Three-phase line sequence detection method and detection system based on multi-dimensional visual analysis

Abstract

The invention discloses a three-phase line sequence detection method and system based on multi-dimensional visual analysis, and the method comprises the steps: carrying out the statistics of the material codes of all motor products, and dividing the line sequences of three-phase lines for the installation of the motor products into a positive phase sequence, a negative phase sequence, and a non-phase sequence; shooting images of line sequence conditions of all three-phase lines to form a basic image set for training a visual model; scanning a to-be-tested motor product material code, and obtaining corresponding three-phase line sequence information; shooting an image of the to-be-detected motor product, and transmitting the image to a three-phase line sequence detection system; and analyzing the image through the trained visual model, and outputting a three-phase line sequence judgment result. The visual model is trained through the pigment recognition technology and the neural network algorithm, automatic detection is achieved, the detection speed and accuracy are improved, and human errors are reduced.

Description

Technical Field

[0001] The present application relates to the field of visual detection technology, and more specifically, to a three-phase line sequence detection method and detection system based on multi-dimensional visual analysis. Background Art

[0002] In the background technology of detecting the line sequence of three-phase lines, the traditional method mainly relies on manual operation and visual inspection equipment box. The manual detection method has the following limitations: a. Low detection efficiency. Manually checking the sequence of three-phase lines takes a lot of time. Especially in large-scale production, this inspection method is particularly inefficient.

[0003] b. Easy to get tired and make mistakes. Long-term repetitive work can easily lead to fatigue of inspectors, thus increasing the risk of mistakes. Once a mistake is made, it may cause the motor to malfunction or even damage the motor or other equipment.

[0004] c. Production delays and increased costs. When manual inspections are made, errors need to be re-inspected and corrected, which will lead to production delays. At the same time, the additional costs incurred during error inspection and correction will also burden the company.

[0005] Manual inspection lacks automated inspection methods, and the lack of effective automated inspection methods means that the installation of the three-phase line cannot be monitored in real time and accurately. This may lead to errors in the installation of the three-phase line, which in turn affects the normal operation of the motor.

[0006] Although the technology that relies on visual inspection equipment boxes has improved the degree of automation of inspection to a certain extent, its use dimensions and scenarios are relatively single. This type of equipment can usually only perform visual analysis at fixed angles and fixed dimensions, and its adaptability and flexibility are limited for complex or changing inspection requirements. In addition, visual inspection equipment boxes often need to be used in fixed locations or environments, which limits their convenience and wide range of use.

[0007] To address the above issues, the following measures can be taken: 1. Introduce automated detection equipment, develop and introduce equipment that can automatically detect the sequence of three-phase lines, such as visual inspection systems based on neural network algorithms and pigment recognition technology. These devices can achieve real-time monitoring and accurate judgment of three-phase lines, thereby improving production efficiency and accuracy.

[0008] 2. Optimize the image recognition and processing algorithms, optimize the existing image recognition and processing algorithms, and improve their accuracy and robustness in identifying three-phase lines. At the same time, combine deep learning and other technologies to achieve automated and intelligent monitoring of three-phase line installation.

[0009] 3. Strengthen personnel training and quality control, conduct regular training for inspectors to improve their professional skills and sense of responsibility. At the same time, strengthen quality control to ensure that each process meets standard requirements, thereby reducing the error rate.

[0010] This project involves the combination of pigment recognition technology, neural network algorithm, MES system and PDA camera FTP transmission technology. The combination of these technologies provides strong technical support for the automatic detection of three-phase line sequence. The following is a detailed analysis of these technologies and their application in the project: Pigment recognition technology: Pigment recognition technology can accurately identify the color information in an image, which has a wide range of applications in the field of image recognition. Combined with deep learning algorithms, pigment recognition technology can significantly improve the accuracy and efficiency of recognition by training models to identify specific colors or color combinations. In this project, pigment recognition technology can be used to identify the color of three-phase lines, thereby assisting in determining whether the line sequence is correct.

[0011] The accuracy and robustness of pigment recognition can be further improved by preprocessing and extracting features from images using deep learning algorithms.

[0012] Neural network algorithm: Neural network algorithm can automatically identify and classify images by learning image features. In the field of automated detection, neural network algorithm can handle complex image recognition tasks and improve detection efficiency and accuracy. In this project, neural network algorithm is used to identify and classify three-phase lines in the image and determine whether the line sequence meets the requirements. By training the neural network model, accurate identification of three-phase lines of different shapes, sizes and color combinations can be achieved.

[0013] MES system: MES (Manufacturing Execution System) is a bridge between production management and control systems, and can process data and information in the production process in real time. The MES system has powerful data processing and integration capabilities, which can improve production efficiency and quality control. In this project, the MES system is used to receive and process the inspection result data from the visual inspection system. Through integration with the visual inspection system, the MES system can update the production status in real time, provide quality tracking and production management support.

[0014] PDA camera FTP transmission technology: In the image recognition system based on neural network, image acquisition, processing and transmission are key steps. FTP (File Transfer Protocol) is a file transfer protocol, which is used for the rapid transmission of image data. It is essential to realize the automated visual inspection system and ensure the real-time and accuracy of data. Summary of the invention

[0015] To solve the above problems, the present application provides a three-phase line sequence detection method and detection system based on multi-dimensional visual analysis, aiming to solve the problems of low efficiency, easy errors and high cost existing in traditional manual detection methods.

[0016] A first aspect of an embodiment of the present invention provides a three-phase line sequence detection method based on multi-dimensional visual analysis, comprising: Count the material codes of all motor products and classify the line sequence of the three-phase lines installed in the motor products into positive phase sequence, reverse phase sequence and no phase sequence; Images of all three-phase line sequence conditions are taken to form a basic image set for training the visual model; Scan the material code of the motor product to be tested to obtain the corresponding three-phase line sequence information; Taking an image of the motor product to be tested, and transmitting the image to a three-phase line sequence detection system; The image is analyzed through the trained visual model, and the three-phase line sequence judgment result is output.

[0017] A second aspect of an embodiment of the present invention provides a three-phase line sequence detection system based on multi-dimensional visual analysis, comprising: an MES system and a three-phase line sequence detection system, wherein the MES system interacts with the three-phase line sequence detection system in data; The MES system is used to count the material codes of all motor products.

[0018] In an optional implementation, it also includes: scanning the material code of the motor product to be tested, obtaining corresponding three-phase line sequence information in a three-phase line sequence detection system, and using the obtained three-phase line sequence information as a standard value to determine the results of subsequent tests.

[0019] In an optional implementation, an image of a wire box portion of a three-phase wire installed in the motor product to be tested is taken by a PDA, and the image is transmitted to a three-phase wire sequence detection system by an FTP file transfer protocol and used as an original image for subsequent image analysis; The original image includes a positive phase sequence image, a negative phase sequence image and a non-phase sequence image.

[0020] In an optional implementation, the three-phase line sequence determination result is automatically entered into the MES system; Among them, the three-phase line sequence detection system is also equipped with a real-time reminder function. If the three-phase line sequence detected by the three-phase line sequence detection system does not meet the standard value, the three-phase line sequence detection system will issue an alarm to remind the installer and production manager to recheck the wiring.

[0021] In an optional embodiment, a visual model is trained using a neural network algorithm and a pigment recognition technology, wherein the pigment recognition technology is used to extract color features.

[0022] In an optional implementation, the specific training steps of the visual model are as follows: S1, obtaining a basic image set, including a positive phase sequence image, a reverse phase sequence image and a non-phase sequence image; S2, perform target positioning detection and uniformly mark coordinate points on each basic image; S3, preprocessing the annotated image, wherein the preprocessing includes image enhancement and feature extraction; S4. Based on the preprocessing results, divide the training set and test set to evaluate the visual model.

[0023] A third aspect of an embodiment of the present application provides a three-phase line sequence detection device based on multi-dimensional visual analysis, the device comprising: Data statistics module: used to count the material codes of all motor products and divide the line sequence of the three-phase lines installed in the motor products into positive phase sequence, reverse phase sequence and no phase sequence; Data training module: used to capture images of all three-phase line sequence conditions to form a basic image set for training visual models; Data acquisition module: used to scan the material code of the motor product to be tested and obtain the corresponding three-phase line sequence information; Data transmission module: used to capture images of the motor product to be tested and transmit the images to the three-phase line sequence detection system; Data analysis module: Analyzes images through the trained visual model and outputs the three-phase line sequence judgment results; The data training module also includes: Training the first unit: used to obtain a basic image set, including positive phase sequence images, reverse phase sequence images and non-phase sequence images; Training the second unit: used to locate and detect targets in each basic image and uniformly mark coordinate points; Training the third unit: used to preprocess the annotated image, wherein the preprocessing includes image enhancement and feature extraction; Training Unit 4: It is used to divide the training set and test set according to the preprocessing results and evaluate the visual model.

[0024] A fourth aspect of an embodiment of the present invention provides an electronic device, characterized in that it includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a three-phase line sequence detection method and detection system based on multi-dimensional visual analysis are implemented.

[0025] A fifth aspect of an embodiment of the present invention provides a computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, a three-phase line sequence detection method and detection system based on multi-dimensional visual analysis are implemented.

[0026] In the disclosed embodiment, the three-phase line sequence detection method and detection system based on multi-dimensional visual analysis can realize fast and accurate detection of the three-phase line sequence by using neural network algorithm and pigment recognition technology. The self-learning ability of the neural network algorithm enables the detection model to continuously learn and optimize, improving the adaptability and stability of the system. At the same time, in order to further improve the detection efficiency and accuracy, the detection system combines the MES system code scanning to obtain standard value technology and the PDA multi-dimensional photo real-time FTP transmission MES technology. The MES system can quickly obtain the standard value of the three-phase line by scanning the code, providing an accurate reference basis for the detection system. The PDA multi-dimensional photo function can capture the full range of image information of the three-phase line, ensuring the comprehensiveness and accuracy of the detection data. The real-time FTP transmission technology ensures that the image data can be quickly transmitted to the MES system, which can realize the real-time recording of the detection data, the rapid result output and the prompting of the user, further improving the detection efficiency and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments of the present application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0028] Figure 1 It is a flow chart of a three-phase line sequence detection method based on multi-dimensional visual analysis proposed in one embodiment of the present application; Figure 2 It is a structural diagram of a three-phase line sequence detection system based on multi-dimensional visual analysis proposed in one embodiment of the present application; Figure 3 is a flow chart of visual model training proposed in one embodiment of the present application; Figure 4 It is a schematic diagram of an electronic device of the present application. DETAILED DESCRIPTION

[0029] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0030] Please refer to Figure 1 , Figure 1 1 is a flow chart of a three-phase line sequence detection method based on multi-dimensional visual analysis proposed in Example 1 of the present application. Figure 1 As shown, the three-phase line sequence detection method based on multi-dimensional visual analysis includes: Count the material codes of all motor products and classify the line sequence of the three-phase lines installed in the motor products into positive phase sequence, reverse phase sequence and no phase sequence; In this embodiment, the MES system collects and records the material codes of all motor products. The material code is a unique identifier of the motor product, which is used to track and identify the specific motor product in subsequent steps. The three-phase line sequence of the motor product installation is divided into three categories: positive phase sequence, reverse phase sequence, and no phase sequence. This is defined based on the phase relationship between the three-phase current and voltage when the motor is running.

[0031] Images of all three-phase line sequence conditions are taken to form a basic image set for training the visual model; In this embodiment, a neural network algorithm and a large amount of labeled image data are used to train a visual model. The model will learn to identify the line sequence features of the three-phase lines in the image. After training, the visual model will be used to analyze the image of the motor product to be tested. The model will extract the key features in the image and determine the line sequence of the three-phase lines based on these features.

[0032] Scan the material code of the motor product to be tested to obtain the corresponding three-phase line sequence information; In this embodiment, the material code of the motor product to be tested is scanned in order to obtain the three-phase line sequence information associated with the motor product to be tested (in actual situations, the material code itself may not directly contain the line sequence information, but it can be used as a unique identifier of the motor product to retrieve relevant information from the database or trigger the detection process).

[0033] Taking an image of the motor product to be tested, and transmitting the image to a three-phase line sequence detection system; In this embodiment, an image of a wire box portion of a three-phase line installed in a motor product to be tested is captured by a PDA, and the image is transmitted to a three-phase line sequence detection system via an FTP file transfer protocol and used as an original image for subsequent image analysis.

[0034] The image is analyzed through the trained visual model, and the three-phase line sequence judgment result is output.

[0035] In this embodiment, the three-phase line sequence judgment result generated in the three-phase line sequence detection system is automatically entered into the MES system; wherein, the three-phase line sequence detection system is also configured with a real-time reminder function. If the three-phase line sequence detected by the three-phase line sequence detection system does not conform to the standard value, the three-phase line sequence detection system will issue an alarm to remind the installer and production manager to recheck the wiring.

[0036] Please refer to Figure 2 , Figure 2 is a structural diagram of a three-phase line sequence detection system based on multi-dimensional visual analysis proposed in Example 1 of the present application. Figure 2 As shown, the three-phase line sequence detection system based on multi-dimensional visual analysis includes: An MES system and a three-phase line detection system, wherein the MES system interacts with the three-phase line detection system in data; The MES system is used to count the material codes of all motor products.

[0037] In this embodiment, the MES system is mainly used to count and manage the material codes of all motor products. The material code is the unique identifier of the motor product during the production process, which is used to track the production progress, quality status, and material usage of the product. There is a data interaction interface between the MES system and the three-phase line detection system. When the three-phase line detection system completes the detection of the three-phase line sequence, it will send the detection results (including the material code of the motor product and the corresponding line sequence detection results) to the MES system.

[0038] The three-phase line detection system is based on multi-dimensional visual analysis technology and can automatically detect whether the line sequence of the three-phase line in the motor product is correct. The system collects images of the motor product and analyzes the images using neural network algorithms and pigment recognition technology to obtain the line sequence detection results of the three-phase line. The three-phase line detection system needs to obtain the material code of the motor product to be tested from the MES system in order to match the test results with the specific motor product. At the same time, the system will also send the test results back to the MES system to achieve closed-loop management of data.

[0039] Furthermore, the material code of the motor product to be tested is scanned, and the corresponding three-phase line sequence information is obtained in the three-phase line sequence detection system. The obtained three-phase line sequence information is used as a standard value to determine the results of subsequent tests.

[0040] In this embodiment, a scanning device (such as a scanner) is used to scan the material code of the motor product to be tested. The material code is a unique identifier of the motor product and contains key information related to the product. After the scan is successful, the three-phase line detection system will retrieve the corresponding three-phase line sequence information from the database according to the material code. This part of information usually includes the connection order and phase relationship of the three-phase line of the motor product. The retrieved three-phase line sequence information is used as the standard value for comparison and judgment of subsequent test results.

[0041] Furthermore, an image of a wire box portion of a three-phase wire installed in the motor product to be tested is taken by a PDA, and the image is transmitted to a three-phase wire sequence detection system by an FTP file transfer protocol and used as an original image for subsequent image analysis; The original image includes a positive phase sequence image, a negative phase sequence image and a non-phase sequence image.

[0042] In this embodiment, when shooting through a PDA, first check whether the camera of the PDA device is clean and undamaged to ensure the shooting quality. The PDA is a handheld mobile terminal that can adjust the light intensity of the shooting environment according to the light conditions and supports manual focus. The focus point can be adjusted to the three-phase wire box to ensure that the image of this part is clear. After shooting, the PDA device will automatically save the image to the specified storage location. The captured image can be viewed in the album or file manager of the PDA device to ensure that the image quality meets the requirements.

[0043] In the three-phase line sequence detection system, set up an FTP server to receive image files. This server needs to be configured with necessary information such as IP address, port number, user name and password. The acquisition device or the computer connected to it will upload the image file to the FTP server through the FTP file transfer protocol. This process may need to be triggered manually, or it can be automatically uploaded by writing a script or program. After the FTP server receives the image file, it will store it in the specified directory. The three-phase line sequence detection system will read these image files from the FTP server and store them in the system's database or file system for subsequent analysis and processing.

[0044] Furthermore, the three-phase line sequence judgment result is automatically entered into the MES system; Among them, the three-phase line sequence detection system is also equipped with a real-time reminder function. If the three-phase line sequence detected by the three-phase line sequence detection system does not meet the standard value, the three-phase line sequence detection system will issue an alarm to remind the installer and production manager to recheck the wiring.

[0045] In this embodiment, after the three-phase line sequence detection system completes the image analysis, it will generate a judgment result of the three-phase line sequence, which may include positive phase sequence, reverse phase sequence, no phase sequence or specific phase error information. The three-phase line sequence detection system will automatically enter the judgment result into the MES system. It is usually achieved through an API interface or database connection to ensure the real-time and accuracy of the data. The MES system will store these test results for subsequent data analysis and quality traceability. Through data analysis, potential problems in the production process can be identified and the production process can be optimized.

[0046] After completing the image analysis, the three-phase line sequence detection system will compare the judgment result with the preset standard value. The standard value is usually set according to the design and specifications of the motor product and is used to judge the correctness of the three-phase line sequence. If the judgment result does not match the standard value, that is, there is an error or abnormality in the three-phase line sequence, the system will immediately issue an alarm. The alarm can be in the form of sound, light, screen display, etc., to ensure that the installer and production manager can find and deal with the problem in time. After the alarm is issued, the system will remind the installer and production manager to recheck the wiring. The installer can make corrections according to the instructions of the system, and the production manager can monitor the entire process to ensure that the problem is solved in time. This step can ensure the quality and safety of the motor product while improving production efficiency through real-time reminders and automatic entry functions.

[0047] Furthermore, the visual model is trained using a neural network algorithm and a pigment recognition technology, wherein the pigment recognition technology is used to extract color features.

[0048] In this embodiment, a suitable neural network model is selected for image analysis and feature extraction. A large amount of annotated three-phase line image data is collected, including images of different situations such as positive phase sequence, reverse phase sequence and no phase sequence. Pigment recognition technology is used to extract color features from the image, and these color features can be used to distinguish the different colors of the three-phase line, so as to determine the line sequence. Combining the neural network algorithm with the pigment recognition technology, a visual model that can extract hierarchical features in the image and recognize color features can be trained. This fusion model can more accurately determine the line sequence of the three-phase line.

[0049] Please refer to Figure 3 , Figure 3 This is a flow chart of visual model training proposed in one embodiment of the present application. Figure 3 As shown, the specific training steps of the visual model are as follows: S1, obtaining a basic image set, including a positive phase sequence image, a reverse phase sequence image and a non-phase sequence image; S2, perform target positioning detection and uniformly mark coordinate points on each basic image; S3, preprocessing the annotated image, wherein the preprocessing includes image enhancement and feature extraction; S4. Based on the preprocessing results, divide the training set and test set to evaluate the visual model.

[0050] In this embodiment, first, a large number of basic image sets containing positive phase sequence, reverse phase sequence and no phase sequence images are collected. These images should cover various possible three-phase line layouts and color combinations of motor products to ensure the diversity and representativeness of the image set to cover various situations that may be encountered in actual production. Secondly, target positioning detection is performed on each basic image to identify the position of the three-phase line and mark uniform coordinate points on the image. These points are used for subsequent feature extraction and model training. Then, the annotated image is enhanced to improve image quality and reduce the impact of noise and illumination changes on model training. This includes but is not limited to contrast enhancement, sharpening, denoising, etc. Feature extraction: Extract key features from the enhanced image, which will be used to train the visual model. Feature extraction can be based on a variety of information such as color, shape, texture, etc. The preprocessing step should be adjusted and optimized according to the actual situation to ensure that the extracted features have sufficient sensitivity and robustness for the recognition of the three-phase line sequence. The preprocessed image set is divided into a training set and a test set. The training set is used to train the visual model, while the test set is used to evaluate the performance of the model. Use the training set to train the visual model and continuously adjust the model parameters to optimize its recognition performance. Use the test set to evaluate the trained model. Evaluation indicators may include accuracy, recall, F1 score, etc. Through the evaluation results, we can understand the advantages and disadvantages of the model and further optimize and improve it.

[0051] The embodiment of the present disclosure provides a three-phase line sequence detection device based on multi-dimensional visual analysis, the device comprising: Data statistics module: used to count the material codes of all motor products and divide the line sequence of the three-phase lines installed in the motor products into positive phase sequence, reverse phase sequence and no phase sequence; Data training module: used to capture images of all three-phase line sequence conditions to form a basic image set for training visual models; Data acquisition module: used to scan the material code of the motor product to be tested and obtain the corresponding three-phase line sequence information; Data transmission module: used to capture images of the motor product to be tested and transmit the images to the three-phase line sequence detection system; Data analysis module: Analyzes images through the trained visual model and outputs the three-phase line sequence judgment results; The data training module also includes: Training the first unit: used to obtain a basic image set, including positive phase sequence images, reverse phase sequence images and non-phase sequence images; Training the second unit: used to locate and detect targets in each basic image and uniformly mark coordinate points; Training the third unit: used to preprocess the annotated image, wherein the preprocessing includes image enhancement and feature extraction; Training Unit 4: It is used to divide the training set and test set according to the preprocessing results and evaluate the visual model.

[0052] The present disclosure also provides an electronic device. Figure 4 , Figure 4 Schematic diagram of an electronic device shown in an embodiment of the present disclosure. Figure 4 As shown, the electronic device 100 includes: a memory 110 and a processor 120. The memory 110 and the processor 120 are connected via a bus communication. A computer program is stored in the memory 110. The computer program can be run on the processor 120, thereby implementing the steps in the three-phase line sequence detection method and detection system based on multi-dimensional visual analysis disclosed in the embodiment of the present disclosure.

[0053] The disclosed embodiment also provides a computer-readable storage medium. When the instructions in the computer-readable storage medium are executed by a processor of a computer device, the computer device is enabled to perform the steps in the three-phase line sequence detection method and detection system based on multi-dimensional visual analysis as in the disclosed embodiment.

[0054] In summary, the present application develops a line sequence visual inspection system for the three-phase lines of the drive motor through a computer program to improve inspection efficiency and accuracy, reduce human errors, reduce production costs, and realize automation of quality tracking and production management.

[0055] The detection system of the present invention also has the characteristics of flexible use dimensions and flexible use scenarios. Through the analysis of two-dimensional rotation, mirroring, and three-dimensional multi-faceted dimensions, comprehensive and accurate detection of the three-phase line sequence can be achieved. The convenience of being able to perform detection anytime and anywhere as long as there is a detection model greatly improves the flexibility and efficiency of the detection work. These advantages make the present invention have broad application prospects and market competitiveness in the field of three-phase line sequence detection, and provide strong technical support for the intelligent production process and the improvement of product quality.

[0056] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the methods, devices, electronic devices, and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes 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 terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal 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.

[0057] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including 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.

[0058] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement 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.

[0059] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present application.

[0060] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0061] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present application.

[0062] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0063] The above is a detailed introduction to a three-phase line sequence detection method and detection system based on multi-dimensional visual analysis provided by the present application. This article uses specific examples to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for general technical personnel in this field, according to the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A three-phase line sequence detection method based on multi-dimensional visual analysis, characterized in that: include: Count the material codes of all motor products and classify the line sequence of the three-phase lines installed in the motor products into positive phase sequence, reverse phase sequence and no phase sequence; Images of all three-phase line sequence conditions are taken to form a basic image set for training the visual model; Scan the material code of the motor product to be tested to obtain the corresponding three-phase line sequence information; Taking an image of the motor product to be tested, and transmitting the image to a three-phase line sequence detection system; The image is analyzed through the trained visual model, and the three-phase line sequence judgment result is output.

2. A three-phase line sequence detection system based on multi-dimensional visual analysis, characterized in that: include: An MES system and a three-phase line detection system, wherein the MES system interacts with the three-phase line detection system in data; The MES system is used to count the material codes of all motor products.

3. The three-phase line sequence detection method and detection system based on multi-dimensional visual analysis according to claims 1 and 2 is characterized in that: Scan the material code of the motor product to be tested, obtain the corresponding three-phase line sequence information in the three-phase line sequence detection system, and use the obtained three-phase line sequence information as the standard value to determine the results of subsequent tests.

4. The three-phase line sequence detection method and detection system based on multi-dimensional visual analysis according to claims 1 and 2, characterized in that: An image of the wire box of the three-phase wire installed in the motor product to be tested is taken by a PDA, and the image is transmitted to the three-phase wire sequence detection system through the FTP file transfer protocol and used as the original image for subsequent image analysis; The original image includes a positive phase sequence image, a negative phase sequence image and a non-phase sequence image.

5. The three-phase line sequence detection method and detection system based on multi-dimensional visual analysis according to claim 3 is characterized in that: The three-phase line sequence judgment result is automatically entered into the MES system; Among them, the three-phase line sequence detection system is also equipped with a real-time reminder function. If the three-phase line sequence detected by the three-phase line sequence detection system does not meet the standard value, the three-phase line sequence detection system will issue an alarm to remind the installer and production manager to recheck the wiring.

6. The three-phase line sequence detection method and detection system based on multi-dimensional visual analysis according to claims 1 and 2, characterized in that: The visual model is trained using a neural network algorithm and pigment recognition technology, which is used to extract color features.

7. The three-phase line sequence detection method and detection system based on multi-dimensional visual analysis according to claim 6 is characterized in that: The specific training steps of the visual model are as follows: S1, obtaining a basic image set, including a positive phase sequence image, a reverse phase sequence image and a non-phase sequence image; S2, perform target positioning detection and uniformly mark coordinate points on each basic image; S3, preprocessing the annotated image, wherein the preprocessing includes image enhancement and feature extraction; S4. Based on the preprocessing results, divide the training set and test set to evaluate the visual model.

8. A three-phase line sequence detection device based on multi-dimensional visual analysis, characterized in that: The device comprises: Data statistics module: used to count the material codes of all motor products and divide the line sequence of the three-phase lines installed in the motor products into positive phase sequence, reverse phase sequence and no phase sequence; Data training module: used to capture images of all three-phase line sequence conditions to form a basic image set for training visual models; Data acquisition module: used to scan the material code of the motor product to be tested and obtain the corresponding three-phase line sequence information; Data transmission module: used to capture images of the motor product to be tested and transmit the images to the three-phase line sequence detection system; Data analysis module: Analyzes images through the trained visual model and outputs the three-phase line sequence judgment results; The data training module also includes: Training the first unit: used to obtain a basic image set, including positive phase sequence images, reverse phase sequence images and non-phase sequence images; Training the second unit: used to locate and detect targets in each basic image and uniformly mark coordinate points; Training the third unit: used to preprocess the annotated image, wherein the preprocessing includes image enhancement and feature extraction; Training Unit 4: It is used to divide the training set and test set according to the preprocessing results and evaluate the visual model.

9. An electronic device, characterized in that: include: A processor, a memory, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the three-phase line sequence detection method and detection system based on multi-dimensional visual analysis as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, it implements the three-phase line sequence detection method and detection system based on multi-dimensional visual analysis as described in any one of claims 1 to 7.

Images