Differential shell defect detection method and device, computer equipment and storage medium

Abstract

The invention relates to the technical field of automobile part detection, in particular to a differential shell defect detection method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: positioning a differential shell by using an installation positioning module of a detection station, starting a light source module and a code scanning module, and identifying and recording serial number information of the differential shell; acquiring external images of the differential shell at different angles; based on a preset defect identification data set, performing defect detection on the external images at different angles, and outputting a defect detection result; and adjusting the preset defect identification data set according to a defect detection result. By adopting the method, the detection efficiency and accuracy of the differential shell can be improved, and the product quality is ensured.

Description

Technical Field

[0001] The present application relates to the technical field of automobile parts detection, and in particular to a differential housing defect detection method, device, computer equipment, computer-readable storage medium and computer program product. Background Art

[0002] The new energy vehicle industry is developing rapidly under the guidance of national policies and driven by technological innovation. New energy transmission products generally include hybrid transmissions and reducers, among which the differential is an important component of the transmission product, which plays the role of transmitting torque and realizing the differential function of the left and right vehicles. The differential assembly is generally composed of a differential housing, planetary gears, axle gears and planetary gear shafts. As the main component, the differential housing mainly plays the role of transmitting torque and supporting the normal operation of the internal bevel gears and the main reduction gear. If there is a problem with the quality of the differential housing, it will cause abnormal operation or even fracture failure, bringing reliability risks.

[0003] Traditionally, appearance inspection relies on manual work, which is highly subjective and inaccurate in evaluation, and is not conducive to quality control. Therefore, there is an urgent need for a differential case defect detection method, device, computer equipment, computer readable storage medium, and computer program product that can improve the detection efficiency and accuracy of the differential case and ensure product quality. Summary of the invention

[0004] Based on this, it is necessary to provide a differential case defect detection method, device, computer equipment, computer readable storage medium and computer program product that can improve the detection efficiency and accuracy of the differential case and ensure product quality in response to the above technical problems.

[0005] In a first aspect, the present application provides a differential housing defect detection method, comprising:

[0006] Use the installation and positioning module of the inspection station to locate the differential housing, start the light source module and the code scanning module, and identify and record the serial number information of the differential housing;

[0007] Collect external images of the differential housing at different angles;

[0008] Based on the preset defect recognition data set, perform defect detection on external images at different angles and output defect detection results;

[0009] According to the defect detection result, the preset defect recognition data set is adjusted.

[0010] In one embodiment, before positioning the differential housing using the installation and positioning module of the detection station, the method further includes:

[0011] Collecting an external image of at least one standard defect-free sample to construct the preset defect recognition data set, wherein the preset defect recognition data set includes a standard comparison pattern and a defect learning set;

[0012] The camera module is calibrated by using a fixed-size ruler to calibrate the data and determine the ratio between the image pixels and the actual size.

[0013] In one embodiment, after outputting the defect detection result, the method further includes:

[0014] If the defect detection result meets the requirements, the defect detection result and corresponding number information are stored;

[0015] When the defect detection result does not meet the requirements, an error value is fed back and an alarm is issued.

[0016] In one embodiment, the collecting of external images of the differential housing at different angles includes:

[0017] Divide the differential case into key areas and non-key areas, wherein the key areas include the differential case bearing shaft diameter, the main reducer mounting stop and the differential case window;

[0018] External images at different angles are collected for both the key area and other areas, wherein the image collection frequency of the key area is greater than the image collection frequency of other areas.

[0019] In one of the embodiments, the detection station is integrated with a positioning module, a code scanning module and a light source module;

[0020] The installation and positioning module comprises a clamping unit, and the clamping unit is used to assemble the differential housing to the inspection station at a fixed position and a fixed angle.

[0021] In one embodiment, the defect detection is performed on external images at different angles based on a preset defect recognition data set, and the defect detection results are output, including:

[0022] Acquire image features of external images at different angles, and convert image formats of the image features into data formats;

[0023] Identify defect types and defect sizes based on image features converted into data format and a preset defect recognition data set;

[0024] Output defect detection results based on defect type and defect size.

[0025] In a second aspect, the present application also provides a differential case defect detection device, comprising:

[0026] The device includes a detection station, a defect detection module and a data update module. The detection station includes an installation positioning module, an image acquisition module, a code scanning module and a light source module:

[0027] The installation and positioning module is used to locate the differential housing; the light source module and the code scanning module are used to identify and record the serial number information of the differential housing;

[0028] The image acquisition module is used to acquire external images of the differential housing at different angles;

[0029] The defect detection module is used to perform defect detection on external images at different angles based on a preset defect recognition data set in real time and output defect detection results;

[0030] The data updating module is used to adjust the preset defect recognition data set according to the defect detection result.

[0031] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0032] Use the installation and positioning module of the inspection station to locate the differential housing, start the light source module and the code scanning module, and identify and record the serial number information of the differential housing;

[0033] Collect external images of the differential housing at different angles;

[0034] Based on the preset defect recognition data set, perform defect detection on external images at different angles and output defect detection results;

[0035] According to the defect detection result, the preset defect recognition data set is adjusted.

[0036] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0037] Use the installation and positioning module of the inspection station to locate the differential housing, start the light source module and the code scanning module, and identify and record the serial number information of the differential housing;

[0038] Collect external images of the differential housing at different angles;

[0039] Based on the preset defect recognition data set, perform defect detection on external images at different angles and output defect detection results;

[0040] According to the defect detection result, the preset defect recognition data set is adjusted.

[0041] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0042] Use the installation and positioning module of the inspection station to locate the differential housing, start the light source module and the code scanning module, and identify and record the serial number information of the differential housing;

[0043] Collect external images of the differential housing at different angles;

[0044] Based on the preset defect recognition data set, perform defect detection on external images at different angles and output defect detection results;

[0045] According to the defect detection result, the preset defect recognition data set is adjusted.

[0046] The above-mentioned differential housing defect detection method, device, computer equipment, computer-readable storage medium and computer program product reduce the subjectivity and inaccuracy of manual detection through automated detection processes, and improve the efficiency and accuracy of differential housing defect detection. By using machine vision detection technology, automated detection can be achieved on the production line, greatly reducing the labor cost and improving production efficiency. Through precise image processing and defect recognition, the surface and internal defects of the differential housing, such as pores, flow marks, cracks, scratches, etc., can be effectively detected, thereby improving product quality and reliability. It is possible to achieve real-time detection of the differential housing and quickly output the detection results, which helps to timely discover and deal with quality problems and reduce the risk of defective products entering the market. Through feedback from actual test results, the preset defect recognition data set can be continuously adjusted and optimized, making the defect detection model more accurate and improving the accuracy of detection. Through precise defect detection, unqualified products can be effectively identified, the scrap rate can be reduced, and the material utilization rate and production efficiency can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions 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 related drawings can be obtained based on these drawings without paying creative work.

[0048] Figure 1 A diagram showing an application environment of a differential case defect detection method in one embodiment;

[0049] Figure 2 Schematic diagram of a flow chart of a differential case defect detection method in one embodiment;

[0050] Figure 3 is a schematic flow chart of a differential case defect detection method in another embodiment;

[0051] Figure 4 is a structural block diagram of a differential case defect detection device in the most detailed embodiment;

[0052] Figure 5 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0054] The differential housing defect detection method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown, the terminal 102 communicates with the server 104 through a network. The data storage system can store data that the server 104 needs to process. The data storage system can be integrated on the server 104, or placed on the cloud or other network servers.

[0055] The terminal 102 is used to locate the differential housing using the installation positioning module of the inspection station, start the light source module and the code scanning module, identify and record the serial number information of the differential housing; collect external images of the differential housing at different angles; the server 104 is used to perform defect detection on external images at different angles based on a preset defect recognition data set, and output defect detection results; according to the defect detection results, adjust the preset defect recognition data set.

[0056] Among them, the terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car devices, projection devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. Head-mounted devices can be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. The server 104 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0057] In an exemplary embodiment, Figure 2 As shown, a differential housing defect detection method is provided, and the method is applied to Figure 1The terminal in is taken as an example to illustrate, including the following steps S202 to S208. Among them:

[0058] Step S202: Use the installation and positioning module of the inspection station to position the differential housing, start the light source module and the code scanning module, and identify and record the serial number information of the differential housing.

[0059] Specifically, the inspection station includes installing a positioning module, which is designed to ensure that the differential housing can be placed on the inspection station at a fixed position and angle. This ensures that the position and angle of the differential housing are consistent each time the inspection is performed, thereby ensuring the consistency and accuracy of the inspection.

[0060] The function of the light source module is to provide uniform and sufficient lighting so that the camera module can clearly capture images of the differential housing at all angles. The code scanning module is used to identify the QR code or other identifiers on the differential housing. This QR code contains the unique identification information of the differential housing, such as product number, production batch, etc. By scanning the code, the system can record and track the inspection information of each differential housing, which is very important for subsequent quality control and product traceability.

[0061] Once the differential housing is correctly placed and clamped, the sensor will recognize that the differential housing has been clamped and transmit a signal to the industrial control computer, indicating that the inspection can begin. At the same time, the code scanning module will read the QR code information on the differential housing and record it in the system. In this way, the inspection results of each differential housing can be associated with its number, which is convenient for subsequent data analysis and quality tracking.

[0062] Step S204, collecting external images of the differential housing at different angles.

[0063] Specifically, the differential housing is a three-dimensional structure with multiple surfaces and angles. To ensure comprehensive inspection, images need to be captured from different angles to cover all important areas of the differential housing. Multiple cameras are arranged around the differential housing using a camera module, which can capture images of the differential housing at various angles simultaneously or sequentially. This ensures that every detail of the housing is captured from different perspectives. The captured images need to have sufficient resolution and clarity so that subsequent image processing and defect detection algorithms can accurately identify defects.

[0064] To ensure image quality, the light source module provides uniform lighting, eliminates shadows and reflections, and makes defect features in the image more obvious.

[0065] The captured images are fed into the image processing module in the industrial control computer for feature extraction and defect identification. This may include using image processing algorithms (such as SIFT, SURF, ORB, etc.) to identify and mark potential defects. Data calibration is performed using a fixed-size ruler to clarify the actual size represented by a single pixel in the image, so that the actual area of ​​the defect can be calculated. The image is corrected by perspective transformation to obtain accurate data.

[0066] Step S206, based on the preset defect recognition data set, defect detection is performed on external images at different angles, and the defect detection results are output.

[0067] Specifically, a preset defect recognition dataset containing various known defect types is constructed. This dataset usually includes images of differential housings in normal and various defective states, as well as detailed annotation information of these images, such as defect location, type, size, etc.

[0068] Preprocess the collected external images, including denoising, contrast enhancement, brightness and color balance adjustment, etc., to improve image quality and make defect features more obvious. Use image processing technology to extract key feature points and descriptors from the image, which can represent important information in the image, such as edges, corners, textures, etc. Compare the extracted features with the features in the preset defect recognition data set, and use machine learning algorithms to identify defects in the image. This may include using classifiers to determine whether there are defects in the image and the type of defects.

[0069] Once a defect is identified, the system needs to determine the exact location of the defect and classify it as a specific type in a preset data set. For the identified defects, the system needs to calculate their size and area. This is usually done by converting pixel dimensions to actual dimensions, which may involve perspective transformation and ruler calibration. Based on preset rules and standards, the detected defects are judged to determine whether to accept or reject the differential housing.

[0070] The defect detection results are output, which may include the defect location, type, size, area, and whether it is qualified. If the test results do not meet the requirements, the system will issue an alarm through the feedback module and stop the test process, waiting for manual intervention. Qualified test results will be stored and bound to the differential housing number information for subsequent quality tracking and tracing.

[0071] Step S208: adjusting the preset defect recognition data set according to the defect detection result.

[0072] Specifically, results are collected from actual defect detection processes, including correctly identified defects and false positives or missed negatives. For false positives (where the system incorrectly identifies a non-defect as a defect) and missed negatives (where the system fails to identify a defect that actually exists), detailed analysis is performed to determine the cause of the problem. Images of false positives and missed negatives are added to the preset defect recognition dataset as new training samples. This helps the system learn and recognize defect types that it failed to correctly identify before.

[0073] Retrain the machine learning model using the updated dataset, including using supervised learning algorithms such as convolutional neural networks (CNNs) or other image recognition models. Adjust and optimize algorithm parameters based on the new dataset and test results to improve the accuracy of defect identification. Perform verification and testing after updating the dataset and model to ensure that the improved system can more accurately identify defects. Continuously monitor the performance of the defect detection system to ensure that it remains efficient and accurate in the actual production environment. Establish a feedback loop so that each test result can be used to further optimize and adjust the preset defect identification dataset.

[0074] In the above-mentioned differential housing defect detection method, the subjectivity and inaccuracy of manual detection are reduced through the automated detection process, and the efficiency and accuracy of differential housing defect detection are improved. By using machine vision detection technology, automated detection can be realized on the production line, which greatly reduces the labor cost and improves production efficiency. Through precise image processing and defect recognition, the surface and internal defects of the differential housing, such as pores, flow marks, cracks, scratches, etc., can be effectively detected, thereby improving product quality and reliability. It is possible to realize real-time detection of the differential housing and quickly output the test results, which helps to timely discover and deal with quality problems and reduce the risk of defective products entering the market. Through the feedback of actual test results, the preset defect recognition data set can be continuously adjusted and optimized, making the defect detection model more accurate and improving the accuracy of detection. Through precise defect detection, unqualified products can be effectively identified, the scrap rate can be reduced, and the material utilization rate and production efficiency can be improved.

[0075] In an exemplary embodiment, Figure 3 As shown, before positioning the differential housing using the installation positioning module of the detection station, the following is also included:

[0076] Step S302, collecting an external image of at least one standard defect-free sample to construct a preset defect recognition data set, where the preset defect recognition data set includes a standard comparison pattern and a defect learning set;

[0077] Step S304, calibrating the camera module, performing data calibration using a ruler of a fixed size, and determining the ratio between image pixels and actual size.

[0078] Specifically, the purpose of collecting external images of standard defect-free samples is to establish a high-quality benchmark dataset for subsequent defect detection and comparison. Select at least one differential case sample that is known to be defect-free, and use a camera module to collect its external images from multiple angles. These images are stored as "standard defect-free images" in a preset defect recognition dataset for comparison with the actual detected differential case images.

[0079] Next, a preset defect recognition dataset is constructed, where the standard comparison pattern includes standard defect-free sample images collected from multiple angles, which will serve as the benchmark for detection. The defect learning set includes images of various known defects, such as shrinkage, sand holes, bumps and cracks, which are used to train the machine learning model to enable it to identify and classify these defects.

[0080] The purpose of calibrating the camera module is to ensure that the image captured by the camera module is consistent with the size of the actual object, so as to accurately measure and identify defects. Operation: Use a fixed-size ruler (such as a calibration plate or calibration block) to calibrate the data. The ruler usually has patterns or marks of known sizes, which are used to determine the proportional relationship between the pixels in the image and the actual size. Data calibration: By comparing the pixel size of the ruler in the image with its actual physical size, the actual length represented by each pixel is calculated. This helps to convert the measurement value in the image into the actual physical size, so as to accurately identify and measure defects.

[0081] Through the calibration process, the actual length corresponding to each pixel in the image is determined (for example, each pixel represents 0.1 mm). In subsequent defect detection, this ratio is used to convert the defect size in the image into the actual physical size for accurate defect analysis and judgment.

[0082] In this embodiment, through the above steps, it can be ensured that the defect detection system of the differential case has been calibrated and prepared before starting the actual detection, thereby improving the accuracy and reliability of the detection.

[0083] In an exemplary embodiment, after outputting the defect detection result, the method further includes:

[0084] When the defect detection results meet the requirements, the defect detection results and corresponding number information are stored;

[0085] When the defect detection results do not meet the requirements, the error value is fed back and an alarm is issued.

[0086] Specifically, when the defect detection results show that the differential housing meets the preset quality standards and requirements, the detection results and related number information are stored in the database or data storage system. This usually includes detailed information such as the location, type, size, area, and number of the defect, as well as the number of the differential housing. Ensure that the detection results of each differential housing are correctly associated with its number information to facilitate subsequent quality tracking and traceability. These records can be used for quality control reports, statistical analysis, and historical data review to monitor the stability and improvement of the production process.

[0087] When the defect detection results show that the differential housing does not meet the preset quality standards and requirements. The system automatically marks the non-compliant detection results as errors and feeds back to the operator or control system. Trigger the alarm system, such as sound and light alarms or automatic message notifications, to immediately notify relevant personnel to deal with the unqualified differential housing. In some cases, the system may automatically stop the inspection process until the problem is resolved to prevent unqualified products from flowing into the next production link. Record all non-compliant inspection results, including error type, time, number of the relevant differential housing, etc., to facilitate subsequent problem analysis and corrective measures. For differential housings that are detected to be non-compliant, subsequent processing is required according to the factory's non-conforming product processing process, which may include rework, scrapping or isolation. Use the stored inspection results and problem records to analyze the root causes of quality problems and take corresponding quality improvement measures.

[0088] In this embodiment, through these steps, it can be ensured that the defect detection of the differential housing is not only accurate and efficient, but also can respond to quality problems in a timely manner, thereby improving the overall production quality and efficiency.

[0089] In an exemplary embodiment, collecting external images of the differential housing at different angles includes:

[0090] Divide the differential case into key areas and non-key areas. The key areas include the differential case bearing shaft diameter, the main reducer mounting stop and the differential case window.

[0091] External images at different angles are collected for both the key area and other areas, wherein the image collection frequency of the key area is greater than the image collection frequency of other areas.

[0092] Specifically, the purpose of dividing key areas and non-key areas is to improve detection efficiency and accuracy. First, it is necessary to determine the key areas on the differential housing, which have a greater impact on function and performance and therefore require more detailed inspection.

[0093] Key areas: including but not limited to the differential case bearing shaft diameter, main reducer mounting stop and differential case window. These areas require special attention due to their functional importance.

[0094] Non-key areas: Although other parts except key areas also need to be inspected, a lower inspection frequency can be adopted.

[0095] Collect external images of key areas:

[0096] High-frequency acquisition: Due to the importance of the focus area, images need to be acquired at a higher frequency to ensure that any possible defects can be captured.

[0097] Multi-angle coverage: Ensure that images of key areas are captured from multiple angles to fully inspect the exterior quality of these areas.

[0098] Image quality: For images of key areas, higher resolution and clearer image quality may be required to facilitate subsequent defect detection.

[0099] Capture external images of non-critical areas:

[0100] Lower frequency acquisition: A lower image acquisition frequency can be used in non-key areas to balance the coverage and efficiency of detection.

[0101] Basic coverage: Although less frequent, it is still necessary to ensure basic image coverage of non-critical areas from different angles to facilitate the detection of obvious defects.

[0102] Specific operations of image acquisition:

[0103] Camera module layout: According to the shape and size of the differential housing, the camera modules are reasonably arranged to ensure that all key and non-key areas are covered.

[0104] Light source control: Adjust the light source to ensure adequate lighting at different angles, especially when capturing images of key areas.

[0105] Automatic control: Control the shooting frequency and angle of the camera module and the adjustment of the light source through the automatic control system.

[0106] Finally, the image acquisition frequency and angle of each area and the corresponding image data are recorded. The acquired images are preprocessed, such as denoising and contrast enhancement, to improve the accuracy of subsequent defect detection.

[0107] In this embodiment, through a targeted image acquisition strategy, it is possible to ensure that the key areas of the differential housing receive sufficient attention while maintaining the efficiency and cost-effectiveness of the overall inspection process, which helps to improve the quality control level of the differential housing and reduce potential failure risks.

[0108] In an exemplary embodiment, the detection station is integrated with a positioning module, a code scanning module and a light source module;

[0109] The installation and positioning module comprises a clamping unit, which is used to assemble the differential housing onto the inspection station at a fixed position and a fixed angle.

[0110] Specifically, the function of the mounting and positioning module is to ensure that the differential housing maintains the correct position and angle during the inspection process. The clamping unit is part of the mounting and positioning module and is used to fix the differential housing to ensure that it does not move or rotate during the inspection process. When the differential housing is placed on the inspection station, the clamping unit is automatically or manually triggered to assemble the differential housing in a fixed position and at a fixed angle. The clamping unit needs to be strong enough to withstand the forces that may be generated during the inspection process while ensuring that no damage is caused to the differential housing.

[0111] In this embodiment, by positioning the differential housing, it can be ensured that it will not move or rotate during the detection process, which is conducive to collecting more accurate external images.

[0112] In an exemplary embodiment, based on a preset defect recognition data set, defect detection is performed on external images at different angles, and defect detection results are output, including:

[0113] Acquire image features of external images at different angles, and convert image formats of the image features into data formats;

[0114] Identify defect types and defect sizes based on image features converted into data format and a preset defect recognition data set;

[0115] Output defect detection results based on defect type and defect size.

[0116] Specifically, a camera module is used to collect external images of the differential housing from different angles. Image processing techniques (such as edge detection, corner detection, texture analysis, etc.) are used to extract key features from the image. Common feature extraction algorithms include SIFT, SURF, ORB, etc. The extracted image features are converted from image format to data format, usually numerical data, for computer processing and analysis, including converting pixel values, color information, texture information, etc. into vector or matrix form.

[0117] Compare and analyze the converted data features with the features in the preset defect recognition data set. Use machine learning or deep learning models (such as support vector machines, neural networks, etc.) to identify the defect types in the image based on the models trained with the preset defect recognition data set. For the identified defects, measure their size through image processing techniques (such as pixel counting, geometric analysis, etc.) and convert the pixel size into the actual physical size.

[0118] Determine if the differential housing meets quality requirements based on the identified defect type and size, and preset quality standards. This includes determining the specific location of the defect on the differential housing. Identify the type of defect, such as cracks, dents, bulges, etc. The actual physical size of the defect, including length, width, depth, etc. Determine if the differential housing is qualified based on preset standards. Record the test results in a database and provide feedback to the production process as needed, such as alarms, stopping the production line, etc.

[0119] In this embodiment, through the above steps, automated and intelligent defect detection is achieved, detection efficiency and accuracy are improved, interference from human factors is reduced, and consistency and reliability of product quality are ensured.

[0120] The most detailed embodiment of this application is:

[0121] like Figure 4 As shown, the differential case defect detection device based on visual inspection includes a detection station, a camera module, and an industrial control computer.

[0122] The inspection station is used to place the differential housing, and the inspection station should include installation positioning devices, sensors, code scanning modules, and light source modules. The installation positioning module needs to ensure that the differential housing can be assembled on the inspection station at a fixed position and fixed angle, and should include a reliable clamping module; the sensor includes a usable weight sensor or displacement sensor, which is used to identify whether the differential housing has been clamped and transmitted to the industrial control computer to identify whether to start the inspection or whether it has been removed after the inspection; the code scanning module is used to identify the QR code on the differential housing and record the information of the differential housing currently being inspected; the light source module is used to illuminate the differential housing to facilitate the identification of images at various angles.

[0123] The camera module contains multiple cameras for images of the differential housing at various angles.

[0124] Industrial control computers are used to obtain image data, learn data, process data and determine whether the inspection meets the requirements. Industrial control computers should include: rule compilation module, image processing module, self-learning module, data analysis module, storage module and feedback module. The rule compilation module is used to input the offline inspection judgment requirements; the image processing module is used to obtain the image in the camera module, record the standard defect-free image and the inspection image, and process the image into data; the self-learning module is used to store the results in the feature library after the defect is detected, and improve the defect recognition standard; the data analysis module compares the standard defect-free image, identifies the defect category and calculates the defect size of the inspection part, and judges the data based on the rule requirements; the storage module is used to record the current calculation results and images when the test results meet the judgment requirements; the feedback module is used to alarm and stop the inspection when the test results do not meet the judgment requirements.

[0125] The differential case defect detection method based on visual inspection includes:

[0126] Before testing, a standard comparison pattern and defect learning set should be constructed, and the information of multiple standard defect-free samples should be entered on the same testing table as the testing standard. At the same time, various defective samples should be entered on the testing table, and the defect areas should be delineated and the defect categories should be marked, such as shrinkage, sand holes, bumps and cracks, so that the machine can automatically learn for subsequent defect type identification.

[0127] The camera module is calibrated, and the data is calibrated using a fixed-size ruler to clarify the actual size represented by a single pixel in the image. The defect area can be obtained by calculating the number of pixels. At the same time, the image needs to be corrected by perspective transformation to obtain accurate data.

[0128] Special defect samples need to be tested before and after the production line starts to ensure that the testing equipment can effectively identify and accurately determine the defect type, defect area and size. The formal testing process is as follows:

[0129] 1.1 Place the differential housing on the installation and positioning module of the inspection station. When the sensor recognizes the correct sample information, it automatically clamps and starts the corresponding inspection process;

[0130] 1.2 After the detection process starts, the light source and barcode scanner are started to record the current assembly number information;

[0131] 1.3 The camera module is arranged around the differential housing, and the shooting is started. The camera module takes pictures according to the inspection requirements. The arrangement requirements should be able to completely shoot the differential housing, so that the image can be acquired without rotating the inspection table, thereby improving the inspection efficiency and accuracy;

[0132] 1.4 The industrial control computer processes the images recorded by the camera module in real time for analysis and judgment. The specific implementation process is as follows:

[0133] 1.4.1 The rule compilation module has set the corresponding differential case inspection requirements, including: key area division (differential case bearing shaft diameter, main reducer mounting stop and differential case window are generally key areas), defect category, defect size requirements, and defect quantity requirements;

[0134] 1.4.2 The specific detection process performed by the image processing module is as follows: Based on feature extraction and matching, the image processing library is used to extract image features (such as SIFT, SURF, ORB, etc.), the features of standard defect-free samples and standard defective samples are compared, the corresponding defects are identified, and the number of pixels is calculated to confirm the current defect size and area.

[0135] 1.5 The data processing module calculates the specific value and compares it with the detection requirements of different areas. If it meets the requirements, the corresponding data will be transferred to the storage module for storage and bound to the scan code information; if it does not meet the requirements, the error value will be fed back to the feedback module, and the alarm will be stopped.

[0136] 1.6 The self-learning module enters each image determined to be a defect into the feature database, improves the database, and improves the accuracy of defect recognition.

[0137] 1.7 After the inspection is completed, remove the differential assembly. The gravity sensor in the inspection station recognizes that the workpiece has been removed, resets the inspection program, and waits for the next inspection.

[0138] 1.8 The detection system automatically counts the defect results of a certain period according to the preset defect categories and areas to support production line problem troubleshooting and optimization.

[0139] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0140] Based on the same inventive concept, the embodiment of the present application also provides a differential case defect detection device for implementing the differential case defect detection method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations of one or more differential case defect detection device embodiments provided below can refer to the limitations of the differential case defect detection method above, and will not be repeated here.

[0141] In an exemplary embodiment, Figure 5 As shown, a differential housing defect detection device is provided, the device includes a detection station, a defect detection module and a data update module, and the detection station includes an installation positioning module, an image acquisition module, a code scanning module and a light source module:

[0142] Install a positioning module for locating the differential housing; a light source module and a code scanning module for identifying and recording the serial number information of the differential housing;

[0143] An image acquisition module, used for acquiring external images of the differential housing at different angles;

[0144] The defect detection module is used to perform defect detection on external images at different angles in real time based on a preset defect recognition data set and output defect detection results;

[0145] The data updating module is used to adjust the preset defect recognition data set according to the defect detection results.

[0146] In an exemplary embodiment, the image acquisition module is specifically used to acquire an external image of at least one standard defect-free sample, construct a preset defect recognition data set, and the preset defect recognition data set includes a standard comparison pattern and a defect learning set; calibrate the camera module, perform data calibration through a fixed-size ruler, and determine the ratio of image pixels to actual size.

[0147] In an exemplary embodiment, the defect detection module is used to store the defect detection result and the corresponding number information when the defect detection result meets the requirements; and to feedback an error value and issue an alarm when the defect detection result does not meet the requirements.

[0148] In an exemplary embodiment, the differential case is divided into key areas and non-key areas, wherein the key areas include the differential case bearing shaft diameter, the main reducer mounting stop and the differential case window;

[0149] The image acquisition module is specifically used to acquire external images of different angles for both the key area and other areas, wherein the image acquisition frequency of the key area is greater than the image acquisition frequency of other areas.

[0150] In an exemplary embodiment, the inspection station integrates an installation and positioning module, a code scanning module and a light source module; the installation and positioning module includes a clamping unit, and the clamping unit is used to assemble the differential housing to the inspection station at a fixed position and a fixed angle.

[0151] In an exemplary embodiment, the defect detection module is specifically used to obtain image features of external images at different angles and convert the image format of the image features into a data format; identify the defect type and defect size based on the image features converted into the data format and a preset defect recognition data set; and output the defect detection result according to the defect type and defect size.

[0152] Each module in the above differential case defect detection device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0153] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 5 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (NearFieldCommunication, NFC) or other technologies. When the computer program is executed by the processor, a differential housing defect detection method is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0154] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0155] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0156] Use the installation and positioning module of the inspection station to locate the differential housing, start the light source module and the code scanning module, and identify and record the serial number information of the differential housing;

[0157] Collect external images of the differential housing at different angles;

[0158] Based on the preset defect recognition data set, perform defect detection on external images at different angles and output defect detection results;

[0159] Adjust the preset defect recognition data set based on the defect detection results.

[0160] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0161] Collecting at least one external image of a standard defect-free sample to construct a preset defect recognition data set, wherein the preset defect recognition data set includes a standard comparison pattern and a defect learning set;

[0162] The camera module is calibrated by using a fixed-size ruler to calibrate the data and determine the ratio between the image pixels and the actual size.

[0163] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0164] When the defect detection results meet the requirements, the defect detection results and corresponding number information are stored;

[0165] When the defect detection results do not meet the requirements, the error value is fed back and an alarm is issued.

[0166] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0167] Divide the differential case into key areas and non-key areas. The key areas include the differential case bearing shaft diameter, the main reducer mounting stop and the differential case window.

[0168] External images at different angles are collected for both the key area and other areas, wherein the image collection frequency of the key area is greater than the image collection frequency of other areas.

[0169] In one embodiment, the detection station is integrated with a positioning module, a code scanning module and a light source module;

[0170] The installation and positioning module comprises a clamping unit, which is used to assemble the differential housing onto the inspection station at a fixed position and a fixed angle.

[0171] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0172] Acquire image features of external images at different angles, and convert image formats of the image features into data formats;

[0173] Identify defect types and defect sizes based on image features converted into data format and a preset defect recognition data set;

[0174] Output defect detection results based on defect type and defect size.

[0175] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0176] Use the installation and positioning module of the inspection station to locate the differential housing, start the light source module and the code scanning module, and identify and record the serial number information of the differential housing;

[0177] Collect external images of the differential housing at different angles;

[0178] Based on the preset defect recognition data set, perform defect detection on external images at different angles and output defect detection results;

[0179] Adjust the preset defect recognition data set based on the defect detection results.

[0180] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0181] Collecting at least one external image of a standard defect-free sample to construct a preset defect recognition data set, wherein the preset defect recognition data set includes a standard comparison pattern and a defect learning set;

[0182] The camera module is calibrated by using a fixed-size ruler to calibrate the data and determine the ratio between the image pixels and the actual size.

[0183] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0184] When the defect detection results meet the requirements, the defect detection results and corresponding number information are stored;

[0185] When the defect detection results do not meet the requirements, the error value is fed back and an alarm is issued.

[0186] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0187] Divide the differential case into key areas and non-key areas. The key areas include the differential case bearing shaft diameter, the main reducer mounting stop and the differential case window.

[0188] External images at different angles are collected for both the key area and other areas, wherein the image collection frequency of the key area is greater than the image collection frequency of other areas.

[0189] In one embodiment, the detection station is integrated with a positioning module, a code scanning module and a light source module;

[0190] The installation and positioning module comprises a clamping unit, which is used to assemble the differential housing onto the inspection station at a fixed position and a fixed angle.

[0191] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0192] Acquire image features of external images at different angles, and convert image formats of the image features into data formats;

[0193] Identify defect types and defect sizes based on image features converted into data format and a preset defect recognition data set;

[0194] Output defect detection results based on defect type and defect size.

[0195] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0196] Use the installation and positioning module of the inspection station to locate the differential housing, start the light source module and the code scanning module, and identify and record the serial number information of the differential housing;

[0197] Collect external images of the differential housing at different angles;

[0198] Based on the preset defect recognition data set, perform defect detection on external images at different angles and output defect detection results;

[0199] Adjust the preset defect recognition data set based on the defect detection results.

[0200] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0201] Collecting at least one external image of a standard defect-free sample to construct a preset defect recognition data set, wherein the preset defect recognition data set includes a standard comparison pattern and a defect learning set;

[0202] The camera module is calibrated by using a fixed-size ruler to calibrate the data and determine the ratio between the image pixels and the actual size.

[0203] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0204] When the defect detection results meet the requirements, the defect detection results and corresponding number information are stored;

[0205] When the defect detection results do not meet the requirements, the error value is fed back and an alarm is issued.

[0206] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0207] Divide the differential case into key areas and non-key areas. The key areas include the differential case bearing shaft diameter, the main reducer mounting stop and the differential case window.

[0208] External images at different angles are collected for both the key area and other areas, wherein the image collection frequency of the key area is greater than the image collection frequency of other areas.

[0209] In one embodiment, the detection station is integrated with a positioning module, a code scanning module and a light source module;

[0210] The installation and positioning module comprises a clamping unit, which is used to assemble the differential housing onto the inspection station at a fixed position and a fixed angle.

[0211] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0212] Acquire image features of external images at different angles, and convert image formats of the image features into data formats;

[0213] Identify defect types and defect sizes based on image features converted into data format and a preset defect recognition data set;

[0214] Output defect detection results based on defect type and defect size.

[0215] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0216] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0217] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0218] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A differential case defect detection method, characterized in that: The method comprises: Use the installation and positioning module of the inspection station to locate the differential housing, start the light source module and the code scanning module, and identify and record the serial number information of the differential housing; Collect external images of the differential housing at different angles; Based on the preset defect recognition data set, perform defect detection on external images at different angles and output defect detection results; According to the defect detection result, the preset defect recognition data set is adjusted.

2. The method according to claim 1, characterized in that Before positioning the differential housing using the installation and positioning module of the detection station, the method further includes: Collecting an external image of at least one standard defect-free sample to construct the preset defect recognition data set, wherein the preset defect recognition data set includes a standard comparison pattern and a defect learning set; The camera module is calibrated by using a fixed-size ruler to calibrate the data and determine the ratio between the image pixels and the actual size.

3. The method according to claim 2, characterized in that After outputting the defect detection result, the method further includes: If the defect detection result meets the requirements, the defect detection result and corresponding number information are stored; When the defect detection result does not meet the requirements, an error value is fed back and an alarm is issued.

4. The method according to claim 1, characterized in that: The collecting of external images of the differential housing at different angles includes: Divide the differential case into key areas and non-key areas, wherein the key areas include the differential case bearing shaft diameter, the main reducer mounting stop and the differential case window; External images at different angles are collected for both the key area and other areas, wherein the image collection frequency of the key area is greater than the image collection frequency of other areas.

5. The method according to claim 1, characterized in that The detection station is integrated with a positioning module, a code scanning module and a light source module; The installation and positioning module comprises a clamping unit, and the clamping unit is used to assemble the differential housing to the inspection station at a fixed position and a fixed angle.

6. The method according to claim 1, characterized in that The method of performing defect detection on external images at different angles based on a preset defect recognition data set and outputting defect detection results includes: Acquire image features of external images at different angles, and convert image formats of the image features into data formats; Identify defect types and defect sizes based on image features converted into data format and a preset defect recognition data set; Output defect detection results based on defect type and defect size.

7. A differential case defect detection device, characterized in that: The device includes a detection station, a defect detection module and a data update module. The detection station includes an installation positioning module, an image acquisition module, a code scanning module and a light source module: The installation and positioning module is used to locate the differential housing; the light source module and the code scanning module are used to identify and record the serial number information of the differential housing; The image acquisition module is used to acquire external images of the differential housing at different angles; The defect detection module is used to perform defect detection on external images at different angles based on a preset defect recognition data set in real time and output defect detection results; The data updating module is used to adjust the preset defect recognition data set according to the defect detection result.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images