CN115240193B - Surface treatment method and system for electric automobile motor spindle - Google Patents
Surface treatment method and system for electric automobile motor spindle Download PDFInfo
- Publication number
- CN115240193B CN115240193B CN202210903046.9A CN202210903046A CN115240193B CN 115240193 B CN115240193 B CN 115240193B CN 202210903046 A CN202210903046 A CN 202210903046A CN 115240193 B CN115240193 B CN 115240193B
- Authority
- CN
- China
- Prior art keywords
- defect
- probability
- motor spindle
- surface defect
- outputting
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000004381 surface treatment Methods 0.000 title claims abstract description 22
- 230000007547 defect Effects 0.000 claims abstract description 213
- 238000009826 distribution Methods 0.000 claims abstract description 53
- 238000004364 calculation method Methods 0.000 claims abstract description 40
- 238000012545 processing Methods 0.000 claims abstract description 32
- 238000004458 analytical method Methods 0.000 claims description 66
- 230000002159 abnormal effect Effects 0.000 claims description 49
- 239000000463 material Substances 0.000 claims description 26
- 239000002344 surface layer Substances 0.000 claims description 23
- 230000005856 abnormality Effects 0.000 claims description 13
- 238000010219 correlation analysis Methods 0.000 claims description 12
- 230000003287 optical effect Effects 0.000 claims description 11
- 230000003213 activating effect Effects 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 9
- 230000003746 surface roughness Effects 0.000 claims description 8
- 238000005070 sampling Methods 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 4
- 238000004891 communication Methods 0.000 claims 1
- 238000003754 machining Methods 0.000 abstract description 19
- 230000000694 effects Effects 0.000 abstract description 7
- 238000005520 cutting process Methods 0.000 description 4
- 230000008030 elimination Effects 0.000 description 4
- 238000003379 elimination reaction Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 230000002596 correlated effect Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000007514 turning Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 239000010687 lubricating oil Substances 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000000875 corresponding effect Effects 0.000 description 1
- 238000005336 cracking Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000017525 heat dissipation Effects 0.000 description 1
- 230000008595 infiltration Effects 0.000 description 1
- 238000001764 infiltration Methods 0.000 description 1
- 230000015654 memory Effects 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 239000007769 metal material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 229910052755 nonmetal Inorganic materials 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
- G06V20/693—Acquisition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
- G06V20/695—Preprocessing, e.g. image segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
- G06V20/698—Matching; Classification
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02K—DYNAMO-ELECTRIC MACHINES
- H02K15/00—Methods or apparatus specially adapted for manufacturing, assembling, maintaining or repairing of dynamo-electric machines
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02K—DYNAMO-ELECTRIC MACHINES
- H02K15/00—Methods or apparatus specially adapted for manufacturing, assembling, maintaining or repairing of dynamo-electric machines
- H02K15/14—Casings; Enclosures; Supports
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10056—Microscopic image
- G06T2207/10061—Microscopic image from scanning electron microscope
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30204—Marker
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Manufacturing & Machinery (AREA)
- Power Engineering (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Quality & Reliability (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention provides a surface treatment method and a system for a motor spindle of an electric automobile, which relate to the technical field of data processing, wherein microscopic image characteristics are obtained by analyzing microscopic images of a target motor spindle, surface defect identification is carried out according to the microscopic image characteristics, and a surface defect set is output; based on the surface defect set, surface defect distribution coordinates are obtained, defect anomaly probability calculation is carried out according to the surface defect distribution coordinates, anomaly probability is obtained, and when the anomaly probability is greater than or equal to a preset anomaly probability, an early warning instruction is generated to remind a target motor spindle of anomaly. The technical problems that in the prior art, the surface defects of the machining motor main shaft are found and eliminated, the dependence on manual experience is strong, and whether the surface defects exist on the motor main shaft or not is judged by technicians based on working experience are solved. The technical effect of quickly knowing whether the surface defects are generated in the machining of the motor spindle is achieved, and the dependence of the task for detecting the surface defects on the experience of technicians is reduced.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a surface treatment method and system for a motor spindle of an electric automobile.
Background
The main shaft of the motor is an important part in the motor, is a tie for converting electromechanical energy between the motor and equipment, and plays roles of supporting rotating parts and determining the relative position of the rotating parts to a stator.
In the machining process of the motor spindle, the motor spindle is processed and generated by adopting the process steps such as blanking, turning, infiltration grinding and the like, and when the motor spindle is machined, defects are generated on the surface of the motor spindle due to the influence of factors such as temperature change and cutting speed of the motor spindle caused by the turning process, and in order to avoid the surface defects of the motor spindle, the motor spindle is usually processed by adopting a mode of adjusting the process parameters such as power, lubricating oil adding frequency and the like of the turning and other machining processes and changing the heat radiating area and the material properties of a machining tool.
In the prior art, the defect of the surface layer of the machining motor spindle is found and eliminated with strong dependence on manual experience, and the technical problem that whether the surface layer defect exists on the motor spindle needs to be judged by technicians based on working experience is solved.
Disclosure of Invention
The application provides a surface treatment method and a surface treatment system for an electric automobile motor spindle, which are used for solving the technical problems that in the prior art, the detection and elimination of surface defects of a processed motor spindle are strong in dependence on manual experience, and whether the surface defects exist on the motor spindle or not is judged by technicians based on working experience.
In view of the above problems, the present application provides a surface treatment method and system for a motor spindle of an electric vehicle.
In a first aspect of the present application, there is provided a surface treatment method for a motor spindle of an electric vehicle, the method comprising: according to the optical microscope, carrying out microscopic image acquisition on a target motor spindle, and outputting a microscopic image set; connecting a microscopic image management system and constructing an image feature analysis model; inputting the microscopic image set into the image feature analysis model, and outputting microscopic image features according to the image feature analysis model; carrying out surface defect identification according to the microscopic image characteristics, and outputting a surface defect set; obtaining surface defect distribution coordinates based on the surface defect set; performing defect anomaly probability calculation according to the surface defect distribution coordinates to obtain anomaly probability; judging whether the abnormal probability is larger than or equal to a preset abnormal probability; and if the abnormal probability is greater than or equal to the preset abnormal probability, generating an early warning instruction, wherein the early warning instruction is used for reminding the main shaft of the target motor of abnormality.
In a second aspect of the present application, there is provided a surface treatment system for an electric vehicle motor spindle, the system comprising: the image acquisition execution module is used for acquiring microscopic images of the main shaft of the target motor according to the optical microscope and outputting a microscopic image set; the analysis model construction module is used for connecting a microscopic image management system and constructing an image characteristic analysis model; the image feature generation module is used for inputting the microscopic image set into the image feature analysis model and outputting microscopic image features according to the image feature analysis model; the surface defect identification module is used for carrying out surface defect identification according to the microscopic image characteristics and outputting a surface defect set; the defect distribution obtaining module is used for obtaining surface defect distribution coordinates based on the surface defect set; the anomaly probability calculation module is used for carrying out defect anomaly probability calculation according to the surface layer defect distribution coordinates to obtain anomaly probability; the abnormal probability comparison module is used for judging whether the abnormal probability is greater than or equal to a preset abnormal probability; and the early warning instruction generation module is used for generating an early warning instruction if the abnormal probability is greater than or equal to the preset abnormal probability, wherein the early warning instruction is used for reminding the main shaft of the target motor of abnormal existence.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
according to the method provided by the embodiment of the application, microscopic image acquisition is carried out on a target motor spindle according to an optical microscope, a microscopic image set is output, a high-precision image is provided for subsequent motor spindle surface defect type analysis, a microscopic image management system is connected, an image feature analysis model is built, the microscopic image set is input into the image feature analysis model, and microscopic image features are output according to the image feature analysis model; performing surface defect identification according to the microscopic image characteristics, outputting a surface defect set, obtaining a specific type of surface defects of a motor spindle, and obtaining surface defect distribution coordinates based on the surface defect set; and carrying out defect anomaly probability calculation according to the surface layer defect distribution coordinates to obtain anomaly probability, judging whether the anomaly probability is greater than or equal to a preset anomaly probability, avoiding the need of processing a motor spindle processing device for small defects without damage, and generating an early warning instruction to remind the target motor spindle of anomaly if the anomaly probability is greater than or equal to the preset anomaly probability. The technical effect of quickly knowing whether the machining process of the motor spindle generates the surface defects which need to be adjusted to eliminate the machining process is achieved, and the dependence of the surface defect discovery task on the experience of technicians is reduced.
Drawings
Fig. 1 is a schematic flow chart of a surface treatment method of a motor spindle of an electric automobile provided by the application;
fig. 2 is a schematic flow chart of obtaining defect anomaly probability in the surface treatment method of the electric automobile motor spindle provided by the application;
fig. 3 is a schematic flow chart of defect anomaly probability adjustment in the surface treatment method of the electric automobile motor spindle provided by the application;
fig. 4 is a schematic structural diagram of a surface treatment system for a spindle of an electric vehicle motor provided in the present application.
Reference numerals illustrate: the system comprises an image acquisition and execution module 11, an analysis model construction module 12, an image feature generation module 13, a surface layer defect identification module 14, a defect distribution acquisition module 15, an anomaly probability calculation module 16, an anomaly probability comparison module 17 and an early warning instruction generation module 18.
Detailed Description
The application provides a surface treatment method and a surface treatment system for an electric automobile motor spindle, which are used for solving the technical problems that in the prior art, the detection and elimination of surface defects of a processed motor spindle are strong in dependence on manual experience, and whether the surface defects exist on the motor spindle or not is judged by technicians based on working experience.
Aiming at the technical problems, the technical scheme provided by the application has the following overall thought:
an image feature analysis model is constructed to analyze the acquired microscopic image of the motor main shaft of the electric automobile, whether the surface layer defect image features exist in the microscopic image is determined, identification is carried out in the microscopic image with the surface layer defect image features, the distribution coordinates of defects on the motor main shaft body are positioned, and whether the process to be regulated exists in the machining process or not is judged by analyzing whether the defect abnormality probability is higher than an abnormality probability threshold value. The method and the device realize quick learning of whether the machining of the motor main shaft generates the surface defects which need to be subjected to machining process adjustment, and reduce the dependence of the surface defect discovery task on experience of technicians.
Example 1
As shown in fig. 1, the present application provides a surface treatment method of an electric vehicle motor spindle, where the method is applied to a surface treatment system of the electric vehicle motor spindle, and the system is communicatively connected to an optical microscope, and the method includes:
s100, acquiring microscopic images of a main shaft of a target motor according to the optical microscope, and outputting a microscopic image set;
specifically, the motor spindle is an important part in the motor, is a tie for performing electromechanical energy conversion between the motor and equipment, and plays roles of supporting rotating parts and determining the relative positions of the rotating parts to the stator.
In this embodiment, a space rectangular coordinate system is set in a microscopic image acquisition area, and microscopic image acquisition is performed on the surface of the target motor spindle by using an optical microscope, so as to obtain a microscopic image set capable of reflecting the processing condition and the processing trace of the surface of the target motor spindle, each image in the microscopic image set is marked with an image acquisition coordinate, and whether the processing performed on the target motor spindle causes defects on the surface of the target motor spindle can be known based on the microscopic image set.
S200, connecting a microscopic image management system and constructing an image feature analysis model;
s300, inputting the microscopic image set into the image feature analysis model, and outputting microscopic image features according to the image feature analysis model;
specifically, in this embodiment, the method of constructing and training an image feature analysis model is preferably used to analyze the acquired microscopic image set to obtain defect information existing on the surface of the spindle of the target motor.
The method for constructing and training the image feature analysis model is not limited in this embodiment, and training of the image feature analysis model can be performed based on the historical acquired microscopic image set and the historical defect image features as training data, test data and verification data.
And uploading the acquired microscopic image set to the microscopic image management system, and inputting the microscopic image set into the image feature analysis model through the microscopic image management system to perform image feature analysis so as to obtain the microscopic image features reflecting whether surface defects exist in each microscopic image.
S400, performing surface layer defect identification according to the microscopic image characteristics, and outputting a surface layer defect set;
s500, obtaining surface defect distribution coordinates based on the surface defect set;
specifically, the types of surface defects present in the target motor spindle include, but are not limited to, inclusions, fine cracks, grinding cracks, and impact pits. And carrying out surface defect identification on the surface defect type of the motor spindle based on the microscopic image feature comparison output by the image feature analysis model to obtain a plurality of surface defect microscopic images, so as to form the surface defect set.
As can be seen from the explanation of the description of step S100, in this embodiment, each image in the acquired microscopic image set is marked with an image acquisition coordinate, and the surface defect distribution coordinate is obtained based on the image acquisition coordinate marked with the surface defect mark obtained by back-pushing the surface defect set.
Meanwhile, image similarity analysis is carried out on a plurality of images with similar surface layer defect distribution coordinates, so that the defect anomaly probability calculation accuracy is prevented from being reduced due to the fact that the same defect is recorded for multiple times.
S600, carrying out defect anomaly probability calculation according to the surface defect distribution coordinates to obtain anomaly probability;
further, as shown in fig. 2, the defect anomaly probability calculation is performed according to the surface defect distribution coordinates to obtain an anomaly probability, and the method step S600 provided in the present application further includes:
s610, acquiring the same batch of motor spindles of the target motor spindle;
s620, sampling the same batch of motor spindles, and outputting a sample motor spindle;
s630, outputting sample surface layer defect distribution coordinates according to the sample motor spindle;
s640, when the similarity between the sample surface defect distribution coordinates and the surface defect distribution coordinates reaches a preset similarity threshold, activating a defect anomaly probability calculation module to obtain the anomaly probability.
Further, activating a defect anomaly probability calculation module to obtain the anomaly probability, where step S640 of the method provided in the present application further includes:
s641, activating the abnormal probability calculation module, and performing density analysis on the surface defect distribution coordinates according to the abnormal probability calculation module to obtain a density analysis result, wherein the density analysis result is an analysis result for identifying the surface defect density;
s642, carrying out abnormal probability calculation according to the density analysis result, and outputting the abnormal probability.
Specifically, in this embodiment, random sampling is performed from a plurality of motor spindles produced in the same batch as the target motor spindle, so as to obtain a sample motor spindle set composed of a plurality of motor spindles, and the sample motor spindle is processed by adopting the motor spindle surface defect collection method in steps S100 to S500, so as to obtain a plurality of sample surface defect distribution coordinates of a plurality of sample motor spindles.
And setting a similarity threshold value between sample surface layer defect distribution and target motor spindle surface layer defect distribution coordinates based on a motor spindle processing technician with abundant experience, and obtaining the preset similarity threshold value.
And comparing the similarity between the sample surface defect distribution coordinates and the surface defect distribution coordinates, and when the similarity between the sample surface defect distribution coordinates and the surface defect distribution coordinates reaches a preset similarity threshold, indicating that the surface defect existing in the current target motor spindle is a problem in the processing technology rather than an accidental accident during single processing.
It should be understood that when the motor spindle is processed, the product defect rate is set, so that the defect that the surface defect does not affect the operation of the motor spindle is avoided, the processing equipment needs to be adjusted, the operation and maintenance of the production line are suspended, and the economic benefit is reduced.
In this embodiment, when the similarity between the surface defect distribution coordinates of the sample and the surface defect distribution coordinates reaches a preset similarity threshold, a defect anomaly probability calculation module is activated to perform density analysis on the surface defect distribution coordinates, obtain an area ratio of the surface defect of the target motor spindle in a predetermined surface area, obtain a density analysis result, identify the surface defect density, perform anomaly probability calculation according to the density analysis result, and output the anomaly probability.
According to the method, the surface defects of the target motor main shaft are compared with the surface defects of other motor main shafts in the same batch, the surface defects caused by accidental machining errors are eliminated, after the surface defects of the target motor main shaft are determined to belong to machining normal errors, the defect anomaly probability is calculated, accurate judgment of the surface defect types of the target motor main shaft is determined, accurate judgment of defect severity is achieved, and the technical effect that production efficiency is reduced due to high-frequency adjustment of a machining device is avoided.
S700, judging whether the abnormal probability is larger than or equal to a preset abnormal probability;
s800, if the abnormal probability is greater than or equal to the preset abnormal probability, generating an early warning instruction, wherein the early warning instruction is used for reminding the main shaft of the target motor of abnormal state.
Specifically, in this embodiment, the preset anomaly probability is consistent with the preset similarity threshold in step S600, and may be set by a motor spindle processing technician with abundant experience. When the abnormal probability is larger than the preset abnormal probability, the method indicates that the current machining parameters are adopted to machine the motor spindle, and the severity of defects existing on the surface layer of the obtained motor spindle is as high as the severity of the defects which are required to be reduced by adjusting the machining process parameters.
In this embodiment, first, a preset anomaly probability is set, then, whether the anomaly probability is greater than or equal to a preset anomaly probability is judged, and if the anomaly probability is greater than or equal to the preset anomaly probability, an early warning instruction is generated, wherein the early warning instruction is used for reminding that the target motor spindle is abnormal.
According to the embodiment, microscopic image acquisition is carried out on a target motor spindle according to an optical microscope, a microscopic image set is output, a high-precision image is provided for subsequent motor spindle surface defect type analysis, a microscopic image management system is connected, an image feature analysis model is built, the microscopic image set is input into the image feature analysis model, and microscopic image features are output according to the image feature analysis model; performing surface defect identification according to the microscopic image characteristics, outputting a surface defect set, obtaining a specific type of surface defects of a motor spindle, and obtaining surface defect distribution coordinates based on the surface defect set; and carrying out defect anomaly probability calculation according to the surface layer defect distribution coordinates to obtain anomaly probability, judging whether the anomaly probability is greater than or equal to a preset anomaly probability, avoiding the need of processing a motor spindle processing device for small defects without damage, and generating an early warning instruction to remind the target motor spindle of anomaly if the anomaly probability is greater than or equal to the preset anomaly probability. The technical effect of quickly knowing whether the machining process of the motor spindle generates the surface defects which need to be adjusted to eliminate the machining process is achieved, and the dependence of the surface defect discovery task on the experience of technicians is reduced.
Further, if the anomaly probability is greater than or equal to the preset anomaly probability, after generating the early warning instruction, the method steps provided in the application further include:
s910, connecting a process parameter control system of the target motor spindle according to the early warning instruction to acquire real-time control parameters;
s920, performing correlation analysis according to the surface layer defect set, and outputting a correlation control index;
s930, carrying out parameter identification from the real-time control parameters by using the related control indexes, and outputting identification parameters;
s940, processing by taking the identification parameter as a parameter to be processed.
Specifically, in this embodiment, when the anomaly probability is greater than or equal to the preset anomaly probability, an early warning instruction is generated to remind that the target motor spindle is abnormal, and the electric vehicle motor spindle surface processing system is connected to the process parameter control system of the target motor spindle to acquire real-time control parameters based on the early warning instruction.
And performing correlation analysis according to a plurality of defect states in the surface defect set to obtain a processing device control index corresponding to each defect state, for example, the annular crack on the surface of the motor spindle is related to the cutting process. And carrying out correlation analysis based on the surface defect set of the target motor spindle to obtain a correlation control index with correlation or correspondence with the surface defect type, such as lubricating oil adding frequency, processing device output power, heat dissipation instantaneity and the like.
And carrying out parameter identification from the real-time control parameters by using the related control indexes, outputting identification parameters, processing by using the identification parameters as parameters to be processed, and adjusting the parameters to be processed.
According to the method, parameters of the processing device causing the surface defects are analyzed, parameters to be processed are obtained from a plurality of real-time control parameters, parameter adjustment is to be performed, the parameters to be processed are perfectly eliminated, accurate adjustment references are provided for motor spindle processing operators, and the operators are assisted to eliminate motor spindle production defects from a processing end as soon as possible.
Further, performing correlation analysis according to the surface defect set, and outputting a correlation control index, where the method provided in step S920 further includes:
s921, obtaining a surface defect type according to the surface defect set;
s922, respectively carrying out correlation analysis on each defect type according to the surface defect type to obtain a correlation control index set;
s923, outputting the relevant control indexes according to the relevant control index sets, wherein the relevant control indexes are indexes with the largest relevant coefficients in each set based on the relevant control index sets.
Specifically, in this embodiment, the method for performing the apparent defect analysis determination on the target motor spindle is to classify a plurality of apparent defects in the apparent defect set according to the defect image characteristics, so as to obtain the apparent defect types, such as cracks, openings, depressions and bumps. And respectively carrying out correlation analysis on each defect type according to the surface defect type, determining one or more control indexes causing each defect type to occur, and generating the correlation control index set.
And outputting an index with the maximum correlation coefficient in each set in the correlated control index sets as a correlated control index according to the correlated control index sets, and indicating technicians to perform parameter control adjustment to eliminate surface defects generated in the processing process.
According to the method and the device, the surface defect causes are analyzed, the parameter control index is output, and the technical effects of reducing the waste of human resources during surface defect elimination analysis and improving the efficiency of maintenance and adjustment of the processing device are achieved through clear surface defect elimination guidance for technicians.
Further, as shown in fig. 3, the method steps provided in the present application further include:
s650, acquiring material composition information of the target motor spindle;
s660, analyzing the main shaft material property according to the material composition information, and determining the material hardness and the surface roughness;
s670, determining a probability error according to the hardness of the material and the surface roughness;
s680, adjusting the abnormal probability according to the probability error.
In particular, it should be understood that the material properties of the motor spindle may also cause surface defects in the produced motor spindle to a different extent, for example, when the motor spindle is processed, the high heat generated by the cutting process may cause cracking of a part of the motor shaft blank made of metal, and the motor shaft blank made of non-metal is easy to generate grinding cracks during the cutting process.
In order to eliminate the interference of the machining metal material characteristics of the motor spindle on the defect anomaly probability accuracy, in the embodiment, material component information of the target motor spindle is obtained, spindle material properties are analyzed according to the material component information, material hardness and surface roughness are determined, the interference of the material hardness and the surface roughness on the defect anomaly probability is obtained, the probability error is obtained, and the anomaly probability is adjusted according to the probability error.
According to the method, the error degree of defect abnormality probability caused by the processing characteristics of the material property during processing is determined by analyzing the material property angle, the obtained defect abnormality probability is corrected, the defect abnormality probability which is only related to the processing device is obtained, and the technical effect of improving the defect abnormality probability accuracy is achieved.
Example two
Based on the same inventive concept as the surface treatment method of the electric vehicle motor spindle in the foregoing embodiment, as shown in fig. 4, the present application provides a surface treatment system of an electric vehicle motor spindle, wherein the system includes:
the image acquisition execution module 11 is used for acquiring microscopic images of the main shaft of the target motor according to the optical microscope and outputting a microscopic image set;
the analysis model construction module 12 is used for connecting a microscopic image management system and constructing an image characteristic analysis model;
an image feature generating module 13, configured to input the microscopic image set into the image feature analysis model, and output microscopic image features according to the image feature analysis model;
the surface defect identification module 14 is used for carrying out surface defect identification according to the microscopic image characteristics and outputting a surface defect set;
a defect distribution obtaining module 15, configured to obtain surface defect distribution coordinates based on the surface defect set;
the anomaly probability calculation module 16 is configured to perform defect anomaly probability calculation according to the surface defect distribution coordinates, so as to obtain anomaly probability;
an anomaly probability comparison module 17 for judging whether the anomaly probability is greater than or equal to a preset anomaly probability;
and the early warning instruction generating module 18 is configured to generate an early warning instruction if the abnormality probability is greater than or equal to the preset abnormality probability, where the early warning instruction is used to remind the target motor spindle of abnormality.
Further, the system provided by the present application further includes:
the control parameter obtaining unit is used for connecting a process parameter control system of the target motor spindle according to the early warning instruction to obtain real-time control parameters;
the control index output unit is used for carrying out correlation analysis according to the surface layer defect set and outputting a correlation control index;
the parameter identification marking unit is used for carrying out parameter identification from the real-time control parameters by the related control indexes and outputting identification parameters;
and the parameter processing execution unit is used for processing by taking the identification parameter as a parameter to be processed.
Further, the control index output unit further includes:
the defect type determining unit is used for obtaining the surface defect type according to the surface defect set;
the control index obtaining unit is used for respectively carrying out correlation analysis on each defect type according to the surface defect type to obtain a related control index set;
and the control index output unit is used for outputting the relevant control index according to the relevant control index sets, wherein the relevant control index is the index with the largest relevant coefficient in each set in the relevant control index sets.
Further, the anomaly probability computation module 16 further includes:
the same batch device obtaining unit is used for obtaining the same batch of motor spindles of the target motor spindles;
the sample sampling execution unit is used for sampling by the motor spindle in the same batch and outputting a sample motor spindle;
the defect coordinate output unit is used for outputting the distribution coordinates of the defects of the surface layer of the sample according to the spindle of the sample motor;
and the anomaly probability calculation unit is used for activating a defect anomaly probability calculation module when the similarity between the sample surface defect distribution coordinates and the surface defect distribution coordinates reaches a preset similarity threshold value to obtain the anomaly probability.
Further, the anomaly probability calculation unit further includes:
the defect density analysis unit is used for activating the abnormal probability calculation module, carrying out density analysis on the surface defect distribution coordinates according to the abnormal probability calculation module, and obtaining a density analysis result, wherein the density analysis result is an analysis result for identifying the surface defect density;
and the abnormal probability output unit is used for carrying out abnormal probability calculation according to the density analysis result and outputting the abnormal probability.
Further, the system provided by the present application further includes:
a material composition obtaining unit for obtaining material composition information of the target motor spindle;
a material property analysis unit for analyzing the material property of the main shaft by the material composition information and determining the hardness and the surface roughness of the material;
a probability error determining unit configured to determine a probability error in accordance with the material hardness and the surface roughness;
and the abnormal probability adjusting unit is used for adjusting the abnormal probability according to the probability error.
Any of the methods or steps described above may be stored as computer instructions or programs in various non-limiting types of computer memories, and identified by various non-limiting types of computer processors, thereby implementing any of the methods or steps described above.
Based on the above-mentioned embodiments of the present invention, any improvements and modifications to the present invention should fall within the scope of the present invention without departing from the principles of the present invention.
Claims (4)
1. A surface treatment method for a motor spindle of an electric vehicle, the method being applied to a surface treatment system for a motor spindle of an electric vehicle, the system being in communication with an optical microscope, the method comprising:
according to the optical microscope, carrying out microscopic image acquisition on a target motor spindle, and outputting a microscopic image set;
connecting a microscopic image management system and constructing an image feature analysis model;
inputting the microscopic image set into the image feature analysis model, and outputting microscopic image features according to the image feature analysis model;
carrying out surface defect identification according to the microscopic image characteristics, and outputting a surface defect set;
obtaining surface defect distribution coordinates based on the surface defect set;
performing defect anomaly probability calculation according to the surface defect distribution coordinates to obtain anomaly probability;
performing defect anomaly probability calculation according to the surface layer defect distribution coordinates to obtain anomaly probability, and further comprising:
acquiring the same batch of motor spindles of the target motor spindle;
sampling by the motor spindle in the same batch, and outputting a sample motor spindle;
outputting sample surface layer defect distribution coordinates according to the sample motor spindle;
when the similarity between the sample surface defect distribution coordinates and the surface defect distribution coordinates reaches a preset similarity threshold, activating a defect anomaly probability calculation module to obtain the anomaly probability;
the method comprises the steps of activating a defect anomaly probability calculation module to obtain the anomaly probability, and further comprises the following steps:
activating the abnormal probability calculation module, and performing density analysis on the surface defect distribution coordinates according to the abnormal probability calculation module to obtain a density analysis result, wherein the density analysis result is an analysis result for identifying the surface defect density;
performing abnormal probability calculation according to the density analysis result, and outputting the abnormal probability;
judging whether the abnormal probability is larger than or equal to a preset abnormal probability;
if the abnormality probability is greater than or equal to the preset abnormality probability, generating an early warning instruction, wherein the early warning instruction is used for reminding the main shaft of the target motor of abnormality;
according to the early warning instruction, connecting a process parameter control system of the target motor spindle to obtain real-time control parameters;
performing correlation analysis according to the surface defect set, and outputting a correlation control index;
carrying out parameter identification from the real-time control parameters by using the related control indexes, and outputting identification parameters;
and processing by taking the identification parameter as a parameter to be processed.
2. The method of claim 1, wherein a correlation analysis is performed from the set of surface defects, and wherein a correlation control index is output, the method further comprising:
acquiring a surface defect type according to the surface defect set;
respectively carrying out correlation analysis on each defect type according to the surface defect type to obtain a correlation control index set;
and outputting the relevant control index according to the relevant control index sets, wherein the relevant control index is the index with the largest relevant coefficient in each set in the relevant control index sets.
3. The method of claim 1, wherein the method further comprises:
acquiring material composition information of the target motor spindle;
analyzing the main shaft material property by using the material component information to determine the material hardness and the surface roughness;
determining a probability error according to the hardness of the material and the surface roughness;
and adjusting the abnormal probability according to the probability error.
4. A surface treatment system for an electric vehicle motor spindle, the system comprising:
the image acquisition execution module is used for acquiring microscopic images of the main shaft of the target motor according to the optical microscope and outputting a microscopic image set;
the analysis model construction module is used for connecting a microscopic image management system and constructing an image characteristic analysis model;
the image feature generation module is used for inputting the microscopic image set into the image feature analysis model and outputting microscopic image features according to the image feature analysis model;
the surface defect identification module is used for carrying out surface defect identification according to the microscopic image characteristics and outputting a surface defect set;
the defect distribution obtaining module is used for obtaining surface defect distribution coordinates based on the surface defect set;
the anomaly probability calculation module is used for carrying out defect anomaly probability calculation according to the surface layer defect distribution coordinates to obtain anomaly probability;
the anomaly probability computation module further includes:
the same batch device obtaining unit is used for obtaining the same batch of motor spindles of the target motor spindles;
the sample sampling execution unit is used for sampling by the motor spindle in the same batch and outputting a sample motor spindle;
the defect coordinate output unit is used for outputting the distribution coordinates of the defects of the surface layer of the sample according to the spindle of the sample motor;
the anomaly probability calculation unit is used for activating a defect anomaly probability calculation module when the similarity between the sample surface defect distribution coordinates and the surface defect distribution coordinates reaches a preset similarity threshold value to obtain the anomaly probability;
the anomaly probability calculation unit further includes:
the defect density analysis unit is used for activating the abnormal probability calculation module, carrying out density analysis on the surface defect distribution coordinates according to the abnormal probability calculation module, and obtaining a density analysis result, wherein the density analysis result is an analysis result for identifying the surface defect density;
the abnormal probability output unit is used for carrying out abnormal probability calculation according to the density analysis result and outputting the abnormal probability;
the abnormal probability comparison module is used for judging whether the abnormal probability is greater than or equal to a preset abnormal probability;
the early warning instruction generation module is used for generating an early warning instruction if the abnormal probability is greater than or equal to the preset abnormal probability, wherein the early warning instruction is used for reminding the main shaft of the target motor of abnormal;
the system further comprises:
the control parameter obtaining unit is used for connecting a process parameter control system of the target motor spindle according to the early warning instruction to obtain real-time control parameters;
the control index output unit is used for carrying out correlation analysis according to the surface layer defect set and outputting a correlation control index;
the parameter identification marking unit is used for carrying out parameter identification from the real-time control parameters by the related control indexes and outputting identification parameters;
and the parameter processing execution unit is used for processing by taking the identification parameter as a parameter to be processed.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210903046.9A CN115240193B (en) | 2022-07-29 | 2022-07-29 | Surface treatment method and system for electric automobile motor spindle |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210903046.9A CN115240193B (en) | 2022-07-29 | 2022-07-29 | Surface treatment method and system for electric automobile motor spindle |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115240193A CN115240193A (en) | 2022-10-25 |
CN115240193B true CN115240193B (en) | 2023-12-22 |
Family
ID=83677834
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210903046.9A Active CN115240193B (en) | 2022-07-29 | 2022-07-29 | Surface treatment method and system for electric automobile motor spindle |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115240193B (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108645867A (en) * | 2018-05-25 | 2018-10-12 | 哈尔滨工业大学 | Large-aperture optical plane of crystal microdefect quickly seeks position and batch detector methods |
CN209296559U (en) * | 2018-12-15 | 2019-08-23 | 勤基电路板(深圳)有限公司 | The appearance of circuit board detects production line |
CN110619620A (en) * | 2018-06-04 | 2019-12-27 | 杭州海康威视数字技术股份有限公司 | Method, device and system for positioning abnormity causing surface defects and electronic equipment |
CN111709909A (en) * | 2020-05-12 | 2020-09-25 | 安徽艾睿思智能科技有限公司 | General printing defect detection method based on deep learning and model thereof |
CN113466261A (en) * | 2021-07-26 | 2021-10-01 | 鸿安(福建)机械有限公司 | PCB board automatic checkout device |
CN114359270A (en) * | 2022-03-09 | 2022-04-15 | 山东华硕汽车配件科技有限公司 | Computer vision-based automobile engine oil way copper bush defect detection method |
CN114600154A (en) * | 2019-10-31 | 2022-06-07 | 科磊股份有限公司 | BBP-assisted defect detection process for SEM images |
-
2022
- 2022-07-29 CN CN202210903046.9A patent/CN115240193B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108645867A (en) * | 2018-05-25 | 2018-10-12 | 哈尔滨工业大学 | Large-aperture optical plane of crystal microdefect quickly seeks position and batch detector methods |
CN110619620A (en) * | 2018-06-04 | 2019-12-27 | 杭州海康威视数字技术股份有限公司 | Method, device and system for positioning abnormity causing surface defects and electronic equipment |
CN209296559U (en) * | 2018-12-15 | 2019-08-23 | 勤基电路板(深圳)有限公司 | The appearance of circuit board detects production line |
CN114600154A (en) * | 2019-10-31 | 2022-06-07 | 科磊股份有限公司 | BBP-assisted defect detection process for SEM images |
CN111709909A (en) * | 2020-05-12 | 2020-09-25 | 安徽艾睿思智能科技有限公司 | General printing defect detection method based on deep learning and model thereof |
CN113466261A (en) * | 2021-07-26 | 2021-10-01 | 鸿安(福建)机械有限公司 | PCB board automatic checkout device |
CN114359270A (en) * | 2022-03-09 | 2022-04-15 | 山东华硕汽车配件科技有限公司 | Computer vision-based automobile engine oil way copper bush defect detection method |
Also Published As
Publication number | Publication date |
---|---|
CN115240193A (en) | 2022-10-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN115047162B (en) | Defect detection method and system for heat treatment of steel pipe | |
CN113378725B (en) | Multi-scale-channel attention network-based tool fault diagnosis method, equipment and storage medium | |
US20120253694A1 (en) | Method and apparatus for judging status of mechanical system | |
CN110146019B (en) | Workpiece size online detection and automatic compensation method based on industrial camera | |
US20230008435A1 (en) | Tool Wear Monitoring Device, Tool Wear Monitoring System, and Program | |
CN116009480A (en) | Fault monitoring method, device and equipment of numerical control machine tool and storage medium | |
US10295475B2 (en) | Inspection of machined holes | |
JP2019098515A (en) | Blade tool state inspection system and method | |
CN114840932B (en) | Method for improving TC4 titanium alloy surface roughness prediction precision by multi-factor coupling | |
CN117351006B (en) | Deep learning-based method and system for detecting surface defects of automobile sheet metal part | |
US20160070253A1 (en) | Monitoring hole machining | |
CN113752086A (en) | Method and device for detecting state of numerical control machine tool cutter | |
CN108956142A (en) | A kind of bearing fault recognition methods | |
CN115240193B (en) | Surface treatment method and system for electric automobile motor spindle | |
Agarwal et al. | Analyzing the evolution of tool wear area in trochoidal milling of Inconel 718 using image processing methodology | |
CN117806231A (en) | Machine tool operation and machining control system and method based on Internet of things | |
JP4842782B2 (en) | Defect review method and apparatus | |
CN110530495B (en) | Cutting chatter monitoring method based on vibration analysis | |
CN115625317B (en) | Surface water wave optimization processing method and system for die casting regulation and control | |
US8346383B2 (en) | Method for determining the machining quality of components, particularly for metal cutting by NC machines | |
CN113053471B (en) | Method for nondestructive on-line detection of Brinell hardness of fan spindle | |
CN117001453B (en) | Motor stator and rotor punching burr control method and system | |
CN113752084A (en) | Intelligent monitoring method and system for performance of numerical control machine tool cutter | |
CN111562768A (en) | Parallel multi-channel numerical control machine tool | |
CN115213735B (en) | System and method for monitoring cutter state in milling process |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |