Method, system and device for determining abnormal welding type of welding spot and storage medium

Abstract

The invention discloses a method, system and device for determining an abnormal welding type of a welding spot and a storage medium. The method comprises the steps that to-be-detected data of a welding spot in a vehicle in the welding process are obtained, and the to-be-detected data are at least used for representing the welding state of the welding spot in the welding process; the to-be-detected data are recognized through expert priori knowledge, a recognition result is obtained, and the expert priori knowledge is associated with detected data of a normal welding spot with the normal welding state in the vehicle in the welding process; in response to the identification result, representing that the welding state of the welding spot is an abnormal welding state, performing welding detection on the to-be-detected data to obtain a detection result; and determining an abnormal welding type corresponding to the abnormal welding state based on a detection result. The technical problem that the abnormal welding type of the welding spot cannot be accurately determined is solved.

Description

Technical Field

[0001] This application relates to the field of vehicles, and more specifically, to a method, system, apparatus, and storage medium for determining abnormal welding types of weld joints. Background Technology

[0002] Currently, with the development of modern manufacturing, especially in the automotive industry, welding technology is the main means of connecting metal parts, and its welding quality directly affects the safety and durability of products.

[0003] In related technologies, traditional manual inspection methods for solder joint quality mainly rely on visual inspection and simple mechanical measurements. This method is not only inefficient but also susceptible to the influence of individual skills and fatigue, making it difficult to guarantee consistency and accuracy. Therefore, this method suffers from the technical problem of being unable to accurately determine the abnormal welding type of the solder joint.

[0004] There is currently no effective solution to the above problems. Summary of the Invention

[0005] This application provides a method, system, apparatus, and storage medium for determining abnormal welding types of solder joints, so as to at least solve the technical problem of being unable to accurately determine the abnormal welding types of solder joints.

[0006] According to one aspect of the embodiments of this application, a method for determining the abnormal welding type of a weld joint is provided. The method may include: acquiring inspection data of a weld joint in a vehicle during the welding process, wherein the inspection data is at least used to characterize the welding state of the weld joint during the welding process; using expert prior knowledge to identify the inspection data and obtain an identification result, wherein the expert prior knowledge is associated with the inspection data of a normal weld joint in the vehicle whose welding state is normal during the welding process; in response to the identification result characterizing the welding state of the weld joint as an abnormal welding state, performing welding inspection on the inspection data and obtaining an inspection result; and determining the abnormal welding type corresponding to the abnormal welding state based on the inspection result.

[0007] Optionally, the expert prior knowledge includes at least a reference curve, standard heat, and / or standard energy. The expert prior knowledge is used to identify the data to be tested and obtain identification results, including: running the welding program corresponding to the weld point; retrieving the reference curve corresponding to a normal weld point under the welding program, and based on the reference curve, determining the standard heat and / or standard energy corresponding to the normal weld point; controlling the service layer of the detection system to identify the data to be tested based on the reference curve, standard heat, and / or standard energy, and obtain identification results.

[0008] Optionally, the data to be detected includes at least time-series data and image data. The time-series data is used to characterize the dynamic characteristics of the weld joint during the welding process. The service layer of the control detection system identifies the data to be detected based on a reference curve, standard heat, and / or standard energy to obtain an identification result, including: controlling the service layer to determine a first similarity between the reference curve and the time-series data, and based on the time-series data, determining the energy corresponding to the weld joint, and / or the heat corresponding to the weld joint; determining a second similarity between the energy and the standard energy, and / or determining a third similarity between the heat and the standard heat; and determining the identification result based on the first similarity, the second similarity, and / or the third similarity.

[0009] Optionally, in response to the identification result indicating that the welding state of the weld point is an abnormal welding state, welding detection is performed on the data to be detected to obtain the detection result, including: in response to the identification result indicating that the welding state of the weld point is an abnormal welding state, calling the anomaly identification model to perform welding detection on the image data to obtain the detection result, wherein the anomaly identification model is trained based on historical detection data of abnormal weld points in the vehicle with abnormal welding states during the welding process.

[0010] Optionally, based on the detection results, the abnormal welding type corresponding to the abnormal welding state is determined, including: based on the detection results, determining the incomplete weld data and weld penetration data of the weld point, wherein the incomplete weld data is used to represent the degree of incomplete weld of the weld point, and the weld penetration data is used to represent the degree of weld penetration of the weld point; and determining the abnormal welding type based on the degree of incomplete weld and the degree of weld penetration.

[0011] According to another aspect of the embodiments of this application, a system for determining the abnormal welding type of a weld joint is also provided. This system may include: a presentation layer for acquiring collected data to be inspected, wherein the data to be inspected is at least used to characterize the welding state of a weld joint in a vehicle during the welding process; an application layer for preprocessing the data to be inspected; a service layer for using expert prior knowledge to identify the data to be inspected and obtain an identification result; in response to the identification result characterizing the welding state of the weld joint as an abnormal welding state, performing welding inspection on the data to be inspected and obtaining a detection result; and determining the abnormal welding type corresponding to the abnormal welding state based on the detection result, wherein the expert prior knowledge is associated with the detected data of normal weld joints in the vehicle whose welding state is normal during the welding process.

[0012] According to another aspect of the embodiments of this application, an apparatus for determining the abnormal welding type of a weld joint is also provided. The apparatus may include: an acquisition unit for acquiring data to be inspected of a weld joint in a vehicle during the welding process, wherein the data to be inspected is at least used to characterize the welding state of the weld joint during the welding process; an identification unit for identifying the data to be inspected using expert prior knowledge to obtain an identification result, wherein the expert prior knowledge is associated with previously inspected data of a normal weld joint in the vehicle whose welding state is normal during the welding process; a detection unit for performing welding inspection on the data to be inspected in response to the identification result characterizing the welding state of the weld joint as an abnormal welding state, to obtain a detection result; and a determination unit for determining the abnormal welding type corresponding to the abnormal welding state based on the detection result.

[0013] According to another aspect of the embodiments of this application, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored program, wherein, when the program is running, it controls the device where the computer-readable storage medium is located to execute the method for determining the abnormal welding type of the solder joint according to the embodiments of this application.

[0014] According to another aspect of the embodiments of this application, a processor is also provided for running a program, wherein the program is executed by the processor to perform the method for determining the abnormal welding type of the solder joint according to the embodiments of this application.

[0015] According to another aspect of the embodiments of this application, a program product is also provided, the program product including computer instructions, wherein when the computer instructions are executed by a processor, they implement the method for determining the abnormal welding type of the solder joint according to the embodiments of this application.

[0016] According to another aspect of the embodiments of this application, a vehicle is also provided, which can be used to perform the method for determining the abnormal welding type of the weld joint according to the embodiments of this application.

[0017] In this embodiment, data to be inspected on weld joints in a vehicle during the welding process is acquired. This data at least characterizes the welding state of the weld joints during the welding process. Prior expert knowledge is used to identify the data, yielding an identification result. This prior expert knowledge is associated with previously inspected data of normal weld joints in the vehicle whose welding state is normal. In response to the identification result indicating an abnormal welding state, welding inspection is performed on the data to be inspected, yielding a detection result. Based on the detection result, the abnormal welding type corresponding to the abnormal welding state is determined. In other words, in this embodiment, data to be inspected on weld joints in a vehicle during the welding process is acquired. Prior expert knowledge is used to identify the data, yielding an identification result. If the identification result indicates an abnormal welding state, welding inspection can be performed on the data to determine the abnormal welding type corresponding to the abnormal welding state. This achieves the technical effect of accurately determining the abnormal welding type of the weld joint and solves the technical problem of not being able to accurately determine the abnormal welding type of the weld joint. Attached Figure Description

[0018] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0019] Figure 1 This is a flowchart of a method for determining the abnormal welding type of a solder joint according to an embodiment of this application;

[0020] Figure 2 This is a schematic diagram of a system for determining abnormal welding types of solder joints according to an embodiment of this application;

[0021] Figure 3 This is a schematic diagram of a device for determining the abnormal welding type of a weld joint according to an embodiment of this application;

[0022] Figure 4 This is a structural block diagram of a computer terminal according to an embodiment of this application;

[0023] Figure 5 This is a block diagram of an electronic device according to an embodiment of the present application of a method for determining abnormal welding types of solder joints. Detailed Implementation

[0024] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0025] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0026] According to an embodiment of this application, an embodiment of a method for determining an abnormal welding type of a solder joint is provided. The steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Although a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than that shown here.

[0027] This embodiment proposes a method for determining the abnormal welding type of a weld joint. The method can acquire the data to be inspected of the weld joint in the vehicle during the welding process; use expert prior knowledge to identify the data to be inspected and obtain the identification result; if the identification result indicates that the welding state of the weld joint is an abnormal welding state, welding inspection can be performed on the data to be inspected to determine the abnormal welding type corresponding to the abnormal welding state of the weld joint. This achieves the technical effect of accurately determining the abnormal welding type of the weld joint and solves the technical problem of not being able to accurately determine the abnormal welding type of the weld joint.

[0028] Figure 1 This is a flowchart of a method for determining the abnormal welding type of a solder joint according to an embodiment of this application. Figure 1 As shown, the method may include the following steps:

[0029] Step S102: Obtain the inspection data of the weld points in the vehicle during the welding process, wherein the inspection data is used at least to characterize the welding status of the weld points during the welding process.

[0030] In the technical solution provided in step S102 of this application, the aforementioned weld point can be a weld point in a vehicle, such as a weld point of a component in a vehicle, or an electric welding weld point in a vehicle. The aforementioned data to be detected can be used to characterize the welding state of the weld point in the vehicle during the welding process. It can be data generated during the welding process, a data set that can be used to characterize the welding state of the weld point, and can at least include time-series data, image data, etc. The aforementioned time-series data can be parameters that change over time during the welding process, such as welding current, voltage, welding pressure, weld point temperature, etc. For example, in a welding record, if the current suddenly drops after the start of welding, this may indicate a potential welding quality problem. The aforementioned image data can be an image of the weld point's appearance acquired by an image acquisition device such as a camera. It can be a single static photograph or continuous video frames. For example, a high-definition image of a weld point showing cracks or pores on the surface of the weld point are signs of abnormal welding. It should be noted that the location of the weld point, the type of data to be detected, and the content of the time-series data are only illustrative examples and are not specifically limited.

[0031] Optionally, during the welding process in the vehicle, data about the weld points can be collected in real time or from historical records. The data to be monitored should include information reflecting the welding status, such as parameters like welding current, voltage, weld temperature, welding time, and welding pressure, as well as possible visual image data, such as images or video recordings of the weld points. This data provides a basis for subsequent analysis and judgment.

[0032] Optionally, current shunting reduces the welding current flowing to the new weld point, and the generated heat may not be sufficient for the weld point to grow to the specified size. Therefore, the welding status of the weld point can be determined by judging the timing current in the timing data. Electrode asymmetry reduces the welding current density and delays the peak value of the main welding resistance, thereby causing a reduction in the weld nugget size. Therefore, the welding quality of the weld point can be determined by inspecting the electrodes.

[0033] Optionally, data on weld points during the welding process can be collected from the vehicle welding production line to obtain data to be inspected. This data can be used to characterize the state of the weld points during the welding process, including but not limited to the dynamic characteristics of the welding process, the appearance quality of the weld points, and related process parameters. For example, it can be time-series data that varies over time, such as welding current, welding voltage, welding time, and welding pressure. Time-series data can be used to reflect the dynamic characteristics of the welding process. The aforementioned data to be inspected may also include image data, which can be an image of the weld point's appearance captured by a camera, including the shape, size, color, and surface roughness of the weld point. The aforementioned data to be inspected may also include acoustic data; the welding state of the weld point can be determined by analyzing the frequency, amplitude, and other characteristics of the sound waves. It should be noted that the data to be inspected here is only an example and is not specifically limited.

[0034] For example, by analyzing the timing data of welding current and voltage, the stability of the welding process and the complete fusion of the weld joint can be assessed. For instance, abnormal fluctuations in current data during welding may indicate an unstable welding condition and questionable weld quality. Furthermore, image data can be used to detect surface defects such as cracks, porosity, dents, and solder overflow. For example, analyzing weld images and discovering multiple micropores on the weld surface may indicate insufficient welding gas shielding or inappropriate solder selection.

[0035] For example, suppose on a car body welding production line, the welding current at a weld point is monitored and suddenly drops during the welding process, then quickly recovers, but fails to reach the expected peak current. This timing data change may indicate a temporary increase in resistance between the weldment components, causing the current drop, which may then recover to near normal, but fails to reach the current level required for sufficient fusion. According to expert prior knowledge, this current timing characteristic is usually associated with a cold weld, meaning the weld point has failed to form sufficient intermetallic bonding, potentially leading to unstable electrical connections. Therefore, the timing data of this weld point is marked as "data to be detected" for further analysis and confirmation using the system's depth detection algorithm. Furthermore, images of the weld point captured by a camera may show slight dents and uneven coloring on the weld point surface; these features are not common in weld points under normal welding conditions. The anomalous features in the image data further support the initial judgment that the weld point may have a welding quality problem.

[0036] Optionally, by collecting and analyzing this data, the system can preliminarily determine the state of the weld joint during the welding process, providing a basis for further in-depth inspection and identification of abnormal welding types. This process is an important component of data-driven decision-making in intelligent welding inspection systems, ensuring the control and optimization of welding quality during vehicle manufacturing.

[0037] Step S104: Use expert prior knowledge to identify the data to be tested and obtain the identification result. The expert prior knowledge is associated with the detected data of normal weld points in the vehicle in the normal welding state during the welding process.

[0038] In the technical solution provided in step S104 of this application, the aforementioned expert prior knowledge can be a series of rules, patterns, or judgment criteria summarized based on professional experience or historical data. It can be used to quickly identify whether the welding state of a weld joint is normal, or it can be determined based on the time-series data of a normal weld joint under normal welding conditions. The identification result can be a conclusion drawn after making a preliminary judgment on the welding data using expert prior knowledge. It can be used to determine whether a weld joint may be in an abnormal welding state, and can be represented by numbers, text, or images. For example, 0 can be used to represent an abnormal welding state, and 1 can be used to represent a normal welding state. Alternatively, by analyzing a segment of welding current time-series data, if current fluctuations are found to exceed the normal range, the identification result may mark the weld joint as "suspected abnormal." It should be noted that this is only an example, and no specific limitations are made on the type of expert prior knowledge, the method of determination, or the form of the identification result.

[0039] For example, expert prior knowledge might suggest that during normal welding, the current at the weld joint typically shows a stable upward trend followed by a gradual decline. Therefore, based on this prior knowledge, if the current at the weld joint drops sharply or fluctuates excessively in the initial stages of welding, it may indicate a problem with the welding condition. Another example is the knowledge that, based on normal welding conditions, the diameter of the weld joint falls within a certain range of the design specifications. A diameter exceeding this range might indicate improper welding parameter settings, leading to substandard weld quality. Therefore, after obtaining image data, this expert prior knowledge can be used to identify the image data and obtain an identification result. This identification result can be used to characterize the weld joint as having abnormal welding quality. It should be noted that this is merely an illustrative example, and no specific limitations are placed on the method of determining the identification result based on expert prior knowledge. Any method that determines the identification result based on expert prior knowledge should be within the scope of protection of this application.

[0040] Optionally, after collecting the data to be tested, expert prior knowledge can be used to perform preliminary identification on the collected data. Expert prior knowledge can be data stored in the form of rule bases, threshold judgments, statistical models, etc., and is associated with the detected data of normal weld points in the vehicle during the welding process. It is used to identify whether the data conforms to the characteristics of a normal welding state. For example, based on the detected data of normal weld points during the welding process, the image data and time series data corresponding to the weld points in a normal welding state can be determined. The obtained image data and time series data can be identified as expert prior knowledge, or expert prior knowledge can be determined based on image data and / or time series data.

[0041] Step S106: In response to the identification result indicating that the welding state of the weld point is an abnormal welding state, welding inspection is performed on the data to be inspected to obtain the inspection result.

[0042] In the technical solution provided in step S106 of this application, the detection result can be used to determine whether the welding state of the solder joint is truly an abnormal welding state, and if the welding state of the solder joint is abnormal, what the abnormal welding type is. For example, it can be data obtained by detecting time-series data and / or image data in the data to be detected. The abnormal welding types of the solder joint can include problems such as cold solder joints, burn-through, solder joint misalignment, and non-compliant solder joint size. It should be noted that this is only an example and no specific limitation is made on the types of abnormal welding.

[0043] Optionally, if the identification results indicate that the solder joint's welding condition may be abnormal, the process can proceed to the deep detection stage. This step involves using more advanced algorithms, such as deep learning models, to perform a detailed analysis of the data to be detected that is in an abnormal welding state. The purpose of deep detection is to accurately determine whether there are quality problems with the solder joint and the severity of the problems. This process may include further data preprocessing, feature extraction, model prediction, and other steps to obtain the final detection results.

[0044] For example, a trained classification detection model can be used to inspect the welding data to obtain the detection result. Alternatively, an anomaly detection model can be invoked, utilizing expert prior knowledge to inspect the data and obtain the identification result. If the identification result characterizes the welding state of the weld point as an abnormal state, the classification detection model can then be invoked to inspect the data to obtain the detection result. This detection result can be used to determine whether the welding state of the weld point is truly an abnormal welding state, and the corresponding abnormal welding type. It should be noted that this is only an example and does not impose specific limitations on the welding inspection and identification methods for weld points.

[0045] Step S108: Based on the detection results, determine the abnormal welding type corresponding to the abnormal welding state.

[0046] In the technical solution provided in step S108 of this application, after using the prior knowledge of experts to perform preliminary detection on the data to be tested, in order to improve the accuracy of weld point identification, the data to be tested can be further tested to obtain the test results. The test results are used to determine whether the welding state of the weld point is really abnormal, and the abnormal welding type corresponding to the abnormal welding state.

[0047] For example, suppose in step S104, expert prior knowledge can identify abnormal current timing fluctuations at a solder joint, initially judging it to be a possible cold solder joint. Moving to step S106, a deep learning model performs a detailed analysis of the solder joint's image data, confirming that the solder joint does indeed exhibit poor contact, and the solder has failed to fully fill the gaps between the metal parts. Finally, in step S108, the system determines the solder joint to be a "cold solder joint" based on the detection results, requiring secondary welding repair. Through these steps, the intelligent detection system can quickly screen potential abnormal solder joints, then accurately identify the type of abnormality through deep detection, thereby taking timely measures to avoid product defects or safety hazards caused by welding quality problems.

[0048] Optionally, based on the detection results of step S106, the specific type of abnormality of the solder joint can be determined. Abnormal welding types may include various situations such as incomplete soldering, burn-through, solder joint misalignment, and non-compliant solder joint size. This determination process may rely on the classification ability of the algorithm, or through further comparison with an expert knowledge base, to ensure accurate classification of the abnormal welding state.

[0049] In welding inspection, "distance" typically refers to the deviation between the weld point and the desired position, while "accuracy" relates to the precision and reliability of the inspection results. Through the aforementioned inspection process, the system can improve the accuracy of detecting abnormal welding conditions while reducing the possibility of false alarms and missed alarms. Preliminary identification based on expert prior knowledge can filter out most normal weld points, reducing the computational burden of depth detection, which in turn can meticulously analyze the remaining weld point data to ensure accurate identification of abnormal welding types. For example, in the field of visual inspection, deep learning models can identify minute weld point offsets, even those that might be overlooked in the preliminary identification based on expert prior knowledge. By learning a large number of image features of normal and abnormal weld points, the model can determine whether the weld point position meets design requirements and whether the shape and size of the weld point are within allowable tolerances. This precise inspection capability is crucial for quality control in vehicle manufacturing.

[0050] In this embodiment, by combining rapid identification of expert prior knowledge with precise analysis of deep learning models, the intelligent detection process can effectively identify abnormal welding states in the vehicle welding process and accurately determine the type of abnormal welding, thereby providing strong support for quality control in vehicle manufacturing.

[0051] Through steps S102 and S108 of this application, data to be inspected on weld joints in a vehicle during the welding process is obtained. This data at least characterizes the welding state of the weld joints during the welding process. Prior expert knowledge is used to identify the data to be inspected, resulting in an identification result. This prior expert knowledge is associated with previously inspected data on normal weld joints in the vehicle whose welding state is normal. In response to the identification result indicating an abnormal welding state, welding inspection is performed on the data to be inspected, resulting in an inspection result. Based on the inspection result, the abnormal welding type corresponding to the abnormal welding state is determined. In other words, in this embodiment, data to be inspected on weld joints in a vehicle during the welding process is obtained; prior expert knowledge is used to identify the data to be inspected, resulting in an identification result. If the identification result indicates an abnormal welding state, welding inspection can be performed on the data to be inspected to determine the abnormal welding type corresponding to the abnormal welding state. This achieves the technical effect of accurately determining the abnormal welding type of the weld joint and solves the technical problem of not being able to accurately determine the abnormal welding type of the weld joint.

[0052] The method described in this embodiment will be further described below.

[0053] As an optional implementation, the expert prior knowledge includes at least a reference curve, standard heat and / or standard energy. Step S104 involves using the expert prior knowledge to identify the data to be tested and obtaining identification results, including: running the welding program corresponding to the solder joint; retrieving the reference curve corresponding to the normal solder joint under the welding program, and determining the standard heat and / or standard energy corresponding to the normal solder joint based on the reference curve; controlling the service layer of the detection system to identify the data to be tested based on the reference curve, standard heat and / or standard energy, and obtaining identification results.

[0054] In this embodiment, the expert prior knowledge may include a reference curve, standard heat, and / or standard energy. The standard heat can be the heat corresponding to a normal solder joint in the soldering state, and the standard energy can be the energy corresponding to a normal solder joint in the soldering state. It should be noted that, in addition to the reference curve, standard heat, and / or standard energy, the expert prior knowledge may also include other data; no specific limitations are imposed here.

[0055] Optionally, the aforementioned reference curve can refer to an ideal curve showing the change of process parameters such as welding current, voltage, and pressure over time at a normal weld joint under a specific welding procedure. This curve can be used as a benchmark to detect whether the weld joint condition deviates from the normal range. The aforementioned standard heat can refer to the total amount of heat that a weld joint should absorb and release under normal welding conditions, as the generation and distribution of heat directly affect the melting and solidification process of the weld joint, ultimately determining its quality. The aforementioned standard energy can refer to welding energy, which may include electrical energy, and can refer to the expected total energy required to complete a normal weld joint under a given welding procedure.

[0056] Optionally, when it is necessary to identify the welding status of a weld joint, the corresponding welding procedure can be determined first based on the location, material, and welding equipment used for the weld joint to be inspected. This welding procedure can include the setting of welding parameters, such as current, voltage, welding time, and pressure. Then, a reference curve related to this welding procedure can be retrieved from a database. This reference curve can be constructed based on historical time-series data and experimental verification of normal weld joints and can be used to characterize the ideal state of process parameters of normal weld joints changing over time under the same welding conditions. Based on the reference curve, the heat or energy standard that a normal weld joint should achieve under this welding procedure can be calculated. This step can be determined by analyzing data points on the reference curve and calculating the cumulative value of heat or energy over a specific time period. Finally, the current inspection data of the weld joint (such as the actual welding current, pressure curve, and heat and energy consumption) can be compared with the reference curve, standard heat, and / or standard energy obtained from expert prior knowledge. If the data deviates from the reference curve or fails to meet the standard heat and energy requirements, the system will mark the weld joint as abnormal and generate corresponding identification results, such as "suspected cold weld" or "potential burn-through."

[0057] For example, suppose the welding quality of a weld point on a car body is being inspected. This weld point uses a specific resistance spot welding program, program code one. At the beginning of step S104, the location and material information of the weld point can be identified, determining that it follows welding program code one. Subsequently, a reference curve corresponding to welding program code one can be retrieved. This curve records in detail the changes in ideal welding current and pressure over time. Simultaneously, based on this reference current, the standard heat consumption of the weld point under the standard welding program can be calculated to be 1000 joules, and the standard energy consumption to be 13000 joules. Further, the current, pressure, and other data of the weld point during the actual welding process can be read, and its actual heat and energy consumption can be calculated. If the measured data shows that the heat consumption is only 800 joules, far below the standard heat, and the current curve fluctuates significantly throughout the welding cycle, and the peak current fails to reach the threshold set on the reference curve, the system will determine that the weld point may have suffered from insufficient heat or unstable current during the welding process, resulting in a cold weld. In this situation, the identification result will be marked as "cold solder joint," prompting the operator or system to perform a second soldering or take other remedial measures. Through this series of identification steps based on expert prior knowledge, the system can quickly and accurately determine the soldering status of the solder joint.

[0058] In this embodiment, a detection system can be pre-built. This system can run the welding program corresponding to the solder joint; retrieve the reference curve corresponding to the normal solder joint under the welding program; and based on the reference curve, determine the standard heat and / or standard energy corresponding to the normal solder joint. Furthermore, the service layer of the detection system can be controlled to identify the data to be detected based on the reference curve, standard heat, and / or standard energy, and obtain the identification result.

[0059] Optionally, the aforementioned detection system may include a presentation layer, an application layer, a service layer, and a system layer. The presentation layer can display the visual project development interface, which may include a toolbar, a workflow editing area, and a status bar, and can display the collected data to be detected, recognition results, and detection results. The application layer can interact with the presentation layer and the service layer, serving as an interaction medium between the two layers. The application layer may include business applications, used for system management, image processing, image recognition, detection and recognition, 3D detection, geometric measurement, coordinate calibration, flowchart logic tools, communication, and deep learning. For example, the application layer can be used to preprocess the collected image data and calibrate data such as the coordinates and size of solder joints. The application layer can interact with third-party systems. These third-party systems may deploy archives, model libraries, human resources (HR) systems, and manufacturing execution systems (MES). The service layer can be used to call recognition models for anomaly detection and classification of solder joints.

[0060] As an optional implementation, the data to be detected includes at least time-series data and image data. The time-series data is used to characterize the dynamic characteristics of the weld joint during the welding process. The service layer of the control detection system identifies the data to be detected based on a reference curve, standard heat, and / or standard energy to obtain an identification result. This includes: controlling the service layer to determine a first similarity between the reference curve and the time-series data, and based on the time-series data, determining the energy corresponding to the weld joint, and / or the heat corresponding to the weld joint; determining a second similarity between the energy and the standard energy, and / or determining a third similarity between the heat and the standard heat; and determining the identification result based on the first similarity, the second similarity, and / or the third similarity.

[0061] In this embodiment, the data to be detected may include at least time-series data and image data. After acquiring the data to be detected, the service layer can be controlled to determine a first similarity between the reference curve and the time-series data, and based on the time-series data, determine the energy corresponding to the solder joint, and / or the heat corresponding to the solder joint; determine a second similarity between the energy and the standard energy, and / or determine a third similarity between the heat and the standard heat; and determine the recognition result based on the first similarity, the second similarity, and / or the third similarity.

[0062] Optionally, the identification result can be obtained by judging the first similarity, second similarity, and / or third similarity based on a similarity threshold. For example, if the first similarity, second similarity, and / or third similarity all meet the similarity threshold, the identification result can be used to characterize the welding state of the weld joint as a normal welding state. If at least one of the first similarity, second similarity, and / or third similarity fails to meet the similarity threshold, the identification result can be used to characterize the welding state of the weld joint as an abnormal welding state. Alternatively, the first similarity, second similarity, and / or third similarity can be weighted to obtain a calculation result, and the similarity threshold can be used to judge the calculation result to obtain the identification result. It should be noted that the determination of the identification result here is only an example, and any method that determines the identification result based on the first similarity, second similarity, and / or third similarity should be within the scope of protection of this application.

[0063] Optionally, the aforementioned time-series data can be used to reflect the trends of parameters such as current, voltage, temperature, and pressure over time during the welding process, and can be used to assess the continuity and stability of the welding process and its correlation with welding quality. The aforementioned image data can be used to provide a visual view of the weld joint's appearance and structure, and can be used to detect the weld joint's geometry, surface condition (such as cracks and porosity), and weld morphology. The service layer of the detection system can be controlled to compare the time-series data (e.g., the curves of welding current and voltage changes over time) with a predefined reference curve, calculating the similarity between the two to obtain a first similarity. The higher the similarity, the closer the welding process is to ideal process conditions. Simultaneously, based on the electrical parameters such as current and voltage in the time-series data, combined with the welding time, the actual energy and heat absorbed by the weld joint during the welding process can be calculated to obtain a second and third similarity. The similarity of energy and heat helps determine whether the weld joint has received sufficient energy input, thereby ensuring a good welding effect. The aforementioned first similarity can be used to reflect the consistency of the dynamic characteristics of the welding process with standard processes. The second and third similarity scores mentioned above can respectively measure the difference between the energy and heat obtained by the solder joint and the ideal state.

[0064] Furthermore, these three similarities can be used as inputs to generate recognition results in several ways: One or more thresholds can be set; when the similarity falls below these thresholds, the solder joint is considered to have quality problems, such as cold solder joints or burn-through. Alternatively, each similarity can be assigned a weight, and the solder joint status can be comprehensively evaluated by calculating a weighted average similarity. The weights can be flexibly adjusted according to the importance of different welding parameters. Another option is to utilize a trained machine learning model (such as a support vector machine, random forest, or deep learning model) with the three similarities as feature inputs to predict the welding status of the solder joint and the possible types of anomalies.

[0065] As an optional implementation, in response to the identification result indicating that the welding state of the weld point is an abnormal welding state, welding detection is performed on the data to be detected to obtain the detection result, including: in response to the identification result indicating that the welding state of the weld point is an abnormal welding state, calling the anomaly identification model to perform welding detection on the image data to obtain the detection result, wherein the anomaly identification model is trained based on historical detection data of abnormal weld points in the vehicle with abnormal welding states during the welding process.

[0066] In this embodiment, an anomaly recognition model can be pre-trained based on historical detection data of abnormal weld points in the vehicle during the welding process, indicating abnormal welding conditions. When it is determined that the welding condition of a weld point may be abnormal, the service layer of the detection system can be used to call the anomaly recognition model to perform welding detection on the image data and obtain the detection result.

[0067] Optionally, if the preliminary identification of the weld joint data based on expert prior knowledge indicates that the welding state of the weld joint deviates from the normal range and enters an abnormal welding state, this identification result can be responded to immediately. This means that the preliminary analysis has identified a potential problem, requiring further investigation and analysis to determine the details and severity of the problem. In response to the identification result of the abnormal welding state, an anomaly recognition model can be called from a model library. This model is specifically designed to analyze and identify image data of abnormal weld joints. It can be a deep learning model, such as a convolutional neural network (CNN) or a more complex structure. This anomaly recognition model has been trained on a large amount of historical detection data of abnormal weld joints and is capable of identifying and classifying various types of welding defects.

[0068] Optionally, the training data for the anomaly recognition model comes from anomalous weld points in vehicles that have been historically detected as having abnormal welding conditions. This data includes, but is not limited to: weld point images, which cover various common welding defects such as incomplete welds, burn-through, cracks, and porosity; process parameter data corresponding to the anomalous weld points, such as time-series data including welding current, voltage, temperature, and pressure, as well as the status information of the welding equipment; it may also include defect type labeling of the image data, or pre-classification in a semi-automatic manner to provide the label information required for model training.

[0069] Optionally, after invoking the anomaly detection model, deep analysis can be performed on the image data to identify and classify the weld points in the image. The detection results can include a precise judgment of the abnormal welding type and detailed information such as the possible location, size, and shape of defects. This process can not only confirm the initially identified abnormal welding state but also further refine the problem, providing a basis for taking corrective measures.

[0070] It should be noted that when the identification result is determined to characterize the welding state of the weld joint as an abnormal welding state, the anomaly identification model can be used to perform welding detection on the image data to obtain the detection result. Alternatively, the anomaly identification model can be used to detect time-series data to obtain the detection result, or both can be performed, and the final detection result can be determined based on the detection results of both. It should be noted that any method that uses an identification model to detect the data to be detected to obtain the detection result should be within the scope of protection of this application.

[0071] For example, suppose that during the manufacturing process of a car body, the intelligent inspection system for welding quality initially identifies a weld point where the welding current deviates significantly from the reference curve and the heat is below the standard value, preliminarily determining that the welding state of this weld point is abnormal. In response to this identification result, an anomaly detection model can be invoked to analyze the image data of the weld point. During in-depth inspection of the image data, the model may identify features such as fine cracks and irregular dimensions on the weld point surface. Based on the model's judgment, the system's detection result not only confirms that the weld point is in an abnormal welding state, but also specifically points out that the defects are cracks and dimensional inconsistencies, and can even provide the length of the cracks and the deviation of the actual weld point size from the standard size.

[0072] As an optional implementation, step S108, based on the detection results, determines the abnormal welding type corresponding to the abnormal welding state, including: based on the detection results, determining the incomplete weld data and weld penetration data of the weld point, wherein the incomplete weld data is used to represent the degree of incomplete weld of the weld point, and the weld penetration data is used to represent the degree of weld penetration of the weld point; and determining the abnormal welding type based on the degree of incomplete weld and the degree of weld penetration.

[0073] In this embodiment, after preliminary analysis by the detection system, a series of data and indicators (i.e., detection results) regarding the weld joint status can be obtained. These results may include, but are not limited to: current / voltage timing data used to assess whether the welding energy input is sufficient; image analysis to obtain weld joint size information and surface defects such as cracks, porosity, and weld penetration depth. The actual heat absorbed and energy consumed during the welding process are calculated and compared with standard heat and energy to determine whether the energy input meets expectations. Based on the above detection results, further data on incomplete welds and burn-through welds can be determined. The incomplete weld data can be used to determine whether a weld joint is incomplete and to characterize the degree of incomplete weld. The burn-through data can be used to determine whether a weld joint is burn-through and to determine the degree of burn-through weld.

[0074] It should be noted that abnormal welding types, in addition to incomplete welding and welding, can also include abnormal welding types under other circumstances.

[0075] For example, if the test results show insufficient welding energy, incomplete melting of the weld joint, or weld joint size and penetration depth failing to meet the specified standards, the system will calculate the area ratio of the incomplete weld or the thickness of the unfused material as a quantitative indicator of the degree of incomplete weld. When the test results show excessive welding energy, the solder penetrates the thickness of the welding material, or there are obvious cracks or through-holes below the weld joint, the system will calculate the depth of material penetration or the area of ​​the through-hole as a quantitative indicator of the degree of weld penetration. After quantifying the degree of incomplete weld and weld penetration, the specific type of abnormal welding can be determined based on the magnitude of these two indicators, combined with relevant standards and thresholds.

[0076] Optionally, if the degree of incomplete soldering exceeds a preset threshold, and the degree of burn-through is low or within the normal range, the system will identify the abnormal welding type as incomplete soldering. Incomplete soldering usually means that the solder joint has failed to form sufficient intermetallic bonding force, which may be caused by insufficient welding energy, improper welding parameter settings, or poor contact between the welding torch and the workpiece. Conversely, if the degree of burn-through exceeds a preset threshold, but the degree of incomplete soldering is low, the system will identify the abnormal welding type as burn-through. Burn-through problems are usually caused by excessive welding energy, which causes the solder to penetrate into the underlying welding material. This not only affects the structural integrity of the solder joint but may also damage the material on the back of the workpiece. In addition, in some cases, the solder joint may have both incomplete soldering and burn-through problems. In this case, it is necessary to comprehensively judge the abnormal welding type based on the relative magnitude of the two, which may be classified as "serious welding abnormality" and requires further process adjustments or equipment inspection.

[0077] In this embodiment, the data to be inspected of the weld joints in the vehicle during the welding process is obtained; the data to be inspected is identified using expert prior knowledge to obtain the identification result; if the identification result indicates that the welding state of the weld joint is an abnormal welding state, welding inspection can be performed on the data to be inspected to determine the abnormal welding type corresponding to the abnormal welding state of the weld joint, thereby achieving the technical effect of accurately determining the abnormal welding type of the weld joint and solving the technical problem of not being able to accurately determine the abnormal welding type of the weld joint.

[0078] According to an embodiment of this application, a system for determining abnormal welding types of solder joints is also provided. It should be noted that the system for determining abnormal welding types of solder joints in this embodiment can be used to execute the method for determining abnormal welding types of solder joints in Embodiment 1 of this application.

[0079] Figure 2 This is a schematic diagram of a system for determining abnormal welding types of solder joints according to an embodiment of this application. Figure 2 As shown, the system 20 for determining the abnormal welding type of the solder joint may include: a presentation layer 202, an application layer 204, and a service layer 206.

[0080] In this embodiment, the presentation layer can be used to acquire the collected data to be detected, wherein the data to be detected is at least used to characterize the welding status of the weld points in the vehicle during the welding process.

[0081] In this embodiment, the application layer can be used to preprocess the data to be detected.

[0082] In this embodiment, the service layer can be used to identify the data to be tested using expert prior knowledge and obtain identification results; in response to the identification results indicating that the welding state of the weld point is an abnormal welding state, welding inspection is performed on the data to be tested and inspection results are obtained; based on the inspection results, the abnormal welding type corresponding to the abnormal welding state is determined, wherein the expert prior knowledge is associated with the inspection data of normal weld points in the vehicle whose welding state is normal during the welding process.

[0083] Optionally, the aforementioned detection system may include a presentation layer, an application layer, a service layer, and a system layer. The presentation layer can display the visual project development interface, which may include a toolbar, a workflow editing area, and a status bar, and can display the collected data to be detected, recognition results, and detection results. The application layer can interact with the presentation layer and the service layer, serving as an interaction medium between the two layers. The application layer may include business applications, used for system management, image processing, image recognition, detection and recognition, 3D detection, geometric measurement, coordinate calibration, flowchart logic tools, communication, and deep learning. For example, the application layer can be used to preprocess the collected image data and calibrate data such as the coordinates and size of solder joints. The application layer can interact with third-party systems. These third-party systems may deploy archives, model libraries, human resources (HR) systems, and manufacturing execution systems (MES). The service layer can be used to call recognition models for anomaly detection and classification of solder joints.

[0084] According to an embodiment of this application, a device for determining the abnormal welding type of a solder joint is also provided. It should be noted that the device for determining the abnormal welding type of a solder joint in this embodiment can be used to execute the method for determining the abnormal welding type of a solder joint in Embodiment 1 of this application.

[0085] Figure 3 This is a schematic diagram of a device for determining the abnormal welding type of a weld joint according to an embodiment of this application. Figure 3 As shown, the device 30 for determining the abnormal welding type of the weld point may include: an acquisition unit 302, an identification unit 304, a detection unit 306, and a determination unit 308.

[0086] The acquisition unit 302 is used to acquire the inspection data of the weld joint in the vehicle during the welding process, wherein the inspection data is used to characterize the welding state of the weld joint during the welding process.

[0087] The identification unit 304 is used to identify the data to be tested using expert prior knowledge and obtain the identification result. The expert prior knowledge is associated with the detected data of normal weld points in the vehicle where the welding state is normal during the welding process.

[0088] The detection unit 306 is used to perform welding inspection on the data to be inspected in response to the identification result indicating that the welding state of the weld point is an abnormal welding state, and to obtain the inspection result.

[0089] The determining unit 308 is used to determine the abnormal welding type corresponding to the abnormal welding state based on the detection results.

[0090] The device for determining the abnormal welding type of a weld joint in this embodiment acquires, through an acquisition unit, data to be inspected on the weld joint in the vehicle during the welding process, wherein the data to be inspected is used to characterize the welding state of the weld joint during the welding process; through an identification unit, the data to be inspected is identified using expert prior knowledge to obtain an identification result, wherein the expert prior knowledge is associated with the previously detected data of a normal weld joint in the vehicle whose welding state is normal during the welding process; through an detection unit, in response to the identification result characterizing the welding state of the weld joint as an abnormal welding state, welding inspection is performed on the data to be inspected to obtain a detection result; through a determination unit, the abnormal welding type corresponding to the abnormal welding state is determined based on the detection result, thereby achieving the technical effect of accurately determining the abnormal welding type of the weld joint and solving the technical problem of not being able to accurately determine the abnormal welding type of the weld joint.

[0091] Embodiments of this application may provide a computer terminal, which may be any computer terminal device in a group of computer terminals. Optionally, in this embodiment, the aforementioned computer terminal may also be replaced by a mobile terminal or other terminal device.

[0092] Optionally, in this embodiment, the computer terminal may be located in at least one of a plurality of network devices in a computer network.

[0093] In this embodiment, the computer terminal described above can execute the program code for the following steps in the method for determining the abnormal welding type of a weld joint: acquiring the data to be inspected of the weld joint in the vehicle during the welding process, wherein the data to be inspected is at least used to characterize the welding state of the weld joint during the welding process; using expert prior knowledge to identify the data to be inspected and obtaining an identification result, wherein the expert prior knowledge is associated with the detected data of a normal weld joint in the vehicle whose welding state is normal during the welding process; in response to the identification result characterizing the welding state of the weld joint as an abnormal welding state, performing welding inspection on the data to be inspected and obtaining an inspection result; and determining the abnormal welding type corresponding to the abnormal welding state based on the inspection result.

[0094] Optionally, Figure 4 This is a structural block diagram of a computer terminal according to an embodiment of this application, such as... Figure 4 As shown, the computer terminal 408 may include one or more (only one is shown in the figure) processors 402, memory 404, and transmission devices 406.

[0095] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the method and apparatus for determining abnormal welding types of solder joints in this embodiment. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby realizing the aforementioned method for determining abnormal welding types of solder joints. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to computer terminal 408 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0096] The processor can invoke information and application programs stored in the memory via a transmission device to perform the following steps: acquiring inspection data of weld joints in the vehicle during the welding process, wherein the inspection data is used at least to characterize the welding state of the weld joints during the welding process; identifying the inspection data using expert prior knowledge to obtain an identification result, wherein the expert prior knowledge is associated with the inspection data of normal weld joints in the vehicle whose welding state is normal during the welding process; in response to the identification result characterizing the welding state of the weld joint as an abnormal welding state, performing welding inspection on the inspection data to obtain an inspection result; and determining the abnormal welding type corresponding to the abnormal welding state based on the inspection result.

[0097] Those skilled in the art will understand that Figure 4The structure shown is for illustrative purposes only. Computer terminal 408 can also be a smartphone (such as an Android phone, iOS phone, etc.), tablet computer, PDA, mobile Internet device (MID), PAD and other terminal devices. Figure 4 This does not limit the structure of the computer terminal 408 described above. For example, the computer terminal 408 may also include components that are more advanced than those described above. Figure 4 The more or fewer components shown (such as network interfaces, display devices, etc.), or having the same Figure 4 The different configurations shown.

[0098] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0099] According to an embodiment of this application, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored program, wherein the program executes the method for determining the abnormal welding type of the solder joint in Embodiment 1.

[0100] Optionally, in this embodiment, the computer-readable storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.

[0101] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: acquiring inspection data of weld joints in the vehicle during the welding process, wherein the inspection data is used at least to characterize the welding state of the weld joints during the welding process; using expert prior knowledge to identify the inspection data and obtain an identification result, wherein the expert prior knowledge is associated with the inspection data of normal weld joints in the vehicle whose welding state is normal during the welding process; in response to the identification result characterizing the welding state of the weld joint as an abnormal welding state, performing welding inspection on the inspection data and obtaining an inspection result; and determining the abnormal welding type corresponding to the abnormal welding state based on the inspection result.

[0102] Optionally, the aforementioned computer-readable storage medium may also execute program code that performs the following steps: running the welding program corresponding to the solder joint; retrieving the reference curve corresponding to the normal solder joint under the welding program, and based on the reference curve, determining the standard heat and / or standard energy corresponding to the normal solder joint; controlling the service layer of the detection system to identify the data to be detected based on the reference curve, standard heat and / or standard energy, and obtaining the identification result.

[0103] Optionally, the aforementioned computer-readable storage medium may also execute program code that performs the following steps: controlling the service layer, determining a first similarity between the reference curve and the timing data, and based on the timing data, determining the energy corresponding to the solder joint, and / or the heat corresponding to the solder joint; determining a second similarity between the energy and the standard energy, and / or determining a third similarity between the heat and the standard heat; and determining the identification result based on the first similarity, the second similarity, and / or the third similarity.

[0104] Optionally, the aforementioned computer-readable storage medium may also execute program code that performs the following steps: in response to the identification result characterizing the welding state of the weld point as an abnormal welding state, calling the anomaly identification model to perform welding detection on the image data and obtaining the detection result, wherein the anomaly identification model is trained based on historical detection data of abnormal weld points in the vehicle whose welding state is abnormal during the welding process.

[0105] Optionally, the aforementioned computer-readable storage medium may also execute program code for the following steps: determining the poor weld data and weld penetration data of the solder joint based on the detection results, wherein the poor weld data is used to represent the degree of poor weld of the solder joint, and the weld penetration data is used to represent the degree of weld penetration of the solder joint; and determining the abnormal welding type based on the degree of poor weld and the degree of weld penetration.

[0106] In this embodiment, the data to be inspected of the weld joints in the vehicle during the welding process is acquired; the data to be inspected is identified using expert prior knowledge to obtain the identification result; if the identification result indicates that the welding state of the weld joint is an abnormal welding state, welding inspection can be performed on the data to be inspected to determine the abnormal welding type corresponding to the abnormal welding state of the weld joint, thereby achieving the technical effect of accurately determining the abnormal welding type of the weld joint and solving the technical problem of not being able to accurately determine the abnormal welding type of the weld joint.

[0107] According to an embodiment of this application, a processor is also provided for running a program, wherein the method for determining the abnormal welding type of the solder joint in Embodiment 1 is executed when the program is run by the processor.

[0108] Optionally, in this embodiment, the computer terminal may be located in at least one of a plurality of network devices in a computer network.

[0109] In this embodiment, the computer terminal described above can execute the program code for the following steps in the method for determining the abnormal welding type of a weld joint: acquiring the data to be inspected of the weld joint in the vehicle during the welding process, wherein the data to be inspected is at least used to characterize the welding state of the weld joint during the welding process; using expert prior knowledge to identify the data to be inspected and obtaining an identification result, wherein the expert prior knowledge is associated with the detected data of a normal weld joint in the vehicle whose welding state is normal during the welding process; in response to the identification result characterizing the welding state of the weld joint as an abnormal welding state, performing welding inspection on the data to be inspected and obtaining an inspection result; and determining the abnormal welding type corresponding to the abnormal welding state based on the inspection result.

[0110] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the method and apparatus for determining abnormal welding types of solder joints in the embodiments of this application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby realizing the aforementioned method for determining abnormal welding types of solder joints. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to a computer terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0111] The processor can invoke information and application programs stored in the memory via a transmission device to perform the following steps: acquiring inspection data of weld joints in the vehicle during the welding process, wherein the inspection data is used at least to characterize the welding state of the weld joints during the welding process; identifying the inspection data using expert prior knowledge to obtain an identification result, wherein the expert prior knowledge is associated with the inspection data of normal weld joints in the vehicle whose welding state is normal during the welding process; in response to the identification result characterizing the welding state of the weld joint as an abnormal welding state, performing welding inspection on the inspection data to obtain an inspection result; and determining the abnormal welding type corresponding to the abnormal welding state based on the inspection result.

[0112] Optionally, the processor may also execute program code that performs the following steps: running the welding program corresponding to the solder joint; retrieving the reference curve corresponding to the normal solder joint under the welding program, and determining the standard heat and / or standard energy corresponding to the normal solder joint based on the reference curve; controlling the service layer in the detection system to identify the data to be detected based on the reference curve, standard heat and / or standard energy, and obtaining the identification result.

[0113] Optionally, the processor may also execute program code that performs the following steps: controlling the service layer, determining a first similarity between the reference curve and the timing data, and based on the timing data, determining the energy corresponding to the solder joint, and / or the heat corresponding to the solder joint; determining a second similarity between the energy and the standard energy, and / or determining a third similarity between the heat and the standard heat; and determining the identification result based on the first similarity, the second similarity, and / or the third similarity.

[0114] Optionally, the processor may also execute program code that performs the following steps: in response to the recognition result indicating that the welding state of the weld point is an abnormal welding state, the anomaly recognition model is invoked to perform welding detection on the image data to obtain the detection result, wherein the anomaly recognition model is trained based on historical detection data of abnormal weld points in the vehicle with abnormal welding states during the welding process.

[0115] Optionally, the processor may also execute program code that performs the following steps: based on the detection results, determine the poor solder joint data and the burn-through data of the solder joint, wherein the poor solder joint data is used to indicate the degree of poor solder joint, and the burn-through data is used to indicate the degree of burn-through of the solder joint; and based on the degree of poor solder joint and the degree of burn-through, determine the abnormal welding type.

[0116] By using the embodiments of this application, the data to be inspected of the weld joints in the vehicle during the welding process is obtained; the data to be inspected is identified using expert prior knowledge to obtain the identification result; if the identification result indicates that the welding state of the weld joint is an abnormal welding state, welding inspection can be performed on the data to be inspected to determine the abnormal welding type corresponding to the abnormal welding state of the weld joint, thereby achieving the technical effect of accurately determining the abnormal welding type of the weld joint and solving the technical problem of not being able to accurately determine the abnormal welding type of the weld joint.

[0117] According to an embodiment of this application, a computer program product is also provided, which includes computer instructions, wherein when the computer instructions are executed by a processor, they implement the method for determining the abnormal welding type of the solder joint in Embodiment 1.

[0118] Embodiments of this application may provide an electronic device that may include a memory and a processor.

[0119] Figure 5This is a block diagram of an electronic device according to an embodiment of this application, describing a method for determining abnormal solder joint types. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present application described and / or claimed herein.

[0120] like Figure 5 As shown, device 500 includes a computing unit 501, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 502 or a computer program loaded from storage unit 508 into random access memory (RAM) 503. RAM 503 can also store various programs and data required for the operation of device 500. The computing unit 501, ROM 502, and RAM 503 are interconnected via bus 504. Input / output (I / O) interface 505 is also connected to bus 504.

[0121] Multiple components in device 500 are connected to I / O interface 505, including: input unit 506, such as keyboard, mouse, etc.; output unit 507, such as various types of monitors, speakers, etc.; storage unit 508, such as disk, optical disk, etc.; and communication unit 509, such as network card, modem, wireless transceiver, etc. Communication unit 509 allows device 500 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0122] The computing unit 501 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 501 performs the various methods and processes described above, such as data verification methods. For example, in some embodiments, the data verification method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 508. In some embodiments, part or all of the computer program may be loaded and / or installed on device 500 via ROM 502 and / or communication unit 509. When the computer program is loaded into RAM 503 and executed by the computing unit 501, one or more steps of the data verification method described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to perform a data verification method by any other suitable means (e.g., by means of firmware).

[0123] According to an embodiment of this application, a method for determining the abnormal welding type of a solder joint is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0124] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0125] The program code used to implement the methods of this application may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing device, such that when executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0126] In the context of this application, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0127] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display, detector) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or pathball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0128] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication (e.g., a communication network) of any form or medium. Examples of communication networks include Local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.

[0129] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0130] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0131] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0132] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0133] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0134] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0135] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0136] The above are merely preferred embodiments of this application. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for determining the abnormal welding type of a weld joint, characterized in that, include: The inspection data of weld points in a vehicle during the welding process is obtained, wherein the inspection data is used at least to characterize the welding state of the weld points during the welding process. The data to be detected is identified using expert prior knowledge to obtain an identification result, wherein the expert prior knowledge is associated with the detected data of normal weld points in the vehicle whose welding state is normal during the welding process. In response to the identification result indicating that the welding state of the weld point is an abnormal welding state, welding detection is performed on the data to be detected to obtain the detection result; Based on the detection results, the abnormal welding type corresponding to the abnormal welding state is determined.

2. The method according to claim 1, characterized in that, The expert prior knowledge includes at least a reference curve, standard calorific value, and / or standard energy. The step of using the expert prior knowledge to identify the data to be detected and obtaining the identification result includes: Run the welding program corresponding to the weld point; Retrieve the reference curve corresponding to the normal solder joint under the welding procedure, and based on the reference curve, determine the standard heat and / or the standard energy corresponding to the normal solder joint; The service layer of the control and detection system identifies the data to be detected based on the reference curve, the standard heat and / or the standard energy, and obtains the identification result.

3. The method according to claim 2, characterized in that, The data to be detected includes at least time-series data and image data. The time-series data characterizes the dynamic characteristics of the weld joint during the welding process. The service layer of the control and detection system identifies the data to be detected based on the reference curve, the standard heat, and / or the standard energy, obtaining the identification result, including: The service layer is controlled to determine a first similarity between the reference curve and the timing data, and based on the timing data, to determine the energy corresponding to the solder joint and / or the heat corresponding to the solder joint. Determine a second similarity between the energy and the standard energy, and / or determine a third similarity between the heat and the standard heat; The identification result is determined based on the first similarity, the second similarity, and / or the third similarity.

4. The method according to claim 3, characterized in that, In response to the identification result indicating that the welding state of the weld joint is an abnormal welding state, welding detection is performed on the data to be detected to obtain a detection result, including: In response to the recognition result indicating that the welding state of the weld point is the abnormal welding state, the anomaly recognition model is invoked to perform welding detection on the image data to obtain the detection result. The anomaly recognition model is trained based on historical detection data of abnormal weld points in the vehicle whose welding state is abnormal during the welding process.

5. The method according to any one of claims 1 to 4, characterized in that, The step of determining the abnormal welding type corresponding to the abnormal welding state based on the detection results includes: Based on the detection results, the data on poor solder joints and the data on burn-through are determined, wherein the data on poor solder joints are used to indicate the degree of poor solder joints, and the data on burn-through are used to indicate the degree of burn-through of the solder joints; The abnormal welding type is determined based on the degree of incomplete welding and the degree of weld penetration.

6. A system for determining abnormal solder joint types, characterized in that, include: The presentation layer is used to acquire the collected data to be detected, wherein the data to be detected is used at least to characterize the welding status of the weld points in the vehicle during the welding process; The application layer is used to preprocess the data to be detected; The service layer is used to identify the data to be tested using expert prior knowledge to obtain an identification result; in response to the identification result indicating that the welding state of the weld point is an abnormal welding state, welding inspection is performed on the data to be tested to obtain an inspection result; based on the inspection result, the abnormal welding type corresponding to the abnormal welding state is determined, wherein the expert prior knowledge is associated with the inspected data of normal weld points in the vehicle whose welding state is normal during the welding process.

7. A device for determining the abnormal welding type of a weld joint, characterized in that, include: An acquisition unit is used to acquire inspection data of weld points in a vehicle during the welding process, wherein the inspection data is used at least to characterize the welding state of the weld points during the welding process. The identification unit is used to identify the data to be detected using expert prior knowledge and obtain an identification result, wherein the expert prior knowledge is associated with the detected data of the normal weld points in the vehicle whose welding state is normal during the welding process. The detection unit is configured to perform welding detection on the data to be detected in response to the identification result indicating that the welding state of the weld point is an abnormal welding state, and obtain the detection result. The determining unit is used to determine the abnormal welding type corresponding to the abnormal welding state based on the detection results.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform the method according to any one of claims 1 to 5.

9. A processor, characterized in that, The processor is used to run a program, wherein the program is executed by the processor to perform the method according to any one of claims 1 to 5.

10. A computer program product, characterized in that, Includes computer instructions that, when executed by a processor, implement the method of any one of claims 1 to 5.

Images