Automobile gear batch defect detection method, device and equipment and storage medium

Abstract

The present application relates to gear defect detection technical field, disclose a kind of automobile gear batch defect detection method, device, equipment and storage medium, obtain the first gear detection image containing several gears to be detected, according to defect detection resolution requirement, determine several projection light sources, drive several projection light sources to execute light source projection in turn to transparent positioning plate, collect the second gear detection image received by projection panel, extract the actual abnormal shape pattern of gear projection that meets the defect detection resolution requirement and the area difference of figure of gear projection theoretical abnormal shape pattern, judge whether the gear to be detected of target batch exists gear defect. Therefore, the present application uses batch defect detection and light source projection amplification mode, the parts of multiple gears in random and different positions are projected and amplified and parallel defect judgment, can realize the batch defect detection of high accuracy of same batch gear, significantly improve gear batch defect detection efficiency, reduce the threshold of gear defect detection.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of gear defect detection, and in particular to an automobile gear batch defect detection method, device, equipment and storage medium. BACKGROUND

[0002] As a core component of the automobile transmission system, the small modulus gear has the characteristics of compact size and fine tooth shape. Due to its wide application in the differential planetary gear, the low gear drive gear of the gearbox and the electric power steering system, defects in the small modulus gear will directly affect the reliability of the transmission system, amplify the chain effect of the production chain and the quality traceability of the related production link, increase the production cost of the small modulus gear, and affect the vehicle driving safety. The defect detection of the small modulus gear is directly related to the reliability and production economy of the vehicle.

[0003] For the tooth shape distortion problem of the small modulus gear (mainly the tooth shape local distortion caused by the tool wear of the hobbing / inserting machine tool affecting the tool precision and the temperature sensor long-term use affecting the heat treatment precision, which often leads to batch tooth shape distortion of the same batch of gears), the traditional gear defect detection based on image analysis has higher requirements for the camera resolution and the precision of the defect recognition model due to the small size and large number of small modulus gears. It cannot timely find the problems of the gear production equipment, leading to the output of batch defective products. Moreover, due to the one-by-one detection, the operation capacity of the image analysis equipment is required to be high. The common influence of many factors greatly increases the equipment construction cost of the small modulus gear production detection in the production line.

[0004] Therefore, how to improve the accuracy and efficiency of the small modulus gear batch defect detection, reduce the equipment construction cost of the small modulus gear production detection, timely find the problems of the gear production equipment, and improve the production yield and production benefit of the small modulus gear is a technical problem to be solved. SUMMARY

[0005] The present application provides an automobile gear batch defect detection method, device, equipment and storage medium, which aims to solve at least one of the above technical problems.

[0006] To achieve the above purpose, the present application provides an automobile gear batch defect detection method, which comprises the following steps:

[0007] Obtaining a first gear detection image in a gear detection area; wherein the first gear detection image comprises a plurality of target batch detection gears randomly tiled on a transparent positioning plate;

[0008] The first gear detection image is analyzed, the detection position of each gear to be detected on the transparent positioning plate is extracted, and several projection light sources are determined according to the defect detection resolution requirements.

[0009] Several projection light sources are driven to project onto the transparent positioning plate in sequence. The second gear detection image received on the projection panel is collected each time the light source projection is performed. The actual irregular shape of the gear projection that meets the defect detection resolution requirements in each second gear detection image is extracted.

[0010] Based on the projection mapping relationship between the actual irregular shape of the gear projection and the gear to be inspected, the difference in graphic area between the actual irregular shape of the gear projection and the theoretical irregular shape of the gear projection for each gear to be inspected is calculated to determine whether there are tooth defects in the target batch of gears to be inspected.

[0011] Optionally, the step of acquiring the first gear detection image within the gear detection area specifically includes:

[0012] Based on the conveying mechanism and the vibration mechanism, the transparent positioning plate is controlled to perform conveying and vibration actions, which drive the gear delivery device to output and deliver several gears to be tested to be randomly laid flat on the transparent positioning plate, and the transparent positioning plate is conveyed to the gear detection area; wherein, the gear detection area is provided with a first image acquisition device in the direction facing the transparent positioning plate;

[0013] When the transparent positioning plate is detected to have entered the acquisition position of the gear detection area, the first gear detection image containing several gears to be detected in the target batch is acquired by the first image acquisition device.

[0014] Optionally, the first gear inspection image is analyzed to extract the inspection position of each gear to be inspected on the transparent positioning plate. Based on the defect detection resolution requirements, several projection light source steps are determined, specifically including:

[0015] Several positioning auxiliary lines are extracted from the first gear detection image. Based on the positional relationship between each gear to be detected and the several positioning auxiliary lines in the first gear detection image, the detection position of each gear to be detected on the transparent positioning plate is determined.

[0016] Based on the actual size information of the gears to be inspected in the target batch and the required size information corresponding to the defect detection resolution requirements, the required projection magnification ratio of the gears to be inspected is calculated.

[0017] Based on the detection position of each gear to be tested on the transparent positioning plate and the required projection magnification, several projection light sources are selected from a light source panel with several candidate light sources arranged in the direction facing the transparent positioning plate.

[0018] Optionally, based on the detection position of each gear to be tested on the transparent positioning plate and the required projection magnification, a step of selecting several projection light sources from a light source panel with several candidate light sources positioned facing the transparent positioning plate is specifically included:

[0019] The position of each candidate light source in the light source panel is obtained. Based on the position of the light source, the detection position of each gear to be tested on the transparent positioning plate, the first distance between the light source panel and the transparent positioning plate, and the second distance between the transparent positioning plate and the projection panel, the projection distance value between the projection positions of several edge projection points of each gear to be tested on the transparent positioning plate and the projection position of the center projection point on the transparent positioning plate when each candidate light source performs light source projection is calculated.

[0020] Statistically calculate the total projection distance values ​​of several edge projection points of each gear to be tested on the transparent positioning plate, and add the candidate light sources whose projection magnification ratio, determined by the projection distance value and the actual size information of the gear to be tested, exceeds the required projection magnification ratio into the candidate light source list corresponding to the gear to be tested.

[0021] Select the minimum number of candidate light sources from the list of all candidate light sources for the gears to be inspected as the projection light source for the target batch of gear defect detection on the light source panel, so that when the projection light source performs light source projection, each gear to be inspected has at least one gear projection with a projection distance value that has a projection magnification ratio that exceeds the projection magnification requirement ratio.

[0022] Optionally, several projection light sources are driven to sequentially project onto the transparent positioning plate, and the second gear detection image received on the projection panel is acquired at each projection. The actual irregular shape of the gear projection that meets the defect detection resolution requirements is extracted from each second gear detection image. Specifically:

[0023] Several projection light sources are driven to project light onto all the gears to be detected on the transparent positioning plate in sequence. A second image acquisition device is set on the side of the projection panel away from the projection direction in the gear detection area to acquire the second gear detection image received on the projection panel when each light source projection is performed.

[0024] Extract a gear projection that meets the projection magnification requirement for each gear from all the second gear inspection images from several projection light sources. Use this as the actual irregular shape of the gear projection that meets the defect detection resolution requirements. Establish the projection mapping relationship between each gear projection actual irregular shape and the corresponding gear to be inspected and the corresponding projection light source.

[0025] Optionally, based on the projection mapping relationship between the actual irregular shape of the gear projection and the gear to be inspected, the step of calculating the difference in graphic area between the actual irregular shape of the gear projection and the theoretical irregular shape of the gear projection for each gear to be inspected, and determining whether there are tooth defects in the target batch of gears to be inspected, specifically includes:

[0026] Based on the detection position of each gear to be tested on the transparent positioning plate, the theoretical irregular shape of the gear projection when the detection position of the gear to be tested on the transparent positioning plate is affected by the light source projection of the corresponding projection light source is queried in the pre-entered gear test database.

[0027] The gear test database is configured to store: a set of theoretical irregular shapes of gear projections obtained when the gears to be tested are projected by different light sources at different test positions on the transparent positioning plate during the projection simulation test of the target batch of gears to be tested in advance;

[0028] For the extracted actual irregular shape of gear projection and the queried theoretical irregular shape of gear projection, the difference in the graphic area of ​​each gear to be detected is calculated as the quantification value of tooth defect.

[0029] Based on the quantization value of the tooth profile defect of each gear to be tested and the corresponding quantization threshold of the tooth profile defect, it is determined whether there is at least one gear to be tested whose quantization value of the tooth profile defect exceeds the corresponding quantization threshold of the tooth profile defect. If so, it is determined that the gears to be tested in the target batch have tooth profile defects.

[0030] Optionally, the projection simulation test of the gear to be tested specifically includes:

[0031] Construct a simulation model of the area to be detected, which includes a projection panel, a transparent positioning plate, and a light source panel. Write a simulation projection script to traverse the gears to be detected located at different detection positions on the transparent positioning plate and different projection light sources on the light source panel.

[0032] The simulation model is driven to execute the simulation projection script, record and statistically analyze the theoretical irregular shape of the gear projection when the gear to be tested is projected by different light sources at different detection positions on the transparent positioning plate, and construct a gear test database containing a set of theoretical irregular shape of gear projection.

[0033] Furthermore, to achieve the above objectives, the present invention also provides a batch defect detection device for automotive gears, comprising:

[0034] The acquisition module is used to acquire a first gear detection image within the gear detection area; wherein, the first gear detection image includes several gears to be detected in the target batch, which are randomly laid flat on a transparent positioning plate;

[0035] The analysis module is used to analyze the first gear detection image, extract the detection position of each gear to be detected on the transparent positioning plate, and determine a number of projection light sources according to the defect detection resolution requirements.

[0036] The projection module is used to drive several projection light sources to project onto the transparent positioning plate in sequence, and to collect the second gear detection image received on the projection panel at each time the light source projection is performed, and to extract the actual irregular shape of the gear projection that meets the defect detection resolution requirements in each second gear detection image;

[0037] The judgment module is used to calculate the difference in graphic area between the actual irregular shape of the gear projection and the theoretical irregular shape of the gear projection for each gear under test based on the projection mapping relationship between the actual irregular shape of the gear projection and the gear under test, and to determine whether there are tooth defects in the target batch of gears under test.

[0038] In addition, to achieve the above objectives, the present invention also provides a batch defect detection device for automotive gears, the batch defect detection device for automotive gears comprising: a memory, a processor, and a batch defect detection program for automotive gears stored in the memory and executable on the processor, wherein when the batch defect detection program for automotive gears is executed by the processor, it implements the steps of the batch defect detection method for automotive gears as described above.

[0039] In addition, to achieve the above objectives, the present invention also provides a storage medium storing a batch defect detection program for automotive gears, wherein the batch defect detection program for automotive gears, when executed by a processor, implements the steps of the above-described batch defect detection method for automotive gears.

[0040] The beneficial effects of this invention are as follows: It proposes a method, apparatus, equipment, and storage medium for batch defect detection of automotive gears. The method involves acquiring a first gear detection image containing several gears to be detected within a gear detection area; extracting the detection position of each gear on the transparent positioning plate; determining several projection light sources based on defect detection resolution requirements; driving these projection light sources to sequentially project onto the transparent positioning plate; acquiring a second gear detection image received on the projection panel during each projection; extracting the actual irregular shape of the gear projection that meets the defect detection resolution requirements; and calculating the area difference between the actual irregular shape and the theoretical irregular shape of the gear projection for each gear based on the projection mapping relationship between the actual irregular shape and the gear to be detected, thereby determining whether the target batch of gears to be detected has tooth defects. Therefore, this invention achieves high-accuracy batch defect detection of gears in the same batch by using a light source projection magnification method to obtain irregular magnified images of multiple gears in the same batch. Then, by comparing the irregular magnified images with standard images, multiple gears are projected and magnified at random and different locations for parallel defect judgment. This significantly improves the efficiency of batch defect detection of gears and lowers the threshold for gear defect detection. Attached Figure Description

[0041] Figure 1 This is a schematic diagram of the device structure of the hardware operating environment involved in the embodiments of the present invention;

[0042] Figure 2 This is a schematic flowchart of an embodiment of the batch defect detection method for automotive gears of the present invention;

[0043] Figure 3 This is a structural block diagram of a batch defect detection device for automotive gears according to an embodiment of the present invention. Detailed Implementation

[0044] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0045] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0046] like Figure 1 As shown, Figure 1 This is a schematic diagram of the device structure of the hardware operating environment involved in the embodiments of the present invention.

[0047] like Figure 1As shown, the device may include: a processor 1001, such as a CPU; a communication bus 1002; a user interface 1003; a network interface 1004; and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen or an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be high-speed RAM or non-volatile memory, such as a disk drive. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0048] Those skilled in the art will understand that Figure 1 The structure of the device shown does not constitute a limitation on the device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0049] like Figure 1 As shown, the memory 1005, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and a batch defect detection program for automotive gears.

[0050] exist Figure 1 In the terminal shown, network interface 1004 is mainly used to connect to the backend server and communicate data with it; user interface 1003 is mainly used to connect to the client (user terminal) and communicate data with it; while processor 1001 can be used to call the batch defect detection program for automotive gears stored in memory 1005 and perform the following operations:

[0051] Acquire a first gear detection image within the gear detection area; wherein, the first gear detection image includes several gears to be detected from the target batch, which are randomly laid flat on a transparent positioning plate;

[0052] The first gear detection image is analyzed, the detection position of each gear to be detected on the transparent positioning plate is extracted, and several projection light sources are determined according to the defect detection resolution requirements.

[0053] Several projection light sources are driven to project onto the transparent positioning plate in sequence. The second gear detection image received on the projection panel is collected each time the light source projection is performed. The actual irregular shape of the gear projection that meets the defect detection resolution requirements in each second gear detection image is extracted.

[0054] Based on the projection mapping relationship between the actual irregular shape of the gear projection and the gear to be inspected, the difference in graphic area between the actual irregular shape of the gear projection and the theoretical irregular shape of the gear projection for each gear to be inspected is calculated to determine whether there are tooth defects in the target batch of gears to be inspected.

[0055] The specific embodiments of the present invention applied to the device are basically the same as the embodiments of the batch defect detection method for automotive gears described below, and will not be repeated here.

[0056] This invention provides a method for batch defect detection of automotive gears, referring to... Figure 2 , Figure 2 This is a flowchart illustrating an embodiment of the batch defect detection method for automotive gears of the present invention.

[0057] In this embodiment, a method for batch defect detection of automotive gears includes the following steps:

[0058] S100: Acquire a first gear detection image within the gear detection area; wherein, the first gear detection image includes several gears to be detected in the target batch, which are randomly laid flat on the transparent positioning plate;

[0059] S200: Analyze the first gear detection image, extract the detection position of each gear to be detected on the transparent positioning plate, and determine several projection light sources according to the defect detection resolution requirements;

[0060] S300: Drives several projection light sources to project onto the transparent positioning plate in sequence, and collects the second gear detection image received on the projection panel each time the light source projection is performed, and extracts the actual irregular shape of the gear projection that meets the defect detection resolution requirements in each second gear detection image;

[0061] S400: Based on the projection mapping relationship between the actual irregular shape of the gear projection and the gear to be inspected, calculate the difference in graphic area between the actual irregular shape of the gear projection and the theoretical irregular shape of the gear projection for each gear to be inspected, and determine whether there are tooth defects in the target batch of gears to be inspected.

[0062] It should be noted that the tooth profile distortion problem of small module gears (mainly caused by the wear of hobbing / shaping machine tools affecting tool accuracy and the long-term use of temperature sensors affecting heat treatment accuracy, resulting in local tooth profile distortion, which often leads to batch tooth profile distortion in the same batch of gears) is a significant challenge for traditional image analysis-based gear defect detection. Due to the small size and large number of small module gears, traditional methods place high demands on camera resolution and the accuracy of defect recognition models, making it difficult to detect problems in gear production equipment in a timely manner, leading to the production of batches of defective products. Furthermore, since inspection can only be performed one by one, the computational power of image analysis equipment is highly demanding. The combined effect of these factors greatly increases the equipment construction cost for production inspection of small module gears on the production line.

[0063] To address the aforementioned issues, this embodiment acquires a first gear inspection image containing several gears to be inspected. Based on the defect detection resolution requirements, several projection light sources are determined and driven to sequentially project onto a transparent positioning plate. A second gear inspection image received by the projection panel is then acquired. The actual irregular shape of the gear projection, meeting the defect detection resolution requirements, is extracted, and the area difference between this and the theoretical irregular shape is compared to determine whether the target batch of gears has tooth defects. Therefore, this invention employs a batch defect detection and light source projection magnification method, projecting and magnifying multiple gears at random and different locations for parallel defect judgment. This enables high-accuracy batch defect detection of gears in the same batch, significantly improving the efficiency of batch gear defect detection and lowering the threshold for gear defect detection.

[0064] In a preferred embodiment, the step of acquiring a first gear detection image within the gear detection area specifically includes:

[0065] S110: Based on the conveying mechanism and the vibration mechanism, the transparent positioning plate is controlled to perform conveying and vibration actions, driving the gear delivery device to output and deliver a number of gears to be tested to be randomly laid flat on the transparent positioning plate, and the transparent positioning plate is conveyed to the gear detection area; wherein, the gear detection area is provided with a first image acquisition device in the direction facing the transparent positioning plate;

[0066] S120: When the transparent positioning plate is detected to have entered the acquisition position of the gear detection area, a first gear detection image containing several gears to be detected in the target batch is acquired by the first image acquisition device.

[0067] In this embodiment, the conveying mechanism is located between the transparent positioning plate placement area and the gear detection area. The transparent positioning plate is placed on the transmission motion surface of the conveying mechanism in the transparent positioning plate placement area, and then the conveying mechanism conveys several transparent positioning plates to the gear detection area.

[0068] Based on this, the feeding end outlet of the gear feeding device is located in the feeding area between the transparent positioning plate placement area and the gear detection area. When the transparent positioning plate moves to the feeding area, the gear to be tested is gently fed onto the transparent positioning plate through the inclined feeding end outlet. Then, the vibration mechanism set on the conveying mechanism is used to make the gear to be tested naturally dispersed during the transmission process, ensuring that several gears to be tested output by the gear feeding device are randomly laid flat on the transparent positioning plate, avoiding the influence of overlapping or non-flat posture of the gears to be tested on the subsequent tooth shape defect detection based on image acquisition.

[0069] For example, the vibration mechanism can use several telescopic support rods set on the conveying mechanism. Each telescopic support rod is equipped with an adsorption device. The adsorption devices of several telescopic support rods can support and adsorb and fix multiple positions under the transparent positioning plate. By controlling the extension and retraction of the support rods at different positions, the adsorbed and fixed transparent positioning plate can vibrate at different angles and frequencies to disperse the gears to be tested that are placed on the transparent positioning plate.

[0070] In some embodiments, when the gear inspection task is heavy, a single transparent positioning plate needs to lay more gears to be inspected. In order to further ensure that several gears to be inspected are laid flat on the transparent positioning plate without interfering with each other, a manual adjustment station can be set up before the gear inspection area to adjust the posture of the gears to be inspected by manual adjustment, thereby further avoiding the impact on defect detection.

[0071] In some embodiments, a sensing sensor is provided in the gear detection area. When the sensor detects that the transparent positioning plate has entered a preset acquisition area position within the gear detection area, it controls a first image acquisition device positioned in the gear detection area facing the transparent positioning plate to acquire an image of the gear to be detected on the transparent positioning plate. It should be noted that since the gears to be detected will randomly disperse and lie flat on the transparent positioning plate after vibration, the first gear detection image acquired by the first image acquisition device can be used to analyze the position of each gear to be detected. This facilitates subsequent querying of the theoretical irregular shape of the gear projection for each gear to be detected, thereby achieving the detection of tooth profile defects in the gears to be detected.

[0072] In a preferred embodiment, the first gear detection image is analyzed, the detection position of each gear to be detected on the transparent positioning plate is extracted, and several projection light source steps are determined according to the defect detection resolution requirements. Specifically, this includes:

[0073] S210: Extract several positioning auxiliary lines from the first gear detection image, and determine the detection position of each gear to be detected on the transparent positioning plate based on the positional relationship between each gear to be detected and the several positioning auxiliary lines in the first gear detection image;

[0074] S220: Based on the actual size information of the gears to be inspected in the target batch and the required size information corresponding to the defect detection resolution requirements, calculate the required projection magnification of the gears to be inspected.

[0075] S230: Based on the detection position of each gear to be tested on the transparent positioning plate and the required projection magnification, select several projection light sources from a light source panel with several candidate light sources arranged in the direction facing the transparent positioning plate.

[0076] In this embodiment, by setting several positioning auxiliary lines in the first image acquisition device (which can be formed by installing a glass reticle with a grid or scale inside the lens, and these marks are directly imaged onto the sensor to form fixed auxiliary lines; or by using a camera processor to superimpose composition auxiliary lines located at preset pixel positions on the image after image imaging to form fixed auxiliary lines), the detection position of the gear to be detected on the transparent positioning plate is determined based on the positional relationship between each gear to be detected and several positioning auxiliary lines in the first gear detection image (e.g., the distance from the center of the gear to be detected to each positioning auxiliary line).

[0077] Following this, by obtaining the actual size information of the gears to be inspected in the target batch and the required size corresponding to the defect detection resolution requirements, the projection magnification requirement for the gears to be inspected is calculated based on the required size information and the actual size information. The required size information and the actual size information can be configured as the required radius value and the actual radius value from the gear center to the gear edge of the gear to be inspected. It should be noted that due to the small size of small module gears, the resolution of the configured industrial camera cannot meet the requirements for tooth distortion defect recognition. In this case, magnification processing is required to enlarge the actual size information of the gear edge to the required radius value (this required radius value is the minimum radius value that the industrial camera can recognize for tooth distortion, which can be obtained through pre-testing and recording). Therefore, the projection magnification requirement can be calculated by dividing the required radius value by the actual radius value. After obtaining the projection magnification requirement, several projection light sources can be selected from a light source panel with several candidate light sources positioned in the direction facing the transparent positioning plate, based on the detection position of each gear to be inspected on the transparent positioning plate and the projection magnification requirement.

[0078] In a preferred embodiment, the step of selecting several projection light sources from a light source panel with several candidate light sources arranged in the direction facing the transparent positioning plate, based on the detection position of each gear to be detected on the transparent positioning plate and the required projection magnification, specifically includes:

[0079] S231: Obtain the light source layout position of each candidate light source in the light source panel, and calculate the projection distance value between the projection positions of several edge projection points of each gear under test on the transparent positioning plate and the projection position of the center projection point on the transparent positioning plate when each candidate light source performs light source projection.

[0080] S232: Calculate the total projection distance values ​​of several edge projection points of each gear to be tested on the transparent positioning plate, and put the candidate light sources whose projection magnification ratio determined by the projection distance value and the actual size information of the gear to be tested exceeds the projection magnification requirement into the candidate light source list corresponding to the gear to be tested.

[0081] S233: Select the minimum number of candidate light sources from the list of all candidate light sources for the gears to be inspected as the projection light source for the target batch of gear defects detection on the light source panel, so that when the projection light source performs light source projection, each gear to be inspected has at least one projection distance value with a projection magnification factor that exceeds the projection magnification requirement factor.

[0082] In this embodiment, the light source panel is configured to have several candidate light sources. Each candidate light source can perform light source projection on the gear to be tested on the transparent positioning plate after being selected, so that the gear shape of the gear to be tested is projected on the projection panel. Then, the second image acquisition device acquires the magnified gear projection actual irregular shape on the projection panel, thereby performing gear defect detection and judgment.

[0083] It should be noted that while the light source panel has several candidate light sources, not every gear shape projection obtained when a candidate light source projects onto the gear to be inspected on the transparent positioning plate meets the required size for defect detection resolution. Therefore, it is necessary to calculate the projection distance (i.e., the actual radius value) between the projection positions of several edge projection points of each gear to be inspected on the transparent positioning plate and the projection position of the center projection point on the transparent positioning plate when each candidate light source performs light projection, based on the light source layout position of each candidate light source, the detection position of each gear to be inspected on the transparent positioning plate, the first distance between the light source panel and the transparent positioning plate, and the second distance between the transparent positioning plate and the projection panel. Based on this projection distance value, the projection light source (i.e., the projection light source that meets the required size for defect detection resolution) is selected from the several candidate light sources to perform light projection.

[0084] In practical applications, to address the issue of high processing speed and capability requirements for image analysis equipment in batch gear image acquisition and inspection, this embodiment employs a projection light source far fewer than the number of gears to be inspected to project light onto several gears in the target batch. This forms a gear-shaped projection on the projection panel that includes all the gears to be inspected. Furthermore, considering that the number of projection light sources is far less than the number of gears to be inspected, and that the actual radius of the gear-shaped projection needs to meet the required dimensions, when selecting the light source projection, an oblique projection is used for each gear to be inspected, rather than a direct projection (direct projection would result in a gap between the light source panel and the transparent positioning plate). The first distance and the second distance between the transparent positioning plate and the projection panel are too close, which makes the magnification unable to meet the requirements. When tilting the projection, the farther the distance between the light source position and the gear to be detected, the greater the magnification of the gear shape projection on the tooth part in the direction of the light source projection. On the one hand, it can improve the magnification of the gear projection and satisfy the projection magnification ratio determined by the projection distance value and the actual size information of the gear to be detected, which exceeds the projection magnification requirement. On the other hand, the number of projection light sources is less than the number of gears to be detected, which also inevitably makes most of the projection methods themselves tilted projection. Based on the principle of tilted projection, the obtained gear shape projection is a gear projection irregular shape.

[0085] Based on this, by statistically analyzing the total projection distance values ​​of several edge projection points of each gear under test on the transparent positioning plate when each candidate light source performs light source projection, it is determined whether the projection distance value when each candidate light source performs light source projection is greater than the required size corresponding to the defect detection resolution requirement. If so, it indicates that when the candidate light source performs light source projection on the gear under test, the gear projection irregular shape obtained on the projection panel has a part with a projection magnification ratio that meets the projection magnification requirement ratio. At this time, the candidate light source is added to the candidate light source list of the gear under test.

[0086] After obtaining the candidate light source list for each gear to be inspected, the minimum number of candidate light sources are selected from the list of all gears to be inspected as the projection light sources for the light source panel to detect defects in the target batch of gears. In this way, when performing the light source projection image acquisition, as few second gear detection images as possible are used. Thus, by selecting far fewer projection light sources and acquiring second gear detection images than the number of gears to be inspected, the number of image processing operations is minimized while meeting the required size corresponding to the defect detection resolution requirements. This enables high-accuracy batch defect detection of the same batch of gears, significantly improving the efficiency of batch defect detection of gears.

[0087] In a preferred embodiment, the steps of driving several projection light sources to sequentially project light onto the transparent positioning plate, acquiring the second gear detection image received on the projection panel at each light source projection, and extracting the actual irregular shape of the gear projection that meets the defect detection resolution requirements from each second gear detection image are as follows:

[0088] S310: Drive several projection light sources to sequentially project light onto all the gears to be detected on the transparent positioning plate, and use a second image acquisition device set on the side of the projection panel away from the projection direction in the gear detection area to acquire the second gear detection image received on the projection panel each time the light source projection is performed;

[0089] S320: Extract a gear projection that meets the projection magnification requirement for each gear from all the second gear inspection images of several projection light sources, and use it as the actual irregular shape of the gear projection that meets the defect detection resolution requirements. Establish the projection mapping relationship between each gear projection actual irregular shape and the corresponding gear to be inspected and the corresponding projection light source.

[0090] In this embodiment, after obtaining the projection light source for the target batch of gears to be inspected, several projection light sources on the drive light source panel are sequentially used to project light onto all the gears to be inspected on the transparent positioning plate, projecting the gear shape containing all the gears to be inspected onto the projection panel. It should be noted that the projection panel is configured as a rear projection panel with diffuse characteristics, so that after projection on one side, the gear projection graphic can be clearly displayed on the other side. A second image acquisition device located on the other side acquires the second gear inspection image received on the projection panel each time light source projection is performed. Subsequently, a gear projection that meets the required projection magnification ratio for each gear to be inspected is extracted from all the second gear inspection images from the several projection light sources, and this is used as the actual irregular shape of the gear projection.

[0091] In a preferred embodiment, the step of determining whether the gears in the target batch have tooth defects, based on the projection mapping relationship between the actual irregular shape of the gear projection and the gear to be inspected, and calculating the difference in graphic area between the actual irregular shape of the gear projection and the theoretical irregular shape of the gear projection for each gear to be inspected, specifically includes:

[0092] S410: Based on the detection position of each gear to be tested on the transparent positioning plate, query the pre-entered gear test database for the theoretical irregular shape of the gear projection when the detection position of the gear to be tested on the transparent positioning plate is affected by the light source projection of the corresponding projection light source.

[0093] The gear test database is configured to store: a set of theoretical irregular shapes of gear projections obtained when the gears to be tested are projected by different light sources at different test positions on the transparent positioning plate during the projection simulation test of the target batch of gears to be tested in advance;

[0094] S420: For the extracted actual irregular shape of the gear projection and the queried theoretical irregular shape of the gear projection, calculate the difference in the graphic area of ​​each gear to be detected as the quantification value of the tooth defect.

[0095] S430: Based on the quantization value of the tooth profile defect of each gear to be tested and the corresponding quantization threshold of the tooth profile defect, determine whether there is at least one gear to be tested whose quantization value of the tooth profile defect exceeds the corresponding quantization threshold of the tooth profile defect. If so, determine that the gears to be tested in the target batch have tooth profile defects.

[0096] In this embodiment, after obtaining the actual irregular shape of the gear projection for each gear to be tested, based on the detection position of the gear to be tested on the transparent positioning plate, the theoretical irregular shape of the gear projection when the detection position on the transparent positioning plate is projected by the corresponding projection light source is queried. The difference between the area of ​​the theoretical irregular shape of the gear projection and the actual irregular shape of the gear projection is used as the quantification value of the tooth shape defect. The quantification value of the tooth shape defect is compared with the tooth shape defect quantification threshold corresponding to the current position relationship between the gear to be tested and the projection light source. If the quantification value of the tooth shape defect of at least one gear to be tested exceeds the corresponding tooth shape defect quantification threshold, it indicates that the gears to be tested in the target batch have tooth shape defects.

[0097] It should be noted that the degree to which tooth defects on the gear are magnified varies depending on the positional relationship between the gear under test and the projection light source. Therefore, it is necessary to set a quantification threshold for tooth defects when the positional relationship between the gear under test and the projection light source is different. When judging tooth defects, the quantification value of tooth defects determined by the area of ​​the theoretical irregular shape of the gear projection and the actual irregular shape of the gear projection is compared with the quantification threshold of tooth defects corresponding to the current positional relationship between the gear under test and the projection light source, so as to improve the accuracy of defect detection and judgment.

[0098] In practical applications, considering that tooth profile distortion in the same batch of gears to be tested often occurs in batches, meaning that tooth profile distortion in the batch of gears to be tested is not an isolated case, but rather accounts for a certain proportion, this embodiment uses the oblique projection method. Although it can only magnify a part of each gear to be tested to achieve tooth profile distortion judgment, it can simultaneously judge the tooth profile distortion of several gears to be tested in the same batch. As long as any one gear to be tested has tooth profile distortion (i.e., the tooth profile defect quantification value exceeds the corresponding tooth profile defect quantification threshold), it can be determined that the target batch of gears to be tested has tooth profile defects and tooth profile distortion.

[0099] Therefore, this embodiment utilizes tilted projection to magnify the distorted tooth profile, reducing the difficulty of defect detection. On the other hand, it employs batch defect detection to obtain magnified images of multiple gears in the same batch for parallel judgment, avoiding the impact of tilted projection on the accuracy of defect detection, which can only magnify a portion of the gear to be detected. This enables high-accuracy batch defect detection of gears in the same batch, significantly improving the efficiency of batch defect detection and lowering the threshold for gear defect detection.

[0100] In a preferred embodiment, the projection simulation test of the gear to be tested specifically includes:

[0101] S411: Construct a simulation model of the area to be detected, including a projection panel, a transparent positioning plate, and a light source panel; write a simulation projection script to traverse the gears to be detected located at different detection positions on the transparent positioning plate and different projection light sources on the light source panel.

[0102] S412: Drive the simulation model to execute the simulation projection script, record and statistically analyze the theoretical irregular shape of the gear projection when the gear to be tested is projected by different light sources at different detection positions on the transparent positioning plate, and construct a gear test database containing a set of theoretical irregular shape of gear projection.

[0103] Reference Figure 3 , Figure 3 This is a structural block diagram of an embodiment of the automotive gear batch defect detection device of the present invention.

[0104] like Figure 3 As shown, the batch defect detection device for automotive gears proposed in this embodiment of the invention includes:

[0105] The acquisition module 10 is used to acquire a first gear detection image within the gear detection area; wherein, the first gear detection image includes several gears to be detected in the target batch, which are randomly laid flat on the transparent positioning plate;

[0106] The analysis module 20 is used to analyze the first gear detection image, extract the detection position of each gear to be detected on the transparent positioning plate, and determine a number of projection light sources according to the defect detection resolution requirements.

[0107] Projection module 30 is used to drive several projection light sources to project onto the transparent positioning plate in sequence, and to collect the second gear detection image received on the projection panel at each time the light source projection is performed, and to extract the actual irregular shape of the gear projection that meets the defect detection resolution requirements in each second gear detection image.

[0108] The judgment module 40 is used to calculate the difference in graphic area between the actual irregular shape of the gear projection and the theoretical irregular shape of the gear projection for each gear under test based on the projection mapping relationship between the actual irregular shape of the gear projection and the gear under test, and to determine whether there are tooth defects in the target batch of gears under test.

[0109] Other embodiments or specific implementations of the batch defect detection device for automotive gears of the present invention can be referred to the above-described method embodiments, and will not be repeated here.

[0110] Furthermore, the present invention also proposes a batch defect detection device for automotive gears, the batch defect detection device for automotive gears comprising: a memory, a processor, and a batch defect detection program for automotive gears stored in the memory and executable on the processor, wherein when the batch defect detection program for automotive gears is executed by the processor, it implements the steps of the batch defect detection method for automotive gears as described above.

[0111] The specific implementation method of the batch defect detection equipment for automotive gears in this application is basically the same as the embodiments of the batch defect detection method for automotive gears described above, and will not be repeated here.

[0112] Furthermore, this invention also proposes a readable storage medium, which includes a computer-readable storage medium storing a batch defect detection program for automotive gears. The readable storage medium may be... Figure 1The memory 1005 in the terminal can also be at least one of ROM (Read-Only Memory) / RAM (Random Access Memory), magnetic disk, optical disk, etc. The readable storage medium includes several instructions to cause a batch defect detection device for automotive gears with a processor to execute the batch defect detection method for automotive gears described in various embodiments of the present invention.

[0113] The specific implementation in the readable storage medium of this application is basically the same as the embodiments of the above-described batch defect detection method for automotive gears, and will not be repeated here.

[0114] It is understood that in the description of this specification, references to terms such as "one embodiment," "another embodiment," "other embodiments," or "first embodiment to Nth embodiment," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0115] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0116] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0117] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0118] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A method for batch defect detection of automotive gears, characterized in that, Includes the following steps: Acquire a first gear detection image within the gear detection area; wherein, the first gear detection image includes several gears to be detected from the target batch, which are randomly laid flat on a transparent positioning plate; The first gear inspection image is analyzed to extract the inspection position of each gear on the transparent positioning plate. Based on the defect detection resolution requirements, several projection light sources are determined; specifically, this includes: Several positioning auxiliary lines are extracted from the first gear detection image. Based on the positional relationship between each gear to be detected and the several positioning auxiliary lines in the first gear detection image, the detection position of each gear to be detected on the transparent positioning plate is determined. Based on the actual size information of the gears to be inspected in the target batch and the required size information corresponding to the defect detection resolution requirements, the required projection magnification ratio of the gears to be inspected is calculated. The position of each candidate light source in the light source panel is obtained. Based on the position of the light source, the detection position of each gear to be tested on the transparent positioning plate, the first distance between the light source panel and the transparent positioning plate, and the second distance between the transparent positioning plate and the projection panel, the projection distance value between the projection positions of several edge projection points of each gear to be tested on the transparent positioning plate and the projection position of the center projection point on the transparent positioning plate when each candidate light source performs light source projection is calculated. Statistically calculate the total projection distance values ​​of several edge projection points of each gear to be tested on the transparent positioning plate, and add the candidate light sources whose projection magnification ratio, determined by the projection distance value and the actual size information of the gear to be tested, exceeds the required projection magnification ratio into the candidate light source list corresponding to the gear to be tested. Select the minimum number of candidate light sources from the list of all candidate light sources for the gears to be inspected as the projection light source for the light source panel to inspect the defects of the target batch of gears, so that when the projection light source performs light source projection, each gear to be inspected has at least one gear projection with a projection distance value that has a projection magnification factor that exceeds the projection magnification requirement factor. In selecting the light source projection, oblique projection is used instead of orthographic projection for the light source projection of each gear to be detected; Several projection light sources are driven to project onto the transparent positioning plate in sequence. The second gear detection image received on the projection panel is collected each time the light source projection is performed. The actual irregular shape of the gear projection that meets the defect detection resolution requirements in each second gear detection image is extracted. Based on the projection mapping relationship between the actual irregular shape of the gear projection and the gear to be inspected, the difference in graphic area between the actual irregular shape of the gear projection and the theoretical irregular shape of the gear projection for each gear to be inspected is calculated to determine whether there are tooth defects in the target batch of gears to be inspected.

2. The method for batch defect detection of automotive gears as described in claim 1, characterized in that, The steps for acquiring the first gear detection image within the gear detection area specifically include: Based on the conveying mechanism and the vibration mechanism, the transparent positioning plate is controlled to perform conveying and vibration actions, which drive the gear delivery device to output and deliver several gears to be tested to be randomly laid flat on the transparent positioning plate, and the transparent positioning plate is conveyed to the gear detection area; wherein, the gear detection area is provided with a first image acquisition device in the direction facing the transparent positioning plate; When the transparent positioning plate is detected to have entered the acquisition position of the gear detection area, the first gear detection image containing several gears to be detected in the target batch is acquired by the first image acquisition device.

3. The method for batch defect detection of automotive gears as described in claim 1, characterized in that, The process involves driving several projection light sources to sequentially project onto a transparent positioning plate, acquiring second gear detection images received on the projection panel at each projection, and extracting the actual irregular shape of the gear projection that meets the defect detection resolution requirements from each second gear detection image. Specifically: Several projection light sources are driven to project light onto all the gears to be detected on the transparent positioning plate in sequence. A second image acquisition device is set on the side of the projection panel away from the projection direction in the gear detection area to acquire the second gear detection image received on the projection panel when each light source projection is performed. Extract a gear projection that meets the projection magnification requirement for each gear from all the second gear inspection images from several projection light sources. Use this as the actual irregular shape of the gear projection that meets the defect detection resolution requirements. Establish the projection mapping relationship between each gear projection actual irregular shape and the corresponding gear to be inspected and the corresponding projection light source.

4. The method for batch defect detection of automotive gears as described in claim 1, characterized in that, Based on the projection mapping relationship between the actual irregular shape of the gear projection and the gear to be inspected, the step of calculating the difference in graphic area between the actual irregular shape of the gear projection and the theoretical irregular shape of the gear projection for each gear to be inspected, and determining whether the gears in the target batch have tooth profile defects, specifically includes: Based on the detection position of each gear to be tested on the transparent positioning plate, the theoretical irregular shape of the gear projection when the detection position of the gear to be tested on the transparent positioning plate is affected by the light source projection of the corresponding projection light source is queried in the pre-entered gear test database. The gear test database is configured to store: a set of theoretical irregular shapes of gear projections obtained when the gears to be tested are projected by different light sources at different test positions on the transparent positioning plate during the projection simulation test of the target batch of gears to be tested in advance; For the extracted actual irregular shape of gear projection and the queried theoretical irregular shape of gear projection, the difference in the graphic area of ​​each gear to be detected is calculated as the quantification value of tooth defect. Based on the quantization value of the tooth profile defect of each gear to be tested and the corresponding quantization threshold of the tooth profile defect, it is determined whether there is at least one gear to be tested whose quantization value of the tooth profile defect exceeds the corresponding quantization threshold of the tooth profile defect. If so, it is determined that the gears to be tested in the target batch have tooth profile defects.

5. The method for batch defect detection of automotive gears as described in claim 4, characterized in that, The projection simulation test of the gear to be tested specifically includes: Construct a simulation model of the area to be detected, which includes a projection panel, a transparent positioning plate, and a light source panel. Write a simulation projection script to traverse the gears to be detected located at different detection positions on the transparent positioning plate and different projection light sources on the light source panel. The simulation model is driven to execute the simulation projection script, record and statistically analyze the theoretical irregular shape of the gear projection when the gear to be tested is projected by different light sources at different detection positions on the transparent positioning plate, and construct a gear test database containing a set of theoretical irregular shape of gear projection.

6. A batch defect detection device for automotive gears, characterized in that, include: The acquisition module is used to acquire a first gear detection image within the gear detection area; wherein, the first gear detection image includes several gears to be detected in the target batch, which are randomly laid flat on a transparent positioning plate; The analysis module is used to analyze the first gear inspection image, extract the inspection position of each gear to be inspected on the transparent positioning plate, and determine several projection light sources according to the defect detection resolution requirements; specifically including: Several positioning auxiliary lines are extracted from the first gear detection image. Based on the positional relationship between each gear to be detected and the several positioning auxiliary lines in the first gear detection image, the detection position of each gear to be detected on the transparent positioning plate is determined. Based on the actual size information of the gears to be inspected in the target batch and the required size information corresponding to the defect detection resolution requirements, the required projection magnification ratio of the gears to be inspected is calculated. The position of each candidate light source in the light source panel is obtained. Based on the position of the light source, the detection position of each gear to be tested on the transparent positioning plate, the first distance between the light source panel and the transparent positioning plate, and the second distance between the transparent positioning plate and the projection panel, the projection distance value between the projection positions of several edge projection points of each gear to be tested on the transparent positioning plate and the projection position of the center projection point on the transparent positioning plate when each candidate light source performs light source projection is calculated. Statistically calculate the total projection distance values ​​of several edge projection points of each gear to be tested on the transparent positioning plate, and add the candidate light sources whose projection magnification ratio, determined by the projection distance value and the actual size information of the gear to be tested, exceeds the required projection magnification ratio into the candidate light source list corresponding to the gear to be tested. Select the minimum number of candidate light sources from the list of all candidate light sources for the gears to be inspected as the projection light source for the light source panel to inspect the defects of the target batch of gears, so that when the projection light source performs light source projection, each gear to be inspected has at least one gear projection with a projection distance value that has a projection magnification factor that exceeds the projection magnification requirement factor. In selecting the light source projection, oblique projection is used instead of orthographic projection for the light source projection of each gear to be detected; The projection module is used to drive several projection light sources to project onto the transparent positioning plate in sequence, and to collect the second gear detection image received on the projection panel at each time the light source projection is performed, and to extract the actual irregular shape of the gear projection that meets the defect detection resolution requirements in each second gear detection image; The judgment module is used to calculate the difference in graphic area between the actual irregular shape of the gear projection and the theoretical irregular shape of the gear projection for each gear under test based on the projection mapping relationship between the actual irregular shape of the gear projection and the gear under test, and to determine whether there are tooth defects in the target batch of gears under test.

7. A batch defect detection device for automotive gears, characterized in that, The automotive gear batch defect detection device includes: a memory, a processor, and an automotive gear batch defect detection program stored in the memory and executable on the processor. When the automotive gear batch defect detection program is executed by the processor, it implements the steps of the automotive gear batch defect detection method as described in any one of claims 1 to 5.

8. A storage medium, characterized in that, The storage medium stores a batch defect detection program for automotive gears, which, when executed by a processor, implements the steps of the batch defect detection method for automotive gears as described in any one of claims 1 to 5.

Images