Spot welding quality detection method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses a spot welding quality detection method and device, electronic equipment and a storage cut-off device. The method comprises the following steps: acquiring a welding spot image of a target welding spot, wherein the welding spot image comprises images of the target welding spot in multiple directions; acquiring a welding signal corresponding to the target welding spot, wherein the welding signal comprises welding signal curve data; preprocessing the welding spot image and the welding signal, and performing data fusion on the preprocessed welding spot image and the preprocessed welding signal curve data to obtain fused welding spot data; and determining a quality detection result of the target welding spot based on the fused welding spot data. According to the embodiment of the invention, the advantages of the two kinds of data can be fully utilized, the detection comprehensiveness and accuracy are improved, the data fusion technology can also realize information complementation and redundancy elimination, the detection process is further simplified, and the detection efficiency is improved.

Description

Technical Field

[0001] The present application relates to the technical field of industrial welding, and particularly relates to a spot welding quality detection method, device, electronic device, and computer-readable storage medium. Background Art

[0002] Resistance spot welding generates high heat in the metal joint area by applying current and pressure, melting and bonding metal parts together. This process has advantages such as high speed, high efficiency, easy automation, and high cost-effectiveness, so it is widely used in multiple fields. For example, resistance spot welding is one of the indispensable processes in automobile manufacturing. It is used to connect multiple parts of the vehicle body, such as doors, roofs, floors, etc., to ensure the overall strength and safety of the vehicle. In addition to automobiles, resistance spot welding is also applied in the manufacturing of truck trailers, buses, recreational vehicles, and railway vehicles to connect various metal parts. Moreover, in the manufacturing of office furniture and electrical appliances, resistance spot welding is also commonly used to connect metal parts to improve the stability and durability of products.

[0003] However, resistance spot welding involves complex interactions between electromagnetic, thermal, mechanical, fluid flow, and metallurgical phenomena at the bonding interface. This process is difficult to control properly. The quality of the solder joints is not only manifested in the appearance of the solder joints. For internal defects of the solder joints, such as cracks and pores, a single type of image data is difficult to effectively detect. These internal defects have an important impact on the quality and performance of the solder joints, but the quality of the solder joints cannot be accurately judged only by the surface image. Therefore, how to accurately detect the quality of the solder joints is an urgent problem to be solved at present. Summary of the Invention

[0004] To solve the above technical problems, embodiments of the present application provide a spot welding quality detection method, device, electronic device, computer-readable storage medium, and computer program product.

[0005] According to one aspect of the embodiments of the present application, a spot welding quality detection method is provided, including: obtaining a solder joint image of a target solder joint, where the solder joint image includes images of the target solder joint from multiple orientations; obtaining a welding signal corresponding to the target solder joint, where the welding signal includes welding signal curve data; preprocessing the solder joint image and the welding signal, and performing data fusion on the preprocessed solder joint image and the preprocessed welding signal curve data to obtain fused solder joint data; and determining a quality detection result of the target solder joint based on the fused solder joint data.

[0006] According to one aspect of the embodiments of the present application, the welding signal curve data includes a welding current curve, a welding voltage curve, and a dynamic resistance curve. The method further includes: determining welding process parameters of the target solder joint based on the welding current curve, the welding voltage curve, and the dynamic resistance curve, where the welding process parameters include welding parameters that can be controlled or measured during the welding process; determining welding signal characteristics of the target solder joint based on the welding process parameters.

[0007] According to one aspect of the embodiments of the present application, the method further includes: inputting the welding current curve, the welding voltage curve, and the dynamic resistance curve into a time-domain convolutional network model; performing a convolution operation on the welding current curve, the welding voltage curve, and the dynamic resistance curve through the time-domain convolutional network model to obtain solder joint characteristics of the target solder joint.

[0008] According to one aspect of the embodiments of the present application, the method further includes: obtaining solder joint coordinate data corresponding to the target solder joint; extracting solder joint image characteristics of the target solder joint based on the solder joint coordinate data and the solder joint image.

[0009] The extracting the solder joint image characteristics of the target solder joint based on the solder joint coordinate data and the solder joint image includes: extracting the solder joint shape and the solder joint position of the target solder joint from the solder joint image based on the solder joint coordinate data; determining the solder joint image characteristics of the target solder joint based on the solder joint shape and the solder joint position.

[0010] According to one aspect of the embodiments of the present application, the method further includes: extracting physical characteristics of the target solder joint from the solder joint characteristics, and extracting visual characteristics of the target solder joint from the solder joint image characteristics; performing data fusion on the physical characteristics and the visual characteristics to obtain a fusion result; if the fusion result meets a preset fusion data requirement, obtaining fused solder joint data based on the fusion result.

[0011] According to one aspect of the embodiments of the present application, the method further includes: establishing a preset spatio-temporal mapping relationship between the physical characteristics and the visual characteristics; determining the correlation relationship between the physical characteristics and the visual characteristics in terms of time and space based on the preset spatio-temporal mapping relationship; determining a quality inspection result of the target solder joint based on the correlation relationship and the fused solder joint data.

[0012] According to one aspect of the embodiments of the present application, a spot welding quality detection device is provided. The device includes: a first acquisition module for acquiring a solder joint image of a target solder joint, where the solder joint image includes images of all orientations of the target solder joint; a second acquisition module for acquiring a welding signal corresponding to the target solder joint, where the welding signal includes welding signal curve data; a fusion module for preprocessing the solder joint image and the welding signal, and performing data fusion on the preprocessed solder joint image and the preprocessed welding signal curve data to obtain fused solder joint data; and a determination module for determining a quality detection result of the target solder joint based on the fused solder joint data.

[0013] According to one aspect of the embodiments of the present application, an electronic device is provided, including: one or more processors; a storage device for storing one or more programs, and when the one or more programs are executed by the one or more processors, the electronic device implements the spot welding quality detection method as described above.

[0014] According to one aspect of the embodiments of the present application, a computer-readable storage medium is provided, on which computer-readable instructions are stored, and when the computer-readable instructions are executed by a processor of a computer, the computer executes the spot welding quality detection method as described above.

[0015] According to one aspect of the embodiments of the present application, a computer program product is further provided, including a computer program, and when the computer program is executed by a processor, the steps in the spot welding quality detection method as described above are implemented.

[0016] In the technical solution provided by the embodiments of the present application, by performing data fusion processing on the spot welding solder joint image and the welding signal, the advantages of the two types of data can be fully utilized, the comprehensiveness and accuracy of detection can be improved, and the data fusion technology can also achieve information complementarity and redundancy elimination, further simplifying the detection process and improving the detection efficiency. Moreover, by fusing two modalities of spot welding data to determine the quality detection result of the target solder joint, timely feedback can be provided for the adjustment and optimization of the production process, improving product quality and production efficiency.

[0017] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. Description of the Drawings

[0018] The drawings here are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application. Obviously, the drawings in the following description are only some embodiments of the present application, and those of ordinary skill in the art can obtain other drawings based on these drawings without creative efforts. In the drawings:

[0019] Figure 1 It is a schematic diagram of the implementation environment for spot welding quality detection shown in an exemplary embodiment of the present application;

[0020] Figure 2 It is a flowchart of the spot welding quality detection method shown in an exemplary embodiment of the present application;

[0021] Figure 3 It is a flowchart of a spot welding quality detection method shown in another exemplary embodiment of the present application;

[0022] Figure 4 It is a flowchart of a spot welding quality detection method shown in another exemplary embodiment of the present application;

[0023] Figure 5 It is a flowchart of a spot welding quality detection method shown in another exemplary embodiment of the present application;

[0024] Figure 6 It is a flowchart of a spot welding quality detection method shown in another exemplary embodiment of the present application;

[0025] Figure 7 It is a flowchart of a spot welding quality detection method shown in another exemplary embodiment of the present application;

[0026] Figure 8 It is a flowchart of a spot welding quality detection method shown in another exemplary embodiment of the present application;

[0027] Figure 9 It is a schematic diagram of the brief process for spot welding quality detection in an exemplary application scenario;

[0028] Figure 10 It is a block diagram of the spot welding quality detection device shown in an exemplary embodiment of the present application;

[0029] Figure 11 It shows a schematic diagram of the structure of the computer system of the electronic device suitable for implementing the embodiments of the present application.

[0030] Reference numerals:

[0031] 110 - Image acquisition device, 120 - Welding group control system, and 130 - Server side. Detailed implementation manners

[0032] Exemplary embodiments will be described in detail herein, and examples thereof are shown in the accompanying drawings. When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0033] The block diagrams shown in the accompanying drawings are only functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0034] The flowcharts shown in the accompanying drawings are only exemplary illustrations and do not necessarily include all content and operations / steps, nor do they necessarily have to be executed in the order described. For example, some operations / steps can be decomposed, while some operations / steps can be combined or partially combined, so the actual execution order may change according to the actual situation.

[0035] As used in this application, "a plurality of" means two or more. "And / or" describes the association relationship of associated objects and indicates that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally represents an "or" relationship between the associated objects before and after.

[0036] First of all, it should be noted that resistance spot welding (RSW) is an efficient process suitable for automated production and is widely used in the connection of metal sheet components, especially playing an important role in the automotive manufacturing industry. The following is a detailed analysis of the applications of resistance spot welding and common defects in quality inspection. Resistance spot welding generates high heat in the metal joint area by applying current and pressure, melting and bonding metal components together. This process has the advantages of high speed, high efficiency, easy automation, and high cost-effectiveness, so it is widely used in multiple fields: Automotive industry: Resistance spot welding is one of the indispensable processes in automotive manufacturing. It is used to connect multiple components of the vehicle body, such as doors, roofs, and floors, ensuring the overall strength and safety of the vehicle; Transportation: In addition to automobiles, resistance spot welding is also applied in the manufacturing of truck trailers, buses, recreational vehicles, and railway vehicles for connecting various metal components; Furniture and appliances: In the manufacturing of office furniture and appliances, resistance spot welding is also commonly used to connect metal components, improving the stability and durability of products; Aerospace: Although the aerospace field has extremely high requirements for welding quality, resistance spot welding still plays an important role in the connection of certain components, such as some metal sheet components of aircraft structures.

[0037] Multiple defects may be found in the quality inspection of resistance spot welding, and these defects may affect the strength and reliability of the welded joints. The following are some common defect types: Incomplete fusion: Too small welding current or too short welding time may result in incomplete melting of the solder joints, forming incomplete fusion. The solder joints with incomplete fusion have insufficient strength and are prone to fracture under stress; Burn-through of the solder joint: Too large welding current, insufficient electrode pressure, or too long welding time may cause the solder joint to burn through. The burned-through solder joint will damage the structural integrity of the metal component and reduce the strength of the welded joint; Distortion of the solder joint: Too large spot welding current and electrode pressure, or too small cross-sectional size of the electrode tip may cause the solder joint to be distorted. The distorted solder joint will affect the appearance quality and assembly accuracy of the product; Excessive indentation: Long-term use of the electrode or poor cooling effect may lead to excessive indentation of the solder joint. The solder joint with excessive indentation will weaken the thickness of the metal component and reduce its load-bearing capacity; Deviation of the solder joint position: The deviation of the solder joint position from the specified position will affect the strength and stability of the welded joint. Especially in automotive manufacturing, the deviation of the solder joint position may cause instability of the vehicle body structure; Edge solder joint: When the solder joint is not included by the edge of the metal sheet, it will greatly reduce the strength of the solder joint. Edge solder joints are usually caused by not considering the solder joint edge distance during the design of the solder joint or the carelessness of the operator.

[0038] To ensure the quality of resistance spot welding, a series of quality control measures should be taken, including pre-welding prevention, quality control during the welding process, and post-welding finished product inspection, etc. These measures help to detect and eliminate welding defects in a timely manner, improving the reliability and safety of products.

[0039] Figure 1 This is a schematic diagram of the implementation environment for fully demonstrating spot welding quality detection in the body production process shown in an exemplary embodiment of the present application. As Figure 1 shown, during the body production process, the spot welding images of a target spot weld at multiple orientations can be collected by the relevant image acquisition device 110, and then the welding signal corresponding to the target spot weld can be collected by the corresponding welding group control system 120. The welding signal includes the curve data corresponding to the welding signal of the target spot weld. Furthermore, the spot welding images collected by the image acquisition device 110 and the welding signals collected by the welding group control system 120 can be sent to the server 130, so that the server 130 can perform data fusion on the spot welding images and the welding signals to obtain the fused spot weld data. Then, by training and learning the data distribution of the spot welding images and the change characteristics of the spot welding signals, the multi-modal spot welding quality detection model comprehensively judges the spot weld quality and outputs the spot weld detection result, thereby realizing the quality detection of the spot welds.

[0040] Among them, Figure 1 the server 130 shown is a server. For example, it can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. There is no limitation here either. The image acquisition device 110 and the welding group control system 120 can communicate with the navigation server 220 through wireless networks such as 3G (third-generation mobile information technology), 4G (fourth-generation mobile information technology), 5G (fifth-generation mobile information technology), and MQTT (Message Queuing Telemetry Transport). There is no limitation here either.

[0041] Resistance spot welding involves complex interactions between electromagnetic, thermal, mechanical, fluid flow, and metallurgical phenomena at the joint interface. This process is difficult to control properly. The quality of the spot welds is not only manifested in the appearance of the spot welds. For internal defects in the spot welds, such as cracks and pores, a single type of image data is difficult to effectively detect. These internal defects have an important impact on the quality and performance of the spot welds, but the quality of the spot welds cannot be accurately judged only by the surface images. Therefore, how to accurately detect the quality of the spot welds is an urgent problem to be solved at present.

[0042] The problems pointed out above are generally applicable in common spot welding scenarios. To solve these problems, embodiments of the present application respectively propose a spot welding quality detection method, a spot welding quality detection device, an electronic device, a computer-readable storage medium, and a computer program product. The following will describe these embodiments in detail.

[0043] Please refer to Figure 2 , Figure 2 which is a flowchart of the spot welding quality detection method shown in an exemplary embodiment of the present application. This method can be applied to Figure 1 the real-time environment shown in , and is specifically executed by the server 130 in this implementation environment. It should be understood that this method can also be applicable to other exemplary implementation environments and be specifically executed by devices in other implementation environments. This embodiment does not limit the implementation environment applicable to this method.

[0044] As Figure 2 shown, in an exemplary embodiment, the spot welding quality detection method at least includes steps S210 to S240, which are introduced in detail as follows:

[0045] Step S210, obtain a solder joint image of the target solder joint, where the solder joint image includes images of multiple orientations of the target solder joint.

[0046] Specifically, first, according to the actual application scenario, an appropriate industrial camera can be selected according to the size, shape, and required resolution of the solder joint. Then, according to the parameters of the camera and the observation distance of the solder joint, an appropriate lens focal length can be selected, and an appropriate light source illumination system can be designed to ensure that the solder joint can be clearly imaged in different orientations. This may require considering various light source types (such as LEDs, halogen lamps, etc.) and illumination methods (such as direct illumination, diffuse illumination, etc.). Then, to obtain images of multiple orientations of the solder joint, multiple cameras can be installed, or the relative positions of the camera and the solder joint can be moved to achieve this, so as to ensure that the features of the solder joint can be clearly captured in the images of each orientation. If multiple cameras are used for simultaneous acquisition, it is necessary to ensure that they can be synchronously triggered so that the images of multiple orientations can be accurately registered and fused subsequently.

[0047] After the solder joint image is collected, it is necessary to perform denoising processing on the collected image to remove interference caused by factors such as uneven illumination and camera noise, and perform enhancement processing on the image, such as contrast enhancement, sharpening, etc., to improve the visibility of the solder joint features.

[0048] In addition, in some feasible embodiments, feature points or feature lines of the solder joints can also be extracted from the images in each orientation. After that, the images in different orientations are registered by using the feature points or feature lines, that is, they are aligned to the same coordinate system. Finally, the registered images in multiple orientations are fused to generate a synthetic image containing all-round information of the solder joints.

[0049] Step S220: Obtain the welding signal corresponding to the target solder joint. The welding signal includes welding signal curve data.

[0050] Specifically, ensure that the welding group control system is correctly installed and configured, including components such as the software system, server, welding parameter collector, and network (wired or wireless). Check whether the connections between the system components are stable and reliable to ensure the accuracy and real-time performance of data transmission. Set the welding parameters of the welding machine according to the welding process requirements, such as current, voltage, welding speed, etc. Ensure that the communication interface between the welding machine and the welding group control system is connected properly and can transmit welding signals in real time. Then, start the system and connect to the server by opening the software interface of the welding group control system. Select the target solder joint on the software interface and set the corresponding acquisition parameters, such as sampling frequency, acquisition time, etc. Start the welding operation of the welding machine. The welding group control system starts to collect welding signals in real time, including parameters such as welding current and voltage. The system records these parameters in the form of curve data and displays them on the software interface. If it is necessary to export the welding signal curve data for further analysis, the export function can be selected on the software interface to save the data as files in formats such as Excel and CSV.

[0051] Step S230: Preprocess the solder joint image and the welding signal, and perform data fusion on the preprocessed solder joint image and the preprocessed welding signal curve data to obtain the fused solder joint data.

[0052] Specifically, use filtering algorithms (such as Gaussian filtering, mean filtering, etc.) to remove noise in the image and improve image quality. For specific noise types in the solder joint image (such as speckle noise, salt-and-pepper noise, etc.), select the corresponding denoising algorithm to extract key features from the solder joint image, such as the shape, size, position, etc. of the solder joint, and use image processing algorithms (such as edge detection, contour extraction, etc.) to extract these features. Filter the welding signal to remove high-frequency noise and interference, select the appropriate filter type (such as low-pass filter, band-pass filter, etc.), and adjust the parameters of the filter. Extract key features from the welding signal, such as the maximum value, minimum value, average value, etc. of the welding current, which can reflect the stability of the welding process and the quality of the solder joint. Align the preprocessed solder joint image and welding signal in time or space, which can ensure that the image and signal have a consistent reference system during fusion. Fuse the features extracted from the solder joint image and welding signal, and feature splicing, feature selection, or feature dimensionality reduction and other methods can be used to achieve feature fusion, and then select the appropriate data fusion algorithm, such as weighted average, Bayesian fusion, neural network fusion, etc., and adjust the parameters and models of the fusion algorithm according to the actual application scenario and data characteristics.

[0053] Step S240, determine the quality inspection result of the target solder joint based on the fused solder joint data.

[0054] Specifically, first, parse the fused solder joint data, including solder joint image information and welding signal information, and extract the geometric features of the solder joint (such as size, shape, position, etc.) and the parameter features of the welding process (such as current, voltage, welding time, etc.). Using image processing technology and signal processing technology, further extract the key features of the solder joint, which may include the edge contour, gray distribution, texture features, etc. of the solder joint, as well as the waveform features and spectral features of the welding signal. According to the requirements of the welding process and industry standards, formulate the solder joint quality assessment criteria, which may include the size range of the solder joint, shape requirements, stability indicators of the welding process, etc. Corresponding thresholds or ranges can also be set for each assessment criterion. For example, the size of the solder joint should be within a certain range, and the current fluctuation during the welding process should be within a certain range, etc. Compare the extracted solder joint features with the assessment criteria to determine whether the solder joint meets the quality requirements, and the matching can be performed by calculating the deviation or similarity between the feature value and the threshold.

[0055] In this embodiment, by performing data fusion processing on the spot welding joint image and the welding signal, the advantages of both types of data can be fully utilized to improve the comprehensiveness and accuracy of detection. Moreover, the data fusion technology can also achieve information complementarity and redundancy elimination, further simplifying the detection process and improving the detection efficiency. Additionally, by fusing the spot welding data of two modalities to determine the quality detection result of the target welding joint, timely feedback can be provided for the adjustment and optimization of the production process, thereby improving the product quality and production efficiency.

[0056] Further, based on the above embodiment, please refer to Figure 3 , in one of the exemplary embodiments provided by the application, the above welding signal curve data includes a welding current curve, a welding voltage curve, and a dynamic resistance curve. The specific implementation process of the above welding quality detection method may further include step S310 and step S320, which are introduced in detail as follows:

[0057] Step S310: Determine the welding process parameters of the target welding joint based on the welding current curve, the welding voltage curve, and the dynamic resistance curve. The welding process parameters include the welding parameters that can be controlled or measured during the welding process.

[0058] Step S320: Determine the welding signal characteristics of the target welding joint based on the welding process parameters.

[0059] Specifically, the welding current is one of the key parameters in the welding process, which directly affects the penetration depth, width, and welding speed of the weld. By analyzing the welding current curve, key information such as the current peak value, average value, and fluctuation range during the welding process can be obtained, and these information are helpful for judging the stability of the welding process and the forming quality of the weld. And the welding voltage is another important welding parameter, which affects the width and penetration depth of the weld. By analyzing the welding voltage curve, the voltage change situation during the welding process can be understood, including the voltage stability and fluctuation range. The change of the voltage curve can also reflect the stability of the welding arc and the melting state of the welding material. Also, the dynamic resistance is the curve of the resistance of the welding point changing with time during the welding process, which reflects information such as the melting, deformation, and deformation rate of the welding point. By analyzing the dynamic resistance curve, the melting state of the welding point, the heat input situation during the welding process, and potential problems of the welding quality can be judged.

[0060] Furthermore, by combining the welding current curve and the welding voltage curve, the relationship characteristics between them can be analyzed. For example, observing whether the current and voltage change synchronously, and the phase difference between them, etc. These characteristics help to judge the stability of the welding process and the stability of the arc. By analyzing the change trend and fluctuation range of the dynamic resistance curve, the melting state of the welding point and the heat input situation during the welding process can be obtained. For example, observing whether the dynamic resistance gradually decreases over time and whether there are abnormal fluctuations, etc. By comprehensively analyzing the welding current curve, the welding voltage curve and the dynamic resistance curve, the stability of the welding process can be evaluated. For example, observing whether there are abnormal fluctuations or mutations in these curves and their correlations, etc. The stability characteristics are of great significance for judging the quality of the welding and optimizing the welding process.

[0061] In this embodiment, by real-time monitoring the changes in welding current, welding voltage and dynamic resistance, the key parameters during the welding process can be accurately controlled to ensure the stability and consistency of the welding process. And by accurately obtaining the welding process parameters, parameters such as the penetration depth and width of the weld of the solder joint can be clearly known, and the overall quality of the solder joint can be accurately determined.

[0062] Furthermore, based on the above embodiment, please refer to Figure 4 , in one of the exemplary embodiments provided in this application, the specific implementation process of the above welding quality detection method may further include step S410 and step S420, which are introduced in detail as follows:

[0063] Step S410, input the welding current curve, the welding voltage curve and the dynamic resistance curve into the time-domain convolutional network model;

[0064] Step S420, perform a convolution operation on the welding current curve, the welding voltage curve and the dynamic resistance curve through the time-domain convolutional network model to obtain the solder joint characteristics of the target solder joint.

[0065] Specifically, during the welding process, in order to accurately evaluate the welding quality and optimize the welding process, it is necessary to monitor and analyze the key parameters in real time during the welding process. Among them, welding current, welding voltage, and dynamic resistance are important parameters reflecting the welding state. In order to effectively extract the solder joint features from these parameters, a time-domain convolutional network model is adopted. First, the welding current curve, welding voltage curve, and dynamic resistance curve collected in real time during the welding process are used as input data. Among them, these data are usually presented in the form of time series and contain the dynamic change information during the welding process. Next, these input data are input into the time-domain convolutional network model. Among them, the time-domain convolutional network model is a neural network specifically designed to process time series data and has strong feature extraction capabilities. Inside the model, through multiple convolutional operations, the welding current curve, welding voltage curve, and dynamic resistance curve can be deeply mined to extract the key features among them.

[0066] Specifically, the convolutional operation is achieved by sliding a series of filters (also called convolutional kernels) over the input data and calculating the dot product between the filter and the input data. These filters can capture the local features in the input data and gradually construct a higher-level feature representation through multiple convolutional operations. In the time-domain convolutional network model, multiple convolutional layers are adopted to gradually extract the features in the input data. Each convolutional operation outputs a feature map, which contains the feature representations of the input data at different scales. By stacking multiple convolutional layers, a deep feature extraction network can be constructed to achieve a comprehensive analysis of the welding current curve, welding voltage curve, and dynamic resistance curve. Finally, after the convolutional operation of the time-domain convolutional network model, the solder joint features of the target solder joint can be obtained. These features contain the key information during the welding process and can be used for aspects such as evaluating the welding quality, predicting welding defects, and optimizing the welding process.

[0067] Exemplarily, in some realizable embodiments, the welding process parameters of the target solder joint further include: serial number, preparation time, pre-pressure time, preheating time, pulse frequency, cooling time, program number, welding time, holding time, resistance curve, current curve, voltage curve, etc. Furthermore, these process parameters can be input into the time-domain convolutional network model, and then the welding signal features corresponding to the target solder joint can be extracted through the time-domain convolutional network model.

[0068] In this embodiment, the method of extracting the solder joint features by inputting the welding current curve, welding voltage curve, and dynamic resistance curve into the time-domain convolutional network model for convolutional operation has significant beneficial effects in improving the accuracy and efficiency of feature extraction, enhancing the generalization ability of the model, supporting the intelligent monitoring and diagnosis of the welding process, and promoting the intelligent development of welding technology.

[0069] Further, based on the above embodiments, please refer to Figure 5 , in one exemplary embodiment provided by the present application, the specific implementation process of the above spot welding quality detection method may further include step S510 and step S520, which are introduced in detail as follows:

[0070] Step S510, obtain the solder joint coordinate data corresponding to the target solder joint;

[0071] Step S520, extract the solder joint image features of the target solder joint based on the solder joint coordinate data and the solder joint image.

[0072] Specifically, it is first necessary to accurately obtain the solder joint coordinate data corresponding to the target solder joint. This step is crucial because it directly determines the accuracy of subsequent image processing and feature extraction. Specifically, an advanced machine vision system or a positioning sensor in an automated welding device can be used to perform high-precision scanning and positioning of the welded workpiece, and then through a series of complex algorithms and calculations, the system can automatically identify the exact position of the target solder joint and output the corresponding solder joint coordinate data.

[0073] After successfully obtaining the solder joint coordinate data of the target solder joint, the solder joint image features of the target solder joint can be extracted based on these data and the solder joint image. In this process, image processing techniques are usually involved, such as image enhancement, filtering, edge detection, etc. First, using the obtained solder joint coordinate data, accurately intercept the local image area containing the target solder joint in the original solder joint image. Then, preprocess this local image area to improve the image quality and the accuracy of feature extraction. Next, feature extraction algorithms, such as SIFT (Scale-Invariant Feature Transform), SURF (Speeded-Up Robust Features), etc., can be used to extract various image features of the target solder joint, such as shape features, texture features, color features, etc.

[0074] These extracted solder joint image features can not only be used for subsequent welding quality evaluation, but also as the basis for real-time monitoring and control during the welding process. For example, the extracted features can also be compared with the preset standard features to determine whether the quality of the solder joint meets the standard. If it is found that the feature deviation is large, an alarm can be issued in a timely manner or the welding parameters can be adjusted to ensure the stability of the welding process and the consistency of product quality.

[0075] In addition, in some realizable embodiments, the welding quality of the template solder joint is directly determined according to the extracted solder joint image features. For example, when there are particularly obvious defects in the solder joint image features, the welding quality of the target solder joint can be directly determined according to the solder joint image features.

[0076] In this embodiment, the method of obtaining the solder joint coordinate data corresponding to the target solder joint and extracting the solder joint image features based on the coordinate data and the solder joint image has remarkable effects in improving the accuracy of solder joint positioning, optimizing the extraction of solder joint image features, supporting the intelligent detection of solder joint quality, and promoting the automation and intelligence of the welding process.

[0077] Further, based on the above embodiment, please refer to Figure 6 , in one exemplary embodiment provided by the present application, the specific implementation process of extracting the solder joint image features of the target solder joint based on the solder joint coordinate data and the solder joint image may further include step S610 and step S620, which are introduced in detail as follows:

[0078] Step S610, extract the solder joint shape and the solder joint position of the target solder joint from the solder joint image based on the solder joint coordinate data;

[0079] Step S620, determine the solder joint image features of the target solder joint based on the solder joint shape and the solder joint position.

[0080] Specifically, the local area of the target solder joint can be extracted from the solder joint image by using the solder joint coordinate position, and in the intercepted local image, image processing techniques such as edge detection and contour extraction can be used to identify the shape of the target solder joint. The shape features include the contour line, area, perimeter, etc. of the solder joint, which can intuitively reflect the appearance of the solder joint. Of course, based on the solder joint coordinate data, the specific position of the target solder joint is also determined in the image, and the position information is of great significance for evaluating the stability and consistency of the welding process.

[0081] Further, after successfully extracting the shape and position of the target solder joint, the image features of the solder joint are determined by combining this information. These features include but are not limited to: shape features, such as the symmetry, regularity, aspect ratio, etc. of the solder joint, which can reflect the geometric shape and stability of the solder joint; position features, such as the offset and angle of the solder joint relative to the reference point, which can evaluate the positioning accuracy and consistency during the welding process; texture features, if there are obvious texture or color changes on the surface of the solder joint, these features can also be extracted by image processing techniques to further evaluate the quality of the solder joint; these solder joint image features not only provide an important basis for the evaluation of welding quality, but also can be used as a reference for real-time monitoring and control during the welding process. For example, when it is found that the shape or position features of the solder joint deviate from the preset range, an alarm can be issued in time, the welding parameters can be adjusted or manual intervention can be carried out to ensure the stability of the welding process and the consistency of the product quality.

[0082] In this embodiment, the method of extracting the solder joint shape and solder joint position of the target solder joint from the solder joint image based on the solder joint coordinate data and determining the solder joint image features has remarkable effects in improving the accuracy of solder joint recognition, optimizing the spot welding quality detection process, supporting the intelligent recognition of solder joint defects, and promoting the intelligent development of welding technology, etc.

[0083] Further, based on the above embodiment, please refer to Figure 7 , in one exemplary embodiment provided by the present application, the specific implementation process of the above welding quality detection method may further include steps S710 to S730, which are introduced in detail as follows:

[0084] Step S710, extract the physical features of the target solder joint from the solder joint features, and extract the visual features of the target solder joint from the solder joint image features.

[0085] Specifically, the physical features mainly refer to the physical properties of the solder joint itself, such as size, weight, hardness, etc. These features can be obtained through professional measurement equipment and experimental methods. During the welding process, sensors or detection instruments, such as laser rangefinders, electronic balances, hardness testers, etc., can be used to accurately measure the target solder joint to obtain its physical features. In addition, the physical features of the solder joint can also be indirectly obtained by analyzing the parameters during its welding process. For example, by monitoring parameters such as welding current, voltage, and welding time, physical properties such as the molten pool depth and fusion ratio of the solder joint can be inferred. These features can reflect the microstructure and performance of the solder joint and are of great significance for evaluating welding quality. The visual features mainly refer to the performance of the solder joint in the image, such as shape, color, texture, etc. These features can be extracted through image processing techniques. For example, for shape features: through image processing algorithms such as edge detection and contour extraction, the shape features of the solder joint can be extracted from the solder joint image. These features include the contour line, area, perimeter, etc. of the solder joint, which can intuitively reflect the appearance of the solder joint. Color features: If there are obvious color changes on the surface of the solder joint, such as oxidation, burning, etc., the color features of the solder joint can be extracted through methods such as color space conversion and color histogram statistics. These features can reflect the surface state and heat influence degree of the solder joint. Texture features: The texture features of the solder joint surface can be extracted through texture analysis algorithms. These features include the thickness, direction, uniformity, etc. of the texture, which can reflect the microstructure and material properties of the solder joint surface.

[0086] Step S720, perform data fusion on the physical features and visual features to obtain a fusion result;

[0087] Specifically, before data fusion, physical features and visual features need to be preprocessed. This includes steps such as data cleaning, denoising, and standardization to ensure the accuracy and consistency of the data. Then, since physical features and visual features may contain a large amount of information, it is necessary to select the most valuable features for welding quality assessment for fusion. This can be achieved through feature selection algorithms such as mutual information and correlation coefficient. Selecting an appropriate data fusion method is the key to effectively fusing physical features and visual features. Common data fusion methods include weighted average method, principal component analysis (PCA), support vector machine (SVM), etc. These methods can combine physical features and visual features according to the correlation and importance between features, thus generating more representative fusion features.

[0088] Step S730, if the fusion result meets the preset fusion data requirements, then obtain the fused solder joint data based on the fusion result.

[0089] Specifically, the fused result after fusion can be compared with the preset fusion data requirements. Among them, the comparison includes the accuracy, integrity, consistency, real-time performance, security, etc. of the data. That is to say, if the fusion result meets the preset fusion data requirements, then it can be considered that the fusion is successful and the fused data is reliable. In this case, the fused solder joint data can be obtained based on the fusion result. These data may be more comprehensive and accurate, which is helpful for subsequent analysis, decision-making, or optimization.

[0090] In this embodiment, by extracting physical features and visual features from solder joint features and performing data fusion, it has significant effects in comprehensively reflecting the characteristics of solder joints, improving the efficiency and accuracy of data processing, supporting the intelligent assessment of solder joint quality, and promoting the intelligent development of welding technology.

[0091] Further, based on the above embodiment, please refer to Figure 8 , in one of the exemplary embodiments provided in the present application, the specific implementation process of the above spot welding quality detection method may further include steps S810 to S830, which are introduced in detail as follows:

[0092] Step S810, establish a preset spatio-temporal mapping relationship between physical features and visual features.

[0093] Specifically, in order to evaluate the accuracy and effectiveness of the fusion result, the fusion features are matched with the preset spatio-temporal mapping relationship, which includes judging whether the fusion features meet the requirements of different stages of the welding process in the time dimension, and judging whether the fusion features match the position and distribution characteristics of the solder joints in the space dimension.

[0094] Among them, the time mapping relationship refers to establishing a mapping relationship in terms of time according to the requirements of the welding process and the variation law of the solder joint quality. This can include the correspondence between different stages in the welding process (such as preheating, fusion, cooling, etc.) and the solder joint quality characteristics; the space mapping relationship refers to establishing a mapping relationship in terms of space according to the position and distribution characteristics of the solder joints on the workpiece. This can include the correspondence between spatial characteristics such as the relative positions between solder joints, the distances between solder joints and the workpiece edges, etc. and the quality characteristics.

[0095] Then, select the most valuable features for welding quality assessment from the collected physical features and visual features for mapping, and select an appropriate mapping method, such as regression analysis, neural network, support vector machine, etc., to associate the physical features with the visual features. These methods can establish a mapping relationship between the physical features and the visual features according to the correlation and importance between the features.

[0096] Step S820, determine the correlation relationship between the physical features and the visual features in terms of time and space based on the preset spatio-temporal mapping relationship;

[0097] Step S830, determine the quality detection result of the target solder joint based on the correlation relationship and the fused solder joint data.

[0098] Specifically, using the preset spatio-temporal mapping relationship, the correspondence between the change of physical features (such as welding temperature, pressure, etc.) over time and the time points when visual features (such as weld color, texture, etc.) appear can be identified. For example, the high-temperature welding stage may correspond to specific color changes or texture formations of the weld. Similarly, the distribution of physical features at different positions of the weld can be determined corresponding to the visual features in space. For example, the change of welding pressure may produce different visual effects in different weld regions, such as the width, depth of the weld or the smoothness of the surface. Combine the fused solder joint data with the spatio-temporal correlation relationship for comprehensive analysis. This may involve weighting, normalizing or other forms of processing of the physical feature data and the visual feature data to more accurately reflect the welding quality.

[0099] Exemplarily, based on the known welding quality standards and historical data, establish one or more quality assessment models. These models can be rule-based, statistical or machine learning-based, and are used to convert the fused solder joint data and the spatio-temporal correlation relationship into specific quality detection results. Among them, the output quality detection results may include information such as the grade of welding quality, whether it is qualified, the types and positions of existing defects, etc.

[0100] In this embodiment, matching the physical features and visual features on a preset spatio-temporal mapping relationship and generating the fused solder joint data based on the matching result are of great significance for the quality control of the welding process. It can not only improve the accuracy and reliability of the welding quality assessment, but also provide strong support for the real-time monitoring and control of the welding process. At the same time, this method can also assist relevant personnel in discovering potential problems in the welding process, making timely adjustments and optimizations, thereby improving the stability and consistency of the welding process.

[0101] Figure 9 It is a schematic diagram of the brief process for spot welding quality detection in an exemplary application scenario. In the application scenario shown in 9, obtain the solder joint image of the target solder joint, where the solder joint image includes images of multiple orientations of the target solder joint; obtain the welding signal corresponding to the target solder joint, where the welding signal includes welding signal curve data; perform convolution operations on the welding current curve, welding voltage curve, and dynamic resistance curve through a time-domain convolutional network model to obtain the solder joint features of the target solder joint; extract the solder joint image features of the target solder joint based on the solder joint coordinate data and the solder joint image. Extract the physical features of the target solder joint from the solder joint features, and extract the visual features of the target solder joint from the solder joint image features; perform data fusion on the physical features and visual features to obtain a fusion result; if the fusion result meets the preset fusion data requirements, obtain the fused solder joint data based on the fusion result. Establish a preset spatio-temporal mapping relationship between the physical features and visual features; determine the association relationship between the physical features and visual features in terms of time and space based on the preset spatio-temporal mapping relationship; determine the quality detection result of the target solder joint based on the association relationship and the fused solder joint data. For the detailed implementation process, please refer to the descriptions in the foregoing embodiments, and details will not be repeated here.

[0102] Figure 10 is a block diagram of a spot welding quality detection device shown in an exemplary embodiment of the present application. This device can be applied to Figure 1 the implementation environment shown, and is specifically configured in the server 130. This device can also be applicable to other exemplary implementation environments and be specifically configured in other devices. This embodiment does not limit the implementation environment applicable to this device.

[0103] As Figure 10As shown, the exemplary spot welding quality detection device includes: a first acquisition module 1010, configured to acquire a solder joint image of a target solder joint, where the solder joint image includes images of all orientations of the target solder joint; a second acquisition module 1020, configured to acquire a welding signal corresponding to the target solder joint, where the welding signal includes welding signal curve data; a fusion module 1030, configured to preprocess the solder joint image and the welding signal, and perform data fusion on the preprocessed solder joint image and the preprocessed welding signal curve data to obtain fused solder joint data; and a determination module 1040, configured to determine a quality detection result of the target solder joint based on the fused solder joint data.

[0104] According to one aspect of the embodiments of the present application, the above-mentioned second acquisition module 1020 is further configured to determine welding process parameters of the target solder joint based on a welding current curve, a welding voltage curve, and a dynamic resistance curve, where the welding process parameters include welding parameters that can be controlled or measured during the welding process; and determine welding signal characteristics of the target solder joint based on the welding process parameters.

[0105] According to one aspect of the embodiments of the present application, the above-mentioned second acquisition module 1020 is further configured to input the welding current curve, the welding voltage curve, and the dynamic resistance curve into a time-domain convolutional network model; and perform a convolution operation on the welding current curve, the welding voltage curve, and the dynamic resistance curve through the time-domain convolutional network model to obtain solder joint characteristics of the target solder joint.

[0106] According to one aspect of the embodiments of the present application, the above-mentioned first acquisition module 1010 is further configured to acquire solder joint coordinate data corresponding to the target solder joint; and extract solder joint image characteristics of the target solder joint based on the solder joint coordinate data and the solder joint image.

[0107] According to one aspect of the embodiments of the present application, the above-mentioned first acquisition module 1010 is further configured to extract the solder joint shape and the solder joint position of the target solder joint from the solder joint image based on the solder joint coordinate data; and determine solder joint image characteristics of the target solder joint based on the solder joint shape and the solder joint position.

[0108] According to one aspect of the embodiments of the present application, the above-mentioned fusion module 1030 is further configured to extract physical characteristics of the target solder joint from the solder joint characteristics, and extract visual characteristics of the target solder joint from the solder joint image characteristics; perform data fusion on the physical characteristics and the visual characteristics to obtain a fusion result; and if the fusion result meets a preset fusion data requirement, obtain fused solder joint data based on the fusion result.

[0109] According to one aspect of the embodiments of the present application, the above-mentioned determination module 1040 is further configured to establish a preset spatio-temporal mapping relationship between physical features and visual features; determine the association relationship between the physical features and the visual features in terms of time and space based on the preset spatio-temporal mapping relationship; and determine the quality inspection result of the target solder joint based on the association relationship and the fused solder joint data.

[0110] It should be noted that the spot welding quality inspection device provided in the above embodiment and the spot welding quality inspection method provided in the above embodiment belong to the same concept. The specific manners in which each module and unit perform operations have been described in detail in the method embodiment, and will not be elaborated herein. In practical applications, the spot welding quality inspection device provided in the above embodiment may, according to needs, allocate the above functions to different functional modules, that is, divide the internal structure of the device into different functional modules to complete all or part of the functions described above. This is not limited herein either.

[0111] Embodiments of the present application further provide an electronic device, including: one or more processors; a storage device for storing one or more programs, which, when executed by the one or more processors, cause the electronic device to implement the spot welding quality inspection methods provided in the above various embodiments.

[0112] Figure 11 The structural schematic diagram of a computer system of an electronic device suitable for implementing the embodiments of the present application is shown. It should be noted that Figure 11 The shown computer system 1100 of the electronic device is only an example and should not impose any limitation on the functions and usage scope of the embodiments of the present application.

[0113] As Figure 11 shown, the computer system 1100 includes a central processing unit (CPU) 1101, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 1102 or the program loaded from the storage section 1108 into the random access memory (RAM) 1103, such as executing the method described in the above embodiment. In the RAM 1103, various programs and data required for system operation are also stored. The CPU 1101, the ROM 1102, and the RAM 1103 are connected to each other through a bus 1104. The input / output (I / O) interface 1105 is also connected to the bus 1104.

[0114] The following components are connected to the I / O interface 1105: an input section 1106 including a keyboard, a mouse, etc.; an output section 1107 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc. and a speaker, etc.; a storage section 1108 including a hard disk, etc.; and a communication section 1109 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 1109 performs communication processing via a network such as the Internet. A drive 1110 is also connected to the I / O interface 1105 as needed. A removable medium 1111, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1110 as needed so that a computer program read therefrom is installed into the storage section 1108 as needed.

[0115] Specifically, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product that includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 1109, and / or installed from the removable medium 1111. When the computer program is executed by a central processing unit (CPU) 1101, various functions defined in the system of the present application are executed.

[0116] It should be noted that the computer-readable medium shown in the embodiments of the present application may be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable computer program. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. The computer program included on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0117] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present application. Among them, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the above module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order from that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, as well as the combination of blocks in the block diagram or flowchart, may be implemented by a dedicated hardware-based system for performing the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0118] The units involved in the embodiments described in this application can be implemented in software or in hardware, and the described units can also be provided in a processor. Among them, the names of these units do not, in some cases, constitute a limitation on the units themselves.

[0119] Another aspect of this application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the spot welding quality detection method as described above is implemented. The computer-readable storage medium may be included in the electronic device described in the above embodiments, or may exist alone without being assembled into the electronic device.

[0120] Another aspect of this application also provides a computer program product or a computer program. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the spot welding quality detection method provided in the above various embodiments.

[0121] The above content is only a preferred exemplary embodiment of this application and is not used to limit the implementation of this application. Those of ordinary skill in the art can easily make corresponding adaptations or modifications according to the main concept and spirit of this application. Therefore, the protection scope of this application should be subject to the protection scope required by the claims.

Claims

1. A spot welding quality detection method, characterized in that: include: Acquire a welding spot image of a target welding spot, wherein the welding spot image includes images of the target welding spot in multiple orientations; Acquire a welding signal corresponding to the target welding point, wherein the welding signal includes welding signal curve data; Preprocessing the welding spot image and the welding signal, fusing the preprocessed welding spot image and the preprocessed welding signal curve data to obtain fused welding spot data; The quality inspection result of the target solder joint is determined based on the fused solder joint data.

2. The method according to claim 1, characterized in that The welding signal curve data includes a welding current curve, a welding voltage curve and a dynamic resistance curve, and the method further includes: Determine welding process parameters of the target welding spot based on the welding current curve, the welding voltage curve, and the dynamic resistance curve, wherein the welding process parameters include welding parameters that can be controlled or measured during the welding process; A welding signal characteristic of the target weld is determined based on the welding process parameters.

3. The method according to claim 2, characterized in that The method further comprises: Inputting the welding current curve, the welding voltage curve and the dynamic resistance curve into a time domain convolutional network model; The welding current curve, the welding voltage curve and the dynamic resistance curve are convolved by the time domain convolution network model to obtain the welding point characteristics of the target welding point.

4. The method according to claim 1, characterized in that The method further comprises: Acquire welding point coordinate data corresponding to the target welding point; A solder point image feature of the target solder point is extracted based on the solder point coordinate data and the solder point image.

5. The method according to claim 4, characterized in that The step of extracting the solder joint image feature of the target solder joint based on the solder joint coordinate data and the solder joint image comprises: Extracting the solder joint shape and solder joint position of the target solder joint from the solder joint image based on the solder joint coordinate data; A solder joint image feature of the target solder joint is determined based on the solder joint shape and the solder joint position.

6. The method according to any one of claims 1 to 5, characterized in that: The method further comprises: Extracting physical features of the target solder joint from the solder joint features, and extracting visual features of the target solder joint from the solder joint image features; Performing data fusion on the physical feature and the visual feature to obtain a fusion result; If the fusion result meets the preset fusion data requirement, the fused solder joint data is obtained based on the fusion result.

7. The method according to claim 6, characterized in that The method further comprises: Establishing a preset spatiotemporal mapping relationship between the physical feature and the visual feature; Determining the temporal and spatial association relationship between the physical feature and the visual feature based on the preset spatiotemporal mapping relationship; The quality inspection result of the target solder joint is determined based on the association relationship and the fused solder joint data.

8. A spot welding quality inspection device, characterized in that: The device comprises: A first acquisition module is used to acquire a welding spot image of a target welding spot, wherein the welding spot image includes images of all positions of the target welding spot; A second acquisition module, used to acquire a welding signal corresponding to the target welding point, wherein the welding signal includes welding signal curve data; A fusion module is used to pre-process the welding spot image and the welding signal, and fuse the pre-processed welding spot image and the pre-processed welding signal curve data to obtain fused welding spot data; A determination module is used to determine the quality inspection result of the target solder joint based on the fused solder joint data.

9. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, enables the electronic device to implement the spot welding quality detection method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Computer-readable instructions are stored thereon, and when the computer-readable instructions are executed by a processor of a computer, the computer is enabled to execute the spot welding quality detection method according to any one of claims 1 to 7.

Images