Casting straightening method, device, system and equipment

Abstract

The invention discloses a casting straightening method, device, system and equipment, and relates to the technical field of casting manufacturing. The method comprises the steps that first geometric data of a casting to be straightened are obtained; the straightening equipment comprises a plurality of straightening needles; the first geometric data is compared with preset target geometric data, and the target deformation amount of the to-be-straightened casting is calculated; according to the first geometric data and the target deformation amount, global modeling and local prediction processing are conducted on the to-be-straightened casting, and target stroke information of each straightening needle is obtained; and based on the target stroke information, the straightening needle is controlled to execute straightening operation on the to-be-straightened casting, so that the straightening needle is evenly pressed into the to-be-straightened casting. According to the method, the target stroke information of each straightening needle can be accurately calculated, then the straightening needles are controlled to be evenly pressed into the casting to be straightened according to the target stroke information, accurate straightening of castings in complex geometric shapes such as asymmetry or multiple layers is achieved, and the geometric accuracy, the structural integrity and the straightening efficiency of the castings are improved.

Description

Technical Field

[0001] The present application relates to the technical field of casting manufacturing, and in particular to a casting straightening method, device, system and equipment. Background Art

[0002] With the rapid development of product manufacturing, Giga-casting technology, as an integrated die-casting technology, can realize the one-time molding of large-sized single aluminum alloy parts, and has been increasingly used in the automotive field, especially in the manufacturing process of body structures. Among them, Giga-casting uses a large die-casting machine to quickly inject high-temperature molten aluminum alloy and other metal materials into the mold cavity under huge pressure. The molten metal quickly cools and solidifies in the mold to form a large automotive structure at one time, replacing the traditional welding or assembly of multiple small parts. However, in the process of casting thin-walled parts by Giga-casting, thin-walled castings often show obvious warping and deformation during cooling, solidification and heat treatment due to their large geometric dimensions, thin wall thickness and complex geometric characteristics. This not only affects the geometric accuracy, but also may weaken the structural strength and integrity. Deformed parts may be misaligned during assembly, requiring additional processing and adjustment, reducing production efficiency, and incomplete structures may lead to local stress concentration and reduce the overall fatigue resistance of the structure. Therefore, in order to ensure the assembly accuracy of components and improve the overall manufacturing process level, it is crucial to study how to straighten the deformation of castings.

[0003] At present, the relevant technology uses mechanical straightening to straighten castings, but this method requires reliance on specific molds and fixtures, which makes the mold design and manufacturing costs high, and cannot meet the high-precision correction requirements of castings with complex geometric shapes, resulting in low straightening efficiency. Summary of the invention

[0004] The purpose of this application is to provide a casting straightening method, device, system and equipment.

[0005] To achieve the above objectives, this application provides the following solutions: In a first aspect, the present application provides a casting straightening method, comprising: Acquire first geometric data of the casting to be straightened; the first geometric data is acquired by scanning the casting to be straightened by a measuring device when the casting to be straightened is fixed in a mold in a straightening device; the straightening device includes a plurality of straightening needles; Comparing the first geometric data with preset target geometric data to calculate the target deformation amount of the casting to be straightened; According to the first geometric data and the target deformation, global modeling and local prediction processing are performed on the casting to be straightened to determine the target stroke information of each straightening needle; Based on the target stroke information, the straightening needle is controlled to perform a straightening operation on the casting to be straightened, so that the straightening needle is evenly pressed into the casting to be straightened.

[0006] Optionally, according to the first geometric data and the target deformation, global modeling and local prediction processing are performed on the casting to be straightened to determine the target stroke information of each straightening needle, including: Performing global modeling on the casting to be straightened according to the first geometric data to construct a global stiffness model; the global stiffness model includes a global stiffness matrix, and each element in the global stiffness matrix is ​​used to characterize information of each geometric point of the casting to be straightened; The first geometric data is predicted and processed in a trained neural network model to obtain a local stiffness variation; the local stiffness variation is used to characterize the local stiffness variation information of the casting to be straightened; Based on the global stiffness model, the local stiffness variation and the target deformation, the target stroke information of each straightening needle is calculated.

[0007] Optionally, globally modeling the casting to be straightened according to the first geometric data to construct a global stiffness model includes: Obtaining a stroke combination and a preset initial polynomial of the straightening needle; constructing the global stiffness matrix according to the first geometric data; The stroke combination of the straightening needle and the global stiffness matrix are substituted into the initial polynomial to construct the global stiffness model.

[0008] Optionally, based on the global stiffness model, the local stiffness variation and the target deformation, the target stroke information of each straightening needle is calculated, including: Updating the global stiffness matrix according to the local stiffness variation to obtain an updated global stiffness matrix; According to the updated global stiffness matrix and the target deformation, an objective function is constructed, and the target stroke information of each straightening needle is calculated using an optimization algorithm in accordance with minimization of the objective function.

[0009] Optionally, constructing an objective function according to the updated global stiffness matrix and the target deformation, minimizing the objective function, and calculating the target stroke information of each straightening needle using an optimization algorithm, including: Calculating the actual deformation of the casting to be straightened according to the updated global stiffness matrix and the stroke combination of the straightening needle; constructing an objective function based on the actual deformation and the target deformation; Obtaining the maximum and minimum values ​​of the stroke information of the straightening needle; The maximum value and the minimum value are used as constraint conditions, and the stroke combination of the straightening needles is iteratively optimized according to the minimization of the objective function to obtain the target stroke information of each straightening needle.

[0010] Optionally, the method further comprises: When the straightening operation is completed, obtaining second geometric data of the casting to be straightened, and evaluating the casting to be straightened according to the second geometric data and the target geometric data; When the evaluation result does not meet the preset condition, the target stroke information is updated, and the straightening object is controlled to perform a straightening action on the casting to be straightened according to the updated target stroke information until the evaluation result meets the preset condition.

[0011] Optionally, the preset condition includes a preset tolerance range; and evaluating the casting to be straightened according to the second geometric data and the target geometric data comprises: Determining the residual deformation of the casting to be straightened according to the second geometric data and the target geometric data; When the residual deformation exceeds a preset tolerance range, determining that the evaluation result does not meet the preset condition; When the residual deformation does not exceed the preset tolerance range, it is determined that the evaluation result meets the preset condition.

[0012] In a second aspect, the present application provides a casting straightening device, comprising: an acquisition module, for acquiring first geometric data of the casting to be straightened; the first geometric data is acquired by scanning the casting to be straightened by a measuring device when the casting to be straightened is fixed in a mold in a straightening device; the straightening device includes a plurality of straightening needles; A comparison module, used for comparing the first geometric data with preset target geometric data, and calculating a target deformation amount of the casting to be straightened; A stroke determination module, used for performing global modeling and local prediction processing on the casting to be straightened according to the first geometric data and the target deformation, so as to obtain target stroke information of each straightening needle; The straightening module is used to control the straightening needle to perform a straightening operation on the casting to be straightened based on the target stroke information, so that the straightening needle is evenly pressed into the casting to be straightened.

[0013] In a third aspect, the present application provides a casting straightening system, the casting straightening system comprising: a control device, a straightening device and a measuring device; the control device is electrically connected to the measuring device and the straightening device respectively; The straightening device comprises: a mold and a plurality of straightening components, wherein the straightening components are fixedly arranged in the mold, the casting to be straightened is fixed in the mold, and each of the straightening components comprises a straightening needle and a straightening pin fixedly connected to the straightening needle; The measuring device is used to: collect first geometric data of the casting to be straightened and send it to the control device; The control device is used to: obtain first geometric data of the casting to be straightened; compare the first geometric data with preset target geometric data to calculate the target deformation of the casting to be straightened; perform global modeling and local prediction processing on the casting to be straightened according to the first geometric data and the target deformation to obtain target stroke information of each straightening needle; and control the straightening needle to perform a straightening operation on the casting to be straightened based on the target stroke information so that the straightening needle is evenly pressed into the casting to be straightened.

[0014] In a fourth aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of any one of the above-mentioned casting straightening methods.

[0015] According to the specific embodiments provided in this application, this application discloses the following technical effects: The present application provides a casting straightening method, device, system and equipment, which obtains first geometric data of the casting to be straightened, and the first geometric data is obtained by scanning the casting to be straightened by a measuring device when the casting to be straightened is fixed in a mold in a straightening device; the straightening device includes a plurality of straightening needles; the first geometric data is compared with preset target geometric data, and the target deformation of the casting to be straightened is calculated; according to the first geometric data and the target deformation, the casting to be straightened is globally modeled and locally predicted to obtain the target stroke information of each straightening needle; based on the target stroke information, the straightening needle is controlled to perform a straightening operation on the casting to be straightened, so that the straightening needle is evenly pressed into the casting to be straightened. Compared with the prior art, the present invention does not need to rely on specific molds and fixtures, and can compare the acquired first geometric data with the target geometric data to accurately determine the target deformation of the casting to be straightened, thereby providing good data guidance information for the subsequent determination of the stroke of the straightening needle. Based on the first geometric data and the target deformation, the casting to be straightened is globally modeled and locally predicted. The global and local information can be comprehensively considered, and the target stroke information of each straightening needle can be calculated in a finer granularity, thereby controlling the straightening needle to be uniformly pressed into the casting to be straightened according to the target stroke information, thereby achieving precise straightening of castings with complex geometric shapes such as asymmetric or multi-layered shapes, improving the geometric accuracy, structural integrity and straightening efficiency of the castings, and meeting the needs of modern industrial large-scale production. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 This is a structural schematic diagram of a casting straightening system in one embodiment of the present application; Figure 2 A schematic diagram of the structure of a straightening device provided in an embodiment of the present application; Figure 3 A schematic diagram of a process of a casting straightening method provided in one embodiment of the present application; Figure 4 A schematic flow chart of a method for determining target travel information of each straightening needle provided in an embodiment of the present application; Figure 5 A schematic flow chart of a casting straightening method provided in another embodiment of the present application; Figure 6 A schematic diagram of a process for evaluating the straightening of a casting to be straightened provided in an embodiment of the present application; Figure 7 A schematic diagram of the functional modules of a casting straightening device provided in an embodiment of the present application; Figure 8 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0019] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0020] The casting straightening method provided in the embodiment of the present application can be applied to Figure 1 The casting straightening system shown in FIG. The casting straightening system comprises: a control device 10, a straightening device 20 and a measuring device 30. The control device 10 is electrically connected to the measuring device 30 and the straightening device 20 respectively.

[0021] The measuring device 30 is used to collect first geometric data of the casting 40 to be straightened and send the data to the control device 10 .

[0022] The control device 10 is used to: compare the first geometric data with preset target geometric data according to the first geometric data, calculate the target deformation of the casting to be straightened, and then control the straightening to perform a straightening action on the casting to be straightened according to the first geometric data and the target deformation.

[0023] See also Figure 2 As shown, the straightening device 20 comprises: a mold 21 and a plurality of straightening assemblies 22, each straightening assembly 22 comprises a straightening needle 221 and a straightening pin 222 fixedly connected to the straightening needle 221, the straightening assembly 22 is fixedly arranged in the mold 21, and the casting 40 to be straightened is fixed in the mold 21. The straightening device 20 is used to perform a straightening operation on the casting 40 to be straightened.

[0024] Specifically, the mold 21 includes an upper die and a lower die, a straightening pin 221 (Straightening pin tip) and a straightening pin 222 (Straightening pin module). The upper die is fixedly arranged above the entire straightening device 20 structure and is a fixed part. The lower die is fixedly arranged below the entire straightening device 20 structure, opposite to the upper die, and is also fixed. Together with the upper die, it forms a closed space to shape and straighten the casting to be straightened. The straightening pin 221 contacts the casting 40 to be straightened, and the casting 40 to be straightened is straightened by its movement. The straightening pin 222 is used to support and guide the movement of the straightening pin tip to ensure the accuracy and stability of the straightening process. The number of straightening pins 222 can vary according to the shape of the casting 40 to be straightened.

[0025] Among them, the straightening needle 221 can be independently distributed in the mold 21, and the straightening device 20 can also include: a driving structure, the driving structure is used to drive the straightening needle to move, for example, it can include a servo motor or a hydraulic system to drive the straightening needle to move precisely along the set direction. The shape of the straightening needle 221 located at the tip of the straightening pin 222 can be set according to the target geometric shape of the casting to be straightened, for example, it can be any shape suitable for straightening, such as cylindrical, hemispherical, specific local shape, etc., to reduce contact stress concentration and optimize the straightening effect. The straightening needles are distributed in the high rigidity position of the casting to be straightened, which can ensure the overall deformation is stable during the straightening process and avoid local warping. The mold 21 has a certain rigidity, which can ensure that the height does not change when the casting is pressed. By arranging a plurality of independently controlled straightening needles in the straightening device, and their distribution position, casting shape and pressing force can be adjusted according to the geometric characteristics of the casting, through flexible design, the equipment can adapt to castings of various complex geometries, getting rid of the limitations of traditional fixed molds.

[0026] The casting to be straightened is a component that needs to be straightened and is in a curved shape. The casting to be straightened needs to be straightened by the mold structure in the straightening device 20 .

[0027] The working principle of the straightening device 20 is to apply pressure to the casting to be straightened through the relative movement of the movable straightening needle between the upper and lower molds, so as to gradually straighten it and achieve the purpose of straightening. This mold structure is often used in metal processing and other fields to ensure that the produced parts meet specific shape and size requirements.

[0028] Optionally, the measuring device 30 may include a laser scanner or a contact probe for real-time acquisition of current geometric data of the casting to be straightened. The measuring device 30 may transmit data to the control device 10 via an interface.

[0029] The control device 10 includes a terminal 102, a server 104 and a data storage system. The terminal 102 communicates with the server 104 through a network. The data storage system can store data that the server 104 needs to process. The data storage system can be set up separately, integrated on the server 104, or placed on the cloud or other servers. The terminal 102 can send the first geometric data of the casting to be straightened to the server 104. After receiving the first geometric data of the casting to be straightened, the server 104 processes the first geometric data to generate a control instruction to control the straightening device 20 to perform a straightening action on the casting to be straightened. In addition, in some embodiments, the casting straightening method can also be implemented by the server 104 or the terminal 102 alone, such as the terminal 102 can directly generate a control instruction based on the acquired geometric data of the casting to be straightened, and control the straightening device 20 to perform a straightening action on the casting to be straightened. The terminal 102 can be pre-stored with a neural network model or an intelligent algorithm to facilitate the control of the straightening to perform a straightening operation on the casting to be straightened.

[0030] The terminal 102 may be, but is not limited to, various desktop computers, laptop computers, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart vehicle-mounted devices, etc. The portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers, or may be a cloud server.

[0031] In an exemplary embodiment, Figure 3 As shown, a casting straightening method is provided, which is executed by a computer device, and can be executed by a control device such as a terminal or a server alone, or by a terminal and a server together. In the embodiment of the present application, the method is applied to Figure 1 The server 104 in the example is used as an example to illustrate the method, which includes the following steps S201 to S204. Among them: Step S201, obtaining first geometric data of the casting to be straightened; the first geometric data is obtained by scanning the casting to be straightened by a measuring device when the casting to be straightened is fixed in a mold in a straightening device; the straightening device includes a plurality of straightening needles.

[0032] It should be noted that the first geometric data is data of the casting to be straightened before the casting to be straightened is straightened, which may include a point cloud data set, which may be denoted as Ω. The measuring device may include a laser scanner or a contact probe. The first geometric data may be obtained by sending through a measuring device, or may be obtained by importing through an external device, or may be obtained from a blockchain or a database.

[0033] Optionally, in the process of acquiring the first geometric data, the casting to be straightened is first fixed in the lower mold of the straightening device, and the measuring device is started. The current first geometric data of the casting to be straightened is scanned by a laser scanner or a contact probe in the measuring device, and then sent to the control device, so that the control device acquires the first geometric data of the casting to be straightened.

[0034] Step S202, comparing the first geometric data with the preset target geometric data, and calculating the target deformation amount of the casting to be straightened.

[0035] The target geometric data refers to the standard geometric information of the casting to be straightened, which may include standard point cloud data. The target deformation refers to the difference between the first geometric data and the target geometric data.

[0036] After obtaining the first geometric data, it is necessary to compare the first geometric data Ω with the target geometric data Ωt, determine the geometric point in the first geometric data and the target point corresponding to the geometric point in the target geometric data, determine the distance from the geometric point to the measurement origin and the distance from the target point to the measurement origin, and then perform difference processing on the distance from the geometric point to the measurement origin and the distance from the target point to the measurement origin to obtain the target deformation of the casting to be straightened, which can be expressed by the following formula:

[0037] Among them, d is the distance from the geometric point in the first geometric data to the measurement origin, dt is the distance from the target point in the target geometric data to the measurement origin, and δt is the target deformation.

[0038] In this step, by comparing the first geometric data with the target geometric data, the target deformation amount can be accurately determined, thereby achieving accurate quantification of the current deformation amount of the casting to be straightened, and providing good data guidance information for determining the subsequent straightening stroke.

[0039] Step S203, performing global modeling and local prediction processing on the casting to be straightened according to the first geometric data and the target deformation, and obtaining target stroke information of each straightening needle.

[0040] It is understandable that in order to accurately determine the characteristics of the casting to be straightened, global modeling and local prediction are required. Global modeling can describe the mechanical properties of the casting to be straightened, such as stiffness, as a whole. Analyzing the casting to be straightened as a unified whole helps to understand the overall characteristics of the casting to be straightened. At the same time, in actual castings, some local areas are often prone to problems such as insufficient stiffness or excessive deformation. Local prediction can accurately locate these key areas to meet the needs of complex geometric parts.

[0041] Specifically, after obtaining the first geometric data, global modeling processing is performed based on the first geometric data of the casting to be straightened to obtain global feature information of the casting to be straightened, and local feature prediction is performed based on the first geometric data and the target deformation to obtain local feature information of the casting to be straightened, and then an optimization algorithm is used to determine the target stroke information of the straightening needle based on the global feature information, local feature information and target deformation.

[0042] The target stroke information refers to the moving path information of the straightening needle when straightening the casting to be straightened, and the moving path information may include moving direction information and position information.

[0043] In this step, global modeling and local prediction processing are performed on the casting to be straightened according to the first geometric data and the target deformation, which can comprehensively consider the local characteristics and global characteristics of the casting to be straightened, so as to accurately obtain the target stroke information of each straightening needle, facilitate accurate control of the straightening operation of the straightening needle, and improve the straightening efficiency.

[0044] Step S204: Based on the target stroke information, the straightening needle is controlled to perform a straightening operation on the casting to be straightened, so that the straightening needle is evenly pressed into the casting to be straightened.

[0045] Specifically, after determining the target stroke information, the control device can send a control instruction to the driving structure in the straightening device, so that the driving structure receives and responds to the control instruction, and drives the straightening needle to move to the specified position according to the target stroke information. The specified position refers to the position where the straightening needle corresponds when the casting to be straightened needs to be pressed into place. Among them, the driving structure includes a servo motor or a hydraulic structure, and the number of driving structures can be one or more. For example, taking the driving structure as a servo motor, when the number of servo motors is one, one servo motor can drive all the straightening needles to their respective specified positions; when the number of servo motors is multiple, each servo motor can drive one or more corresponding straightening needles to their respective specified positions.

[0046] Among them, when the straightening needle reaches the specified position, the control device controls the driving structure to drive the straightening needle to gradually press into the casting to be straightened, and monitors its deformation process in real time to ensure that the pressing force into the casting to be straightened is evenly distributed and no additional deformation is introduced.

[0047] In this step, there is no need to customize molds for each casting shape, which reduces the dependence on customized molds, greatly reduces production costs, and shortens the process cycle through automated and intelligent processes. By controlling the straightening needle to perform straightening operations on the casting to be straightened according to the target stroke information, the automatic straightening of the casting to be straightened can be achieved, which significantly reduces the development cost of the mold, and multiple straightening needles are provided to achieve synchronous straightening of multiple positions of the casting, which significantly improves the operating efficiency. At the same time, the distribution position, shape and stroke of the straightening needle can be flexibly adjusted according to the rigidity distribution and geometric characteristics of the casting, and the stiffness changes caused by the geometric shape can be dynamically captured through the neural network model, so that the system can adapt to castings of various complex shapes, and by arranging the straightening needles in the high-rigidity area of ​​the mold, the risk of local excessive deformation is reduced, covering the diverse straightening needs from simple geometry to complex asymmetric structures, breaking through the scope of application of the traditional fixed mold method, and improving the universality of the technology.

[0048] The present application provides a casting straightening method, which comprises obtaining first geometric data of the casting to be straightened, wherein the first geometric data is obtained by scanning the casting to be straightened by a measuring device when the casting to be straightened is fixed in a mold in a straightening device; the straightening device comprises a plurality of straightening needles; the first geometric data is compared with preset target geometric data, and a target deformation amount of the casting to be straightened is calculated; according to the first geometric data and the target deformation amount, the casting to be straightened is globally modeled and locally predicted to obtain target stroke information of each straightening needle; based on the target stroke information, the straightening needle is controlled to perform a straightening operation on the casting to be straightened, so that the straightening needle is evenly pressed into the casting to be straightened. Compared with the prior art, the present invention does not need to rely on specific molds and fixtures, and can compare the acquired first geometric data with the target geometric data to accurately determine the target deformation of the casting to be straightened, thereby providing good data guidance information for the subsequent determination of the stroke of the straightening needle. Based on the first geometric data and the target deformation, the casting to be straightened is globally modeled and locally predicted. The global and local information can be comprehensively considered, and the target stroke information of each straightening needle can be calculated in a finer granularity, thereby controlling the straightening needle to be uniformly pressed into the casting to be straightened according to the target stroke information, thereby achieving precise straightening of castings with complex geometric shapes such as asymmetric or multi-layered shapes, improving the geometric accuracy, structural integrity and straightening efficiency of the castings, and meeting the needs of modern industrial large-scale production.

[0049] In another exemplary embodiment of the present application, in order to achieve accurate straightening of the casting to be straightened, it is necessary to determine the target stroke information of each straightening needle. Figure 4 As shown, the method includes the following steps S301 to S303: Step S301 : globally modeling the casting to be straightened according to the first geometric data to construct a global stiffness model; the global stiffness model includes a global stiffness matrix, and each element in the global stiffness matrix is ​​used to characterize information of each geometric point of the casting to be straightened.

[0050] Step S302, predicting and processing the first geometric data in a trained neural network model to obtain a local stiffness variation; the local stiffness variation is used to characterize local stiffness variation information of the casting to be straightened.

[0051] Step S303, calculating the target stroke information of each straightening needle based on the global stiffness model, the local stiffness change and the target deformation.

[0052] It should be noted that the global stiffness model can be expressed in the form of a polynomial. The neural network model is trained in advance based on historical sample data and corresponding annotation results. It has the ability to predict the local stiffness of the casting and can include multiple neural network layers, such as multiple input layers, hidden layers and output layers. Optionally, the neural network model can include a deep neural network model (DNN) or an XGBoost model.

[0053] Optionally, during the training process of the above-mentioned neural network model, the sample casting geometry data and the corresponding local stiffness labeling results may be first obtained, and then the sample casting geometry data may be input into the initial neural network model to obtain the prediction results, and a loss function may be constructed based on the prediction results and the local stiffness labeling results. The loss function may be minimized and the parameters in the initial neural network model may be iteratively optimized to obtain the neural network model.

[0054] It is understandable that when the parameters in the initial neural network model are updated by the loss function, the parameters in the model may be adjusted according to the loss function when the initial neural network model has not converged, so that the initial neural network model converges, thereby obtaining a neural network model. The convergence of the initial neural network model may mean that the difference between the prediction result and the local stiffness labeling result is less than a preset threshold, or that the rate of change of the difference between the prediction result and the local stiffness labeling result approaches a lower value. When the calculated loss function is small, or the difference between the loss function output from the previous round of iteration approaches 0, the initial neural network model is considered to have converged, thereby obtaining a neural network model.

[0055] After obtaining the first geometric data, the casting to be straightened is globally modeled to construct a global stiffness model, including: obtaining a stroke combination of the straightening needle and a preset initial polynomial; substituting the stroke combination of the straightening needle and the global stiffness matrix into the initial polynomial to construct a global stiffness model.

[0056] It can be understood that the above-mentioned stroke combination C of the straightening needles can be represented by a matrix or a vector, and the stroke combination C of the straightening needles can be obtained by scanning each straightening needle in the straightening device with a measuring device.

[0057] Specifically, taking the global stiffness model as a polynomial as an example, after obtaining the first geometric data, the stroke combination of the straightening needle and the preset initial polynomial can be obtained. The preset initial polynomial can be customized according to the complexity of the casting and the modeling accuracy requirements. For example, for castings with more complex shapes, low-order polynomials (such as first-order or second-order) may be sufficient to describe their stiffness characteristics; for castings with more complex shapes, third-order or higher-order polynomials may be required. Then, the global stiffness matrix Kglobal is constructed according to the first geometric data, and the actual deformation δ is determined according to the stroke combination C of the straightening needle and the global stiffness matrix. Substitute the stroke combination C of the straightening needle, the actual deformation δ, and the global stiffness matrix Kglobal into the initial polynomial to obtain the global stiffness model, which is represented by δ=KglobalC.

[0058] In this embodiment, by globally modeling the first geometric data, a preliminary estimate of the macroscopic stiffness of the casting to be straightened can be made, thereby accurately constructing a global stiffness model, and dynamically capturing the influence of the casting's geometric deformation on stiffness through a neural network model, so that the local stiffness change can be obtained in a finer granularity.

[0059] After constructing the global stiffness model, in order to consider the influence of geometric deformation on stiffness, it is necessary to use a neural network model to predict the local stiffness change ΔK of the casting to be straightened. For example, taking the neural network model as a DNN model, the first geometric data is input into the trained DNN model, and the processed first geometric data is input through the input layer in the DNN model, and normalized to obtain a normalized result. The normalized result is then input into the hidden layer for processing to capture the complex relationship between the input features and the target variable. The intermediate result is obtained through a linear transformation, and the intermediate result is processed through the output layer. Finally, it is normalized through an activation function to obtain the local stiffness change ΔK.

[0060] Furthermore, after obtaining the global stiffness model and the local stiffness change, the target stroke information of each straightening needle is calculated based on the global stiffness model, the local stiffness change and the target deformation, including: updating the global stiffness matrix according to the local stiffness change to obtain an updated global stiffness matrix; constructing an objective function according to the updated global stiffness matrix and the target deformation, and calculating the target stroke information of each straightening needle using an optimization algorithm according to the minimization of the objective function.

[0061] In this embodiment, the global stiffness matrix Kglobal is updated by the local stiffness change ΔK, and the updated global stiffness matrix is ​​obtained by the formula K=Kglobal+ΔK. Then, the actual deformation of the casting to be straightened is calculated according to the updated global stiffness matrix and the stroke combination of the straightening needles. Based on the actual deformation and the target deformation, an objective function is constructed. The maximum and minimum values ​​of the stroke information of the straightening needles are obtained. The maximum and minimum values ​​are used as constraints, and the stroke combination of the straightening needles is iteratively optimized according to the minimization of the objective function to obtain the target stroke information of each straightening needle.

[0062] Among them, the stroke combination of the straightening needle can be used as the initial stroke information of the straightening needle. After obtaining the updated global stiffness matrix, the updated global stiffness matrix and the stroke combination of the straightening needle can be multiplied to obtain the current actual deformation of the casting to be straightened, and then the maximum and minimum values ​​of the straightening needle stroke information of each straightening needle are obtained and used as constraints. The maximum and minimum values ​​can be customized according to actual needs, which need to meet the actual straightening process requirements. Then, based on the target deformation δt and the actual deformation δ, the objective function is constructed, and the | ∣ indicates that according to the minimization of the objective function, the L-BFGS-B optimization algorithm is used to iteratively optimize the stroke combination of the straightening needle to obtain the target stroke information of each straightening needle, which is between the minimum and maximum values.

[0063] It can be understood that the above L-BFGS-B optimization algorithm starts the iterative optimization process based on the initial straightening needle stroke information. In each iteration, the algorithm uses the gradient information of the previous iteration to construct an approximate Hessian matrix inverse according to the principle of the quasi-Newton method, thereby determining the search direction and determining the step length through linear search, so that after moving the step length along the direction, the objective function can be sufficiently reduced. The algorithm has the ability to handle boundary constraints. When the iterative value exceeds the boundary, the algorithm will automatically adjust it to the boundary, or make corrections in the selection of the search direction and step length to avoid generating infeasible solutions.

[0064] In this embodiment, by combining the method of global stiffness modeling and local stiffness prediction, the traditional mathematical model and advanced machine learning technology are used to calculate the target stroke information of each straightening needle, which can comprehensively and accurately deal with the stiffness problem in the straightening process of the casting to be straightened, and the L-BFGS-B optimization algorithm is used to adjust the straightening needle stroke to the optimal state, and the straightening time is much lower than the traditional optimization method, thereby realizing accurate prediction and optimization of the straightening needle stroke, so as to control the straightening needle to straighten according to the optimal target stroke, thereby effectively eliminating residual deformation and ensuring the straightening effect. By controlling the straightening needle to be evenly pressed into the casting to be straightened, uniform pressure can be ensured and the problem of local over-bridge or under-bridge can be eliminated. This is of great significance to improving the production quality and production efficiency of castings in the manufacturing industry, and can greatly improve the straightening efficiency of castings.

[0065] In another exemplary embodiment of the present application, in order to accurately perform straightening processing on the straightening casting, it is necessary to evaluate the straightening effect of the straightening casting, see Figure 5 As shown, the above method also includes the following operation steps: S401~S402.

[0066] Step S401, when the straightening operation is completed, second geometric data of the casting to be straightened is obtained, and the casting to be straightened is evaluated according to the second geometric data and the target geometric data.

[0067] Step S402, when the evaluation result does not meet the preset condition, the target stroke information is updated, and the straightening is controlled to perform the straightening action on the casting to be straightened according to the updated target stroke information until the evaluation result meets the preset condition.

[0068] In this embodiment, after the initial straightening operation is performed on the casting to be straightened, the measuring device can be used to scan the structural shape information of the casting to be straightened again and send it to the control device, so that the control device obtains the second geometric data of the casting to be straightened. The second geometric data is the data of the casting to be straightened obtained after the straightening operation is performed on the casting to be straightened, which may include a point cloud data set, which can be recorded as Ωs.

[0069] The above-mentioned preset conditions may include a preset tolerance range, which can be customized according to actual needs. After obtaining the second geometric data, the residual deformation of the casting to be straightened is determined according to the second geometric data Ωs and the target geometric data Ωt. ; When the residual deformation exceeds the preset tolerance range, the evaluation result is determined to be not in compliance with the preset conditions; when the residual deformation does not exceed the preset tolerance range, the evaluation result is determined to be in compliance with the preset conditions.

[0070] Specifically, after obtaining the second geometric data Ωs, the second geometric data Ωs and the target geometric data Perform differential processing to obtain the residual deformation, and then use the formula δr=Ωt-Ωs to obtain the residual deformation , and then determine whether the residual deformation exceeds the preset tolerance range. When the residual deformation exceeds the preset tolerance range, it is determined that the evaluation result does not meet the preset conditions, and it is necessary to continue to straighten the casting to be straightened, update the target stroke information, and control the straightening to perform the straightening action on the casting to be straightened according to the updated target stroke information until the evaluation result meets the preset conditions; when the residual deformation does not exceed the preset tolerance range, it is determined that the evaluation result meets the preset conditions.

[0071] Optionally, after the straightening operation is completed, the current straightening data can be stored in the database. The current straightening data may include the first geometric data, second geometric data, target deformation, residual deformation, and straightening effect of the casting to be straightened. The current straightening data is used as reference data to optimize the parameters of the global stiffness model and the neural network model.

[0072] In this step, the feedback and accumulation of residual deformation data can dynamically improve the performance of the straightening system, ensure long-term accuracy and efficiency, and realize full closed-loop control from geometric data acquisition, straightening stroke calculation to actual straightening action without human intervention. After straightening, the residual deformation data can be fed back in real time, and the reliability is further improved by adjusting the straightening parameters to update the algorithm model. The geometric shape deviation of complex castings can be reduced to the target tolerance range, ensuring its assembly accuracy and structural integrity.

[0073] See also Figure 6 As shown, Figure 6The schematic diagram of the process of evaluating the straightening of the casting to be straightened provided in the embodiment of the present application, taking the preset tolerance as X% as an example, includes a target geometry casting (Target geometry) and a casting to be straightened (Distorted part), the target geometry casting includes target geometry data, the casting to be straightened includes first geometry data, and the target geometry casting is marked with a preset target tolerance (Target tolerance: X%), which is the ideal state and allowable error range that the casting needs to achieve in the end. The casting to be straightened is a part that is deformed in actual production. Then, according to the first geometry data and the target geometry data, the casting to be straightened is compared to realize the distortion evaluation (Distortionevaluation), obtain the target deformation amount, and judge whether the target deformation amount is less than X%. When the target deformation amount is less than X%, the straightening process of the casting to be straightened is completed (Straightening process finished); if the target deformation amount is not less than X%, the next step is entered, and it needs to be straightened. Through the first geometric data and the target deformation, the casting to be straightened is globally modeled and locally predicted, the target stroke information of each straightening pin is determined, and then the straightening pin is controlled to perform the straightening operation (Straightening stroke) on the casting to be straightened according to the target stroke information, so that the straightening pin is evenly pressed into the casting to be straightened, and it is stored in the database as the straightening history data, which is used to provide reference data for subsequent straightening processing to improve the subsequent straightening process. When the straightening stroke is completed, it returns to the deformation evaluation stage, continues to obtain the second geometric data of the casting to be straightened, compares the second geometric data with the target geometric data, obtains the residual deformation, and then determines whether the residual deformation is less than X%, and performs straightening processing on the casting to be straightened according to the comparison result until the residual deformation is less than X%. Wherein, X% is, for example, 0.02% of the maximum size of the casting.

[0074] In this embodiment, the deformation data of the casting to be straightened is collected in real time by the measuring device, which can provide data guidance information for the control device to execute the straightening algorithm and control logic, and accurately determine the global stiffness model and local stiffness change by global modeling and local prediction processing, so that the straightening process can not only handle the global deformation, but also accurately straighten the local complex geometric features. Compared with the traditional manual adjustment method, the straightening needle stroke can be accurately determined according to the algorithm, without the need for multiple trial adjustments, thereby reducing time waste, and applying pressure to the casting to be straightened by the straightening needle in the straightening equipment, which significantly reduces residual deformation and improves straightening accuracy.

[0075] Based on the same inventive concept, the embodiment of the present application also provides a casting straightening device for implementing the above-mentioned. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in one or more embodiments of the casting straightening device provided below can refer to the limitations of the casting straightening method above, and will not be repeated here.

[0076] In an exemplary embodiment, Figure 7 As shown, a casting straightening device is provided, comprising: An acquisition module 510 is used to acquire first geometric data of the casting to be straightened; the first geometric data is acquired by scanning the casting to be straightened through a measuring device when the casting to be straightened is fixed in a mold in a straightening device; the straightening device includes a plurality of straightening needles; A comparison module 520, for comparing the first geometric data with preset target geometric data to calculate a target deformation amount of the casting to be straightened; A stroke determination module 530 is used to perform global modeling and local prediction processing on the casting to be straightened according to the first geometric data and the target deformation amount, so as to obtain target stroke information of each straightening needle; The straightening module 540 is used to control the straightening needle to perform a straightening operation on the casting to be straightened based on the target stroke information, so that the straightening needle is evenly pressed into the casting to be straightened.

[0077] As an optional implementation, the itinerary determination module 530 is specifically configured to: Performing global modeling on the casting to be straightened according to the first geometric data to construct a global stiffness model; the global stiffness model includes a global stiffness matrix, and each element in the global stiffness matrix is ​​used to characterize information of each geometric point of the casting to be straightened; The first geometric data is predicted and processed in a trained neural network model to obtain a local stiffness variation; the local stiffness variation is used to characterize the local stiffness variation information of the casting to be straightened; Based on the global stiffness model, local stiffness change and target deformation, the target stroke information of each straightening needle is calculated.

[0078] As an optional implementation, the itinerary determination module 530 is further configured to: Obtaining a stroke combination of the straightening needle and a preset initial polynomial; constructing a global stiffness matrix according to the first geometric data; The stroke combination of the straightening needle and the global stiffness matrix are substituted into the initial polynomial to construct the global stiffness model.

[0079] As an optional implementation, the itinerary determination module 530 is further configured to: The global stiffness matrix is ​​updated according to the local stiffness variation to obtain an updated global stiffness matrix; According to the updated global stiffness matrix and target deformation, the objective function is constructed, and the target stroke information of each straightening needle is calculated using the optimization algorithm according to the minimization of the objective function.

[0080] As an optional implementation, the itinerary determination module 530 is further configured to: The actual deformation of the casting to be straightened is calculated according to the updated global stiffness matrix and the stroke combination of the straightening needle; Based on the actual deformation and the target deformation, an objective function is constructed; Get the maximum and minimum values ​​of the straightening needle's stroke information; The maximum and minimum values ​​are taken as constraints, and the stroke combination of the straightening needles is iteratively optimized according to the minimization of the objective function to obtain the target stroke information of each straightening needle.

[0081] As an optional implementation, the above device is also used for: When the straightening operation is completed, second geometric data of the casting to be straightened is obtained, and the casting to be straightened is evaluated based on the second geometric data and the target geometric data; When the evaluation result does not meet the preset conditions, the target stroke information is updated, and the straightening is controlled to perform the straightening action on the casting to be straightened according to the updated target stroke information until the evaluation result meets the preset conditions.

[0082] As an optional implementation, the above device is also used for: Determining the residual deformation of the casting to be straightened according to the second geometric data and the target geometric data; When the residual deformation exceeds the preset tolerance range, the evaluation result is determined to be not meeting the preset conditions; When the residual deformation does not exceed the preset tolerance range, it is determined that the evaluation result meets the preset condition.

[0083] Among them, the casting straightening device provided in the embodiment of the present application does not need to rely on specific molds and fixtures, and can compare the acquired first geometric data with the target geometric data to accurately determine the target deformation of the casting to be straightened, thereby providing good data guidance information for the subsequent determination of the stroke of the straightening needle, and based on the first geometric data and the target deformation, the casting to be straightened is globally modeled and locally predicted, and can comprehensively consider the global information and local information, and calculate the target stroke information of each straightening needle in a finer granularity, and then control the straightening needle to be evenly pressed into the casting to be straightened according to the target stroke information, thereby realizing precise straightening of castings with complex geometric shapes such as asymmetric or multi-layered, improving the geometric accuracy, structural integrity and straightening efficiency of the castings, and meeting the needs of modern industrial large-scale production.

[0084] In an exemplary embodiment, a casting straightening system is provided. Figure 1 As shown, the system includes: a control device 10, a straightening device 20 and a measuring device 30; the control device 10 is electrically connected to the measuring device 30 and the straightening device 20 respectively; The straightening device 20 comprises: a mold and a plurality of straightening components, the straightening components are fixedly arranged in the mold, the casting 40 to be straightened is fixed in the mold, and each straightening component comprises a straightening needle and a straightening pin fixedly connected to the straightening needle; The measuring device 30 is used to: collect first geometric data of the casting 40 to be straightened and send it to the control device; The control device 10 is used to: obtain first geometric data of the casting 40 to be straightened; compare the first geometric data with preset target geometric data, and calculate the target deformation of the casting 40 to be straightened; perform global modeling and local prediction processing on the casting 40 to be straightened according to the first geometric data and the target deformation, and obtain target stroke information of each straightening needle; based on the target stroke information, control the straightening needle to perform a straightening operation on the casting 40 to be straightened, so that the straightening needle is evenly pressed into the casting to be straightened.

[0085] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 8As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store video tag processing data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a casting straightening method is implemented.

[0086] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0087] In an exemplary embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0088] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0089] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0090] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0091] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0092] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0093] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0094] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A casting straightening method, characterized in that: The casting straightening method comprises: Acquire first geometric data of the casting to be straightened; the first geometric data is acquired by scanning the casting to be straightened by a measuring device when the casting to be straightened is fixed in a mold of a straightening device; the straightening device includes a plurality of straightening needles; Comparing the first geometric data with preset target geometric data to calculate the target deformation amount of the casting to be straightened; According to the first geometric data and the target deformation, global modeling and local prediction processing are performed on the casting to be straightened to determine the target stroke information of each straightening needle; Based on the target stroke information, the straightening needle is controlled to perform a straightening operation on the casting to be straightened, so that the straightening needle is evenly pressed into the casting to be straightened.

2. The casting straightening method according to claim 1, characterized in that: According to the first geometric data and the target deformation, the casting to be straightened is globally modeled and locally predicted to determine the target travel information of each straightening needle, including: Performing global modeling on the casting to be straightened according to the first geometric data to construct a global stiffness model; the global stiffness model includes a global stiffness matrix, and each element in the global stiffness matrix is ​​used to characterize information of each geometric point of the casting to be straightened; The first geometric data is predicted and processed in a trained neural network model to obtain a local stiffness variation; the local stiffness variation is used to characterize the local stiffness variation information of the casting to be straightened; Based on the global stiffness model, the local stiffness variation and the target deformation, the target stroke information of each straightening needle is calculated.

3. The casting straightening method according to claim 2, characterized in that: Performing global modeling on the casting to be straightened according to the first geometric data to construct a global stiffness model includes: Obtaining a stroke combination and a preset initial polynomial of the straightening needle; constructing the global stiffness matrix according to the first geometric data; The stroke combination of the straightening needle and the global stiffness matrix are substituted into the initial polynomial to construct the global stiffness model.

4. The casting straightening method according to claim 2, characterized in that: Calculating target travel information of each straightening needle based on the global stiffness model, the local stiffness change and the target deformation, including: Updating the global stiffness matrix according to the local stiffness variation to obtain an updated global stiffness matrix; According to the updated global stiffness matrix and the target deformation, an objective function is constructed, and the target stroke information of each straightening needle is calculated using an optimization algorithm in accordance with minimization of the objective function.

5. The casting straightening method according to claim 4, characterized in that: According to the updated global stiffness matrix and the target deformation, an objective function is constructed, and according to minimization of the objective function, the target stroke information of each straightening needle is calculated using an optimization algorithm, including: Calculating the actual deformation of the casting to be straightened according to the updated global stiffness matrix and the stroke combination of the straightening needle; constructing an objective function based on the actual deformation and the target deformation; Obtaining the maximum and minimum values ​​of the stroke information of the straightening needle; The maximum value and the minimum value are used as constraint conditions, and the stroke combination of the straightening needles is iteratively optimized according to the minimization of the objective function to obtain the target stroke information of each straightening needle.

6. The casting straightening method according to claim 1, characterized in that: The method further comprises: When the straightening operation is completed, obtaining second geometric data of the casting to be straightened, and evaluating the casting to be straightened according to the second geometric data and the target geometric data; When the evaluation result does not meet the preset condition, the target stroke information is updated, and the straightening is controlled to perform a straightening action on the casting to be straightened according to the updated target stroke information until the evaluation result meets the preset condition.

7. The casting straightening method according to claim 6, characterized in that: The preset conditions include a preset tolerance range; The casting to be straightened is evaluated according to the second geometric data and the target geometric data, including: Determining the residual deformation of the casting to be straightened according to the second geometric data and the target geometric data; When the residual deformation exceeds a preset tolerance range, determining that the evaluation result does not meet the preset condition; When the residual deformation does not exceed the preset tolerance range, it is determined that the evaluation result meets the preset condition.

8. A casting straightening device, characterized in that: The casting straightening device comprises: an acquisition module, for acquiring first geometric data of the casting to be straightened; the first geometric data is acquired by scanning the casting to be straightened by a measuring device when the casting to be straightened is fixed in a mold in a straightening device; the straightening device includes a plurality of straightening needles; A comparison module, used for comparing the first geometric data with preset target geometric data, and calculating a target deformation amount of the casting to be straightened; A stroke determination module, used for performing global modeling and local prediction processing on the casting to be straightened according to the first geometric data and the target deformation, so as to obtain target stroke information of each straightening needle; The straightening module is used to control the straightening needle to perform a straightening operation on the casting to be straightened based on the target stroke information, so that the straightening needle is evenly pressed into the casting to be straightened.

9. A casting straightening system, characterized in that: The casting straightening system comprises: a control device, a straightening device and a measuring device; the control device is electrically connected to the measuring device and the straightening device respectively; The straightening device comprises: a mold and a plurality of straightening components, wherein the straightening components are fixedly arranged in the mold, the casting to be straightened is fixed in the mold, and each of the straightening components comprises a straightening needle and a straightening pin fixedly connected to the straightening needle; The measuring device is used to: collect first geometric data of the casting to be straightened and send it to the control device; The control device is used to: obtain first geometric data of the casting to be straightened; compare the first geometric data with preset target geometric data to calculate the target deformation of the casting to be straightened; perform global modeling and local prediction processing on the casting to be straightened according to the first geometric data and the target deformation to obtain target stroke information of each straightening needle; and control the straightening needle to perform a straightening operation on the casting to be straightened based on the target stroke information so that the straightening needle is evenly pressed into the casting to be straightened.

10. A control device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the casting straightening method according to any one of claims 1 to 7.

Images