Motor quality inspection method and computer equipment

Abstract

The invention discloses a motor quality inspection method and computer equipment, and relates to the field of industrial automation and precision manufacturing, and the method comprises the steps: determining a plurality of part actual shapes and a plurality of surface actual coatings of a target motor according to image data; comparing the actual shapes of the plurality of parts with standard shapes of the parts corresponding to the plurality of target motor parts to obtain first quality inspection results of the actual shapes of the plurality of parts; component color features and component glossiness features are determined according to the multiple surface actual coatings; comparing the component color feature and the component glossiness feature with a component standard color and a component standard glossiness in the surface standard coating respectively to obtain a plurality of second quality inspection results of the surface actual coating; and when the first quality inspection result and the second quality inspection result meet the preset target motor quality standard, returning a quality inspection qualification result. By implementing the method, personalized quality inspection of different motor types is realized through image analysis, and the accuracy and reliability of quality inspection are improved.

Description

Technical Field

[0001] The present application relates to the fields of industrial automation and precision manufacturing, and in particular to a motor quality inspection method and computer equipment. Background Art

[0002] In modern manufacturing, product quality control is one of the key factors to maintain competitiveness. Especially in the field of high-precision equipment manufacturing, such as motor production, the precise production of each component is crucial. This is not only related to the performance of the product, but also directly affects the reliability and life of the product. Therefore, strict inspection of the quality of motors and their components has become a necessary step in the production process.

[0003] Traditional motor quality inspection methods rely on manual visual inspection and simple mechanical measurement. These methods usually include measuring the size of motor components using tools such as calipers and gauges, and manually checking the coating quality of the component surface, such as coating uniformity and color consistency. This manual inspection method is simple and direct in operation and easy to implement.

[0004] However, traditional inspection methods have obvious limitations, resulting in inaccurate quality assessment of motor components, which in turn affects the performance and reliability of the entire machine. In the rapidly developing industrial production, the demand for more efficient and accurate quality inspection technology is becoming increasingly urgent. Summary of the invention

[0005] The present application provides a motor quality inspection method and computer equipment for realizing personalized quality inspection of different motor types through image analysis, thereby improving the accuracy and reliability of quality inspection.

[0006] In a first aspect, the present application provides a motor quality inspection method, which is applied to computer equipment, and the method includes: obtaining image data of a target motor type and a target motor at multiple preset angles at a preset position; determining the actual shapes of multiple components and multiple actual surface coatings of the target motor based on the image data; comparing the actual shapes of the multiple components with the standard shapes of components corresponding to multiple target motor components in a preset target motor parameter database to obtain a first quality inspection result of the actual shapes of the multiple components, wherein the target motor parameter database is determined by the target motor type, and the target motor parameter database includes multiple target motor components and the standard shapes of components and standard surface coatings corresponding to the multiple target motor components; determining component color characteristics and component gloss characteristics based on the actual coatings on the multiple surfaces; comparing the component color characteristics and component gloss characteristics with the standard color of the component and the standard gloss of the component in the standard surface coating, respectively, to obtain a second quality inspection result of the actual coatings on the multiple surfaces; when the first quality inspection result and the second quality inspection result meet the preset target motor quality standard, a qualified quality inspection result is returned.

[0007] In the above embodiment, the computer device performs a comprehensive inspection on the target motor by acquiring the target motor type and multi-angle image data; the actual shape of the component and the actual surface coating are determined by image processing technology, and then compared with the standard shape of the component and the standard surface coating in the target motor parameter database to achieve objective and accurate personalized quality inspection. Because different motor types correspond to different specific parameters, when the computer device performs quality inspection on the target motor type, the computer device needs to perform quality inspection based on the target motor parameter database corresponding to the target motor. By combining the first quality inspection result of the actual shape of multiple components and the second quality inspection result of the actual coating of multiple surfaces with the preset target motor quality standard, it is ensured that the quality inspection result is accurate and reliable. This solution is suitable for the quality control of high-precision equipment such as motors, realizes the intelligence and precision of the quality inspection process, can effectively improve the quality inspection efficiency, and ensure the consistency of quality inspection standards.

[0008] In combination with some embodiments of the first aspect, in some embodiments, the actual shapes of multiple components and the actual coatings on multiple surfaces of the target motor are determined based on image data, specifically including: performing preprocessing operations on the image data based on an image processing algorithm, the preprocessing operations including denoising and contrast enhancement to obtain a clear image; performing semantic segmentation on the clear image to identify multiple component areas and multiple surface coating areas; based on the segmented images of the multiple component areas, extracting contour information of the multiple components to obtain the actual shapes of the multiple components; based on the segmented images of the multiple surface coating areas, extracting color information and light intensity information to obtain the actual coatings on the multiple surfaces.

[0009] In the above embodiment, the image processing process for determining the actual shape of the component and the actual coating on the surface is specifically described. This solution makes full use of image processing technology to make the extraction of the actual shape of the component and the actual coating on the surface more accurate and reliable, providing solid data support for subsequent quality inspection and judgment, which is an important part of the entire quality inspection process and further enhances the intelligence level of this solution.

[0010] In combination with some embodiments of the first aspect, in some embodiments, the actual shapes of multiple components are compared with the standard shapes of components corresponding to multiple target motor components in a preset target motor parameter database to obtain a first quality inspection result of the actual shapes of the multiple components, specifically including: sampling the actual shapes of the components and the standard shapes of the components respectively to obtain an actual contour point sequence set and a standard contour point sequence set, the actual contour points in the actual contour point sequence set correspond to the standard contour points in the standard contour point sequence set; calculating the distance between the actual contour point and the corresponding standard contour point as a matching error; determining the degree of contour matching between the actual contours of the multiple components and the standard contours by comparing the matching error and a preset contour error threshold, to obtain a first quality inspection result.

[0011] In the above embodiment, a specific technical solution for obtaining the first quality inspection result of the actual shapes of multiple components is elaborated in detail, that is, a method of determining the degree of contour matching between the actual outer contours of multiple components and the standard outer contours by using contour sampling and calculating contour distance, so that the shape judgment standard of the target motor can be quantified, the objectivity and consistency of the first quality inspection result are improved, the precision of shape detection is achieved, a reliable reference is provided for the final quality inspection result, and the operability of the method is enhanced.

[0012] In combination with some embodiments of the first aspect, in some embodiments, the component color characteristics and component gloss characteristics are respectively compared with the component standard color and component standard gloss in the surface standard coating to obtain a second quality inspection result of multiple surface actual coatings, specifically including: determining the color error between the component color characteristics and the corresponding component standard color; determining the degree of color matching between the component color characteristics and the component standard color by comparing the color error and a preset coating color error threshold; determining the gloss error between the component gloss characteristics and the corresponding component standard gloss; determining the gloss matching between the component gloss characteristics and the component standard gloss by comparing the gloss error and a preset coating gloss error threshold; and determining the second quality inspection result based on the color matching degree and the gloss matching degree.

[0013] In the above embodiment, the technical process of obtaining the second quality inspection results of the actual coatings on multiple surfaces is described in detail, that is, the color error and gloss error are respectively compared with the preset coating color error threshold and the preset coating gloss error threshold to determine the matching degree, and finally the second quality inspection result is given by combining the two. The image processing technology is reasonably used to quantify the abstract color and gloss standards, ensure the accuracy of the second quality inspection result, further enhance the intelligence and standardization of surface coating detection, and provide an objective basis for the final quality inspection judgment.

[0014] In combination with some embodiments of the first aspect, in some embodiments, after the step of comparing the component color features and the component gloss features with the component standard color and the component standard gloss in the surface standard coating respectively to obtain a second quality inspection result of multiple surface actual coatings, the method also includes: performing three-dimensional reconstruction on the image data of the target motor to obtain a three-dimensional model of the target motor; extracting the dimensional parameters of the three-dimensional model as the actual size of the component; comparing the actual size of the component with the standard size of the component to obtain the component size error, the target motor parameter database including the standard size of the component; determining the size quality inspection results of multiple components based on the component size error and a preset size error threshold.

[0015] In the above embodiment, a component size detection process based on 3D reconstruction to obtain size parameters is added, so that it is possible to comprehensively judge whether the component size is qualified, ensure that the quality inspection is more comprehensive and accurate, further improve the integrity of the quality inspection, avoid missed inspection problems, and have important significance for the precise inspection of complex components.

[0016] In combination with some embodiments of the first aspect, in some embodiments, after the step of comparing the component color characteristics and component gloss characteristics with the component standard color and component standard gloss in the surface standard coating respectively to obtain the second quality inspection results of multiple surface actual coatings, the method also includes: when the first quality inspection result and / or the second quality inspection result does not meet the preset target motor quality standard, marking the reason for the failure to meet the requirements and obtaining a quality inspection defect report; according to the quality inspection defect report, classifying the target motor to obtain a quality inspection classification result.

[0017] In the above embodiment, when the first quality inspection result and / or the second quality inspection result does not meet the preset target motor quality standard, the reason for failure is given and quality inspection classification is performed, so that the quality inspection result is clearer and more intuitive, and supports subsequent quality traceability or product grading, which has a guiding role in quality control and optimization.

[0018] In combination with some embodiments of the first aspect, in some embodiments, before the step of obtaining image data of the target motor type and the target motor at multiple preset angles at a preset position, the method also includes: obtaining a large batch of motor products, the large batch of motor products including different types of motors; in response to a quality inspection instruction for the target motor, using the target motor as a product to be quality inspected.

[0019] In the above embodiment, a process design suitable for large-scale quality inspection is added, and the quality inspection object can be determined according to the selection. Since different motor types have different reference standards, the inspection is carried out according to the quality inspection standards corresponding to the objects, which enhances the scope of application of the method and can cover the quality inspection requirements of all links of production.

[0020] In a second aspect, an embodiment of the present application provides a computer device, comprising: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to cause the computer device to execute the method described in the first aspect and any possible implementation method of the first aspect.

[0021] In a third aspect, an embodiment of the present application provides a computer program product comprising instructions, which, when executed on a computer device, enables the computer device to execute the method described in the first aspect and any possible implementation of the first aspect.

[0022] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, comprising instructions, which, when executed on a computer device, enable the computer device to execute the method described in the first aspect and any possible implementation of the first aspect.

[0023] It is understandable that the computer device provided in the second aspect, the computer program product provided in the third aspect, and the computer storage medium provided in the fourth aspect are all used to execute the method provided in the embodiment of the present application. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method, which will not be repeated here.

[0024] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. Due to the adoption of the technical solution of obtaining the target motor type and multi-angle image data, determining the actual shape of the component and the actual surface coating, and comparing and judging according to the target motor parameter database, intelligent and personalized quality inspection based on image analysis is realized, which effectively solves the problems of incomplete inspection and poor subjective results in the existing traditional manual quality inspection, and thus realizes the effect of highly automated quality inspection process, more accurate and objective results, and customizable quality inspection standards. This quality inspection method greatly improves the quality inspection efficiency, reduces human errors, and can set personalized parameters for different types of motors, ensuring that the quality inspection of each motor is more accurate and reliable, which is of great significance to ensuring the precision manufacturing level of motor products.

[0025] 2. Since image processing technology is used to determine the parametric features of the actual shape of the component and the actual surface coating, the accurate description and quantitative expression of the quality inspection object is achieved, which effectively solves the problem of overly subjective and vague judgments on component shape and surface coating in existing methods, and thus achieves the effect of parameterization of quality inspection judgment standards and accurate and objective judgments. This parameter feature extraction method can make quality inspection comparisons based on precise calculations, greatly improve the fairness and consistency of quality inspections, ensure that each judgment is based on accurate expression of data, and provide a solid foundation for subsequent quality inspections.

[0026] 3. Due to the adoption of a technical solution that compares with the motor parameter database and sets thresholds to determine the quality inspection results, the quality inspection standards can be customized and the judgment rules are unified, which effectively solves the problem of fuzzy quality inspection standards and differences in manual experience in existing methods, thereby achieving a highly standardized quality inspection process and reliable judgment rules. This motor parameter database comparison method can formulate quality inspection standards according to different motor types, set scientific and reasonable thresholds, standardize judgment rules, ensure the consistency of quality inspection results, and greatly improve the fairness and rationality of quality inspection. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is a flow chart of a motor quality inspection method in an embodiment of the present application; Figure 2 is another flow chart of the motor quality inspection method in an embodiment of the present application; Figure 3 It is a schematic diagram of a physical device structure of a computer device in an embodiment of the present application. DETAILED DESCRIPTION

[0028] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification of the present application, the singular expressions "one", "a kind of", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations comprising one or more of the listed items.

[0029] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0030] See also Figure 1 , is a flow chart of a motor quality inspection method in an embodiment of the present application.

[0031] S101, acquiring a target motor type and image data of the target motor at a plurality of preset angles at a preset position; The operator can first select the specific model of the target motor to be inspected (such as XX series three-phase asynchronous motors) on the human-computer interaction interface of the computer device, so that the computer device obtains the target motor type. After the computer device receives the target motor type, the target motor parameter database of the target motor can be obtained according to the file import, or the target motor parameter database of the target motor can be obtained by other means, which is not limited here. The computer device can be connected to a camera to obtain image data of the target motor at multiple preset angles at a preset position. When the image data is actually obtained, the operator can place the target motor at a preset position according to the prompt of the computer device, and the computer device instructs the acquisition device (such as a manipulator or a motion platform) to drive the camera to rotate different viewing angles to shoot the target motor at multiple preset angles. It should be noted that the image data obtained in this step is not limited to visible light images, but can also include other types of images such as infrared and thermal imaging.

[0032] S102, determining actual shapes of multiple components and actual coatings on multiple surfaces of the target motor according to the image data; Optionally, in general, determining the actual shapes of multiple components and multiple actual coatings on surfaces of the target motor based on image data can be achieved in the following manner: performing preprocessing operations on the image data based on an image processing algorithm, the preprocessing operations including denoising and contrast enhancement to obtain a clear image; performing semantic segmentation on the clear image to identify multiple component regions and multiple surface coating regions; extracting contour information of multiple components based on the segmented images of the multiple component regions to obtain the actual shapes of the multiple components; extracting color information and light intensity information based on the segmented images of the multiple surface coating regions to obtain multiple actual coatings on the surfaces.

[0033] The computer device can perform preprocessing operations on the image data obtained at multiple preset angles at a preset position to obtain a clear image. The preprocessing operations include denoising and contrast enhancement. Denoising can filter out the noise points and noise introduced in the image data during shooting. For example, the median filter and other methods can be used to filter out the outlier noise points that are sampled incorrectly, so that the image data is clearer and smoother. Contrast enhancement can expand the brightness difference of the target parts in the image data and highlight the contour edge, texture details and other visual information of the target. For example, histogram equalization can be used to improve the contrast, so that the grayscale areas that were originally close are separated, and the detail level of the image is richer and clearer. After the preprocessing of denoising and contrast enhancement, the computer device can obtain stronger support in the subsequent accurate feature extraction. For example, algorithms such as contour detection and semantic segmentation will be based on clearer and higher contrast image data, thereby improving the accuracy and reliability of feature extraction.

[0034] The computer device uses semantic segmentation, edge detection and other technologies to identify multiple component areas and multiple surface coating areas, and extracts the edge contour information of each component area to determine the actual shape of each component. At the same time, the computer device can analyze the color information and light intensity information of each component surface, determine the material composition of the surface coating, and determine the material of the surface coating, such as enamel, paint, etc. The computer device can also call a graphic analysis algorithm to calculate the color value, glossiness parameters and other characteristic data of each coating area, so as to obtain the parameterized information of the surface coating of each component. It should be noted that the coating parameter determination in this step is not limited to color and glossiness, but can also include parameters such as coating thickness and roughness, which are not limited here.

[0035] S103, comparing the actual shapes of the multiple components with the component standard shapes corresponding to the multiple target motor components in a preset target motor parameter database to obtain a first quality inspection result of the actual shapes of the multiple components, wherein the target motor parameter database is determined by the target motor type, and the target motor parameter database includes the multiple target motor components and the component standard shapes and surface standard coatings corresponding to the multiple target motor components; The computer device pre-establishes a target motor parameter database for a target motor, and the target motor parameter database stores the three-dimensional model data of all standard components in the target motor type. The computer device can extract the standard shape of the component in the target motor parameter database, compare it with the actual shape of the component detected by image analysis, use a three-dimensional modeling algorithm to calculate the degree of fit between the standard shape of the component and the actual shape of the component, and quantify the degree of fit as a shape difference parameter. Furthermore, the computer device can compare the shape difference parameter with the preset shape error threshold in the target motor parameter database to determine the degree of match between the standard shape of the actual component and the actual shape of the component, and obtain a judgment result of whether the quality inspection of the actual shape of each component is qualified as the first quality inspection result. It should be noted that the shape comparison judgment method of this step is not limited to directly calculating the shape fit, and other shape comparison judgment algorithms such as sample contour key point matching can also be used.

[0036] Optionally, under normal circumstances, the actual shapes of multiple components are compared with the standard shapes of components corresponding to multiple target motor components in a preset target motor parameter database to obtain a first quality inspection result of the actual shapes of multiple components. This can be achieved in the following way: the actual shapes of the components and the standard shapes of the components are sampled respectively to obtain an actual contour point sequence set and a standard contour point sequence set, and the actual contour points in the actual contour point sequence set correspond to the standard contour points in the standard contour point sequence set; the distance between the actual contour point and the corresponding standard contour point is calculated as the matching error; by comparing the matching error and the preset contour error threshold, the degree of contour matching between the actual contours of multiple components and the standard contours is determined to obtain the first quality inspection result.

[0037] The computer device uniformly samples the contour of the actual shape of the component to obtain a set of actual contour point sequences P={p1,p2,...pn}. The computer device samples the contour of the standard shape at the same sampling interval to obtain a corresponding contour point sequence Q={q1,q2,...qn}. According to the continuity characteristics of the contour curve, the computer device establishes a one-to-one point matching relationship between P and Q, and calculates the distance between each pair of matching points pi and qi, that is, pi minus the absolute value of qi, as the matching error. By comparing the matching error and the preset shape contour error threshold, if the matching error is greater than the preset shape contour error threshold, then the first quality inspection result is unqualified, and if the matching error is less than the preset shape contour error threshold, then the first quality inspection result is qualified.

[0038] S104, determining component color characteristics and component gloss characteristics according to the actual coatings on the multiple surfaces; The computer device can analyze the actual coating of each component surface through image processing, extract the RGB color parameters of the actual coating of the surface, and calculate the color characteristics of the components such as chromaticity coordinates and saturation corresponding to the RGB color parameters. At the same time, the computer device can calculate the reflectivity, specular reflection component and other parameters of the actual coating of each surface as the component gloss characteristics of the actual coating of the surface. The computer device can also add the calculation of coating thickness, coating roughness and other characteristics to perform multi-dimensional coating characteristic analysis. It should be noted that the component color feature and component gloss feature analysis method of this step are not limited to the above-mentioned algorithm, and other image feature analysis algorithms such as crunch matrix and floodlight component can also be introduced to comprehensively determine the actual coating characteristics of the surface.

[0039] S105, comparing the component color characteristics and the component gloss characteristics with the component standard color and the component standard gloss in the surface standard coating, respectively, to obtain a second quality inspection result of the actual coating of the multiple surfaces; The component color features and component gloss features extracted by the computer device are compared with the target motor parameter database corresponding to the target motor. The computer device can calculate the color difference between the color features and the standard color parameters, and determine whether the two match according to the preset coating color error threshold. At the same time, the computer device calculates the difference between the gloss feature and the corresponding component standard gloss, and determines the degree of matching according to the preset coating gloss error threshold. The computer device combines the matching degree of the color features and the matching degree of the gloss features to obtain two types of judgment results of qualified or unqualified surface coating quality detection as the second quality inspection result. It should be noted that the coating parameter comparison method in this step is not limited to directly calculating the difference, and a discrimination model can also be established to use a machine learning algorithm to predict and determine the coating quality.

[0040] Optionally, in general, the component color characteristics and component gloss characteristics are compared with the component standard color and component standard gloss in the surface standard coating respectively, and the second quality inspection result of the actual coating of multiple surfaces is obtained by: determining the color error between the component color characteristics and the corresponding component standard color; determining the degree of color matching between the component color characteristics and the component standard color by comparing the color error and the preset coating color error threshold; determining the gloss error between the component gloss characteristics and the corresponding component standard gloss; determining the gloss matching between the component gloss characteristics and the component standard gloss by comparing the gloss error and the preset coating gloss error threshold; and determining the second quality inspection result based on the color matching degree and the gloss matching degree.

[0041] S106: When the first quality inspection result and the second quality inspection result meet the preset target motor quality standard, a qualified quality inspection result is returned.

[0042] The computer device can logically combine the component shape detection result in the first quality inspection result and the surface coating detection result in the second quality inspection result, that is, when both results are positive, it is determined that the quality indicators of the target motor in terms of shape and surface coating have reached the preset target motor quality standards. At this time, the computer device can return the result of "Quality Inspection Passed" in the display interface, and instruct the subsequent production process operations to allow qualified products to enter the packaging process. If any quality inspection result is not in compliance, the computer device will return the result of "Quality Inspection Failed". It should be noted that the quality inspection judgment method of this step is not limited to the first-level judgment, and second-level or third-level quality inspection standards can also be set to make more detailed qualified judgments.

[0043] The following is a more detailed description of the process of the method provided by this implementation. Figure 2 , is another flow chart of the motor quality inspection method in the embodiment of the present application.

[0044] The following steps may or may not be performed before step S101, which is not limited here.

[0045] S201, obtaining a large batch of motor products, where the large batch of motor products includes motors of different types; The large batch of motor products includes motors of different types waiting for quality inspection. The computer equipment stores the relevant information of the large batch of motor products. Before the computer equipment detects these motor products, it first roughly scans to determine which product it is, and then obtains its relevant information, which is used as the basis for quality inspection.

[0046] S202 : In response to a quality inspection instruction for a target motor, the target motor is used as a product to be inspected.

[0047] In response to an instruction issued by an operator to perform quality inspection on one of the motors in a large batch of motor products, the motor is determined as a target motor.

[0048] After step S105, the following steps may be performed or not performed, which is not limited here.

[0049] S203, performing three-dimensional reconstruction on the image data of the target motor to obtain a three-dimensional model of the target motor; First, the computer device detects feature points such as SIFT and SURF in the image data, and uses feature descriptors to match the feature points to find the corresponding relationship between the same object points in different images; secondly, based on the matching relationship of the feature points, the computer device can use the Essential matrix algorithm, the absolute orientation algorithm, etc. to estimate the camera motion between two adjacent images, that is, the rotation and translation relationship; then, the computer device can use the popular MVS multi-view stereo matching algorithm, such as PatchMatch, etc., to restore the depth information of each point in the image based on feature matching and motion relationship; then, based on the three-dimensional coordinates and corresponding depths of the feature points, the computer device can use the point cloud algorithm to generate the three-dimensional point cloud data of the target motor, and then use algorithms such as Poisson surface reconstruction to reconstruct the three-dimensional mesh model of the target motor; finally, the computer device can perform post-processing such as smoothing and detail optimization of the three-dimensional model to output the final high-quality three-dimensional model of the target motor.

[0050] S204, extracting the size parameters of the three-dimensional model as the actual size of the component; Import the generated 3D model data of the target motor in common formats such as OBJ, STL, etc. The computer equipment performs semantic segmentation on the 3D model. The 3D semantic segmentation technology based on deep learning can be used to separate different component areas, such as casing, bolts, etc.

[0051] For each component, the computer equipment determines the measurement plane and constructs the local coordinate system of the component to calculate the dimensions in the standard direction, calculate the coordinate range of the component model in the measurement coordinate system, and obtain the length, width and height dimension values ​​of the direction to be measured.

[0052] Repeat the above steps, traverse all the components to be measured and the dimension directions, and calculate the complete dimension parameters of each component, that is, the actual size of the component.

[0053] S205, comparing the actual size of the component with the standard size of the component to obtain the component size error, and the target motor parameter database includes the standard size of the component; The computer device extracts the standard dimensions of the components from the target motor parameter database, including the standard values ​​of the length, width, height and other dimensions. The computer device compares the actual dimensions of the components with the corresponding standard dimensions one by one, and calculates the numerical difference between the two as the component dimension error. The computer device can calculate the error for each dimension separately, or aggregate the errors of each dimension one by one to obtain a comprehensive dimension error vector. Repeat the above operation for multiple components to obtain the component dimension error of each component.

[0054] S206: Determine dimensional quality inspection results of the plurality of components according to the component dimensional errors and a preset dimensional error threshold.

[0055] If the component dimensional error is greater than the preset dimensional error threshold, the dimensional quality inspection result is unqualified; if the component dimensional error is less than the preset dimensional error threshold, the dimensional quality inspection result is qualified.

[0056] S207, when the first quality inspection result and / or the second quality inspection result do not meet the preset target motor quality standard, mark the reasons for the failure to meet the requirements and obtain a quality inspection defect report; When the second quality inspection result meets the preset target motor quality standard but the first quality inspection result does not meet the preset target motor quality standard, determine the reason for failure in the first quality inspection result; when the first quality inspection result meets the preset target motor quality standard but the second quality inspection result does not meet the preset target motor quality standard, determine the reason for failure in the second quality inspection result; when the first quality inspection result and the second quality inspection result do not meet the preset target motor quality standard, determine the reason for failure in the first quality inspection result and the second quality inspection result, and the computer device marks the reason for failure, and generates a quality inspection defect report based on the defect information and defect area of ​​each target motor. Different colors are used to represent different defect areas and defect information in the quality inspection defect report, and detailed information such as the number of the unqualified parts and the defect type are provided.

[0057] S208. Classify the target motor according to the quality inspection defect report to obtain a quality inspection classification result.

[0058] The computer equipment reads the defect information in the quality inspection defect report, which mainly includes indicators such as defect location, defect type, and defect severity. The target motor is classified according to the quality inspection defect report and the preset quality inspection classification rules. The preset quality inspection classification rules can be classified according to defect type, quantity, and severity. For example, if there are more than 2 appearance errors, it is classified as Class B.

[0059] The computer equipment counts the specific defects of each target motor and judges them one by one according to the conditions defined in the preset quality inspection classification rules. If the Class A condition is met, the target motor is judged as Class A, and so on, to complete the judgment of all classification conditions. A target motor may meet multiple classification rules at the same time. At this time, the most serious classification result can be retained according to priority. Finally, the computer equipment obtains the quality inspection classification to which each target motor belongs, such as Class A / B / C. The computer equipment outputs the quality inspection classification results and displays them with visual defect annotations.

[0060] The following describes the computer device in the embodiment of the present invention from the perspective of hardware processing. Figure 3 , which is a schematic diagram of a physical device structure of a computer device in an embodiment of the present application.

[0061] It should be noted that Figure 3The structure of the computer device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0062] like Figure 3 As shown, the computer device includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part 308 to the random access memory (RAM) 303, such as executing the method described in the above embodiment. In RAM 303, various programs and data required for system operation are also stored. CPU 301, ROM 302 and RAM 303 are connected to each other through bus 304. Input / output (I / O) interface 305 is also connected to bus 304.

[0063] The following components are connected to the I / O interface 305: an input section 306 including an audio input device, a button switch, etc.; an output section 307 including a liquid crystal display (LCD) and an audio output device, an indicator light, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed so that a computer program read therefrom is installed into the storage section 308 as needed.

[0064] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 309, and / or installed from a removable medium 311. When the computer program is executed by the central processing unit (CPU) 301, various functions defined in the present invention are performed.

[0065] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, apparatus, or device.

[0066] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings.

[0067] Specifically, the computer device of this embodiment includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, the motor quality inspection method provided in the above embodiment is implemented.

[0068] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the computer device described in the above embodiment; or may exist independently without being assembled into the computer device. The above storage medium carries one or more computer programs, and when the above one or more computer programs are executed by a processor of the computer device, the computer device implements the motor quality inspection method provided in the above embodiment.

[0069] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0070] As used in the above embodiments, the term "when..." may be interpreted to mean "if..." or "after..." or "in response to determining..." or "in response to detecting...", depending on the context. Similarly, the phrases "upon determining..." or "if (the stated condition or event) is detected" may be interpreted to mean "if determining..." or "in response to determining..." or "upon detecting (the stated condition or event)" or "in response to detecting (the stated condition or event)", depending on the context.

[0071] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

Claims

1. A motor quality inspection method, characterized in that: Applied to a computer device, the method comprises: Acquire the target motor type and image data of the target motor at multiple preset angles at a preset position; Determine the actual shapes of multiple components and actual coatings of multiple surfaces of the target motor according to the image data; Comparing the actual shapes of the multiple components with the component standard shapes corresponding to the multiple target motor components in a preset target motor parameter database to obtain a first quality inspection result of the actual shapes of the multiple components, wherein the target motor parameter database is determined by the target motor type, and the target motor parameter database includes the multiple target motor components and the component standard shapes and surface standard coatings corresponding to the multiple target motor components; Determining component color characteristics and component gloss characteristics based on the plurality of actual surface coatings; Comparing the component color feature and the component gloss feature with the component standard color and component standard gloss in the surface standard coating respectively, to obtain a second quality inspection result of the actual coating of the multiple surfaces; When the first quality inspection result and the second quality inspection result meet the preset target motor quality standard, a quality inspection qualified result is returned.

2. The method according to claim 1, characterized in that Determining the actual shapes of multiple components and actual coatings on multiple surfaces of the target motor according to the image data specifically includes: Performing a preprocessing operation on the image data based on an image processing algorithm, wherein the preprocessing operation includes denoising and contrast enhancement to obtain a clear image; Performing semantic segmentation on the clear image to identify the multiple component areas and the multiple surface coating areas; Extracting contour information of the plurality of components according to the segmented images of the plurality of component regions to obtain actual shapes of the plurality of components; Color information and light intensity information are extracted according to the segmented images of the plurality of surface coating regions to obtain the plurality of actual surface coatings.

3. The method according to claim 1, characterized in that The step of comparing the actual shapes of the multiple components with the component standard shapes corresponding to the multiple target motor components in a preset target motor parameter database to obtain a first quality inspection result of the actual shapes of the multiple components specifically includes: The actual shape of the component and the standard shape of the component are sampled respectively to obtain an actual contour point sequence set and a standard contour point sequence set, wherein the actual contour points in the actual contour point sequence set correspond to the standard contour points in the standard contour point sequence set; Calculating the distance between the actual contour point and the corresponding standard contour point as a matching error; By comparing the matching error with a preset outer contour error threshold, the degree of contour matching between the actual outer contours of the multiple components and the standard outer contours is determined to obtain the first quality inspection result.

4. The method according to claim 1, characterized in that: The comparing the component color feature and the component gloss feature with the component standard color and component standard gloss in the surface standard coating respectively to obtain the second quality inspection results of the actual coatings on the multiple surfaces specifically includes: Determining a color error between a component color feature and a corresponding component standard color; Determining the degree of color matching between the component color feature and the component standard color by comparing the color error and a preset coating color error threshold; Determining a gloss error between a component gloss characteristic and a corresponding component standard gloss; Determining the gloss matching degree between the gloss characteristic of the component and the standard gloss of the component by comparing the gloss error with a preset coating gloss error threshold; The second quality inspection result is determined according to the color matching degree and the gloss matching degree.

5. The method according to claim 1, characterized in that After the step of comparing the component color feature and the component gloss feature with the component standard color and component standard gloss in the surface standard coating respectively to obtain the second quality inspection results of the actual coatings on the multiple surfaces, the method further includes: Performing three-dimensional reconstruction on the image data of the target motor to obtain a three-dimensional model of the target motor; Extracting the size parameters of the three-dimensional model as the actual size of the component; Comparing the actual size of the component with the standard size of the component to obtain a component size error, wherein the target motor parameter database includes the standard size of the component; The dimensional quality inspection results of the plurality of components are determined according to the component dimensional errors and a preset dimensional error threshold.

6. The method according to claim 1, characterized in that After the step of comparing the component color feature and the component gloss feature with the component standard color and component standard gloss in the surface standard coating respectively to obtain the second quality inspection results of the actual coatings on the multiple surfaces, the method further includes: When the first quality inspection result and / or the second quality inspection result do not meet the preset target motor quality standard, the reasons for non-compliance are marked to obtain a quality inspection defect report; According to the quality inspection defect report, the target motor is classified to obtain a quality inspection classification result.

7. The method according to claim 1, characterized in that Before the step of acquiring the target motor type and the image data of the target motor at a plurality of preset angles at a preset position, the method further includes: Acquire a large batch of motor products, wherein the large batch of motor products includes motors of different types; In response to a quality inspection instruction for a target motor, the target motor is taken as a product to be inspected.

8. A computer device, characterized in that: The computer device comprises: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code comprises computer instructions, and the one or more processors call the computer instructions so that the computer device executes the method as described in any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instructions are executed on a computer device, the computer device is caused to execute the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product is executed on a computer device, the computer device is caused to execute the method according to any one of claims 1 to 7.

Images