Detection method, device and system for welding quality, medium and program product

Abstract

The invention provides a detection method, device and system for welding quality, a medium and a program product. The detection method comprises the steps that multiple sets of welding data collected by multiple sensors in the welding process are received; preprocessing the plurality of groups of welding data to obtain a plurality of key features; the key features are input into a detection model, so that the detection model determines whether welding defects exist or not through a knowledge graph; under the condition that the existence of the welding defect is determined, outputting an identification result of the existence of the welding defect; in response to the fact that the welding defect in the recognition result belongs to a new welding defect type, new nodes are added in the knowledge graph, and the new nodes comprise a plurality of new welding process parameter nodes corresponding to the key features and new welding defect nodes; and according to the multiple sets of welding data, the incidence relation between the multiple new welding process parameter nodes and the new welding defect nodes is established.

Description

Technical Field

[0001] The present disclosure relates to the field of industrial welding, and in particular to a method, device, system, medium and program product for detecting welding quality. Background Art

[0002] In modern industrial production, welding is one of the indispensable processes in the manufacturing process and is widely used in industries such as automobiles, aerospace, shipbuilding, construction engineering and heavy machinery. The quality of welding directly affects the structural safety, reliability and service life of the product. Therefore, the detection of welding quality has become an important link in ensuring product quality.

[0003] In the relevant technology, welding quality inspection mainly relies on two methods: manual inspection and automatic inspection. Manual inspection uses visual, ultrasonic, X-ray and other means, and experienced technicians check the welds. However, manual inspection is inefficient and easily affected by the experience and fatigue of the inspectors. The misjudgment rate is high, especially when dealing with complex tasks. It is difficult to maintain consistency, and the accuracy rate is about 70%-80%. The automatic inspection system uses technologies such as image processing, ultrasonic detection and infrared imaging. Although it improves efficiency, it still has some shortcomings. For example, automatic inspection relies on static models and is difficult to adapt to changes in different welding conditions. Fixed models cannot cover all defect types, affecting the accuracy of detection. Summary of the invention

[0004] A technical problem solved by the present disclosure is that the accuracy of the welding quality detection method in the related art is low.

[0005] According to one aspect of the present disclosure, a method for detecting welding quality is provided, comprising: receiving multiple groups of welding data collected by multiple sensors during a welding process; preprocessing the multiple groups of welding data to obtain multiple key features; inputting the multiple key features into a detection model so that the detection model determines whether there is a welding defect through a knowledge graph, wherein the knowledge graph comprises multiple nodes and association relationships between the multiple nodes, the multiple nodes comprise welding process parameter nodes and welding defect nodes, the welding process parameter nodes correspond to the welding defect nodes; in the case of determining that a welding defect exists, outputting an identification result of the existence of the welding defect; in response to the welding defect in the identification result belonging to a new welding defect type, adding a new node in the knowledge graph, the new node comprising multiple new welding process parameter nodes and new welding defect nodes corresponding to the multiple key features; and establishing an association relationship between the multiple new welding process parameter nodes and the new welding defect nodes based on the multiple groups of welding data.

[0006] In some embodiments, based on the multiple sets of welding data, an association relationship between the multiple new welding process parameter nodes and the new welding defect node is established, including: based on the multiple sets of welding data, determining the weight value of each new welding process parameter node of the multiple new welding process parameter nodes relative to the new welding defect node.

[0007] In some embodiments, the detection method also includes: comparing each key feature of the multiple key features with the features of each welding process parameter node in the knowledge graph to obtain the welding process parameter node closest to each key feature; calculating the error feature between each key feature and the feature of the closest welding process parameter node; and based on the error feature, adjusting the parameters of the detection model by gradient descent method to minimize the error feature.

[0008] In some embodiments, the multiple nodes in the knowledge graph also include a quality standard node, and the quality standard node includes characteristics of welding process parameters when the welding quality meets the quality requirements.

[0009] In some embodiments, the plurality of sets of welding data include at least two sets of welding current data, welding voltage data, temperature data of the welding zone, weld image data, and acoustic wave data during the welding process.

[0010] In some embodiments, the multiple sets of welding data are preprocessed, including: performing noise reduction, normalization and feature extraction on the multiple sets of welding data to obtain the multiple key features.

[0011] In some embodiments, the detection method also includes: before receiving the multiple sets of welding data, constructing the knowledge graph; wherein constructing the knowledge graph includes: defining the multiple nodes in the knowledge graph, wherein the multiple nodes include multiple welding process parameter nodes and welding defect nodes corresponding to the multiple welding process parameter nodes; using historical data and empirical knowledge to establish an association relationship between the multiple nodes, wherein the association relationship includes a weight value of each welding process parameter node in the multiple welding process parameter nodes relative to the welding defect node.

[0012] According to another aspect of the present disclosure, a detection device for welding quality is provided, comprising: a receiving module for receiving multiple groups of welding data collected by multiple sensors during a welding process; a preprocessing module for preprocessing the multiple groups of welding data to obtain multiple key features; an identification module for inputting the multiple key features into a detection model so that the detection model determines whether there is a welding defect through a knowledge graph, and outputs an identification result of the presence of the welding defect when it is determined that there is a welding defect, wherein the knowledge graph includes multiple nodes and association relationships between the multiple nodes, the multiple nodes include welding process parameter nodes and welding defect nodes, and the welding process parameter nodes correspond to the welding defect nodes; a node setting module for adding a new node in the knowledge graph in response to the welding defect in the identification result belonging to a new welding defect type, the new node including multiple new welding process parameter nodes and new welding defect nodes corresponding to the multiple key features; and a relationship determination module for determining the association relationship between the multiple new welding process parameter nodes and the new welding defect nodes based on the multiple groups of welding data.

[0013] In some embodiments, the relationship determination module is used to determine the weight value of each new welding process parameter node of the multiple new welding process parameter nodes relative to the new welding defect node based on the multiple sets of welding data.

[0014] In some embodiments, the detection device also includes: an adaptive learning module, which is used to compare each key feature of the multiple key features with the features of each welding process parameter node in the knowledge graph to obtain the welding process parameter node closest to each key feature, calculate the error feature between each key feature and the feature of the closest welding process parameter node, and based on the error feature, adjust the parameters of the detection model by gradient descent method to minimize the error feature.

[0015] In some embodiments, the multiple nodes in the knowledge graph also include a quality standard node, and the quality standard node includes characteristics of welding process parameters when the welding quality meets the quality requirements.

[0016] In some embodiments, the plurality of sets of welding data include at least two sets of welding current data, welding voltage data, temperature data of the welding zone, weld image data, and acoustic wave data during the welding process.

[0017] In some embodiments, the preprocessing module is used to perform noise reduction, normalization and feature extraction on the multiple sets of welding data to obtain the multiple key features.

[0018] In some embodiments, the detection device also includes: a graph construction module, used to define the multiple nodes in the knowledge graph, and use historical data and empirical knowledge to establish an association relationship between the multiple nodes, wherein the multiple nodes include multiple welding process parameter nodes and welding defect nodes corresponding to the multiple welding process parameter nodes, and the association relationship includes the weight value of each welding process parameter node in the multiple welding process parameter nodes relative to the welding defect node.

[0019] According to another aspect of the present disclosure, a device for detecting welding quality is provided, comprising: a memory; and a processor coupled to the memory, wherein the processor is configured to execute the aforementioned detection method based on instructions stored in the memory.

[0020] According to another aspect of the present disclosure, a detection system for welding quality is provided, comprising: a current sensor, a voltage sensor, a temperature sensor, an image sensor, a sound sensor and the detection device as described above, wherein the current sensor, the voltage sensor, the temperature sensor, the image sensor and the sound sensor are all electrically connected to the detection device.

[0021] According to another aspect of the present disclosure, a computer-readable storage medium is provided, on which computer instructions are stored. When the computer instructions are executed by a processor, the detection method as described above is implemented.

[0022] According to another aspect of the present disclosure, a computer program product is provided. The computer program product includes a computer program or instructions. When the computer program or instructions are executed by a processor, the detection method as described above is implemented.

[0023] In the above detection method, whether there is a welding defect can be detected based on the collected data and knowledge graph, and when the welding defect belongs to a new type of welding defect, the knowledge graph can be updated, so it can adapt to changes in different welding conditions, improve the accuracy of welding defect detection, and improve product reliability.

[0024] Other features and advantages of the present disclosure will become apparent from the following detailed description of exemplary embodiments of the present disclosure with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The accompanying drawings, which constitute a part of the specification, illustrate embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0026] The present disclosure may be more clearly understood from the following detailed description with reference to the accompanying drawings, in which:

[0027] Figure 1is a flow chart showing a method for detecting welding quality according to some embodiments of the present disclosure;

[0028] Figure 2 is a flow chart showing a method for detecting welding quality according to other embodiments of the present disclosure;

[0029] Figure 3 is a block diagram schematically showing a structure of a device for detecting welding quality according to some embodiments of the present disclosure;

[0030] Figure 4 is a structural block diagram schematically showing a device for detecting welding quality according to other embodiments of the present disclosure;

[0031] Figure 5 is a structural block diagram schematically showing a device for detecting welding quality according to other embodiments of the present disclosure;

[0032] Figure 6 is a structural block diagram schematically showing a device for detecting welding quality according to other embodiments of the present disclosure;

[0033] Figure 7 is a block diagram schematically showing a structure of a system for detecting welding quality according to some embodiments of the present disclosure. DETAILED DESCRIPTION

[0034] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that the relative arrangement of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present disclosure unless otherwise specifically stated.

[0035] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0036] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present disclosure, its application, or uses.

[0037] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered as part of the specification.

[0038] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0039] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0040] Figure 1 is a flow chart showing a method for detecting welding quality according to some embodiments of the present disclosure. The detection method can be implemented by a detection device, for example, the detection device is set in an electronic device. Figure 1 As shown, the detection method includes steps S102 to S112.

[0041] In step S102, multiple groups of welding data collected by multiple sensors during the welding process are received.

[0042] In some embodiments, the plurality of sets of welding data include at least two sets of welding current data, welding voltage data, temperature data of the welding zone, weld image data, and acoustic wave data during the welding process.

[0043] For example, the plurality of sensors include at least two of a current sensor, a voltage sensor, a temperature sensor, an image sensor, and a sound sensor.

[0044] The current sensor is used to collect welding current data I(t) and transmit the welding current data to the detection device. The current sensor can collect welding current data at different times, so that a set of welding current data can be formed and transmitted to the detection device as a set of welding data. In this way, the detection device can monitor the stability of the welding current.

[0045] The voltage sensor is used to collect welding voltage data V(t) and transmit the welding voltage data to the detection device. The voltage sensor can collect welding voltage data at different times, so that a set of welding voltage data can be formed and transmitted to the detection device as a set of welding data. In this way, the detection device can monitor the stability of the welding voltage so as to stabilize the voltage during the welding process.

[0046] The temperature sensor is used to collect temperature data of the welding area and transmit the temperature data to the detection device. The temperature sensor can collect temperature data at different times, so that a set of temperature data can be formed and transmitted to the detection device as a set of welding data. The temperature change can reflect the change of welding heat input.

[0047] The image sensor is used to capture the weld image data Img(t) in real time and transmit the weld image data to the detection device. The image sensor can collect weld images at different times, so that a set of weld images can be formed and transmitted to the detection device as a set of welding data. In this way, the surface quality of the weld can be detected, such as the weld width, surface cracks, etc. For example, the image sensor includes a camera, etc.

[0048] The sound sensor is used to collect the sound wave data S(t) generated during the welding process and transmit the sound wave data to the detection device. The sound sensor can collect the sound wave data at different times, so that a group of sound wave data can be formed and transmitted to the detection device as a group of welding data. The detection device can analyze the acoustic characteristics during welding, such as the strength of the arc light and the noise during the welding process. For example, the sound sensor includes a microphone.

[0049] It should be noted that the above-mentioned multiple sets of welding data may include other welding data, as long as they can be used for defect detection, in addition to welding current data, welding voltage data, temperature data of the welding zone, weld image data and sound wave data during welding. Accordingly, the above-mentioned sensors may include other sensors, as long as they are used to collect corresponding welding data for defect detection, in addition to current sensors, voltage sensors, temperature sensors, image sensors and sound sensors.

[0050] In step S104, multiple sets of welding data are preprocessed to obtain multiple key features.

[0051] In some embodiments, step S104 includes: performing noise reduction, normalization and feature extraction processing on multiple sets of welding data to obtain multiple key features.

[0052] For example, in the process of denoising the raw data, a Kalman filter or wavelet transform can be used to reduce or eliminate the noise in the data and improve the purity of the data. For example, a Kalman filter can remove the noise collected by the sensor and retain important signal components.

[0053] Data from different sensors have different dimensions and ranges. Therefore, through normalization processing (also known as standardization processing), the data format can be unified to facilitate subsequent analysis. Here, known methods or techniques can be used to perform normalization processing. For example, the raw data can be normalized based on the mean and variance of the raw data.

[0054] Next, feature extraction can be performed on the normalized data to obtain key features.

[0055] For example, the peak value, frequency, amplitude, mean and variance of the welding current can be extracted from the welding current data, and these data can be combined into the key feature vector of the welding current.

[0056] For another example, the peak value, frequency, amplitude, mean value, and variance of the welding voltage can be extracted from the welding voltage data, and these data can be combined into a key feature vector of the welding voltage.

[0057] For example, the temperature gradient and peak temperature can be extracted from the temperature data, and these data can be used to form the key feature vector of the temperature data. Here, the extracted features can be used for subsequent knowledge graph analysis and detection model optimization.

[0058] For another example, edge features of welds are extracted from image data.

[0059] Another example is extracting spectral features from acoustic wave data. For example, low-frequency components of 20 Hz to 200 Hz can be collected. Here, low-frequency noise is usually related to the stability of the welding arc, mechanical fluctuations during welding, and the dynamic behavior of the molten pool. Low-frequency components can reveal instability or abnormalities in the welding process, such as arc fluctuations, molten pool instability, etc. The arc fluctuation frequency can also be extracted. Changes in the welding arc can generate low-frequency noise, especially when the arc is unstable or a short circuit occurs. By analyzing these low-frequency components, the stability of the arc can be judged and possible welding defects can be predicted.

[0060] In the above embodiment, by preprocessing the multiple sets of collected data, the data can have higher quality and consistency, which facilitates the subsequent use of the data for detection and optimization.

[0061] In step S106, a plurality of key features are input into the detection model so that the detection model determines whether a welding defect exists through a knowledge graph. The knowledge graph includes a plurality of nodes and associations between the plurality of nodes. The plurality of nodes include a welding process parameter node and a welding defect node, and the welding process parameter node corresponds to the welding defect node.

[0062] The above-mentioned detection model can adopt a detection model known to those skilled in the art. For example, the detection model can be a machine learning model. The detection model can be trained in advance using collected data and knowledge graphs. The detection model performs defect identification, judgment and decision-making in a data-driven manner, which relies on real-time collected data and trained algorithms. The knowledge graph provides a structured knowledge network of welding processes and defects, and helps the detection model understand and reason about possible problems in the welding process by organizing and storing the relationship between different welding parameters and defects. In addition, in the following description, the output results of the detection model (such as defect identification results) can also reversely affect the update of the knowledge graph. The adaptive learning mechanism enables the detection model to update its parameters based on real-time feedback, and the knowledge graph can also be gradually optimized as new information is added in the process. In this way, the two jointly improve the detection capability of the system through continuous feedback and updating.

[0063] The above-mentioned multiple nodes may include multiple welding process parameter nodes. For example, the welding process parameter node may be a node with welding current data as a feature vector, or a node with welding voltage data as a feature vector, or a node with temperature data as a feature vector, and so on.

[0064] For example, the above-mentioned welding defect nodes may be defect nodes such as cracks, pores, and lack of fusion.

[0065] The association between each welding process parameter node and the corresponding welding defect node is reflected in the form of a weight value. For example, the weight value of a welding current parameter node is 0.3, which means that the weight value of the welding current parameter node relative to the corresponding defect node is 0.3.

[0066] In the above steps, by inputting multiple key features into the detection model, the detection model can perform defect recognition through the knowledge graph to determine whether there are welding defects.

[0067] In some embodiments, the plurality of nodes in the above-mentioned knowledge graph further include a quality standard node. The quality standard node includes features of welding process parameters when the welding quality meets the quality requirements. This makes it easier for the detection model to determine whether there are welding defects based on the knowledge graph.

[0068] For example, if multiple key features meet the features of the corresponding quality standard nodes, there is no welding defect. Taking current as an example, the quality standard node can include the allowable range of the current mean (as a feature), so that it can be detected whether the mean value of the welding current is within the allowable range of the current mean value.

[0069] In step S108, when it is determined that a welding defect exists, a recognition result that a welding defect exists is output.

[0070] In addition, in the case where it is determined that there is no welding defect, a recognition result that there is no welding defect is output.

[0071] In step S110, in response to the welding defect in the recognition result belonging to a new welding defect type, a new node is added to the knowledge graph, and the new node includes a plurality of new welding process parameter nodes and a new welding defect node corresponding to a plurality of key features.

[0072] For example, the operator determines that the welding defect belongs to a new welding defect type based on the welding defect in the output recognition result, that is, there is no such welding defect in the knowledge graph, and then the information that the welding defect belongs to the new welding defect type is input into the detection device. For example, the detection device has display information for the operator to judge whether the welding defect belongs to the new welding defect type. After the operator triggers the "yes" confirmation button, the detection device can obtain that the welding defect in the knowledge recognition result belongs to the new welding defect type.

[0073] In response to the welding defect in the recognition result belonging to a new welding defect type, the detection device adds a new node in the knowledge graph. Here, the new node includes multiple new welding process parameter nodes and new welding defect nodes, and the new welding process parameter nodes can correspond to key features. For example, the features of current, voltage and temperature in multiple key features can be used as new welding process parameter nodes respectively.

[0074] In step S112, based on the multiple sets of welding data, association relationships between multiple new welding process parameter nodes and new welding defect nodes are established.

[0075] In some embodiments, step S112 includes: determining, based on multiple sets of welding data, a weight value of each new welding process parameter node of multiple new welding process parameter nodes relative to a new welding defect node.

[0076] As mentioned above, the association relationship is embodied in the form of a weight value. Therefore, here, the weight value of each new welding process parameter node relative to the new welding defect node can be determined based on multiple sets of welding data, that is, the association relationship between each new welding process parameter node and the new welding defect node can be obtained.

[0077] For example, based on the welding current data, welding voltage data and temperature data in multiple groups of welding data, it is found that the change of welding current data has the greatest impact on defects, the welding voltage data has the second greatest impact on defects, and the temperature data has the smallest impact on defects. In this case, the weight value of the welding current parameter node can be set to the largest, the weight value of the welding voltage parameter node can be set to the second largest, and the weight value of the temperature parameter node can be set to the smallest.

[0078] So far, a detection method for welding quality according to some embodiments of the present disclosure is provided. The detection method includes: receiving multiple sets of welding data collected by multiple sensors in a welding process; preprocessing the multiple sets of welding data to obtain multiple key features; inputting the multiple key features into the detection model so that the detection model determines whether there is a welding defect through a knowledge graph, wherein the knowledge graph includes multiple nodes and the association relationship between the multiple nodes, the multiple nodes include welding process parameter nodes and welding defect nodes, and the welding process parameter nodes correspond to the welding defect nodes; in the case of determining that there is a welding defect, outputting the recognition result of the presence of the welding defect; in response to the welding defect in the recognition result belonging to a new welding defect type, adding a new node in the knowledge graph, the new node includes multiple new welding process parameter nodes corresponding to the multiple key features and a new welding defect node; and according to the multiple sets of welding data, establishing the association relationship between multiple new welding process parameter nodes and new welding defect nodes. In this detection method, based on the collected data and the knowledge graph, it is possible to detect whether there is a welding defect, and in the case where the welding defect belongs to a new welding defect type, the knowledge graph can be updated, so that it can adapt to the changes in different welding conditions, improve the accuracy of welding defect detection, and improve the reliability of the product.

[0079] In related technologies, traditional systems lack dynamic update capabilities and cannot adapt to the advancement and complexity of welding technology, resulting in an increase in missed detections and misjudgments. When faced with complex or irregular welds, traditional systems have a high misjudgment rate, and the accuracy of identifying tiny cracks or pores is limited to only about 80%. They also have poor adaptability and are difficult to meet high-precision detection needs.

[0080] In view of this, the detection method of some embodiments of the present disclosure further includes: comparing each key feature of multiple key features with the features of each welding process parameter node in the knowledge graph to obtain the welding process parameter node closest to each key feature; calculating the error feature between each key feature and the feature of the closest welding process parameter node; and based on the error feature, adjusting the parameters of the detection model by the gradient descent method to minimize the error feature. This realizes an adaptive learning mechanism.

[0081] Here, the gradient descent method is an algorithm known to those skilled in the art and will not be described in detail here. The parameters of the detection model are also parameters known to those skilled in the art, for example, the parameters may include weight values ​​in the model, etc.

[0082] Through the above-mentioned adaptive learning mechanism, the accuracy, efficiency and system adaptability of welding quality detection can be improved.

[0083] In some embodiments, the above detection method further includes: before receiving the plurality of sets of welding data, constructing a knowledge graph. Figure 1Before the detection method shown in the figure, a knowledge graph is constructed. The knowledge graph is a complex network structure used to represent various process parameters, quality standards and defect types in the welding process and their relationships. Representing multiple parameters in the welding process and their relationships through the knowledge graph can better reflect the complexity and variability of the welding process and improve the adaptability of the detection.

[0084] Optionally, constructing the knowledge graph may include: defining multiple nodes in the knowledge graph, wherein the multiple nodes include multiple welding process parameter nodes and welding defect nodes corresponding to the multiple welding process parameter nodes. That is, various nodes are defined in the knowledge graph, including welding process parameter nodes (e.g., current, voltage, temperature) and welding defect nodes (e.g., cracks, pores, lack of fusion, etc.). In addition, the quality standard node described above may also be defined in the knowledge graph.

[0085] Optionally, constructing the knowledge graph may further include: using historical data and empirical knowledge to establish an association relationship between multiple nodes. The association relationship includes a weight value of each welding process parameter node in the multiple welding process parameter nodes relative to the welding defect node. That is, the relationship between each node is established using historical data and the empirical knowledge of welding experts. For example, the causal relationship between current fluctuation and crack formation can be determined by statistical analysis methods (such as association rule mining), and the strength of each relationship in the knowledge graph is represented by a weight value.

[0086] In this way, the construction of the knowledge graph is realized. For example, the knowledge graph can be constructed during the system initialization process. By constructing the knowledge graph, subsequent defect detection can be facilitated.

[0087] Figure 2 is a flow chart showing a method for detecting welding quality according to other embodiments of the present disclosure. The detection method can be implemented by a detection device, for example, the detection device is set in an electronic device. Figure 2 As shown, the detection method includes steps S202 to S208.

[0088] In step S202, multiple groups of welding data collected by multiple sensors during the welding process are received.

[0089] For example, multiple sets of welding data include: welding current data, welding voltage data, temperature data of the welding area, weld image data, and sound wave data during welding. During the welding process, multiple sensors are used to synchronously collect various types of data to comprehensively monitor the welding quality.

[0090] In step S204, the nodes in the knowledge graph are updated.

[0091] As mentioned above, multiple key features can be obtained through multiple sets of welding data. After obtaining multiple key features, welding defects are identified through the detection model based on the original knowledge graph. When the system detects that the welding defect belongs to a new welding defect type or the process parameters have changed, it automatically adds a corresponding node to the knowledge graph and establishes a connection with the existing nodes in the knowledge graph (that is, the original nodes). For example, when the system detects a new defect mode (such as a crack type caused by a new welding material), it automatically adds a node for the mode.

[0092] Here, the newly added nodes can represent new welding defect types or changed process parameters, while the existing nodes are the original welding defect types or original process parameters.

[0093] It should be noted that the newly added nodes do not necessarily have to be linked to all existing nodes. For example, they can be linked to existing nodes with significant correlation or similarity. Such links usually depend on factors such as actual data, defect manifestations, and process changes in the welding process. If the newly added node represents a new type of welding defect (such as "pore crack"), then the newly added node may be associated with some specific process parameter nodes such as welding current and welding temperature. The newly added node may not be linked to existing defect types (such as "crack" or "incomplete penetration") unless the formation conditions of these defect types are similar to the new defect type. If the newly added node is a new welding process parameter (such as welding speed under a specific process), then the newly added node may be associated with process parameters such as welding current and voltage, and will not be directly linked to the welding defect type unless this new process parameter plays a decisive role in the occurrence of certain defects.

[0094] In step S206, the relationship between the nodes is updated.

[0095] For example, based on the collected data, the Bayesian update formula is used to dynamically adjust the weights of the nodes in the knowledge graph, thereby adjusting the relationship between the nodes to reflect the latest welding quality status.

[0096] For example, suppose that during the detection process, it is preliminarily believed that the welding current and voltage have a certain influence on the formation of cracks, so an initial weight (prior probability) is given to represent this influence. For example, the initial weight (weight before update) includes: the initial welding current weight (prior probability) and the initial welding voltage weight (prior probability). Assume that the initial welding current weight value is 0.6, indicating that the welding current has a greater influence on the welding crack; assume that the initial welding voltage weight value is 0.4, indicating that the voltage has a relatively small influence on the welding crack.

[0097] Assuming that new data is obtained, it is detected that when the welding current changes greatly, the probability of welding cracks does increase significantly, while the voltage change has little effect on cracks. Therefore, the two weight values ​​can be adjusted through the Bayesian update formula, so that the system can adjust the weights in time when facing new welding defect types or changing process parameters, thereby improving the accuracy of detection.

[0098] In this way, through the above steps S202 to S206, based on the dynamic update mechanism, the knowledge graph can be continuously adjusted and optimized according to real-time data and feedback information to cope with changes in welding environment and process conditions, and improve the accuracy and adaptability of detection.

[0099] In step S208, adaptive learning is performed to optimize the detection model.

[0100] For example, during the detection process, the system compares the features of the collected data and calculates the error between the model output and the expected value in the knowledge graph; based on the error calculation results, the system uses the gradient descent method to adjust the parameters of the detection model to minimize the error; the system uses a feedback loop mechanism to compare the actual detection results with the expected results in the knowledge graph. If the deviation is large, the system will further optimize the model parameters. For example, in order to improve learning efficiency, the system introduces reinforcement learning algorithms (for example, Q learning algorithms) to further optimize the detection model.

[0101] The adaptive learning mechanism can dynamically adjust and optimize the detection model through real-time data feedback, so that the system can cope with complex and changing welding conditions, with greater flexibility and adaptability, and can improve detection accuracy and reduce misjudgment and missed detection problems. In the adaptive learning mechanism, there is no need for manual intervention, and the system can optimize itself. Through real-time feedback and dynamic adjustment, the intelligence level of the system is improved.

[0102] So far, a detection method for welding quality according to other embodiments of the present disclosure is provided. In this detection method, not only can the welding quality knowledge graph be dynamically updated, but also the detection model is automatically optimized under different working conditions through an adaptive learning mechanism, which significantly improves the accuracy, efficiency and adaptability of the system.

[0103] Furthermore, the optimized detection model can also be output.

[0104] In some embodiments, the above detection method may further include: outputting a welding quality report to record each adjustment and defect detection result during the welding process. The welding quality report may include detection data of internal defects in the weld and repair suggestions. This facilitates operators to take corresponding measures based on the welding quality report.

[0105] In some embodiments, the above detection method may further include: if a structural defect (e.g., a serious structural defect) is detected, an alarm is issued and an immediate repair or re-welding is recommended. This makes it easier for operators to learn about the defect and improve product quality through repair and re-welding.

[0106] The following describes the inspection process by taking the welding quality control of the main arm of an aerial platform vehicle as an example.

[0107] In the manufacturing process of aerial platform vehicles, the main arm is one of the key components, and its welding quality directly affects the working performance and safety of the aerial platform vehicle. The main arm is usually welded from high-strength steel plates, and the strength and quality requirements of the welds are extremely high. Traditional welding quality inspection mainly relies on ultrasonic inspection and X-ray inspection, but these methods have the problems of low inspection efficiency, high cost and blind spots, and cannot detect defects in production in time.

[0108] Here, the detection method of the embodiment of the present disclosure is used to detect the welding quality, and the detection process includes the following steps.

[0109] In step 1, multi-source data is collected.

[0110] During the main arm welding process, multiple sensors are installed to monitor welding parameters in real time. The current sensor monitors the welding current to reduce weld quality problems caused by excessive or insufficient current. The voltage sensor monitors the welding voltage to improve the stability of the welding process. The temperature sensor monitors the temperature changes in the welding area to reduce defects caused by overheating or improper cooling of the weld. The camera captures the weld image in real time to detect whether there are defects such as cracks and lack of fusion on the weld surface. The microphone collects the sound waves generated during the welding process to identify possible abnormalities in the welding process.

[0111] In step 2, data preprocessing and feature extraction are performed.

[0112] All collected data are preprocessed, including data noise reduction, data normalization, and feature extraction. For example, edge features are extracted from weld images and spectrum features are extracted from acoustic wave data. These high-quality feature data are input into the knowledge graph to analyze and judge welding quality.

[0113] In step 3, analysis and real-time detection are performed through the knowledge graph.

[0114] The system analyzes the correlation between various parameters through the constructed knowledge graph. For example, current fluctuations may be related to weld crack formation, and temperature changes may be related to weld lack of fusion. The knowledge graph automatically identifies the types of defects that may occur during the welding process by combining historical data and real-time data.

[0115] In step 4, adaptive learning and parameter optimization are performed.

[0116] When the system detects an abnormality during welding (such as current fluctuations or abnormal temperature), it will adjust the welding parameters through an adaptive learning mechanism, such as adjusting the welding current or changing the welding speed, so that the quality of the weld meets the requirements. Through the feedback mechanism, the system continuously optimizes the knowledge graph, making the subsequent detection in the welding process more accurate.

[0117] In step 5, the detection result is obtained and fed back.

[0118] After welding is completed, the system outputs a test report, including the quality assessment of the weld, the type of defects found and their locations, and the welding parameters adjusted by the system. The operator can make further adjustments to the welding process based on the test report. For the detected defects, the system provides an automatic alarm function to prompt the operator to repair them.

[0119] The following describes the inspection process using the quality control in the welding of construction crane chassis as an example.

[0120] As the basic structure of the crane, the chassis of the construction crane bears the weight of the whole machine and the stress concentration during operation. Its welding quality is crucial to the stability of the whole machine. The chassis welding process is complicated and is prone to quality problems such as incomplete welding, undercut, and air holes. If not detected and corrected in time, it may lead to insufficient structural strength of the chassis, affecting the service life and safety of the equipment.

[0121] Here, the detection method of the embodiment of the present disclosure is used to detect the welding quality, and the detection process includes the following steps.

[0122] In step 1, multi-source data is collected.

[0123] During the chassis welding process, current sensors, voltage sensors, and temperature sensors are arranged, and a welding monitoring system is equipped to collect welding parameters and weld images in real time. The system also uses an ultrasonic detector to monitor the welding quality inside the weld, especially to detect internal defects such as incomplete penetration and porosity.

[0124] In step 2, data preprocessing and feature extraction are performed.

[0125] The collected data is pre-processed to eliminate noise interference and standardize it. The ultrasonic data is signal processed to extract the characteristics of internal defects in the weld, such as the intensity and frequency of the echo signal.

[0126] The geometric features of the weld surface (e.g., undercut depth, weld width, etc.) are extracted from the weld image, and the heat input fluctuation information of the welding process is extracted from the current and temperature data.

[0127] In step 3, the knowledge graph is constructed and applied.

[0128] Construct a welding quality knowledge graph for the chassis of an engineering crane, which includes welding process parameters, weld defect types, and quality standards. The knowledge graph records the possible defect types and their countermeasures under various welding parameter combinations.

[0129] The system inputs real-time data into the detection model, which uses the knowledge graph to judge the quality of the weld. If pores are detected inside the weld, it indicates that the possible cause is that the welding temperature is too low, and the system will recommend adjusting the welding temperature.

[0130] In step 4, adaptive learning and optimization are performed.

[0131] The system adjusts the welding process parameters through an adaptive learning mechanism based on the actual weld defects detected. For example, when an incomplete weld defect is detected, the system adjusts the welding speed and current intensity to increase the weld penetration.

[0132] Dynamically updating the knowledge graph enables the system to adapt to materials of different thicknesses and different welding processes.

[0133] In step 5, the detection result is obtained and fed back.

[0134] The system outputs a detailed welding quality report, recording every adjustment and defect detection result during the welding process. The report includes the detection data of internal defects in the weld and its repair suggestions.

[0135] If a serious structural defect is detected, the system can sound an alarm and recommend immediate repair or re-welding.

[0136] In some cases, welding quality inspection technology is developing towards intelligence, automation and adaptability to overcome the limitations of traditional methods. First, multi-source data fusion uses data from multiple sensors such as current, voltage, temperature, image, sound wave, etc. to fully reflect the dynamic changes of the welding process and improve the ability to identify different welding defects. Secondly, knowledge graph technology forms a complex knowledge network by combining welding process, parameters, defect type and detection results to enhance the intelligence level of the detection system. Furthermore, the adaptive learning mechanism can adjust the parameters and strategies of the detection model in real time according to the changes in welding conditions, improve the adaptability and accuracy of the system under different working conditions, and gradually optimize the model through real-time feedback to improve the recognition ability of new defect types.

[0137] In the embodiments of the present disclosure, a method for dynamic updating and adaptive learning of welding quality based on knowledge graph is proposed. Through real-time collection and analysis of welding data, the dynamic updating of knowledge graph is realized, and an adaptive learning mechanism is introduced to improve the accuracy, efficiency and system adaptability of welding quality detection. This innovative method can not only adapt to complex and changeable welding conditions, but also update and optimize the detection model at any time, thereby significantly improving the overall level of welding quality detection.

[0138] Figure 3 Schematically shows a structural block diagram of a device for detecting welding quality according to some embodiments of the present disclosure. Figure 3 As shown, the detection device includes a receiving module 302 , a preprocessing module 304 , an identification module 306 , a node setting module 308 and a relationship determination module 310 .

[0139] The receiving module 302 is used to receive multiple sets of welding data collected by multiple sensors during the welding process.

[0140] For example, the plurality of welding data include at least two of welding current data, welding voltage data, temperature data of the welding zone, weld image data, and sound wave data during the welding process.

[0141] The preprocessing module 304 is used to preprocess multiple sets of welding data to obtain multiple key features.

[0142] For example, the preprocessing module is used to perform noise reduction, normalization and feature extraction on multiple sets of welding data to obtain multiple key features.

[0143] The identification module 306 is used to input multiple key features into the detection model so that the detection model determines whether there is a welding defect through the knowledge graph, and outputs an identification result of the presence of the welding defect when it is determined that there is a welding defect. The knowledge graph includes multiple nodes and associations between the multiple nodes, and the multiple nodes include welding process parameter nodes and welding defect nodes, and the welding process parameter nodes correspond to the welding defect nodes.

[0144] In some embodiments, the multiple nodes in the knowledge graph also include a quality standard node, which includes characteristics of welding process parameters when the welding quality meets the quality requirements.

[0145] The node setting module 308 is used to add new nodes in the knowledge graph in response to the welding defect in the recognition result belonging to a new welding defect type, and the new nodes include multiple new welding process parameter nodes and new welding defect nodes corresponding to multiple key features.

[0146] The relationship determination module 310 is used to determine the association relationship between multiple new welding process parameter nodes and new welding defect nodes based on multiple sets of welding data.

[0147] For example, the relationship determination module 310 is used to determine the weight value of each new welding process parameter node of multiple new welding process parameter nodes relative to the new welding defect node based on multiple groups of welding data.

[0148] So far, a detection device for welding quality according to some embodiments of the present disclosure is provided. The detection device includes a receiving module, a preprocessing module, an identification module, a node setting module and a relationship determination module. In the detection device, whether there is a welding defect can be detected based on the collected data and the knowledge graph, and when the welding defect belongs to a new welding defect type, the knowledge graph can be updated, so that it can adapt to the changes in different welding conditions, improve the accuracy of welding defect detection, and improve the reliability of the product.

[0149] Figure 4 It is a block diagram schematically showing a structure of a device for detecting welding quality according to other embodiments of the present disclosure.

[0150] like Figure 4 As shown, the detection device includes a receiving module 302 , a preprocessing module 304 , an identification module 306 , a node setting module 308 and a relationship determination module 310 .

[0151] In some embodiments, Figure 4 As shown, the detection device also includes an adaptive learning module 412. The adaptive learning module 412 is used to compare each key feature of the multiple key features with the features of each welding process parameter node in the knowledge graph to obtain the welding process parameter node closest to each key feature, calculate the error feature between each key feature and the feature of the closest welding process parameter node, and adjust the parameters of the detection model by the gradient descent method based on the error feature to minimize the error feature.

[0152] In some embodiments, Figure 4 As shown, the detection device also includes a graph construction module 414. The graph construction module 414 is used to define multiple nodes in the knowledge graph, and use historical data and empirical knowledge to establish an association relationship between the multiple nodes, wherein the multiple nodes include multiple welding process parameter nodes and welding defect nodes corresponding to the multiple welding process parameter nodes, and the association relationship includes a weight value of each welding process parameter node in the multiple welding process parameter nodes relative to the welding defect node.

[0153] Figure 5Schematically shows a structural block diagram of a device for detecting welding quality according to other embodiments of the present disclosure. The detection device includes a memory 510 and a processor 520. Among them:

[0154] The memory 510 can be a disk, a flash memory, or any other non-volatile storage medium. The memory is used to store Figure 1 and / or Figure 2 The instructions in the corresponding embodiment.

[0155] The processor 520 is coupled to the memory 510 and can be implemented as one or more integrated circuits, such as a microprocessor or a microcontroller. The processor 520 is used to execute instructions stored in the memory to improve the accuracy of welding defect detection and improve the reliability of the product.

[0156] In some embodiments, it is also possible to Figure 6 As shown, the detection device 600 includes a memory 610 and a processor 620. The processor 620 is coupled to the memory 610 via a BUS 630. The detection device 600 can also be connected to an external storage device 650 via a storage interface 640 to call external data, and can also be connected to a network or another computer system (not shown) via a network interface 660, which will not be described in detail here.

[0157] In this embodiment, the data instructions are stored in the memory, and the instructions are processed by the processor, so as to improve the accuracy of welding defect detection and the reliability of the product.

[0158] Figure 7 is a block diagram schematically showing a structure of a system for detecting welding quality according to some embodiments of the present disclosure.

[0159] like Figure 7 As shown, the detection system includes: a current sensor 710, a voltage sensor 720, a temperature sensor 730, an image sensor 740, a sound sensor 750 and a detection device 760. The current sensor 710, the voltage sensor 720, the temperature sensor 730, the image sensor 740 and the sound sensor 750 are all electrically connected to the detection device 760. For example, the detection device 760 can be as follows Figure 3 , Figure 4 , Figure 5 or Figure 6 The detection device shown.

[0160] The embodiments of the present disclosure significantly improve the accuracy, adaptability and efficiency of welding quality detection by constructing a detection device or detection system for welding quality based on a knowledge graph and combining advanced technologies such as multi-source data fusion, dynamic update and adaptive learning.

[0161] First, multi-source data fusion technology enables the system to comprehensively analyze multi-dimensional data such as current, voltage, temperature, image and sound waves during the welding process, so as to more comprehensively and accurately identify welding defects. Compared with the traditional detection method that relies on a single data source, the method, device or system of the embodiment of the present disclosure improves the accuracy of welding defect identification to 90%-95% in industrial testing, which is higher than the 70%-85% of the traditional method.

[0162] Secondly, the introduction of dynamic knowledge graphs enables the system to update and optimize the detection model in real time. Through continuous learning of new data, the device or system automatically adds or adjusts the nodes and relationships in the graph to always reflect the latest welding quality standards and defect patterns. This dynamic update capability enables the system to maintain high adaptability under different welding conditions, and the detection error can be reduced by 25%-30%.

[0163] In addition, the adaptive learning mechanism further enhances the automation and intelligence level of the device or system. The device or system can automatically adjust the detection model parameters according to real-time feedback, reducing the need for manual intervention. This not only improves the detection efficiency (for example, the efficiency is increased by about 30%-40%), but also reduces the misjudgment and missed judgment rates (for example, the misjudgment rate is reduced by 20%). The device or system can adapt to a variety of complex welding conditions, such as welding operations under different materials, processes and environments, and improve the efficiency and reliability of quality inspection.

[0164] Furthermore, the continuous optimization capability and high scalability of the embodiments of the present disclosure enable the device or system to continuously improve performance in long-term applications, adapt to changes in new materials and new processes, and form a highly intelligent and automated welding quality inspection platform. In summary, the methods, devices and / or systems of the embodiments of the present disclosure have brought significant technological progress in the field of welding quality inspection and have broad industrial application prospects.

[0165] In some embodiments, the present disclosure further provides a computer-readable storage medium (eg, a non-transitory computer-readable storage medium) having computer program instructions stored thereon, which when executed by a processor implements Figure 1 and / or Figure 2 The steps of the method in the corresponding embodiment. Those skilled in the art should understand that the embodiments of the present disclosure can be provided as methods, devices, or computer program products. Therefore, the present disclosure can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present disclosure can take the form of a computer program product implemented on one or more computer-usable non-transient storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0166] The present disclosure is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present disclosure. It should be understood that each process and / or block in the flowchart and / or block diagram and the combination of processes and / or blocks in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0167] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0168] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0169] In some embodiments of the present disclosure, a computer program product is further provided. The computer program product includes a computer program or instructions. When the computer program or instructions are executed by a processor, the detection method as described above is implemented.

[0170] In some embodiments of the present disclosure, a computer program is further provided, comprising: instructions, which, when executed by a processor, cause the processor to perform the detection method as described above.

[0171] So far, the present disclosure has been described in detail. In order to avoid obscuring the concept of the present disclosure, some details known in the art are not described. Based on the above description, those skilled in the art can fully understand how to implement the technical solution disclosed here.

[0172] Although some specific embodiments of the present disclosure have been described in detail by way of example, it should be understood by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present disclosure. It should be understood by those skilled in the art that the above embodiments may be modified without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.

Claims

1. A method for detecting welding quality, comprising: Receiving multiple sets of welding data collected by multiple sensors during the welding process; Preprocessing the plurality of sets of welding data to obtain a plurality of key features; Inputting the multiple key features into a detection model so that the detection model determines whether a welding defect exists through a knowledge graph, wherein the knowledge graph includes multiple nodes and association relationships between the multiple nodes, the multiple nodes include welding process parameter nodes and welding defect nodes, and the welding process parameter nodes correspond to the welding defect nodes; In the case where it is determined that a welding defect exists, outputting an identification result that the welding defect exists; In response to the welding defect in the recognition result belonging to a new welding defect type, adding a new node in the knowledge graph, the new node including a plurality of new welding process parameter nodes and a new welding defect node corresponding to the plurality of key features; and According to the multiple sets of welding data, an association relationship between the multiple new welding process parameter nodes and the new welding defect nodes is established.

2. The detection method according to claim 1, wherein: Establishing association relationships between the multiple new welding process parameter nodes and the new welding defect nodes according to the multiple sets of welding data includes: According to the multiple groups of welding data, a weight value of each new welding process parameter node of the multiple new welding process parameter nodes relative to the new welding defect node is determined.

3. The detection method according to claim 1, further comprising: Compare each key feature of the multiple key features with the feature of each welding process parameter node in the knowledge graph to obtain a welding process parameter node closest to each key feature; Calculating an error characteristic between each of the key characteristics and a characteristic of the closest welding process parameter node; and Based on the error feature, the parameters of the detection model are adjusted by a gradient descent method to minimize the error feature.

4. The detection method according to claim 1, wherein: The multiple nodes in the knowledge graph also include a quality standard node, and the quality standard node includes characteristics of welding process parameters when the welding quality meets the quality requirements.

5. The detection method according to claim 1, wherein: The multiple sets of welding data include at least two sets of welding current data, welding voltage data, temperature data of the welding zone, weld seam image data and sound wave data during the welding process.

6. The detection method according to claim 1, wherein: Preprocessing the multiple sets of welding data includes: The multiple sets of welding data are subjected to noise reduction, normalization and feature extraction processing to obtain the multiple key features.

7. The detection method according to claim 1, further comprising: Before receiving the plurality of sets of welding data, constructing the knowledge graph; Wherein, constructing the knowledge graph includes: Defining the plurality of nodes in the knowledge graph, wherein the plurality of nodes include a plurality of welding process parameter nodes and welding defect nodes corresponding to the plurality of welding process parameter nodes; An association relationship between the multiple nodes is established by using historical data and empirical knowledge, wherein the association relationship includes a weight value of each welding process parameter node in the multiple welding process parameter nodes relative to the welding defect node.

8. A device for detecting welding quality, comprising: A receiving module, used for receiving multiple sets of welding data collected by multiple sensors during the welding process; A preprocessing module, used for preprocessing the plurality of welding data sets to obtain a plurality of key features; an identification module, configured to input the plurality of key features into a detection model, so that the detection model determines whether a welding defect exists through a knowledge graph, and outputs an identification result of the existence of the welding defect when it is determined that the welding defect exists, wherein the knowledge graph includes a plurality of nodes and associations between the plurality of nodes, the plurality of nodes include a welding process parameter node and a welding defect node, and the welding process parameter node corresponds to the welding defect node; a node setting module, configured to add a new node in the knowledge graph in response to the welding defect in the recognition result belonging to a new welding defect type, wherein the new node includes a plurality of new welding process parameter nodes and a new welding defect node corresponding to the plurality of key features; and The relationship determination module is used to determine the association relationship between the multiple new welding process parameter nodes and the new welding defect nodes based on the multiple sets of welding data.

9. The detection device according to claim 8, wherein: The relationship determination module is used to determine the weight value of each new welding process parameter node of the multiple new welding process parameter nodes relative to the new welding defect node based on the multiple groups of welding data.

10. The detection device according to claim 8, further comprising: An adaptive learning module is used to compare each key feature of the multiple key features with the features of each welding process parameter node in the knowledge graph to obtain a welding process parameter node closest to each key feature, calculate an error feature between each key feature and the features of the closest welding process parameter node, and based on the error feature, adjust the parameters of the detection model by a gradient descent method to minimize the error feature.

11. The detection device according to claim 8, wherein: The multiple nodes in the knowledge graph also include a quality standard node, and the quality standard node includes characteristics of welding process parameters when the welding quality meets the quality requirements.

12. The detection device according to claim 8, wherein: The multiple sets of welding data include at least two sets of welding current data, welding voltage data, temperature data of the welding zone, weld seam image data and sound wave data during the welding process.

13. The detection device according to claim 8, wherein: The preprocessing module is used to perform noise reduction, normalization and feature extraction on the multiple sets of welding data to obtain the multiple key features.

14. The detection device according to claim 8, further comprising: A graph construction module is used to define the multiple nodes in the knowledge graph and use historical data and empirical knowledge to establish an association relationship between the multiple nodes, wherein the multiple nodes include multiple welding process parameter nodes and welding defect nodes corresponding to the multiple welding process parameter nodes, and the association relationship includes a weight value of each welding process parameter node in the multiple welding process parameter nodes relative to the welding defect node.

15. A device for detecting welding quality, comprising: Memory; as well as A processor coupled to the memory, wherein the processor is configured to execute the detection method according to any one of claims 1 to 7 based on instructions stored in the memory.

16. A welding quality detection system comprising: A current sensor, a voltage sensor, a temperature sensor, an image sensor, a sound sensor and a detection device as described in any one of claims 8 to 15, wherein the current sensor, the voltage sensor, the temperature sensor, the image sensor and the sound sensor are all electrically connected to the detection device.

17. A computer-readable storage medium having computer instructions stored thereon, wherein the computer instructions, when executed by a processor, implement the detection method according to any one of claims 1 to 7.

18. A computer program product, comprising a computer program or instructions, which implement the detection method according to any one of claims 1 to 7 when executed by a processor.

Images