stretching force.

[0028] The above-mentioned parameters and steps for each unit module to implement corresponding functions in the stretching and bending equipment operation control system based on big data analysis of the present application can refer to the parameters and steps in the embodiment of the stretching and bending equipment operation control method based on big data analysis above, and will not be repeated here.

[0029] like Figure 5 As shown, an embodiment of the present invention further provides an electronic device 300, including a memory 310, a processor 320 and a communication bus 330; the memory 310 and the processor 320 are connected via the communication bus 330. The memory 310 stores a method for controlling the operation of a bending device based on big data analysis as provided in the above embodiment, which can be loaded and executed by the processor 320.

[0030] The memory 310 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 310 can include a program storage area and a data storage area, wherein the program storage area can store instructions for implementing an operating system, instructions for at least one function, and instructions for implementing the stretch bending equipment operation control method based on big data analysis provided in the above embodiment, etc.; the data storage area can store data involved in the stretch bending equipment operation control method based on big data analysis provided in the above embodiment, etc.

[0031] The processor 320 may include one or more processing cores. The processor 320 executes various functions and processes data of the present application by running or executing instructions, programs, code sets or instruction sets stored in the memory 310, calling the data stored in the memory 310. The processor 320 may be at least one of an application-specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a central processing unit (CPU), a controller, a microcontroller and a microprocessor. It can be understood that for different devices, the electronic device used to implement the above-mentioned processor 320 function can also be other, and the embodiment of the present application is not specifically limited.

[0032] The communication bus 330 may include a path to transmit information between the above components. The communication bus 330 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The communication bus 330 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one double arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0033] An embodiment of the present application provides a computer-readable storage medium storing a computer program that can be loaded by a processor and execute a method for controlling the operation of a stretch-bending device based on big data analysis as provided in the above embodiment.

[0034] In an embodiment of the present application, a computer-readable storage medium may be a tangible device that holds and stores instructions used by an instruction execution device. A computer-readable storage medium may be, but is not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any combination thereof. Specifically, a computer-readable storage medium may be a portable computer disk, a hard disk, a USB flash drive, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a podium random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, an optical disk, a magnetic disk, a mechanical encoding device, and any combination thereof.

[0035] The terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not expressly listed, or also includes elements inherent to such process, method, article, or apparatus.

[0036] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of application involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the aforementioned application concept. For example, the above features are replaced with (but not limited to) technical features with similar functions applied in the present application.

Claims

1. A method for controlling the operation of a stretch bending equipment based on big data analysis, characterized in that: The steps include: S1: Collect profile material data and profile cross-section data, and collect profile data and contact surface pressure data between the profile and the mold; S2: Evaluate the bending performance of the profile and the degree of cross-section distortion of the profile during the bending process through the profile material data and profile cross-section data; S3: Evaluate the difference between the profile and the die and the uniformity of the contact surface pressure distribution during the stretch bending process through the contact surface profile data and contact surface pressure data; S4: constructing a bending equipment operation control model, and inputting the evaluation results of step S2 and step S3 into the bending equipment operation control model to obtain the optimal operation control parameters of the bending equipment.

2. The method for controlling the operation of a stretch bending equipment based on big data analysis according to claim 1 is characterized in that: Evaluating the bending performance of the profile in step S2 includes: S21: Obtaining profile material data and profile cross-section data, where the profile material data includes profile material thickness, material density, and material hardness; S22: Calculate the profile section symmetry index based on the profile section data; S23: Calculate the profile material distribution uniformity index based on the profile material data. The profile material distribution uniformity index calculation formula is: ； In the formula Indicates The first material monitoring point measured Type of material parameter value, Indicates The average value of material parameters of each type, Indicates the number of profile material monitoring points, Indicates the type number of material parameters, Indicates the profile material distribution uniformity index; S24: The profile bending performance index is calculated by the profile cross-section symmetry index and the profile material distribution uniformity index. The profile bending performance index is used to evaluate the profile bending performance. The calculation formula of the profile bending performance index is: ； In the formula Represents the cross-section symmetry index of the profile, Indicates the profile material distribution uniformity index, represents the adjustment factor, Indicates the profile bending performance index.

3. The method for controlling the operation of a stretch bending equipment based on big data analysis according to claim 2 is characterized in that: The step S22 comprises: S221: Obtaining the initial profile cross-section image in the profile cross-section data, preprocessing the initial profile cross-section image and calculating the centroid coordinates of the initial profile cross-section ,Preprocessing includes grayscale and binarization; S222: The upper and lower symmetry deviations and the left and right symmetry deviations of the profile section are calculated by the centroid coordinates, and then the profile section symmetry index is calculated. The calculation formula of the profile section symmetry index is: ； In the formula Indicates the upper and lower symmetry deviation of the profile section. Indicates the profile cross-section image The pixel value at position, represents the ordinate of the centroid coordinate, Indicates the left-right symmetry deviation of the profile section. represents the abscissa of the centroid coordinates, The profile cross-section image is The number of pixels on the axis, The profile cross-section image is The number of pixels on the axis, Represents the symmetry index of the profile section.

4. The stretch bending equipment operation control method based on big data analysis according to claim 1 is characterized in that: Evaluating the degree of cross-sectional distortion of the profile in step S2 includes: S25: Obtaining profile cross-section point cloud data from the profile cross-section data, where the profile cross-section point cloud data includes profile standard cross-section point cloud data and profile bending cross-section point cloud data during the bending forming process; S26: Encode the profile standard section point cloud data and the profile bending section point cloud data into ordered contour point sets respectively to obtain a first profile section contour point set and the second profile cross-section contour point set ; S27: Through the first profile section contour point set and the second profile cross-section contour point set Calculate from arrive One-way Hausdorff distance and from arrive One-way Hausdorff distance , and then calculate the profile section distortion index, which is used to evaluate the degree of profile section distortion during the stretch bending process. The profile section distortion index calculation formula is: ； In the formula Represents the point set from the first profile section contour To the second profile section contour point set The one-way Hausdorff distance of Represents the point set from the second profile section contour To the first profile section contour point set The one-way Hausdorff distance of represents the maximum value function, represents the maximum value of Hausdorff distance, Represents the profile section distortion index.

5. The method for controlling the operation of a stretch bending equipment based on big data analysis according to claim 1 is characterized in that: Evaluating the degree of contour difference in step S3 includes: S31: Acquire contact surface contour data, where the contact surface contour data includes an initial profile contact surface contour image and a mold contact surface contour image; S32: using an edge detection algorithm to respectively extract pixels of each point of the contact surface contour in the initial profile contact surface contour image and the mold contact surface contour image, to obtain a first contact surface contour pixel set and a second contact surface contour pixel set; S33: Calculate the minimum Euclidean distance between each pixel in the first contact surface contour pixel set and the pixel in the second contact surface contour pixel set and calculate the contour difference index between the profile and the mold. The contour difference index is used to evaluate the degree of difference between the profile and the mold. The calculation formula of the contour difference index is: ； In the formula Represents the first contact surface contour pixel set The Euclidean distance between a pixel and the nearest neighbor pixel in the second contact surface contour pixel set, represents the number of pixels in the first contact surface contour pixel set, represents the maximum value of the Euclidean distance between the pixels in the first contact surface contour pixel set and the pixels in the second contact surface contour pixel set, Represents the contour difference index.

6. The method for controlling the operation of a stretch bending equipment based on big data analysis according to claim 1 is characterized in that: Evaluating the uniformity of the pressure distribution on the contact surface in step S3 includes: S34: Acquiring contact surface pressure data; S35: The contact surface pressure distribution uniformity index during the stretch bending forming process is calculated using the contact surface pressure data. The contact surface pressure distribution uniformity index is used to evaluate the contact surface pressure distribution uniformity during the stretch bending forming process. The calculation formula for the contact surface pressure distribution uniformity index is: ； In the formula Indicates The contact surface pressure monitored by a pressure sensor, Indicates the maximum contact surface pressure detected by the pressure sensor. Indicates the minimum contact surface pressure detected by the pressure sensor. Indicates the number of pressure sensors, Represents the uniformity index of contact surface pressure distribution.

7. The method for controlling the operation of a stretch bending equipment based on big data analysis according to claim 1 is characterized in that: The bending equipment operation control model in step S4 is constructed based on the BP neural network. The bending equipment operation control model includes an input layer with 4 nodes, a hidden layer with 7 nodes and an output layer with 3 nodes. , Profile section distortion index , Contour Difference Index , contact surface pressure distribution uniformity index The optimal operating control parameters of the bending equipment are input as the input layer, and the optimal operating control parameters of the bending equipment include the bending speed, the pre-stretching force and the supplementary stretching force.

8. A stretching and bending equipment operation control system based on big data analysis, applied to a stretching and bending equipment operation control method based on big data analysis as claimed in any one of claims 1 to 7, characterized in that: The system comprises: A data acquisition module is used to collect profile material data and profile cross-section data, and to collect profile data and contact surface pressure data between the profile and the mold; The first evaluation module is used to evaluate the bending performance of the profile and the degree of cross-section distortion of the profile during the bending forming process through the profile material data and the profile cross-section data; The second evaluation module is used to evaluate the difference between the profile of the profile and the die and the uniformity of the contact surface pressure distribution during the stretch bending forming process through the contact surface profile data and the contact surface pressure data; The control model building module is used to build a bending equipment operation control model, and input the evaluation results of the first evaluation module and the second evaluation module into the bending equipment operation control model to obtain the optimal operation control parameters of the bending equipment.

9. An electronic device, comprising: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; characterized in that the processor executes the stretch bending equipment operation control method based on big data analysis as described in any one of claims 1 to 7 by calling the computer program stored in the memory.

10. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are executed on a computer, the computer executes the stretch bending equipment operation control method based on big data analysis as described in any one of claims 1 to 7.

Images