An intelligent detection system for motor rotor magnetic sheet defects

Abstract

The present invention discloses an intelligent defect detection system for motor rotor magnetic sheets, which relates to the technical field of defect detection. The system includes: a material property analysis module, which is used to construct a material feature library based on the property analysis of commonly used magnetic materials; a key detection index determination module, which is used to analyze and obtain the target material properties of the target motor rotor magnetic sheet, and match and determine the key detection index; a key detection point determination module, which is used to analyze and obtain geometric shape characteristics and generate key detection points; an intelligent defect detection module, which is used to perform targeted defect detection based on key detection indicators and key detection points. The present invention solves the technical problem in the prior art that the diversity of magnetic materials and geometric shapes of motor rotor magnetic sheets affects the accuracy and efficiency of defect detection, and achieves the technical effect of performing targeted intelligent defect detection based on key detection indicators and points, and improving the accuracy and efficiency of motor rotor magnetic sheet defect detection.

Description

Technical Field

[0001] The present invention relates to the technical field of defect detection, and in particular to an intelligent detection system for defects of motor rotor magnetic sheets. Background Art

[0002] The motor rotor magnetic sheet is an important part of the motor, and its performance directly affects the efficiency and reliability of the motor. During the manufacturing and use process, the magnetic sheet may have various defects, such as cracks, corrosion, shedding, pores and inclusions. These defects will not only reduce the performance of the motor, but may also cause motor failure. Therefore, how to effectively detect and identify these defects has become an important issue in motor manufacturing and maintenance.

[0003] Motor rotor magnetic sheets are made of different magnetic materials, which have different magnetic properties, physical properties and chemical properties. In addition, the geometric shapes of motor rotor magnetic sheets are complex and diverse, resulting in low accuracy and efficiency of existing defect detection methods. Summary of the invention

[0004] The present application provides an intelligent defect detection system for motor rotor magnetic sheets, which is used to solve the technical problem in the prior art that the diversity of magnetic materials and geometric shapes of motor rotor magnetic sheets affects the accuracy and efficiency of defect detection.

[0005] The present application provides an intelligent defect detection system for motor rotor magnetic sheets, the system comprising: a material property analysis module, the material property analysis module is used to construct a material feature library based on the property analysis of commonly used magnetic materials; a key detection index determination module, the key detection index determination module is used to analyze and obtain the target material properties of the target motor rotor magnetic sheet, and match and determine the key detection index in combination with the material feature library; a key detection point determination module, the key detection point determination module is used to analyze and obtain the geometric shape characteristics of the target motor rotor magnetic sheet, perform weak point analysis based on the geometric shape characteristics, and generate key detection points; an intelligent defect detection module, the intelligent defect detection module is used to perform targeted defect detection on the target motor rotor magnetic sheet based on the key detection indicators and the key detection points, and obtain a magnetic sheet defect detection result.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] The present application provides an intelligent defect detection system for motor rotor magnetic sheets, which relates to the field of defect detection technology. The system obtains target material properties of target motor rotor magnetic sheets, determines key detection indicators, obtains geometric shape characteristics of target motor rotor magnetic sheets, generates key detection points, and performs targeted defect detection on target motor rotor magnetic sheets based on the key detection indicators and key detection points to obtain magnetic sheet defect detection results. This solves the technical problem in the prior art that the diversity of magnetic materials and geometric shapes of motor rotor magnetic sheets affects the accuracy and efficiency of defect detection, and achieves targeted intelligent defect detection based on key detection indicators and points to improve the technical effect of improving the accuracy and efficiency of motor rotor magnetic sheet defect detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0009] Figure 1 A schematic diagram of the structure of an intelligent detection system for motor rotor magnetic sheet defects provided in an embodiment of the present application.

[0010] Figure 2 A schematic diagram of a process for generating key detection points in an intelligent detection system for motor rotor magnetic sheet defects provided in an embodiment of the present application.

[0011] Figure 3 A schematic diagram of a process for performing targeted defect detection on a target motor rotor magnetic sheet in a motor rotor magnetic sheet defect intelligent detection system provided in an embodiment of the present application.

[0012] Explanation of the accompanying drawings: material property analysis module 11, key detection index determination module 12, key detection point determination module 13, intelligent defect detection module 14. DETAILED DESCRIPTION

[0013] The present application provides an intelligent defect detection system for motor rotor magnetic sheets, which is used to solve the technical problem in the prior art that the diversity of magnetic materials and geometric shapes of motor rotor magnetic sheets affects the accuracy and efficiency of defect detection.

[0014] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0015] It should be noted that the terms "first", "second", etc. in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices.

[0016] Embodiment 1

[0017] like Figure 1 As shown, the present application provides a motor rotor magnetic sheet defect intelligent detection system, the system comprising:

[0018] The material characteristic analysis module 11 is used to construct a material characteristic library based on characteristic analysis of commonly used magnetic materials.

[0019] Furthermore, the material property analysis module 11 is also used to perform the following steps:

[0020] P11: Obtain common magnetic materials for motor rotor magnetic sheets, the common magnetic materials include but are not limited to neodymium iron boron, samarium cobalt, and ferrite; P12: Collect physical property, chemical property and magnetic property data of the common magnetic materials, perform material property analysis, and obtain key characteristic parameters of different magnetic materials, the key characteristic parameters include weak parameters, dominant parameters and the applicable range of each parameter; P13: Based on the key characteristic parameters of the different magnetic materials, perform structured storage and construct the material feature library.

[0021] It should be understood that the material property analysis module 11 of the present application is responsible for deeply analyzing the essential properties of commonly used magnetic materials, and then building a comprehensive and accurate material feature library. At this stage, the module will actively or passively obtain samples of magnetic materials widely used in the market, including but not limited to high-performance neodymium iron boron (NdFeB), high-temperature resistant samarium cobalt (SmCo), and economical and practical ferrite. Each material is selected as a research object because of its unique physical, chemical and magnetic properties.

[0022] Furthermore, a detailed characteristic analysis of the commonly used magnetic materials is carried out. Through laboratory tests, literature research and data provided by suppliers, key data such as the physical properties (such as density, hardness, thermal conductivity), chemical properties (such as corrosion resistance, stability) and magnetic properties (such as magnetization, coercive force, remanence) of each material are collected to analyze the material characteristics and obtain the key characteristic parameters of different magnetic materials. In this process, the module will pay special attention to those weak parameters that can reflect the weak links of the material (such as poor corrosion resistance, high fragility, etc.), as well as the advantageous parameters that show the superior performance of the material (such as high magnetic energy product, good temperature stability). At the same time, the applicability range of each parameter in different application scenarios is analyzed to obtain the key characteristic parameters, providing a scientific basis for subsequent material selection and testing.

[0023] Furthermore, based on the key characteristic parameters of the different magnetic materials, structured storage is performed, and the characteristic parameters of each material will be classified and organized to form a database format that is easy to query and compare. In this way, a material feature library is constructed, which not only contains a detailed characteristic description of each material, but also implies the performance comparison and selection logic between materials, which can provide data support and decision-making basis for the subsequent determination of key detection indicators, detection point selection and defect detection.

[0024] The key detection index determination module 12 is used to analyze and obtain the target material characteristics of the target motor rotor magnetic sheet, and match and determine the key detection index in combination with the material feature library.

[0025] Furthermore, the key detection indicator determination module 12 is also used to perform the following steps:

[0026] P21: Obtain the material type of the target motor rotor magnetic sheet, and based on the material type, obtain the target material characteristics, including physical performance characteristics, chemical performance characteristics and magnetic performance characteristics; P22: Based on the target material characteristics, traverse the material feature library, match and obtain key detection indicators, which are the weak parameters of the target motor rotor magnetic sheet.

[0027] Optionally, the key detection index determination module 12 of the present application is responsible for accurately identifying the key detection indicators of the target motor rotor magnetic sheet to ensure the pertinence and effectiveness of subsequent detection work. At this stage, the module first accurately obtains the material type of the target motor rotor magnetic sheet by reading the product specification, label information or using material identification technology (such as spectral analysis, X-ray diffraction, etc.). Subsequently, based on the identified material type, further in-depth exploration of the material's physical performance characteristics (such as density, hardness, thermal expansion coefficient), chemical performance characteristics (such as corrosion resistance, oxidation resistance) and magnetic performance characteristics (such as magnetization intensity, coercive force, residual magnetism, etc.) as the basis for subsequent matching of key detection indicators.

[0028] Furthermore, after obtaining the comprehensive material properties of the target motor rotor magnetic sheet, these properties are used as query conditions to traverse the constructed material feature library. The feature library stores detailed characteristic parameters of various magnetic materials and their corresponding weak parameters. These weak parameters are often key factors that are prone to problems or affect performance in practical applications. Through an efficient data matching algorithm, the module can quickly retrieve the key detection indicators that best match the target material characteristics from the feature library. These key detection indicators directly point to the weak links that may exist in the manufacturing and use of the target motor rotor magnetic sheet, and can provide clear guidance for subsequent intelligent defect detection. This process not only improves the pertinence and efficiency of detection, but also provides strong support for quality control and performance optimization of motor rotor magnetic sheets.

[0029] The key detection point determination module 13 is used to analyze and obtain the geometric shape characteristics of the target motor rotor magnetic sheet, perform weak point analysis based on the geometric shape characteristics, and generate key detection points.

[0030] Further, such as Figure 2 As shown, the key detection point determination module 13 is also used to perform the following steps:

[0031] P31: Acquire the geometric shape data of the target motor rotor magnetic sheet; P32: Based on the geometric shape data, perform geometric shape analysis to obtain the geometric shape characteristics; P33: Based on the geometric shape characteristics, perform stress distribution simulation, identify stress concentration areas and weak points, and obtain stress distribution simulation results; P34: Utilize historical inspection data of rotor magnetic sheets of the same model to analyze and obtain common defect locations and types, optimize the stress distribution simulation results, and generate the key inspection points, wherein the key inspection points correspond to at least one key inspection indicator respectively.

[0032] In a possible embodiment of the present application, the key detection point determination module 13 of the present application focuses on accurately locating potential weak points by analyzing the geometric shape characteristics of the target motor rotor magnetic sheet, thereby generating key detection points to ensure the comprehensiveness and effectiveness of the detection work. In this step, the module uses high-precision measurement equipment (such as 3D scanners, laser rangefinders, etc.) or directly extracts data from CAD design drawings to ensure that the accurate geometric shape data of the target motor rotor magnetic sheet is obtained. These data include but are not limited to the size, contour, curvature and any special structural features of the magnetic sheet.

[0033] Furthermore, after obtaining the geometric shape data, the geometric processing algorithms (such as edge detection, surface fitting, etc.) are used to conduct in-depth analysis of the data to extract key geometric shape characteristics such as curvature radius, angle change, wall thickness distribution, etc. These characteristics are the basis for subsequent stress distribution simulation and weak point identification. Furthermore, using finite element analysis (FEA) or similar advanced physical simulation technology, the geometric shape characteristics are used as input to construct a physical model of the target motor rotor magnetic sheet and perform stress distribution simulation. During the simulation process, material properties, loading conditions (such as rotational force, temperature gradient, etc.) and boundary conditions are considered to predict the stress distribution of the magnetic sheet under different working conditions. Through simulation, stress concentration areas and potential weak points, that is, key areas where defects are prone to occur, can be clearly identified.

[0034] In order to further improve the accuracy and reliability of key detection points, historical detection data of the same model of rotor magnetic sheets are used for point verification. The historical detection data records the locations and types of common defects found in previous detections, which can provide an effective reference for current detection. The historical data analysis results are comprehensively analyzed with the stress distribution simulation results to verify the rationality of the stress concentration area, and the stress distribution simulation results are optimized based on historical data to ensure that the detection points cover all potential weak areas and common defect locations. Finally, the generated key detection points are not only based on the stress concentration areas of physical simulation, but also combined with the identification experience in actual detection. The key detection points are marked on the physical model, and the key detection indicators corresponding to each point are recorded to achieve comprehensive coverage of potential defects in the motor rotor magnetic sheets.

[0035] The intelligent defect detection module 14 is used to perform targeted defect detection on the target motor rotor magnetic sheet based on the key detection indicators and the key detection points to obtain the magnetic sheet defect detection results.

[0036] Further, such as Figure 3 As shown, the intelligent defect detection module 14 is also used to perform the following steps:

[0037] P41: The intelligent defect detection module includes a visual inspection unit and an ultrasonic inspection unit; P42: Based on the visual inspection unit, preliminary defect detection is performed on the key inspection indicators and the key inspection points to generate preliminary inspection results; P43: Deep defect recognition is performed through the ultrasonic inspection unit, and the preliminary inspection results are verified and calibrated according to the deep defect recognition results to obtain the magnetic sheet defect detection results.

[0038] Optionally, the intelligent defect detection module 14 of the present application integrates advanced visual detection and ultrasonic detection technology, which can realize comprehensive and in-depth defect detection of the target motor rotor magnetic sheet. Among them, the intelligent defect detection module 14 integrates a visual detection unit and an ultrasonic detection unit. The visual detection unit uses a high-resolution camera and image processing technology to intuitively and quickly capture the morphological information of the magnetic sheet surface, while the ultrasonic detection unit deeply detects the microstructure and potential defects inside the magnetic sheet by emitting ultrasonic waves and receiving their reflected signals. This multimodal detection strategy ensures the comprehensiveness and accuracy of the detection.

[0039] Specifically, after obtaining the key detection indicators and key detection points, the intelligent defect detection module first starts the visual inspection unit. The visual inspection unit is equipped with a high-resolution camera and a uniform light source to ensure a stable shooting environment, and fix the target motor rotor magnetic sheet on the detection platform to ensure that its position remains unchanged. Use a high-resolution camera to comprehensively scan the surface of the magnetic sheet, covering all key detection points, and perform high-precision imaging of the designated area of ​​the target motor rotor magnetic sheet. Subsequently, the imaging results are quickly processed using technologies such as image recognition, comparative analysis, and machine learning to identify surface defects related to key detection indicators, such as cracks, scratches, stains, etc., and generate preliminary detection results to achieve rapid screening and positioning of surface defects of the magnetic sheet.

[0040] Furthermore, in order to further improve the accuracy and reliability of the detection, the ultrasonic detection unit is started. This unit will conduct in-depth detection of suspected defect areas or key detection points found in the preliminary detection. By emitting ultrasonic waves and receiving their reflection and transmission signals inside the magnetic sheet, the ultrasonic detection unit can construct a structural image of the inside of the magnetic sheet and identify hidden deep defects such as internal cracks, voids, inclusions, etc. Finally, based on the results of the ultrasonic detection, the preliminary test results are verified and calibrated to eliminate misjudgments and missed detections, ensuring the comprehensiveness and accuracy of the final magnetic sheet defect detection results.

[0041] In summary, the intelligent defect detection module 14 can realize all-round and multi-level defect detection of the target motor rotor magnetic sheet from the surface to the inside by integrating two advanced technologies of visual detection and ultrasonic detection, thereby improving the efficiency and accuracy of detection.

[0042] Further, based on the visual inspection unit, preliminary defect detection is performed on the key inspection indicators and the key inspection points. Step P42 of the embodiment of the present application further includes:

[0043] P42-1: Through the visual inspection unit, image data is collected for the key inspection points to obtain multiple defect recognition image sets, wherein each defect recognition image set contains a multi-angle defect recognition image of a key inspection point; P42-2: Based on the key inspection indicators, multiple key defect feature sample sets are collected respectively, and multiple defect recognition sub-units are trained based on the multiple key defect feature sample sets; P42-3: Using the multiple defect recognition sub-units, multi-angle defect recognition and single-point defect fusion are performed on the multiple defect recognition image sets respectively to obtain the preliminary inspection results.

[0044] It should be understood that the specific process of performing preliminary defect detection for the key detection indicators and the key detection points based on the visual detection unit can be that, first, the visual detection unit will perform detailed image data collection for each key detection point. By adjusting the camera angle, focal length and other parameters, the morphological information of the magnetic sheet surface is captured from different perspectives to ensure that each key detection point can obtain an image set containing multi-angle defect recognition images. Such a design helps to capture defect information that may be missed due to viewing angle limitations, and improves the comprehensiveness and accuracy of detection.

[0045] Furthermore, in order to more accurately identify defects related to key inspection indicators, the system will collect multiple representative key defect feature sample sets according to the specific requirements of each key inspection indicator. These sample sets contain defect instances of various types, degrees and forms, such as image data of cracks, corrosion, and shedding. Then, deep learning algorithms (such as convolutional neural networks) train multiple specialized defect recognition sub-units based on these sample sets. Each sub-unit focuses on identifying a specific type of defect, which can improve the accuracy and efficiency of recognition.

[0046] Furthermore, the trained defect recognition subunits are used to perform multi-angle analysis on each defect recognition image set, identify the defect features at each angle, and record the defect location, type, and severity at each angle. Then, the data fusion algorithm is used to integrate the multi-angle recognition results to form comprehensive defect information at a single point. The integrated defect information is recorded to generate preliminary test results, including the defect location, type, and severity of each key detection point. Rapid screening and positioning of surface defects of magnetic sheets is achieved, providing an important reference for subsequent deep defect identification.

[0047] Furthermore, the plurality of defect recognition subunits are used to perform multi-angle defect recognition and single-point defect fusion on the plurality of defect recognition image sets, respectively. Step P42-3 of the embodiment of the present application further includes:

[0048] P42-31: Extract the first defect recognition image set of the first key detection point based on the multiple defect recognition image sets; P42-32: Take the first defect recognition image set as input, input it into the first defect recognition subunit for multi-angle defect recognition fusion, analyze and obtain the first defect recognition result; P42-33: Take the first defect recognition image set as input, input it into the second defect recognition subunit for multi-angle defect recognition fusion, analyze and obtain the second defect recognition result; P42-34: And so on, traverse and use the multiple defect recognition subunits, obtain multiple defect recognition results, and fuse the multiple defect recognition results to obtain a single-point defect set of the first key detection point.

[0049] Optionally, the specific process of multi-angle defect recognition and single-point defect fusion for each key detection point may be to first extract an image set corresponding to the first key detection point from multiple defect recognition image sets, called the first defect recognition image set. This image set contains high-definition images of the point taken from different angles, which can provide rich data support for subsequent defect recognition. The first defect recognition image set is used as input and sent to the first defect recognition subunit. The subunit uses deep learning algorithms or image processing technology to independently analyze each angle image in the image set and identify possible defect features. And through the multi-angle defect recognition fusion strategy, the recognition results of different angles are comprehensively evaluated, misjudgments and redundant information are eliminated, and the first defect recognition result is generated. This process makes full use of the advantages of multi-angle images and improves the accuracy and reliability of defect recognition.

[0050] Similarly, the first defect recognition image set is input into the second defect recognition subunit, which independently analyzes the image set and identifies different types of defect features as the second defect recognition result. Similarly, the first defect recognition image set is traversed and used with the multiple defect recognition subunits to perform defect recognition on the first defect recognition image set to obtain multiple defect recognition results, which include all defect types of the first key detection point. The multiple defect recognition results are fused to obtain a single-point defect set of the first key detection point. This set not only contains basic information such as the type, location, and size of the defects at the first key detection point, but also contains advanced analysis information such as the severity and development trend of the defects, which can provide strong support for subsequent maintenance decisions.

[0051] Further, deep defect recognition is performed by the ultrasonic detection unit, and the preliminary detection result is verified and calibrated according to the deep defect recognition result. Step P43 of the embodiment of the present application also includes:

[0052] P43-1: Traverse the key detection points to perform ultrasonic scanning and obtain multiple echo signal sets; P43-2: Perform time domain analysis and frequency domain analysis based on the multiple echo signal sets, and classify the analysis results to obtain deep defect identification results, which include surface dominant defects and deep hidden defects; P43-3: According to the characteristic data of the surface dominant defects, traverse the key detection points, verify and calibrate the preliminary detection results, and supplement the preliminary detection results according to the deep hidden defects to obtain the magnetic sheet defect detection results.

[0053] Specifically, deep defect identification is performed through the ultrasonic detection unit, and the preliminary results of the visual detection unit are cross-validated and supplemented. First, the ultrasonic probe and coupling agent are configured to ensure good contact between the probe and the surface of the magnetic sheet. Then, based on the preliminary test results, the ultrasonic probe is positioned at the key test points, and ultrasonic scanning is performed one by one along the key test points through the automated control system. The ultrasonic probe emits high-frequency ultrasonic waves, which penetrate the magnetic sheet and reflect when encountering defects. The probe receives and records the echo signal, and obtains multiple echo signal sets.

[0054] Furthermore, the collected echo signals are preprocessed, including denoising and filtering, to improve signal quality. Each echo signal set is analyzed in the time domain to analyze the time delay of the echo signal and determine the location and depth of the defect. The frequency domain analysis is performed to analyze the spectrum characteristics of the echo signal and identify the type of defect (such as cracks, pores, inclusions, etc.). The results of the time domain analysis and frequency domain analysis are then classified to identify surface dominant defects and deep recessive defects. At the same time, the defect information of each key detection point is recorded, including the defect location, type and severity.

[0055] Furthermore, according to the characteristic data of the surface visible defects (such as position, shape, etc.), the key detection points are traversed to accurately calibrate the preliminary detection results, and the defects that may be missed or misjudged in the preliminary detection are corrected and supplemented. At the same time, according to the identification results of deep hidden defects, the preliminary detection results are supplemented as necessary to ensure the comprehensiveness and accuracy of the final magnetic sheet defect detection results.

[0056] In summary, the embodiments of the present application have at least the following technical effects:

[0057] The present application obtains the target material properties of the target motor rotor magnetic sheet, determines the key detection indicators, obtains the geometric shape characteristics of the target motor rotor magnetic sheet, generates key detection points, and performs targeted defect detection on the target motor rotor magnetic sheet based on the key detection indicators and key detection points to obtain the magnetic sheet defect detection results.

[0058] The technical effect of conducting targeted intelligent defect detection based on key detection indicators and points and improving the accuracy and efficiency of motor rotor magnetic sheet defect detection has been achieved.

[0059] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0060] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0061] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. An intelligent detection system for motor rotor magnetic sheet defects, characterized in that: The system comprises: A material characteristic analysis module, which is used to construct a material characteristic library based on characteristic analysis of commonly used magnetic materials; A key detection index determination module, the key detection index determination module is used to analyze and obtain the target material characteristics of the target motor rotor magnetic sheet, and match and determine the key detection index in combination with the material feature library; A key detection point determination module, the key detection point determination module is used to analyze and obtain the geometric shape characteristics of the target motor rotor magnetic sheet, perform weak point analysis based on the geometric shape characteristics, and generate key detection points; An intelligent defect detection module, wherein the intelligent defect detection module is used to perform targeted defect detection on the target motor rotor magnetic sheet based on the key detection index and the key detection point to obtain a magnetic sheet defect detection result; Based on the characteristic analysis of common magnetic materials, a material feature library is constructed, including: Obtaining common magnetic materials for motor rotor magnetic sheets, wherein the common magnetic materials include neodymium iron boron, samarium cobalt, and ferrite; Collect the physical properties, chemical properties and magnetic properties data of the commonly used magnetic materials, perform material property analysis, and obtain key characteristic parameters of different magnetic materials, wherein the key characteristic parameters include weak parameters, dominant parameters and the applicable range of each parameter; Based on the key characteristic parameters of the different magnetic materials, structured storage is performed to build the material feature library; Analyze and obtain the target material characteristics of the target motor rotor magnetic sheet, combine the material feature library, and match and determine the key detection indicators, including: Obtaining the material type of the target motor rotor magnetic sheet, and based on the material type, obtaining the target material properties, including physical property properties, chemical property properties, and magnetic property properties; Based on the target material characteristics, the material feature library is traversed to match and obtain key detection indicators, where the key detection indicators are weak parameters of the target motor rotor magnetic sheet; Analyze and obtain the geometric shape characteristics of the target motor rotor magnetic sheet, perform weak point analysis based on the geometric shape characteristics, and generate key detection points, including: Acquiring geometric shape data of the target motor rotor magnetic sheet; Based on the geometric shape data, a geometric shape analysis is performed to obtain the geometric shape characteristics; Based on the geometric shape characteristics, stress distribution simulation is performed to identify stress concentration areas and weak points, and stress distribution simulation results are obtained; The historical inspection data of the rotor magnetic sheets of the same model are used to analyze and obtain the common defect locations and types, and the stress distribution simulation results are optimized to generate the key inspection points, wherein the key inspection points correspond to at least one key inspection indicator respectively.

2. The intelligent detection system for motor rotor magnetic sheet defects according to claim 1, characterized in that: Based on the key detection indicators and the key detection points, targeted defect detection is performed on the target motor rotor magnetic sheet, including: The intelligent defect detection module includes a visual detection unit and an ultrasonic detection unit; Based on the visual inspection unit, preliminary defect inspection is performed on the key inspection indicators and the key inspection points to generate preliminary inspection results; The ultrasonic detection unit is used to perform deep defect recognition, and the preliminary detection result is verified and calibrated according to the deep defect recognition result to obtain the magnetic sheet defect detection result.

3. The intelligent detection system for motor rotor magnetic sheet defects according to claim 2, characterized in that: Based on the visual inspection unit, preliminary defect detection is performed on the key inspection indicators and the key inspection points to generate preliminary inspection results, including: By means of the visual inspection unit, image data is collected for the key inspection points to obtain a plurality of defect recognition image sets, wherein each defect recognition image set includes a multi-angle defect recognition image of a key inspection point; Based on the key detection indicators, a plurality of key defect feature sample sets are collected respectively, and a plurality of defect recognition sub-units are trained based on the plurality of key defect feature sample sets; The plurality of defect recognition subunits are used to perform multi-angle defect recognition and single-point defect fusion on the plurality of defect recognition image sets respectively to obtain the preliminary detection result.

4. The intelligent detection system for motor rotor magnetic sheet defects according to claim 3, characterized in that: The plurality of defect recognition subunits are used to respectively perform multi-angle defect recognition and single-point defect fusion on the plurality of defect recognition image sets, including: Extracting a first defect recognition image set of a first key inspection point based on the multiple defect recognition image sets; Taking the first defect recognition image set as input, inputting it into a first defect recognition subunit to perform multi-angle defect recognition fusion, and analyzing to obtain a first defect recognition result; Taking the first defect recognition image set as input, inputting it into the second defect recognition subunit to perform multi-angle defect recognition fusion, and analyzing to obtain a second defect recognition result; By analogy, the multiple defect recognition sub-units are traversed to obtain multiple defect recognition results, and the multiple defect recognition results are fused to obtain a single-point defect set of the first key detection point.

5. The intelligent detection system for motor rotor magnetic sheet defects according to claim 2, characterized in that: The ultrasonic detection unit is used to identify deep defects, and the preliminary detection result is verified and calibrated according to the deep defect identification result, including: Traversing the key detection points to perform ultrasonic scanning and obtain multiple echo signal sets; Based on the multiple echo signal sets, time domain analysis and frequency domain analysis are respectively performed, and the analysis results are classified to obtain deep defect recognition results, wherein the deep defect recognition results include surface dominant defects and deep recessive defects; According to the characteristic data of the surface obvious defects, the key detection points are traversed, the preliminary detection results are verified and calibrated, and the preliminary detection results are supplemented according to the deep hidden defects to obtain the magnetic sheet defect detection results.

Images