CN114782453A - Bearing quality detection method and system based on intelligent manufacturing - Google Patents
Bearing quality detection method and system based on intelligent manufacturing Download PDFInfo
- Publication number
- CN114782453A CN114782453A CN202210715771.3A CN202210715771A CN114782453A CN 114782453 A CN114782453 A CN 114782453A CN 202210715771 A CN202210715771 A CN 202210715771A CN 114782453 A CN114782453 A CN 114782453A
- Authority
- CN
- China
- Prior art keywords
- bearing
- quality
- information
- detection
- weight
- 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.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 199
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 30
- 238000007689 inspection Methods 0.000 claims abstract description 106
- 238000009826 distribution Methods 0.000 claims abstract description 76
- 238000013441 quality evaluation Methods 0.000 claims abstract description 64
- 238000012545 processing Methods 0.000 claims abstract description 42
- 238000000034 method Methods 0.000 claims abstract description 38
- 238000011156 evaluation Methods 0.000 claims description 64
- 230000011218 segmentation Effects 0.000 claims description 37
- 238000012549 training Methods 0.000 claims description 28
- 230000015572 biosynthetic process Effects 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 12
- 238000003786 synthesis reaction Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 11
- 230000007547 defect Effects 0.000 claims description 10
- 238000012360 testing method Methods 0.000 claims description 10
- 238000012795 verification Methods 0.000 claims description 10
- 238000012216 screening Methods 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 8
- 238000002372 labelling Methods 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000001303 quality assessment method Methods 0.000 claims 1
- 238000003860 storage Methods 0.000 description 9
- 230000000694 effects Effects 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000004927 fusion Effects 0.000 description 4
- 238000004088 simulation Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 230000010339 dilation Effects 0.000 description 2
- 239000012535 impurity Substances 0.000 description 2
- 238000002955 isolation Methods 0.000 description 2
- 239000002184 metal Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000000227 grinding Methods 0.000 description 1
- JEIPFZHSYJVQDO-UHFFFAOYSA-N iron(III) oxide Inorganic materials O=[Fe]O[Fe]=O JEIPFZHSYJVQDO-UHFFFAOYSA-N 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- 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
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
- G01M13/04—Bearings
- G01M13/045—Acoustic or vibration analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- 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
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Educational Administration (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Acoustics & Sound (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention discloses a bearing quality detection method and system based on intelligent manufacturing, wherein the method comprises the following steps: obtaining a first bearing detection index set; acquiring service information of a first bearing; constructing a first weight distribution module based on the first bearing detection index set; inputting the first bearing detection index set and the first bearing service information into the first weight distribution module to obtain a first weight distribution result; acquiring first bearing quality inspection information based on the first bearing detection index set, wherein the first bearing quality inspection information comprises first quality inspection information and second quality inspection information; constructing a first bearing quality evaluation model, wherein the first bearing quality evaluation model comprises a first hidden processing layer and a second hidden processing layer; and inputting the first bearing quality inspection information and the first weight distribution result into the first bearing quality evaluation model to obtain a first bearing quality detection result.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to a bearing quality detection method and system based on intelligent manufacturing.
Background
The bearing is an indispensable part in mechanical equipment and plays a key role in normal working operation of the equipment, so that the service life of the quality detection of the service bearing is concerned, the service bearing can be subjected to single quality detection usually in the aspects of whether noise exists, chamfering is uniform, surface rust marks and the like, the service bearing is subjected to accurate and comprehensive quality detection, and timely use and maintenance can be ensured, so that the use efficiency of the bearing is improved.
However, in the process of implementing the technical solution of the invention in the embodiments of the present application, the inventors of the present application find that the above-mentioned technology has at least the following technical problems:
the technical problem that the quality of a bearing in service cannot be accurately detected in the prior art so that the service condition of the bearing cannot be dynamically mastered exists.
Disclosure of Invention
Aiming at the defects in the prior art, the embodiment of the application aims to solve the technical problem that the service condition of a bearing cannot be dynamically mastered because the bearing quality in service cannot be accurately detected in the prior art by providing the bearing quality detection method and system based on intelligent manufacturing. The detection indexes of the bearing to be detected are subjected to weight distribution of an algorithm, data acquisition is carried out on an image quality inspection result and a vibration sound quality inspection result of the bearing to be detected, and then the weight distribution result and the data acquisition result are input into a constructed bearing quality evaluation model for evaluation training, so that the quality detection result of the bearing to be detected is obtained through final training, the accurate detection of the quality of the bearing in service is achieved, the dynamic control of the service condition of the bearing is ensured, and the technical effect of prolonging the service life of the bearing in service is improved.
In one aspect, an embodiment of the present application provides a bearing quality detection method based on intelligent manufacturing, where the method includes: obtaining a first bearing detection index set; acquiring service information of a first bearing; constructing a first weight distribution module based on the first bearing detection index set; inputting the first bearing detection index set and the first bearing service information into the first weight distribution module to obtain a first weight distribution result; acquiring first bearing quality inspection information based on the first bearing detection index set, wherein the first bearing quality inspection information comprises first quality inspection information and second quality inspection information; constructing a first bearing quality evaluation model, wherein the first bearing quality evaluation model comprises a first implicit processing layer and a second implicit processing layer; and inputting the first bearing quality inspection information and the first weight distribution result into the first bearing quality evaluation model to obtain a first bearing quality detection result.
In another aspect, the present application further provides a bearing quality detection system based on intelligent manufacturing, wherein the system includes: a first obtaining unit: the first obtaining unit is used for obtaining a first bearing detection index set; a second obtaining unit: the second obtaining unit is used for obtaining service information of the first bearing; a first building unit: the first construction unit is used for constructing a first weight distribution module based on the first bearing detection index set; a first input unit: the first input unit is used for inputting the first bearing detection index set and the first bearing service information into the first weight distribution module to obtain a first weight distribution result; a first acquisition unit: the first obtaining unit is used for obtaining first bearing quality inspection information based on the first bearing detection index set, wherein the first bearing quality inspection information comprises first quality inspection information and second quality inspection information; a second building element: the second construction unit is used for constructing a first bearing quality evaluation model, and the first bearing quality evaluation model comprises a first hidden processing layer and a second hidden processing layer; a second input unit: the second input unit is used for inputting the first bearing quality inspection information and the first weight distribution result into the first bearing quality evaluation model to obtain a first bearing quality detection result.
In a third aspect, an embodiment of the present application provides a bearing quality detection apparatus based on intelligent manufacturing, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the method according to any one of the first aspect when executing the program.
One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:
1. obtaining a first bearing detection index set; acquiring service information of a first bearing; constructing a first weight distribution module based on the first bearing detection index set; inputting the first bearing detection index set and the first bearing service information into the first weight distribution module to obtain a first weight distribution result; acquiring first bearing quality inspection information based on the first bearing detection index set, wherein the first bearing quality inspection information comprises first quality inspection information and second quality inspection information; constructing a first bearing quality evaluation model, wherein the first bearing quality evaluation model comprises a first hidden processing layer and a second hidden processing layer; and inputting the first bearing quality inspection information and the first weight distribution result into the first bearing quality evaluation model to obtain a first bearing quality detection result. The technical effects that algorithm weight distribution is carried out on detection indexes of the bearing to be detected, data acquisition is carried out on image quality inspection results and vibration sound quality inspection results of the bearing to be detected, and then the weight distribution results and the data acquisition results are input into a constructed bearing quality evaluation model for evaluation training are achieved, so that the quality detection results of the bearing to be detected are obtained through final training, accurate detection on the quality of the bearing in service is achieved, the service condition of the bearing is ensured to be dynamically mastered, and the service life rate of the bearing in service is improved are achieved.
2. The image detection is used as the first quality inspection information, the vibration sound detection is used as the second quality inspection information, and the first quality inspection information and the second quality inspection information are combined to obtain the first bearing quality inspection information, so that the multi-party detection of the image, the vibration sound and the like of the part of the bearing is realized, the comprehensive standard of the quality inspection of the service bearing is ensured, and the accurate comparison standard is provided for the quality detection of the bearing.
The above description is only an overview of the technical solutions of the present application, and the present application may be implemented in accordance with the content of the description so as to make the technical means of the present application more clearly understood, and the detailed description of the present application will be given below in order to make the above and other objects, features, and advantages of the present application more clearly understood.
Drawings
Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of non-limiting embodiments with reference to the following drawings:
FIG. 1 is a schematic flow chart of a bearing quality detection method based on intelligent manufacturing according to an embodiment of the present application;
FIG. 2 is a schematic flowchart of a method for obtaining a first weight distribution result according to an embodiment of the present application;
FIG. 3 is a schematic flow chart of the method for detecting bearing quality based on intelligent manufacturing according to the embodiment of the present application, the method being constructed and trained to obtain the weight evaluation layer;
fig. 4 is a schematic flowchart of a process of acquiring first bearing quality inspection information according to an embodiment of the present application;
FIG. 5 is a schematic flow chart illustrating semantic segmentation of the preprocessed image information according to an embodiment of the present disclosure;
FIG. 6 is a schematic structural diagram of a bearing quality detection system based on intelligent manufacturing according to an embodiment of the present application;
fig. 7 is a schematic structural diagram of an exemplary electronic device according to an embodiment of the present application.
Detailed Description
The embodiment of the application provides a bearing quality detection method and system based on intelligent manufacturing, and solves the technical problem that in the prior art, the quality of a bearing in service cannot be accurately detected, so that the service condition of the bearing cannot be dynamically mastered. The detection indexes of the bearing to be detected are subjected to weight distribution of an algorithm, data acquisition is carried out on an image quality inspection result and a vibration sound quality inspection result of the bearing to be detected, and then the weight distribution result and the data acquisition result are input into a constructed bearing quality evaluation model for evaluation training, so that the quality detection result of the bearing to be detected is obtained through final training, the accurate detection of the quality of the bearing in service is achieved, the dynamic control of the service condition of the bearing is ensured, and the technical effect of prolonging the service life of the bearing in service is improved.
Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only a few embodiments of the present application, and not all embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.
Because the quality of the bearing in service cannot be accurately detected in the prior art, the service condition of the bearing cannot be dynamically mastered. According to the invention, on the premise of not influencing the working efficiency of the bearing, the quality of the bearing in service is accurately detected through the bearing quality evaluation model.
In view of the above technical problems, the technical solution provided by the present application has the following general idea:
the embodiment of the application provides a bearing quality detection method based on intelligent manufacturing, wherein the method comprises the following steps: obtaining a first bearing detection index set; obtaining service information of a first bearing; constructing a first weight distribution module based on the first bearing detection index set; inputting the first bearing detection index set and the first bearing service information into the first weight distribution module to obtain a first weight distribution result; acquiring first bearing quality inspection information based on the first bearing detection index set, wherein the first bearing quality inspection information comprises first quality inspection information and second quality inspection information; constructing a first bearing quality evaluation model, wherein the first bearing quality evaluation model comprises a first implicit processing layer and a second implicit processing layer; and inputting the first bearing quality inspection information and the first weight distribution result into the first bearing quality evaluation model to obtain a first bearing quality detection result.
For better understanding of the above technical solutions, the following detailed descriptions will be provided in conjunction with the drawings and the detailed description of the embodiments.
Example one
As shown in fig. 1, an embodiment of the present application provides a bearing quality detection method based on intelligent manufacturing, where the method includes:
step S100: obtaining a first bearing detection index set;
step S200: obtaining service information of a first bearing;
further, step S200 includes:
step S210: obtaining bearing class information of a first bearing;
step S220: acquiring service environment information of a first bearing;
step S230: analyzing based on the bearing category information and the service environment information to obtain a first service requirement and a second service requirement;
step S240: and fusing the first service requirement and the second service requirement to obtain service information of the first bearing.
In particular, bearings are an important part in modern mechanical equipment. The main function of the bearing detection device is to support a mechanical rotating body, reduce the friction coefficient in the movement process of the mechanical rotating body and ensure the rotation precision of the mechanical rotating body, wherein the first bearing detection index set can be understood as a set of detection indexes such as the existence of impurities in a bearing raceway, whether the metal surface of a bearing is damaged, the deflection angle of the raceway, the hardness, the wear resistance, the vibration sound and the like; the service information of the first bearing is, as the name implies, the service information of the first bearing, namely the service life information and the performance requirement of the first bearing which is used as a basic component of mechanical equipment.
More specifically, the bearing is an important part in the current mechanical equipment. The main function of the bearing detection device is to support a mechanical rotating body, reduce the friction coefficient in the movement process of the mechanical rotating body and ensure the rotation precision of the mechanical rotating body, wherein the first bearing detection index set can be understood as a set of detection indexes such as the existence of impurities in a bearing raceway, whether the metal surface of a bearing is damaged, the deflection angle of the raceway, the hardness, the wear resistance, the vibration sound and the like; the service information of the first bearing is the service information of the first bearing, which is taken as the basic component of the mechanical equipment as well as the service life information and the performance requirement of the first bearing.
More specifically, when the service information of the first bearing is obtained, the bearing class information and the service environment information of the first bearing may be obtained respectively, where the bearing class information may be classified correspondingly according to different classification features, for example, the bearing class information may be classified into a radial bearing and a thrust bearing according to different load directions or nominal contact angles that can be borne, and the bearing class information may be classified into a ball bearing and a roller bearing according to the shape of a rolling element, which are not listed here. Further, the bearing class information and the service environment information may be analyzed, and an actual analysis process may be as follows, a bearing operation environment simulation model may be constructed according to big data, and the bearing class information and the service environment information may be input into the constructed simulation model by performing simulation on an application environment of the bearing, specifically, when the cylindrical roller bearing is applied to an industrial manufacturing device, the cylindrical roller bearing and the industrial manufacturing device may be input into the constructed simulation model, and the application environment thereof may be simulated, so that several performances of the cylindrical roller bearing, which are easy to fail in long-term application, specifically, performances including easy wear, easy inclination of the roller, and the like, may be obtained, wherein the first service requirement may correspond to an application requirement that the first bearing needs to meet wear resistance, and the second service requirement is different from the first service requirement, the application requirements of strong hardness, high rotating speed, etc. may be satisfied by the first bearing, and it should be noted that the first service requirement and the second service requirement of the first bearing are included, but not limited to, and only the first service requirement and the second service requirement are taken as examples for description.
And the service information of the first bearing can be obtained by performing requirement fusion on the first service requirement and the second service requirement, so that an accurate comparison standard is provided for the quality detection of the bearing.
Step S300: constructing a first weight distribution module based on the first bearing detection index set;
step S400: inputting the first bearing detection index set and the first bearing service information into the first weight distribution module to obtain a first weight distribution result;
further, as shown in fig. 2, step S400 includes:
step S410: the first weight distribution module comprises M weight evaluation layers, and information in every two weight evaluation layers in the M weight evaluation layers is isolated;
step S420: respectively inputting the first bearing detection index set and the first bearing service information into M weight evaluation layers to obtain M weight score sets, wherein N detection indexes in the first bearing detection index set correspond to a weight score;
step S430: summing each weight score in the M weight score sets according to N detection indexes in the first bearing detection index set to obtain N total weight evaluation scores;
step S440: and calculating the N total weight evaluation scores based on a first weight distribution formula to obtain a first weight distribution result.
Specifically, the first weight distribution module may be constructed according to the first bearing detection index set, where the first weight distribution module may distribute a weight value occupied by each detection index in the bearing detection index set, may distribute a weight based on an influence of each detection index on the overall performance of the bearing, and so on, and further input the first bearing detection index set and the first bearing service information into the first weight distribution module to obtain a first weight distribution result, where the first bearing detection index set may be understood as a weight target set to be distributed, the first bearing service information may be understood as a weight distribution standard, and further obtain a distributed first weight distribution result, where the first weight distribution result is a weight distribution result occupied by each detection index in the bearing detection index set under the first service environment information, based on the first weight assignment result, targeted fine quality detection can be performed on the first bearing.
More specifically, the first weight distribution module includes M weight evaluation layers, where information isolation is performed between every two weight evaluation layers in the M weight evaluation layers, that is, a message isolation state is maintained between every two weight evaluation layers, weight distribution is performed on all detection indexes under the first service environment information, and then mean calculation is performed on the weight evaluation of the M weight evaluation layers, so that a weight distribution result is relatively fair. Further, by inputting the first bearing detection index set and the first bearing service information into M weight evaluation layers, M weight score sets can be obtained, where the M weight score sets are sets obtained after weight distribution is performed on each weight evaluation layer, that is, in the M evaluation layers, each evaluation layer can perform importance weight evaluation on N detection indexes to obtain M weight score sets, each weight score set includes weight scores of N detection indexes, and further based on the number of the N detection indexes, each weight score is summed up to obtain N total weight evaluation scores, that is, the weight scores of each detection index are summed up to obtain N total weight evaluation scores, and further based on a first weight distribution formula, the N total weight evaluation scores are calculated, specifically, the first weight distribution formula is: for example, if the wear resistance of the bearing is taken as the single detection index for explanation, the wear resistance weight distribution formula is that the wear resistance weight evaluation total score/the weight evaluation total scores of all the detection indexes are calculated in sequence, and a first weight distribution result can be obtained, wherein the first weight distribution result is the percentage of each detection index.
Step S500: acquiring first bearing quality inspection information based on the first bearing detection index set, wherein the first bearing quality inspection information comprises first quality inspection information and second quality inspection information;
further, as shown in fig. 4, step S500 includes:
step S510: acquiring an image information set of a first bearing;
step S520: carrying out extreme value synthesis or average value synthesis on the image information set to obtain preprocessed image information;
step S530: performing semantic segmentation on the preprocessed image information to obtain a semantic segmentation image;
step S540: obtaining the first quality inspection information based on the semantic segmentation image;
step S550: obtaining the second quality inspection information based on vibration detection;
step S560: and combining the first quality inspection information and the second quality inspection information to obtain the first bearing quality inspection information.
Specifically, first bearing quality inspection information may be obtained according to the first bearing detection index set, where the first bearing quality inspection information includes first quality inspection information and second quality inspection information, specifically, the first quality inspection information may perform quality inspection on the bearing from an aspect of image characteristics, and the second quality inspection information may perform quality inspection on the bearing from an aspect of vibration sound when the bearing operates, and it should be noted that the first bearing quality inspection information includes, but is not limited to, the first quality inspection information and the second quality inspection information, and also includes characteristics such as a device manufacturing product standard, such as a side quality inspection on the bearing, and the like.
More specifically, the image acquisition may be performed on the first bearing according to a camera device to obtain the image information set, and then the extreme value synthesis or average value synthesis may be performed on the image information set to obtain the synthesized preprocessed image information, so-called extreme value synthesis or average value synthesis may be understood as performing processing such as boundary fusion or image feature enhancement on a plurality of images in the image information set, so as to avoid the influence of unnecessary factors such as dust, light, and placement position angle on the image precision, and further, performing semantic segmentation on the synthesized preprocessed image information to obtain a semantic segmentation image, generally, the semantic segmentation is a challenging task in a computer vision system, and may be constructed based on a deep learning paradigm, and a deep neural network is an effective method for semantic segmentation, the image classification, the target determination and the boundary positioning can mark a group of objects or non-objects on each area or pixel until the target image characteristics are segmented, and the method is applied to the embodiment, the image classification, the pixel segmentation marking and the like can be carried out on the preprocessed image until the target image characteristics in the preprocessed image, namely the image information of each component of the bearing, are segmented, the image information can be used as the first quality inspection information, namely the image quality inspection can be carried out on the image information of each component of the bearing, the defect images such as grinding marks, roller deflection angles and the like can be obtained according to the semantic segmentation image, and the image quality inspection can be further carried out on the bearing.
In addition, vibration sound generated when the bearing works can be detected based on vibration detection, the vibration sound is detected to serve as the second quality inspection information, the first quality inspection information and the second quality inspection information are combined, the first bearing quality inspection information can be obtained, multi-party detection of part images, vibration sound and the like of the bearing is achieved, and comprehensive standard of quality inspection of the service bearing is guaranteed.
Step S600: constructing a first bearing quality evaluation model, wherein the first bearing quality evaluation model comprises a first hidden processing layer and a second hidden processing layer;
further, step S600 includes:
step S610: constructing a bearing quality evaluation function, and constructing the first hidden processing layer according to the bearing quality evaluation function;
step S620: obtaining a first bearing quality evaluation threshold;
step S630: constructing the second implicit processing layer according to the first bearing quality evaluation threshold value;
step 640: obtaining the first bearing quality evaluation model based on the first implicit processing layer and the second implicit processing layer.
Specifically, when the quality of the first bearing is detected, a first bearing quality evaluation model may be constructed, where the first bearing quality evaluation model includes a first implicit processing layer and a second implicit processing layer, and the second implicit processing layer receives the first implicit processing layer.
More specifically, when the first bearing quality evaluation model is constructed, a bearing quality evaluation function, which is a function for evaluating and calculating i failed detection records in the nth detection index, may be constructed, and the bearing quality evaluation function may be specifically used
It means that there are:
wherein, in the step (A),
indicating the reject ratio of the nth detection index in the first detection index set,
the unqualified number of the nth detection index in the first detection index set is represented,
the total number of bearings for detecting the nth detection index in the first detection index set is represented, and
based on the bearing quality evaluation function, the unqualified detection records of each detection index in the N detection indexes can be summed up, that is, by using the formula: v% = V =
+
+
And performing an addition operation, wherein,
and representing the weight of the nth detection index in the first detection index set in the first weight distribution result, wherein V% represents the failure rate of quality detection, and further constructing the first hidden processing layer according to the addition operation result of the failure detection records.
Furthermore, the first bearing quality evaluation threshold is obtained, which may be understood as a preset bearing failure rate threshold, and here, the first bearing quality evaluation threshold may be interpreted as 1%, and a second implicit processing layer may be constructed based on the first bearing quality evaluation threshold, that is, firstly, a failure detection record of each detection index in a detection index set of a bearing is implicitly processed through the first implicit processing layer, and then, according to the first bearing quality evaluation threshold in the second implicit processing layer, a threshold is defined for a failure rate detection index of the first bearing, so that the first bearing quality evaluation model is finally constructed.
Step S700: and inputting the first bearing quality inspection information and the first weight distribution result into the first bearing quality evaluation model to obtain a first bearing quality detection result.
Specifically, after the first bearing quality evaluation model is constructed, the first bearing quality inspection information and the first weight assignment result may be input to the first bearing quality evaluation model for training until the first bearing quality detection result is obtained. For example, based on the first bearing quality evaluation model, the image quality inspection information, the vibration sound quality inspection information, and the occupied weight of each detection index in the bearing detection index set of the input first bearing may be trained, so that the quality detection result of the first bearing is trained.
The technical effects that algorithm weight distribution is carried out on detection indexes of the bearing to be detected, data acquisition is carried out on image quality inspection results and vibration sound quality inspection results of the bearing to be detected, and then the weight distribution results and the data acquisition results are input into a constructed bearing quality evaluation model for evaluation training are achieved, so that the quality detection results of the bearing to be detected are obtained through final training, accurate detection on the quality of the bearing in service is achieved, the service condition of the bearing is ensured to be dynamically mastered, and the service life rate of the bearing in service is improved are achieved.
Further, as shown in fig. 3, the first weight distribution module includes M weight evaluation layers, and step S410 includes:
step S411: obtaining a first weight evaluation main body set according to the first bearing detection index set;
step S412: screening the first weight evaluation subject set according to the first bearing service information to obtain a second weight evaluation subject set;
step S413: obtaining historical quality detection data of the second weight evaluation subject set, and screening the historical quality detection data according to the first bearing service information to obtain matching historical quality detection data;
step S414: and constructing and training the matching historical quality detection data and identification information for identifying the weight scoring set as training data to obtain the weight evaluation layer.
Specifically, when a weight evaluation layer is constructed, a first weight evaluation subject set can be obtained according to the first bearing detection index set, the first weight evaluation subject set can be characterized as a factory for producing a plurality of bearings, and then the first weight evaluation subject set is screened according to the first bearing service information, that is, the production type of the first bearing and a bearing production enterprise in a service environment are screened, the second weight evaluation subject set is a screening result, and then historical quality detection data of the second weight evaluation subject set is obtained, the historical quality detection data is quality inspection historical data of the screened bearing production enterprise for matching bearings, and by screening the historical quality detection data, matching historical quality detection data can be obtained, the matching historical quality detection data is detection data matched with a currently detected bearing, the matching history quality detection data and the identification information for identifying the weight score set may be used as training data to train and construct the weight evaluation layer. And performing accurate quality detection on the bearing to be detected based on the weight evaluation layer.
Further, as shown in fig. 5, the semantic segmentation is performed on the preprocessed image information to obtain a semantic segmented image, and step S530 includes:
step S531: performing defect labeling on the preprocessed image information to obtain a labeled data set;
step S532: preprocessing the preprocessed image information and the labeled data set to obtain a training data set, a test data set and a verification data set;
step S533: training the constructed bearing semantic segmentation quality detection model by adopting the training data set, the test data set and the verification data set to obtain the bearing semantic segmentation quality detection model;
step S534: and inputting the preprocessed image information into the bearing semantic segmentation quality detection model, and performing bearing quality detection to obtain the semantic segmentation image.
Specifically, when the semantic segmentation quality detection model of the bearing is constructed, specifically, defect labeling may be performed on the preprocessed image information, where the defect labeling may be understood as performing defect feature labeling on an image of a component having a problem or a defect in the bearing, the labeled data set is a defect image label set, and at the same time, the preprocessed image information and the labeled data set are preprocessed to obtain a training data set, a test data set, and a verification data set, where a preprocessing angle process is preprocessing operations such as removing gray scale and enhancing pixel area contrast on an image, the training data set is a set used for image training, the test data set is a set used for image testing, and the verification data set is a set used for image verification.
The training data set, the test data set and the verification data set can be used for training the bearing semantic segmentation quality detection model, and particularly, the bearing semantic segmentation quality detection model can be constructed by a method for improving the characteristic resolution. Restoration of spatial resolution using hole convolution and dilation convolution may generate high resolution topographical maps for dense prediction. The dilated convolution carries another parameter "dilation" (describing the space between kernel values) to the convolution layer, which has the ability to expand the acceptance domain while also losing resolution. Is convolved by a "hole" for computing the non-decimating wavelet transform (UWT). The fully connected layers are converted to convolutional layers with a step size of 8 pixels, the sub-sampling after the last two pooling layers is skipped, and the convolutional filters in the layers are modified by introducing zeros (the length of the last three convolutional layers is increased by 2 times, the length of the first fully connected layer is increased by 4 times). The method is combined with a fully connected Conditional Random Field (CRF), and can effectively generate semantically accurate prediction and tail-removing segmentation mapping. Extended convolution is used to combine the multi-scale context information without loss of resolution and the rescaled image is analyzed for semantic segmentation. And inputting the preprocessed image information into the bearing semantic segmentation quality detection model, and performing bearing quality detection to obtain the semantic segmentation image, so that the semantic segmentation of the preprocessed image is more accurate.
Example two
Based on the same inventive concept as that of the bearing quality detection method based on intelligent manufacturing in the foregoing embodiment, the present invention further provides a bearing quality detection system based on intelligent manufacturing, as shown in fig. 6, the system includes:
the first obtaining unit 11: the first obtaining unit 11 is configured to obtain a first set of bearing detection indicators;
the second obtaining unit 12: the second obtaining unit 12 is configured to obtain first bearing service information;
the first building element 13: the first constructing unit 13 is configured to construct a first weight distribution module based on the first bearing detection index set;
first input unit 14: the first input unit 14 is configured to input the first bearing detection index set and the first bearing service information into the first weight distribution module, so as to obtain a first weight distribution result;
the first acquisition unit 15: the first obtaining unit 15 is configured to obtain first bearing quality inspection information based on the first bearing detection index set, where the first bearing quality inspection information includes first quality inspection information and second quality inspection information;
second building element 16: the second constructing unit 16 is configured to construct a first bearing quality evaluation model, where the first bearing quality evaluation model includes a first implicit processing layer and a second implicit processing layer;
second input unit 17: the second input unit 17 is configured to input the first bearing quality inspection information and the first weight assignment result into the first bearing quality evaluation model, so as to obtain a first bearing quality detection result.
Further, the system further comprises:
a third obtaining unit: the third obtaining unit is used for obtaining bearing type information of the first bearing;
a second acquisition unit: the second acquisition unit is used for acquiring service environment information of the first bearing;
a first analysis unit: the first analysis unit is used for analyzing based on the bearing type information and the service environment information to obtain a first service requirement and a second service requirement;
a first fusion unit: the first fusion unit is used for fusing the first service requirement and the second service requirement to obtain the service information of the first bearing.
Further, the system further comprises:
a fourth obtaining unit: the fourth obtaining unit is used for the first weight distribution module to comprise M weight evaluation layers, and information in every two weight evaluation layers in the M weight evaluation layers is isolated;
a third input unit: the third input unit is used for respectively inputting the first bearing detection index set and the first bearing service information into the M weight evaluation layers to obtain M weight score sets, wherein N detection indexes in the first bearing detection index set correspond to a weight score;
the first calculation unit: the first calculating unit is configured to sum up the weight scores in the M weight score sets according to N detection indexes in the first bearing detection index set to obtain N total weight evaluation scores;
a second calculation unit: the second calculating unit is used for calculating the N total weight evaluation scores based on a first weight distribution formula to obtain a first weight distribution result.
Further, the system further comprises:
a fifth obtaining unit: the fifth obtaining unit is used for obtaining a first weight evaluation subject set according to the first bearing detection index set;
a first screening unit: the first screening unit is used for screening the first weight evaluation subject set according to the first bearing service information to obtain a second weight evaluation subject set;
a sixth obtaining unit: the sixth obtaining unit is configured to obtain historical quality detection data of the second weight evaluation subject set, and filter the historical quality detection data according to the first bearing service information to obtain matching historical quality detection data;
a seventh obtaining unit: the seventh obtaining unit is configured to use the matching history quality detection data and identification information for identifying the weight score set as training data, and construct and train to obtain the weight evaluation layer.
Further, the system further comprises:
a third acquisition unit: the third acquisition unit is used for acquiring an image information set of the first bearing;
a first synthesis unit: the first synthesis unit is used for carrying out extreme value synthesis or average value synthesis on the image information set to obtain preprocessed image information;
a first dividing unit: the first segmentation unit is used for performing semantic segmentation on the preprocessed image information to obtain a semantic segmentation image;
an eighth obtaining unit: the eighth obtaining unit is configured to obtain the first quality inspection information based on the semantic segmentation image;
a ninth obtaining unit: the ninth obtaining unit is configured to obtain the second quality inspection information based on vibration detection;
a tenth obtaining unit: the tenth obtaining unit is configured to obtain the first bearing quality inspection information by combining the first quality inspection information and the second quality inspection information.
Further, the system further comprises:
a first labeling unit: the first labeling unit is used for labeling the defects of the preprocessed image information to obtain a labeled data set;
an eleventh obtaining unit: the eleventh obtaining unit is configured to pre-process the pre-processed image information and the labeled data set to obtain a training data set, a test data set, and a verification data set;
a twelfth obtaining unit: the twelfth obtaining unit is configured to train the constructed bearing semantic segmentation quality detection model by using the training data set, the test data set, and the verification data set, so as to obtain the bearing semantic segmentation quality detection model;
a fourth input unit: the fourth input unit is used for inputting the preprocessed image information into the bearing semantic segmentation quality detection model to perform bearing quality detection, and obtaining the semantic segmentation image.
Further, the system further comprises:
a third construction unit: the third construction unit is used for constructing a bearing quality evaluation function and constructing the first implicit processing layer according to the bearing quality evaluation function;
a thirteenth obtaining unit: the thirteenth obtaining unit is used for obtaining a first bearing quality evaluation threshold value;
a fourth construction unit: the fourth construction unit is used for constructing the second implicit processing layer according to the first bearing quality evaluation threshold value;
a fourteenth obtaining unit: the fourteenth obtaining unit is configured to obtain the first bearing quality evaluation model based on the first implicit processing layer and the second implicit processing layer.
Various modifications and specific examples of the method for detecting bearing quality based on intelligent manufacturing in the first embodiment of fig. 1 are also applicable to the system for detecting bearing quality based on intelligent manufacturing in the present embodiment, and a person skilled in the art can clearly understand the method for implementing the system for detecting bearing quality based on intelligent manufacturing through the foregoing detailed description of the method for detecting bearing quality based on intelligent manufacturing, so for the brevity of the description, detailed descriptions are omitted here.
EXAMPLE III
The computer apparatus of the embodiment of the present application is described below with reference to fig. 7. The computer device may be an application version management server or a terminal, and its internal structure diagram may be as shown in fig. 7. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program to run on the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of processing an application package.
When the computer device is a terminal, the computer device may further include a display screen and an input device. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the configuration shown in fig. 7 is a block diagram of only a portion of the configuration associated with the present application, and is not intended to limit the computing device to which the present application may be applied, and that a particular computing device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In an embodiment, a computer device is further provided, which includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above method embodiments when executing the computer program.
In an embodiment, a computer-readable storage medium is provided, in which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.
In one embodiment, a computer program product or computer program is provided that includes computer instructions stored in a computer readable storage medium. The computer instructions are read by a processor of a computer device from a computer-readable storage medium, and the computer instructions are executed by the processor to cause the computer device to perform the steps in the above-mentioned method embodiments.
The embodiment of the application provides a bearing quality detection method based on intelligent manufacturing, wherein the method comprises the following steps: obtaining a first bearing detection index set; obtaining service information of a first bearing; constructing a first weight distribution module based on the first bearing detection index set; inputting the first bearing detection index set and the first bearing service information into the first weight distribution module to obtain a first weight distribution result; acquiring first bearing quality inspection information based on the first bearing detection index set, wherein the first bearing quality inspection information comprises first quality inspection information and second quality inspection information; constructing a first bearing quality evaluation model, wherein the first bearing quality evaluation model comprises a first implicit processing layer and a second implicit processing layer; and inputting the first bearing quality inspection information and the first weight distribution result into the first bearing quality evaluation model to obtain a first bearing quality detection result.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above may be implemented by hardware instructions of a computer program, which may be stored in a non-volatile computer-readable storage medium, and when executed, may include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is specific and detailed, but not to be understood as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent application shall be subject to the appended claims.
Claims (9)
1. A bearing quality detection method based on intelligent manufacturing is characterized by comprising the following steps:
obtaining a first bearing detection index set;
obtaining service information of a first bearing;
constructing a first weight distribution module based on the first bearing detection index set;
inputting the first bearing detection index set and the first bearing service information into the first weight distribution module to obtain a first weight distribution result;
acquiring first bearing quality inspection information based on the first bearing detection index set, wherein the first bearing quality inspection information comprises first quality inspection information and second quality inspection information;
constructing a first bearing quality evaluation model, wherein the first bearing quality evaluation model comprises a first hidden processing layer and a second hidden processing layer;
and inputting the first bearing quality inspection information and the first weight distribution result into the first bearing quality evaluation model to obtain a first bearing quality detection result.
2. The method of claim 1, wherein the obtaining first bearing service information comprises:
obtaining bearing class information of a first bearing;
acquiring service environment information of a first bearing;
analyzing based on the bearing category information and the service environment information to obtain a first service requirement and a second service requirement;
and fusing the first service requirement and the second service requirement to obtain the service information of the first bearing.
3. The method of claim 1, wherein the inputting the first set of bearing detection metrics and the first bearing service information into a first weight assignment module to obtain a first weight assignment result comprises:
the first weight distribution module comprises M weight evaluation layers, and information in every two weight evaluation layers in the M weight evaluation layers is isolated;
respectively inputting the first bearing detection index set and the first bearing service information into M weight evaluation layers to obtain M weight score sets, wherein N detection indexes in the first bearing detection index set correspond to a weight score;
adding and calculating each weight score in the M weight score sets according to N detection indexes in the first bearing detection index set to obtain N weight evaluation total scores;
and calculating the N total weight evaluation scores based on a first weight distribution formula to obtain a first weight distribution result.
4. The method of claim 3, wherein the first weight assignment module comprises M weight evaluation layers, comprising:
obtaining a first weight evaluation main body set according to the first bearing detection index set;
screening the first weight evaluation subject set according to the first bearing service information to obtain a second weight evaluation subject set;
obtaining historical quality detection data of the second weight evaluation subject set, and screening the historical quality detection data according to the first bearing service information to obtain matching historical quality detection data;
and constructing and training the matching historical quality detection data and identification information for identifying the weight score set as training data to obtain the weight evaluation layer.
5. The method of claim 1, wherein the obtaining first bearing quality inspection information based on the first set of bearing detection indicators comprises:
acquiring an image information set of a first bearing;
carrying out extreme value synthesis or average value synthesis on the image information set to obtain preprocessed image information;
performing semantic segmentation on the preprocessed image information to obtain a semantic segmented image;
obtaining the first quality inspection information based on the semantic segmentation image;
obtaining the second quality inspection information based on vibration detection;
and combining the first quality inspection information and the second quality inspection information to obtain the first bearing quality inspection information.
6. The method of claim 5, wherein said semantically segmenting said preprocessed image information to obtain semantically segmented images, comprises:
performing defect labeling on the preprocessed image information to obtain a labeled data set;
preprocessing the preprocessed image information and the labeled data set to obtain a training data set, a test data set and a verification data set;
training the constructed bearing semantic segmentation quality detection model by adopting the training data set, the test data set and the verification data set to obtain the bearing semantic segmentation quality detection model;
and inputting the preprocessed image information into the bearing semantic segmentation quality detection model, and performing bearing quality detection to obtain the semantic segmentation image.
7. The method of claim 1, wherein the constructing a first bearing quality assessment model comprises:
constructing a bearing quality evaluation function, and constructing the first hidden processing layer according to the bearing quality evaluation function;
obtaining a first bearing quality evaluation threshold;
constructing the second implicit processing layer according to the first bearing quality evaluation threshold;
obtaining the first bearing quality evaluation model based on the first implicit processing layer and the second implicit processing layer.
8. A bearing quality detection system based on intelligent manufacturing, the system comprising:
a first obtaining unit: the first obtaining unit is used for obtaining a first bearing detection index set;
a second obtaining unit: the second obtaining unit is used for obtaining service information of the first bearing;
a first building element: the first construction unit is used for constructing a first weight distribution module based on the first bearing detection index set;
a first input unit: the first input unit is used for inputting the first bearing detection index set and the first bearing service information into the first weight distribution module to obtain a first weight distribution result;
a first acquisition unit: the first acquisition unit is used for acquiring first bearing quality inspection information based on the first bearing detection index set, wherein the first bearing quality inspection information comprises first quality inspection information and second quality inspection information;
a second building element: the second construction unit is used for constructing a first bearing quality evaluation model, and the first bearing quality evaluation model comprises a first hidden processing layer and a second hidden processing layer;
a second input unit: the second input unit is used for inputting the first bearing quality inspection information and the first weight distribution result into the first bearing quality evaluation model to obtain a first bearing quality detection result.
9. An intelligent manufacturing-based bearing quality inspection apparatus comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method of any one of claims 1 to 7 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210715771.3A CN114782453A (en) | 2022-06-23 | 2022-06-23 | Bearing quality detection method and system based on intelligent manufacturing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210715771.3A CN114782453A (en) | 2022-06-23 | 2022-06-23 | Bearing quality detection method and system based on intelligent manufacturing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114782453A true CN114782453A (en) | 2022-07-22 |
Family
ID=82422469
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210715771.3A Pending CN114782453A (en) | 2022-06-23 | 2022-06-23 | Bearing quality detection method and system based on intelligent manufacturing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114782453A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116117587A (en) * | 2023-04-18 | 2023-05-16 | 济宁联威车轮制造有限公司 | Finished product quality detection system based on numerical control lathe generates |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104988278A (en) * | 2015-06-01 | 2015-10-21 | 北京科技大学 | Waste bearing steel relegation reuse method |
| CN110320038A (en) * | 2018-03-30 | 2019-10-11 | 大隈株式会社 | The abnormality diagnostic method and apparatus for diagnosis of abnormality of rolling bearing |
| NL2024358B1 (en) * | 2019-06-03 | 2020-12-08 | Univ Anhui Sci & Technology | Method for quantitatively evaluating dynamic quality of rolling bearing based on permutation entropy |
| CN112098090A (en) * | 2020-09-03 | 2020-12-18 | 中国铁道科学研究院集团有限公司金属及化学研究所 | Intelligent detection system for bearing of railway wagon wheel set |
| CN112287776A (en) * | 2020-10-15 | 2021-01-29 | 上海明略人工智能(集团)有限公司 | Bearing performance index analysis method and system, readable storage medium and electronic equipment |
| CN113252348A (en) * | 2021-05-13 | 2021-08-13 | 盾构及掘进技术国家重点实验室 | Dynamic performance test and evaluation method for main drive bearing of tunnel boring machine |
| CN113670616A (en) * | 2021-09-03 | 2021-11-19 | 苏州大学 | Bearing performance degradation state detection method and system |
-
2022
- 2022-06-23 CN CN202210715771.3A patent/CN114782453A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104988278A (en) * | 2015-06-01 | 2015-10-21 | 北京科技大学 | Waste bearing steel relegation reuse method |
| CN110320038A (en) * | 2018-03-30 | 2019-10-11 | 大隈株式会社 | The abnormality diagnostic method and apparatus for diagnosis of abnormality of rolling bearing |
| NL2024358B1 (en) * | 2019-06-03 | 2020-12-08 | Univ Anhui Sci & Technology | Method for quantitatively evaluating dynamic quality of rolling bearing based on permutation entropy |
| CN112098090A (en) * | 2020-09-03 | 2020-12-18 | 中国铁道科学研究院集团有限公司金属及化学研究所 | Intelligent detection system for bearing of railway wagon wheel set |
| CN112287776A (en) * | 2020-10-15 | 2021-01-29 | 上海明略人工智能(集团)有限公司 | Bearing performance index analysis method and system, readable storage medium and electronic equipment |
| CN113252348A (en) * | 2021-05-13 | 2021-08-13 | 盾构及掘进技术国家重点实验室 | Dynamic performance test and evaluation method for main drive bearing of tunnel boring machine |
| CN113670616A (en) * | 2021-09-03 | 2021-11-19 | 苏州大学 | Bearing performance degradation state detection method and system |
Non-Patent Citations (1)
| Title |
|---|
| 孟超等, 电子科技大学出版社 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116117587A (en) * | 2023-04-18 | 2023-05-16 | 济宁联威车轮制造有限公司 | Finished product quality detection system based on numerical control lathe generates |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ntirogiannis et al. | Performance evaluation methodology for historical document image binarization | |
| EP2528034B1 (en) | Image management device, image management method, program, recording medium, and integrated circuit | |
| CN106778687B (en) | Fixation point detection method based on local evaluation and global optimization | |
| CN110909820A (en) | Image classification method and system based on self-supervision learning | |
| WO2023000160A1 (en) | Hyperspectral remote sensing image semi-supervised classification method, apparatus, and device, and storage medium | |
| CN113360701B (en) | Sketch processing method and system based on knowledge distillation | |
| JP2006172437A (en) | Method for determining position of segment boundary in data stream, method for determining segment boundary by comparing data subset with vicinal data subset, program of instruction executable by computer, and system or device for identifying boundary and non-boundary in data stream | |
| CN111652869B (en) | Slab void identification method, system, medium and terminal based on deep learning | |
| CN111353373A (en) | Correlation alignment domain adaptive fault diagnosis method | |
| Lin et al. | Cascading convolutional neural network for steel surface defect detection | |
| CN111274926B (en) | Image data screening method, device, computer equipment and storage medium | |
| CN114782453A (en) | Bearing quality detection method and system based on intelligent manufacturing | |
| CN111814852A (en) | Image detection method, image detection device, electronic equipment and computer-readable storage medium | |
| CN116704208B (en) | Local interpretable method based on characteristic relation | |
| CN113762151A (en) | Fault data processing method and system and fault prediction method | |
| CN110705631B (en) | SVM-based bulk cargo ship equipment state detection method | |
| CN114255381B (en) | Training method of image recognition model, image recognition method, device and medium | |
| CN115953371A (en) | Insulator defect detection method, device, equipment and storage medium | |
| CN115690431A (en) | Bar code image binarization method and device, storage medium and computer equipment | |
| Niu et al. | Learning Trustworthy Model from Noisy Labels based on Rough Set for Surface Defect Detection | |
| CN118043753A (en) | System and method for estimating remaining useful life of bearing | |
| Wang et al. | Wear debris classification and quantity and size calculation using convolutional neural network | |
| CN111597934A (en) | System and method for processing training data for statistical applications | |
| CN115019400B (en) | Illegal behavior detection method and device | |
| CN115294489B (en) | Semantic segmentation method and system for disaster video data |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220722 |
|
| RJ01 | Rejection of invention patent application after publication |