A resistance spot welding quality monitoring method and system based on edge computing

Abstract

The present invention discloses a resistance spot welding quality monitoring method and system based on edge computing. The method comprises: obtaining the welding voltage data and the welding current data of the resistance spot welding machine, and constructing the welding dynamic resistance curve of the resistance spot welding machine; constructing an embedded neural network model based on the welding dynamic resistance curve of the resistance spot welding machine and the Tensor Flow framework; and performing weld quality prediction on the welding dynamic resistance curve of the resistance spot welding machine based on the embedded neural network model to obtain weld quality prediction results. The present invention can automatically extract the characteristics of the dynamic resistance data and the spot welding quality during the spot welding process, thereby improving the welding quality detection accuracy of the resistance spot welding machine. As a resistance spot welding quality monitoring method and system based on edge computing, the present invention can be widely used in the field of intelligent detection technology for resistance welding manufacturing.

Description

Technical Field

[0001] The present invention relates to the field of intelligent detection technology for resistance welding manufacturing, and in particular to a resistance spot welding quality monitoring method and system based on edge computing. Background Art

[0002] Resistance spot welding is a key technology for joining structural components in manufacturing industries such as home appliances, automobiles, electronics, and aerospace. For example, in automobile manufacturing, the welds used in the vehicle body directly impact the vehicle's structural rigidity and crash safety performance, making the quality of welds a critical factor in ensuring the vehicle's overall quality meets standards. Current research on resistance welding quality testing has conducted in-depth analysis of various types of data from the welding process, including electrical signals, electrode displacement, ultrasonic signals, and image data. Numerous studies have shown that defective welds are reflected in the corresponding welding process data, making it possible to apply data analysis methods in actual production lines. Furthermore, some research on spot welding quality assessment methods based on shallow machine learning models requires intermediate steps such as manual feature extraction, feature analysis and selection, and feature dimensionality reduction. This approach can only extract limited features, and empirically extracted features often fail to analyze the internal and external connections between data changes. Furthermore, after deploying a machine learning model, the model must be updated, a process that also requires manual effort. Summary of the Invention

[0003] In order to solve the above technical problems, the purpose of the present invention is to provide a resistance spot welding quality monitoring method and system based on edge computing, which can automatically extract the dynamic resistance data and spot welding quality characteristics during the spot welding process, thereby improving the welding quality detection accuracy of the resistance spot welding machine.

[0004] The first technical solution adopted by the present invention is: a resistance spot welding quality monitoring method based on edge computing, comprising the following steps:

[0005] Obtain welding voltage data and welding current data of the resistance spot welding machine, and construct a welding dynamic resistance curve of the resistance spot welding machine;

[0006] Based on the dynamic resistance curve of the resistance spot welder and the TensorFlow framework, an embedded neural network model was constructed;

[0007] Based on the embedded neural network model, the welding dynamic resistance curve of the resistance spot welder is used to predict the weld quality, and the weld quality prediction result is obtained.

[0008] Furthermore, the step of obtaining the welding voltage data and the welding current data of the resistance spot welder and constructing the welding dynamic resistance curve of the resistance spot welder specifically includes:

[0009] Obtain welding voltage data of the resistance spot welder through the voltage acquisition module;

[0010] Obtain welding current data of the resistance spot welding machine through the current acquisition module;

[0011] The dynamic resistance curve of the resistance spot welder is calculated according to the welding voltage data and the welding current data of the resistance spot welder to obtain the welding dynamic resistance curve of the resistance spot welder.

[0012] Furthermore, the calculation expression of the dynamic resistance curve is specifically as follows:

[0013]

[0014] In the above formula, R(t) represents the change of dynamic resistance over time, V(t) and I(t) represent the change of welding voltage and welding current over time, respectively.

[0015] Furthermore, the step of constructing an embedded neural network model based on the welding dynamic resistance curve of the resistance spot welder and the Tensor Flow framework specifically includes:

[0016] Performing neural network model training based on a dynamic welding resistance curve of a resistance spot welder to obtain an original neural network model, wherein the original neural network model represents a one-dimensional convolutional neural network model built under a TensorFlow framework;

[0017] The original neural network model is subjected to lightweight operations such as quantization and pruning to obtain an embedded neural network model.

[0018] Furthermore, the embedded neural network model specifically includes an input layer, a first convolutional layer, a first pooling layer, a second convolutional layer, a second pooling layer, a third convolutional layer, a third pooling layer, a first fully connected layer, a second fully connected layer, a third fully connected layer and an output layer, wherein the input layer, the first convolutional layer, the first pooling layer, the second convolutional layer, the second pooling layer, the third convolutional layer, the third pooling layer, the first fully connected layer, the second fully connected layer, the third fully connected layer and the output layer are connected in sequence.

[0019] Furthermore, the step of performing weld quality prediction on the dynamic resistance curve of the resistance spot welder based on the embedded neural network model to obtain the weld quality prediction result specifically includes:

[0020] Input the welding dynamic resistance curve of the resistance spot welder into the embedded neural network model;

[0021] Based on the input layer of the embedded neural network model, the welding dynamic resistance curve of the resistance spot welder is obtained;

[0022] Based on the first convolution layer of the embedded neural network model, feature extraction processing is performed on the welding dynamic resistance curve of the resistance spot welder to obtain the welding dynamic resistance characteristic curve of the first resistance spot welder;

[0023] Based on the first pooling layer of the embedded neural network model, pooling processing is performed on the welding dynamic resistance characteristic curve of the first resistance spot welder to obtain the welding dynamic resistance characteristic curve of the resistance spot welder after the first pooling;

[0024] Based on the second convolutional layer of the embedded neural network model, feature extraction processing is performed on the welding dynamic resistance characteristic curve of the resistance spot welder after the first pooling to obtain the welding dynamic resistance characteristic curve of the second resistance spot welder;

[0025] Based on the second pooling layer of the embedded neural network model, pooling processing is performed on the welding dynamic resistance characteristic curve of the second resistance spot welder to obtain the welding dynamic resistance characteristic curve of the resistance spot welder after the second pooling;

[0026] Based on the third convolutional layer of the embedded neural network model, feature extraction processing is performed on the welding dynamic resistance characteristic curve of the resistance spot welder after the second pooling to obtain a third welding dynamic resistance characteristic curve of the resistance spot welder;

[0027] Based on the third pooling layer of the embedded neural network model, pooling processing is performed on the welding dynamic resistance characteristic curve of the third resistance spot welding machine to obtain the welding dynamic resistance characteristic curve of the resistance spot welding machine after the third pooling;

[0028] Based on the first, second, and third fully connected layers of the embedded neural network model, feature mapping processing is performed on the welding dynamic resistance characteristic curve of the resistance spot welder after the third pooling to obtain the weld quality prediction result;

[0029] Based on the output layer of the embedded neural network model, the solder joint quality prediction results are output.

[0030] Furthermore, it also includes combining the welding voltage data and the welding current data of the resistance spot welding machine with the welding spot quality prediction result and performing a visual display process.

[0031] Furthermore, it also includes:

[0032] The abnormal solder joint data in the solder joint quality prediction results are selected and processed to construct an abnormal solder joint data set;

[0033] Performing data enhancement processing on the abnormal solder joint data set to obtain an enhanced abnormal solder joint data set;

[0034] The embedded neural network model is trained and updated based on the enhanced abnormal solder joint data set to construct an updated embedded neural network model;

[0035] Perform accuracy tests on the updated embedded neural network model and the embedded neural network model, and save the embedded neural network model corresponding to the higher accuracy.

[0036] The second technical solution adopted by the present invention is: a resistance spot welding quality monitoring system based on edge computing, comprising:

[0037] The first module is used to obtain the welding voltage data and the welding current data of the resistance spot welder and construct the welding dynamic resistance curve of the resistance spot welder;

[0038] The second module is used to build an embedded neural network model based on the dynamic resistance curve of the resistance spot welder and the TensorFlow framework;

[0039] The third module is used to predict the quality of the weld spot based on the dynamic resistance curve of the resistance spot welder based on the embedded neural network model to obtain the weld spot quality prediction result.

[0040] The beneficial effects of the method and system of the present invention are as follows: the present invention constructs a dynamic welding resistance curve of the resistance spot welder by acquiring the welding voltage data and the welding current data of the resistance spot welder, further constructs an embedded neural network model based on the dynamic welding resistance curve of the resistance spot welder and the Tensor Flow framework, analyzes and processes the dynamic resistance data in the spot welding process through an end-to-end deep learning model algorithm, takes the original resistance curve data as input and the spot welding quality type as output, realizes automatic extraction of the characteristics of the dynamic resistance data and the spot welding quality in the spot welding process, avoids the complex feature extraction and analysis process, and improves the welding quality detection accuracy of the resistance spot welder. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 This is a flowchart of the steps of a resistance spot welding quality monitoring method based on edge computing of the present invention;

[0042] Figure 2 This is a structural block diagram of a resistance spot welding quality monitoring system based on edge computing in the present invention;

[0043] Figure 3 It is a schematic diagram of the hardware system structure provided by a specific embodiment of the present invention;

[0044] Figure 4 is a schematic diagram of a system architecture provided by a specific embodiment of the present invention;

[0045] Figure 5This is a schematic diagram of the WEB management interface of the cloud platform provided by a specific embodiment of the present invention;

[0046] Figure 6 is a schematic diagram of a system network topology provided by a specific embodiment of the present invention;

[0047] Figure 7 This is a schematic diagram of the workflow of the embedded platform provided by a specific embodiment of the present invention;

[0048] Figure 8 1 is a schematic diagram of a self-update process of a neural network model on a cloud platform provided by a specific embodiment of the present invention;

[0049] Figure 9 It is a structural diagram of the embedded neural network model provided by a specific embodiment of the present invention. DETAILED DESCRIPTION

[0050] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. The step numbers in the following embodiments are provided for ease of description only and do not limit the order of the steps. The order of execution of the steps in the embodiments can be adaptively adjusted based on the understanding of those skilled in the art.

[0051] First, it should be noted that this embodiment of the present invention includes an embedded platform and a cloud platform. The embedded platform preprocesses sensor data to obtain dynamic resistance curve data for resistance spot welders, inputs this data into a neural network for prediction, and outputs the quality type of the welds. The embedded platform then transmits this dynamic resistance curve data and the weld prediction results to the cloud platform via a local area network. The cloud platform displays the dynamic resistance curves and prediction results of multiple resistance spot welders in real time and stores them in a database for model training and updating.

[0052] The system can transmit data by connecting multiple embedded platforms and cloud platforms to the same local area network.

[0053] The embedded platform includes a microprocessor, an edge computing module, a voltage acquisition module, a current acquisition module, an Ethernet chip and Ethernet interface, and a display module. The microprocessor coordinates the operation of the embedded platform. The voltage acquisition module collects voltage data during welding, the current acquisition module collects current data during welding, the edge computing module calculates the neural network model, the Ethernet chip and Ethernet interface enable communication between the embedded platform and the cloud platform, and the display module displays the operating status of the embedded platform. The microprocessor receives voltage and current signals collected by sensors via a data bus. The Ethernet chip communicates with the microprocessor via the RMII interface and transmits data to the Ethernet interface socket via two pairs of transmit and receive differential lines. The display module transmits data to the microprocessor via the FMSC bus and displays voltage and current data, dynamic resistance curves, and solder joint quality prediction results on the display screen. The solder joint quality prediction results are calculated by the edge computing module using a neural network model. The neural network model is a one-dimensional convolutional neural network model built within the TensorFlow framework. After training on the cloud platform, it is quantized and pruned to obtain a lightweight embedded neural network model.

[0054] The cloud platform includes a neural network model training module, a neural network model clipping module, a neural network model push module, a database module, and a WEB management interface; the neural network model training module automatically generates a data set by reading data from the database and performs neural network model training to obtain the original neural network model; the original neural network model is a one-dimensional convolutional neural network model built under the Tensor Flow framework; the neural network model clipping module performs lightweight operations such as quantization and clipping on the trained original neural network model to obtain an embedded neural network model; the neural network model push module sends the embedded neural network model to each embedded platform through the network; the database module receives data from the embedded platform in real time and stores the data; the WEB management interface can view the sensor data and solder joint quality prediction results of all embedded platforms in real time, view the historical records of welding, enter or modify the actual detection quality of solder joints, and view and switch each historical version of the neural network model.

[0055] Reference Figure 1 The present invention provides a resistance spot welding quality monitoring method based on edge computing, which includes the following steps:

[0056] S100, obtaining welding voltage data and welding current data of a resistance spot welder, and constructing a welding dynamic resistance curve of the resistance spot welder;

[0057] Specifically, the welding voltage data of the resistance spot welder is obtained through the voltage acquisition module; the welding current data of the resistance spot welder is obtained through the current acquisition module; the dynamic resistance curve is calculated based on the welding voltage data and the welding current data of the resistance spot welder to obtain the welding dynamic resistance curve of the resistance spot welder.

[0058] The calculation expression of the dynamic resistance curve is as follows:

[0059]

[0060] In the above formula, R(t) represents the change of dynamic resistance over time, V(t) and I(t) represent the change of welding voltage and welding current over time, respectively.

[0061] S200, based on the dynamic resistance curve of the resistance spot welder and the TensorFlow framework, build an embedded neural network model;

[0062] Specifically, a neural network model is trained based on the welding dynamic resistance curve of a resistance spot welder to obtain an original neural network model, which represents a one-dimensional convolutional neural network model built under the Tensor Flow framework; the original neural network model is subjected to lightweight operations such as quantization and cropping to obtain an embedded neural network model.

[0063] In this embodiment, if Figure 9 As shown, the embedded neural network model specifically includes an input layer, a first convolutional layer, a first pooling layer, a second convolutional layer, a second pooling layer, a third convolutional layer, a third pooling layer, a first fully connected layer, a second fully connected layer, a third fully connected layer and an output layer, wherein the input layer, the first convolutional layer, the first pooling layer, the second convolutional layer, the second pooling layer, the third convolutional layer, the third pooling layer, the first fully connected layer, the second fully connected layer, the third fully connected layer and the output layer are connected in sequence.

[0064] S300, based on the embedded neural network model, the welding dynamic resistance curve of the resistance spot welder is used to predict the weld quality and obtain the weld quality prediction result.

[0065] Specifically, the welding dynamic resistance curve of the resistance spot welder is input into the embedded neural network model; based on the input layer of the embedded neural network model, the welding dynamic resistance curve of the resistance spot welder is obtained; based on the first convolution layer of the embedded neural network model, the welding dynamic resistance curve of the resistance spot welder is subjected to feature extraction processing to obtain the welding dynamic resistance characteristic curve of the first resistance spot welder; based on the first pooling layer of the embedded neural network model, the welding dynamic resistance characteristic curve of the first resistance spot welder is subjected to pooling processing to obtain the welding dynamic resistance characteristic curve of the resistance spot welder after the first pooling; based on the second convolution layer of the embedded neural network model, the welding dynamic resistance characteristic curve of the resistance spot welder after the first pooling is subjected to feature extraction processing to obtain the welding dynamic resistance characteristic curve of the second resistance spot welder; based on the second pooling layer of the embedded neural network model, the welding dynamic resistance characteristic curve of the second resistance spot welder is subjected to feature extraction processing to obtain the welding dynamic resistance characteristic curve of the second resistance spot welder The welding dynamic resistance characteristic curve of the welding machine is pooled to obtain the second pooled welding dynamic resistance characteristic curve of the resistance spot welding machine; based on the third convolution layer of the embedded neural network model, the characteristic curve of the welding dynamic resistance characteristic curve of the resistance spot welding machine after the second pooling is subjected to feature extraction processing to obtain the third welding dynamic resistance characteristic curve of the resistance spot welding machine; based on the third pooling layer of the embedded neural network model, the welding dynamic resistance characteristic curve of the third resistance spot welding machine is pooled to obtain the third pooled welding dynamic resistance characteristic curve of the resistance spot welding machine; based on the first fully connected layer, the second fully connected layer, and the third fully connected layer of the embedded neural network model, the welding dynamic resistance characteristic curve of the resistance spot welding machine after the third pooling is subjected to feature mapping processing to obtain the weld quality prediction result; based on the output layer of the embedded neural network model, the weld quality prediction result is output.

[0066] In this embodiment, the embedded platform transmits the dynamic resistance curve of the welding to the edge computing module for prediction through the neural network model and outputs the prediction result of the solder joint quality, and transmits the dynamic resistance curve and quality prediction result to the cloud platform; if the prediction result is normal, the solder joint is judged to be qualified and proceeds to the next welding; if the prediction result is abnormal (defects such as cold solder joint, burn-through, small diameter, etc.), the solder joint is judged to be unqualified and an alarm is issued; multiple welding operations are performed, the defective solder joints are recorded and entered into the cloud platform.

[0067] Another embodiment of the present invention also includes selecting and processing abnormal solder joint data in the solder joint quality prediction results to construct an abnormal solder joint data set; performing data enhancement processing on the abnormal solder joint data set to obtain an enhanced abnormal solder joint data set; training and updating the embedded neural network model based on the enhanced abnormal solder joint data set to construct an updated embedded neural network model; performing accuracy testing on the updated embedded neural network model and the embedded neural network model, and saving the embedded neural network model corresponding to the higher accuracy.

[0068] Specifically, after collecting data from multiple weld spots, the cloud platform generates a data set from all welding data stored in the database and divides it into a training set and a test set in a ratio of 7:3; based on the low probability of defects during welding by a resistance spot welder, the data enhancement method is used to expand the data of defective welds and optimize the model's recognition of defective welds; based on the simple structure of spot welding dynamic resistance data, an original one-dimensional convolutional neural network model is built under the TensorFlow framework and trained using the training set. After training, the model is quantized and cropped to obtain an embedded neural network model, which is then tested using the test set.

[0069] The embedded neural network model is pushed to the embedded platform, which receives the neural network model and updates the model; then a front-end interface of the cloud platform is built to realize the dynamic resistance curve display of resistance spot welding of multiple embedded platforms, and the display and statistical recording of spot welding quality prediction results.

[0070] like Figure 3 As shown in the figure, the embedded platform collects data from the resistance welding robot and transmits it via Ethernet to the cloud server of the cloud platform. The cloud platform includes web management, database system, and model update modules. Each embedded platform is responsible for data collection, analysis, and transmission for one resistance welding robot, and the cloud platform manages multiple embedded platforms.

[0071] like Figure 4 The system architecture of the present invention is shown in Figure 1, which includes an embedded platform and a cloud platform. The embedded platform preprocesses sensor data to obtain dynamic resistance curve data for resistance spot welders, inputs this data into a neural network for prediction, and outputs the quality type of the weld. The embedded platform transmits this dynamic resistance curve data and weld prediction results to the cloud platform via a local area network. The cloud platform displays the dynamic resistance curves and prediction results of multiple resistance spot welders in real time and stores them in a database for model training and updating.

[0072] like Figure 5As shown, the WEB management interface of the cloud platform includes a real-time data viewing page, a historical data viewing page, an actual detection defect entry interface, a historical version model viewing and switching interface, and an embedded platform detection parameter modification page; the real-time data viewing page can view the real-time welding data and solder joint quality detection results of multiple embedded platforms; the historical data viewing page can view the historical welding data of all embedded platforms and modify their data; the actual detection defect entry interface can enter defective solder joints found during actual manual inspection; the historical version model viewing and switching interface can view the accuracy curves and model parameter setting values ​​of all historical versions of the neural network model, and choose to switch the detection model used by the current embedded platform to a certain historical version; the embedded platform detection parameter modification page can adjust the detection parameters of the embedded platform.

[0073] Further, if Figure 6 As shown, the system can consist of one or more embedded platforms and a cloud platform. Data is transmitted between these platforms via a local area network (LAN) connected by switches. An embedded platform collects and processes welding information from a single resistance spot welder. The cloud server stores data from all resistance spot welders.

[0074] In some embodiments, the cloud server is connected to the local area network where the embedded platform is located via Ethernet, and the embedded platform and the cloud server use the TCP protocol to exchange data. The cloud server stores the received data in the database of the cloud platform and visualizes the data on the cloud platform.

[0075] like Figure 7 As shown in the figure, after the resistance spot welder begins operation, the embedded platform collects welding current and voltage data in real time, preprocesses the voltage and current data to generate a dynamic resistance curve, and then inputs the dynamic resistance curve data into the embedded neural network model to predict the weld quality. The prediction result is displayed on the embedded platform's display module. If the prediction result is abnormal, an alarm is issued. Simultaneously, the welding dynamic resistance data and the welding prediction result are transmitted to the cloud server, and the welding status is displayed on the cloud platform web page. After all welding tasks are completed, the cloud platform optimizes the neural network model. Before model optimization, the actual defective welds detected need to be recorded in the cloud platform.

[0076] The actual detection of defective welds and entering them into the cloud platform involves manual random inspection of welds after welding is completed. If the welds are found to be defective during manual inspection, they will be recorded and entered into the cloud platform.

[0077] The optimization of neural network models includes neural network model training, model quantization and pruning, and model push. Figure 8As shown, all solder joint data stored in the cloud server is first extracted. Data enhancement is performed on solder joint data that are actually detected as defects to obtain more defect data. All data is converted into TensorFlow input format, and a training set and test set are generated in a 7:3 ratio for model training. In some embodiments of the present invention, the cloud server stores the solder joint data in a MySQL server. Each embedded platform has a corresponding number, each embedded platform has multiple solder joints with different welding parameters, and each solder joint has its own corresponding model. When training the model, the corresponding model is trained based on the device number and solder joint sequence number.

[0078] Since the probability of welding defects in resistance spot welders is low in actual scenarios, resulting in a small amount of defective data, data enhancement is required. In some embodiments of the present invention, periodic noise, Gaussian white noise or random noise is added to simulate the situation where electromagnetic interference causes interference in data acquisition during welding. In some embodiments, a generative adversarial network is used to generate new welding data. In theory, high-quality synthetic data can be generated, but due to the complexity of the training process of the generative adversarial network, the problem of mode collapse is prone to occur. The signal-to-noise ratio is a measure used to describe the relationship between signal and noise, and is defined as the ratio of signal power to noise power. The higher the signal-to-noise ratio, the greater the signal power is compared to the noise power, indicating that the data quality is better. Its calculation formula is as follows:

[0079]

[0080] In the above formula, P s Indicates the power of the signal, P z Indicates the power of the noise.

[0081] In some embodiments, Gaussian white noise is randomly added to the data in the training set to generate new data with different S values, and the model evaluation accuracy of different S values ​​is statistically analyzed to obtain the S value parameter with the highest test accuracy. After completing the selection of the training set, it is necessary to select a suitable model for training. In some embodiments of the present invention, the dynamic resistance data in the resistance spot welding process under study does not have obvious periodicity, and the length of the original data sample is one-dimensional time series data, which has a simple structure. Therefore, a one-dimensional convolutional neural network is designed to construct an online detection model for resistance welding quality. In some embodiments, the specific implementation method of model training is as follows:

[0082] The solder joint quality evaluation model is constructed using three convolutional feature extractors and three fully connected layers, such as Figure 9As shown in the figure, dynamic resistance curve data is input, and after three rounds of convolution and max pooling, the final pooling layer is obtained. A flattening layer is used to concatenate the multi-channel feature map matrices obtained from these multiple convolutions, and the output vector is used as the input for the fully connected layer. After three layers of dimensionality rescaling, the resulting 5-dimensional feature vector is used as the input for the SoftMax layer. To enhance the model's nonlinear mapping capabilities, a ReLU activation function is added after each convolutional and fully connected layer in the network. Furthermore, techniques such as BatchNorm and Dropout layers are introduced to prevent overfitting and improve the model's generalization.

[0083] In some instances, the algorithm model is written under the open source deep learning framework Tensor Flow, and relevant algorithm modules are selected for training and testing on the device. After the model training is completed, it needs to be quantized and trimmed to be converted into a neural network model that can be used by the embedded platform and the model is tested using a test set. In some embodiments, the microprocessor model used by the embedded platform is RK3588, and the model trained using the Tensor flow framework is saved in .pb format. The TensorFlow model is converted to a TFLite model using TensorFlow Lite Converter, and the default optimization and INT16 data type are selected to perform preliminary quantization of the model. The TFLite model is converted to an RKNN model using RKNN-Toolkit2, and the model is further quantized and optimized. The RKNN model is a neural network model format supported by the Rockchip series of microprocessors. After the embedded model is generated, the simulator provided by RKNN-Toolkit2 is used to simulate the Rockchip NPU to run the RKNN model and the model is tested using a test set.

[0084] After the test is completed, the accuracy of the model is generated. If the accuracy of the model is higher than that of the old version model, the model is pushed to the embedded platform and the old version model is backed up. Since the resistance spot welding quality inspection model is a classification task, there are many evaluation indicators for model accuracy, such as accuracy, precision, and recall. In some embodiments, the accuracy rate (Ac) is used to evaluate the model accuracy, and its calculation formula is as follows:

[0085]

[0086] In the above formula, TP represents true positive examples, TN represents true negative examples, FP represents false positive examples, and FN represents false negative examples.

[0087] Pushing the embedded neural network model involves pushing it to the cloud platform and receiving it on the embedded platform. In some embodiments, the cloud platform issues a TCP message, allowing the embedded platform to receive a model update command, download the model file on the cloud platform to the embedded platform's memory, stop the model prediction program, delete the original model file, and restart the model prediction program to complete the loading of the new model version.

[0088] In summary, the embodiment of the present invention analyzes and processes the dynamic resistance data during the spot welding process through an end-to-end deep learning model algorithm, takes the original resistance curve data as input, and the spot welding quality type as output, thereby realizing automatic extraction of the characteristics of the dynamic resistance data and spot welding quality during the spot welding process, avoiding the complex feature extraction and analysis process, achieving higher detection accuracy, and solving the problems of high detection costs and limitations of manual feature extraction in traditional detection technologies. This method deploys the neural network model on the edge device for calculation, saving computing resources for cloud model training. The cloud automatically trains and updates the model in an idle state, and automatically lightweights and converts the updated model and pushes it to the edge device, eliminating the need for manual upgrades of the edge device. This further improves the automation and intelligence of spot welding spot quality detection.

[0089] Therefore, the embodiments of the present invention have the following advantages over the prior art:

[0090] 1) Applicable to both robotic and manual resistance spot welding, the embedded platform instantly displays the workpiece's welding status after welding, and the cloud platform displays the location of weld defects, enabling inspectors to gain a more comprehensive understanding of the workpiece's welding condition and conduct targeted weld inspection and repair work. The cloud platform can self-learn defects generated by workpiece welding and regularly update the spot welding inspection model. Compared to traditional defect detection, which requires manual intervention for model retraining and deployment, this saves human resources and improves inspection efficiency.

[0091] 2) The collection of solder joint data and prediction of solder joint quality are realized on the embedded platform, making the quality inspection of resistance spot welding more dependent on big data information rather than the experience of inspection engineers, reducing labor costs, improving the level of automated inspection of resistance spot welding, and thus improving the production efficiency of large-scale resistance spot welding. The edge computing implemented on the embedded platform is highly efficient and low-cost. Compared with cloud computing, which requires the deployment of a large number of servers, it reduces the cost of large-scale spot welding inspection.

[0092] 3) The cloud platform is used to obtain and save welding information during the welding process and the spot welding quality prediction results formed by model calculation, which facilitates the analysis of weld quality by inspectors and enables the data of the welding process to be quantified and traced back.

[0093] Reference Figure 2 , a resistance spot welding quality monitoring system based on edge computing, including:

[0094] The first module 201 is used to obtain welding voltage data and welding current data of the resistance spot welder and construct a welding dynamic resistance curve of the resistance spot welder;

[0095] The second module 202 is used to build an embedded neural network model based on the welding dynamic resistance curve of the resistance spot welder and the Tensor Flow framework;

[0096] The third module 203 is used to predict the quality of the weld spot based on the dynamic resistance curve of the resistance spot welder based on the embedded neural network model to obtain the weld spot quality prediction result.

[0097] The contents of the above method embodiments are all applicable to the present system embodiments. The functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0098] The above is a specific description of the preferred implementation of the present invention, but the invention is not limited to the embodiments. Those skilled in the art can make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of this application.

Claims

1. A resistance spot welding quality monitoring method based on edge computing, characterized in that: The following steps are involved: Obtain welding voltage data and welding current data of the resistance spot welding machine, and construct a welding dynamic resistance curve of the resistance spot welding machine; Build an embedded neural network model based on the dynamic resistance curve of the resistance spot welder and the Tensor Flow framework; Based on the embedded neural network model, the welding dynamic resistance curve of the resistance spot welder is used to predict the weld quality, and the weld quality prediction results are obtained, including: Input the welding dynamic resistance curve of the resistance spot welder into the embedded neural network model; Based on the input layer of the embedded neural network model, the welding dynamic resistance curve of the resistance spot welder is obtained; Based on the first convolution layer of the embedded neural network model, feature extraction processing is performed on the welding dynamic resistance curve of the resistance spot welder to obtain the welding dynamic resistance characteristic curve of the first resistance spot welder; Based on the first pooling layer of the embedded neural network model, pooling processing is performed on the welding dynamic resistance characteristic curve of the first resistance spot welder to obtain the welding dynamic resistance characteristic curve of the resistance spot welder after the first pooling; Based on the second convolutional layer of the embedded neural network model, feature extraction processing is performed on the welding dynamic resistance characteristic curve of the resistance spot welder after the first pooling to obtain the welding dynamic resistance characteristic curve of the second resistance spot welder; Based on the second pooling layer of the embedded neural network model, pooling processing is performed on the welding dynamic resistance characteristic curve of the second resistance spot welder to obtain the welding dynamic resistance characteristic curve of the resistance spot welder after the second pooling; Based on the third convolutional layer of the embedded neural network model, feature extraction processing is performed on the welding dynamic resistance characteristic curve of the resistance spot welder after the second pooling to obtain a third welding dynamic resistance characteristic curve of the resistance spot welder; Based on the third pooling layer of the embedded neural network model, pooling processing is performed on the welding dynamic resistance characteristic curve of the third resistance spot welding machine to obtain the welding dynamic resistance characteristic curve of the resistance spot welding machine after the third pooling; Based on the first, second, and third fully connected layers of the embedded neural network model, feature mapping processing is performed on the welding dynamic resistance characteristic curve of the resistance spot welder after the third pooling to obtain the weld quality prediction result; Based on the output layer of the embedded neural network model, the solder joint quality prediction results are output.

2. The resistance spot welding quality monitoring method based on edge computing according to claim 1, characterized in that: The step of obtaining the welding voltage data and the welding current data of the resistance spot welder and constructing the welding dynamic resistance curve of the resistance spot welder specifically includes: Obtain welding voltage data of the resistance spot welder through the voltage acquisition module; Obtain welding current data of the resistance spot welding machine through the current acquisition module; The dynamic resistance curve of the resistance spot welder is calculated according to the welding voltage data and the welding current data of the resistance spot welder to obtain the welding dynamic resistance curve of the resistance spot welder.

3. The resistance spot welding quality monitoring method based on edge computing according to claim 2, characterized in that: The calculation expression of the dynamic resistance curve is specifically as follows: In the above formula, R(t) represents the change of dynamic resistance over time, V(t) and I(t) represent the change of welding voltage and welding current over time, respectively.

4. The resistance spot welding quality monitoring method based on edge computing according to claim 3 is characterized in that: The step of building an embedded neural network model based on the welding dynamic resistance curve of the resistance spot welder and the Tensor Flow framework specifically includes: Performing neural network model training based on a dynamic welding resistance curve of a resistance spot welder to obtain an original neural network model, wherein the original neural network model represents a one-dimensional convolutional neural network model built under a TensorFlow framework; The original neural network model is subjected to lightweight operations such as quantization and pruning to obtain an embedded neural network model.

5. The method for monitoring resistance spot welding quality based on edge computing according to claim 4, characterized in that: The embedded neural network model specifically includes an input layer, a first convolutional layer, a first pooling layer, a second convolutional layer, a second pooling layer, a third convolutional layer, a third pooling layer, a first fully connected layer, a second fully connected layer, a third fully connected layer and an output layer, wherein the input layer, the first convolutional layer, the first pooling layer, the second convolutional layer, the second pooling layer, the third convolutional layer, the third pooling layer, the first fully connected layer, the second fully connected layer, the third fully connected layer and the output layer are connected in sequence.

6. The method for monitoring resistance spot welding quality based on edge computing according to claim 5, characterized in that: The method also includes combining the welding voltage data and the welding current data of the resistance spot welding machine with the welding spot quality prediction result, and performing a visual display process.

7. The method for monitoring resistance spot welding quality based on edge computing according to claim 6, characterized in that: Also includes: The abnormal solder joint data in the solder joint quality prediction results are selected and processed to construct an abnormal solder joint data set; Performing data enhancement processing on the abnormal solder joint data set to obtain an enhanced abnormal solder joint data set; The embedded neural network model is trained and updated based on the enhanced abnormal solder joint data set to construct an updated embedded neural network model; Perform accuracy tests on the updated embedded neural network model and the embedded neural network model, and save the embedded neural network model corresponding to the higher accuracy.

8. A resistance spot welding quality monitoring system based on edge computing, characterized in that: Includes the following modules: The first module is used to obtain the welding voltage data and the welding current data of the resistance spot welder and construct the welding dynamic resistance curve of the resistance spot welder; The second module is used to build an embedded neural network model based on the dynamic resistance curve of the resistance spot welder and the TensorFlow framework; The third module is used to predict the quality of the weld spot based on the dynamic resistance curve of the resistance spot welder based on the embedded neural network model, and obtain the weld spot quality prediction results, which specifically include: Input the welding dynamic resistance curve of the resistance spot welder into the embedded neural network model; Based on the input layer of the embedded neural network model, the welding dynamic resistance curve of the resistance spot welder is obtained; Based on the first convolution layer of the embedded neural network model, feature extraction processing is performed on the welding dynamic resistance curve of the resistance spot welder to obtain the welding dynamic resistance characteristic curve of the first resistance spot welder; Based on the first pooling layer of the embedded neural network model, pooling processing is performed on the welding dynamic resistance characteristic curve of the first resistance spot welder to obtain the welding dynamic resistance characteristic curve of the resistance spot welder after the first pooling; Based on the second convolutional layer of the embedded neural network model, feature extraction processing is performed on the welding dynamic resistance characteristic curve of the resistance spot welder after the first pooling to obtain the welding dynamic resistance characteristic curve of the second resistance spot welder; Based on the second pooling layer of the embedded neural network model, pooling processing is performed on the welding dynamic resistance characteristic curve of the second resistance spot welder to obtain the welding dynamic resistance characteristic curve of the resistance spot welder after the second pooling; Based on the third convolutional layer of the embedded neural network model, feature extraction processing is performed on the welding dynamic resistance characteristic curve of the resistance spot welder after the second pooling to obtain the welding dynamic resistance characteristic curve of the third resistance spot welder; based on the third pooling layer of the embedded neural network model, pooling processing is performed on the welding dynamic resistance characteristic curve of the third resistance spot welder to obtain the welding dynamic resistance characteristic curve of the resistance spot welder after the third pooling; Based on the first, second, and third fully connected layers of the embedded neural network model, feature mapping processing is performed on the welding dynamic resistance characteristic curve of the resistance spot welder after the third pooling to obtain the weld quality prediction result; Based on the output layer of the embedded neural network model, the solder joint quality prediction results are output.

Images