CN113793332A - Experimental instrument defect identification and classification method and system - Google Patents
Experimental instrument defect identification and classification method and system Download PDFInfo
- Publication number
- CN113793332A CN113793332A CN202111344664.6A CN202111344664A CN113793332A CN 113793332 A CN113793332 A CN 113793332A CN 202111344664 A CN202111344664 A CN 202111344664A CN 113793332 A CN113793332 A CN 113793332A
- Authority
- CN
- China
- Prior art keywords
- defect
- information
- experimental instrument
- defects
- experimental
- 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.)
- Granted
Links
- 230000007547 defect Effects 0.000 title claims abstract description 483
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000001514 detection method Methods 0.000 claims abstract description 83
- 238000011156 evaluation Methods 0.000 claims abstract description 82
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 23
- 238000012549 training Methods 0.000 claims description 30
- 239000011159 matrix material Substances 0.000 claims description 16
- 238000012795 verification Methods 0.000 claims description 12
- 238000013507 mapping Methods 0.000 claims description 11
- 238000007781 pre-processing Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 8
- 238000007689 inspection Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 5
- 238000003709 image segmentation Methods 0.000 claims description 5
- 238000012847 principal component analysis method Methods 0.000 claims description 5
- 238000012360 testing method Methods 0.000 claims 2
- 239000000463 material Substances 0.000 description 16
- 238000011176 pooling Methods 0.000 description 6
- 238000010801 machine learning Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000004931 aggregating effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000013136 deep learning model Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 239000011521 glass Substances 0.000 description 2
- 210000005036 nerve Anatomy 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 229920003023 plastic Polymers 0.000 description 2
- 239000004033 plastic Substances 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000012827 research and development Methods 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- 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
- G06T2207/10132—Ultrasound image
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Quality & Reliability (AREA)
- Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)
Abstract
The invention discloses a method and a system for identifying and classifying defects of experimental instruments, which relate to the field of experimental instrument management and comprise the following steps: acquiring ultrasonic image information of an experimental instrument, establishing a defect detection model based on a convolutional neural network, judging whether the experimental instrument has defect information according to the defect detection model, and performing first classification; evaluating the experimental instrument containing the defects according to the defect information to generate an evaluation score, and determining defect grade information according to the evaluation score; performing second classification on the experimental instrument containing the defects according to the defect grade information, and generating defect label information according to a second classification result; and determining the service life of the experimental instrument containing the defects according to the defect grade information, and writing the service life information into the defect label information. In the invention, the defect detection and classification are carried out on the experimental instrument through the defect detection model, so that the potential danger caused by the internal defect of the experimental instrument is eliminated.
Description
Technical Field
The invention relates to the field of experimental instrument management, in particular to a method and a system for identifying and classifying defects of experimental instruments.
Background
Nowadays, with the continuous development of society, the technological level of people is continuously improved, and the experiment is one of necessary means for research and development, and during the experiment, a large amount of experimental instruments made of materials such as glass or plastics are needed. The defects such as cracks and deformities are usually generated in the use process of the experimental instrument made of materials such as glass or plastics and the like due to various reasons, and if the defects are not found in the first time, the experimental accidents are easily caused in the subsequent use process, so that the personal and property losses are caused, and therefore, the defect detection and classification of the experimental instrument in time in a laboratory are particularly important.
In order to realize defect detection identification and classification management of the experimental instrument, a system needs to be developed to be matched with the experimental instrument for realization, the system establishes a defect detection model based on a convolutional neural network by acquiring ultrasonic image information of the experimental instrument, and judges whether the experimental instrument has defect information according to the defect detection model to carry out first classification; evaluating the experimental instrument containing the defects according to the defect information to generate an evaluation score, and determining defect grade information according to the evaluation score; performing second classification on the experimental instrument containing the defects according to the defect grade information, and generating defect label information according to a second classification result; and determining the service life of the experimental instrument containing the defects according to the defect grade information. In the implementation process of the system, how to detect the defects of the experimental instrument through the defect detection model is an urgent problem which needs to be solved.
Disclosure of Invention
In order to solve the technical problems, the invention provides a method and a system for identifying and classifying defects of experimental instruments.
The invention provides a method for identifying and classifying defects of experimental instruments in a first aspect, which comprises the following steps:
acquiring ultrasonic image information of an experimental instrument, and preprocessing the ultrasonic image information;
establishing a defect detection model based on a convolutional neural network, judging whether the experimental instrument has defect information according to the defect detection model, and performing first classification on the experimental instrument according to a judgment result;
evaluating the experimental instrument containing the defects according to the defect information to generate an evaluation score, and determining defect grade information according to the evaluation score;
performing second classification on the experimental instrument containing the defects according to the defect grade information, and generating defect label information according to a second classification result;
and determining the service life of the experimental instrument containing the defects according to the defect grade information, and writing the service life information into the defect label information.
In this scheme, the ultrasonic image information of the experimental instrument is obtained, and the ultrasonic image information is preprocessed, specifically:
filtering and denoising the ultrasonic image information, and performing image enhancement on the denoised ultrasonic image information to obtain an enhanced ultrasonic image;
carrying out image segmentation on the enhanced ultrasonic image information, and carrying out binarization processing to obtain preprocessed ultrasonic image information;
acquiring image characteristics according to the preprocessed ultrasonic image information, wherein the image characteristics comprise a gray level co-occurrence matrix and a geometric invariant matrix;
and converting the image characteristics into a low-dimensional data set by using a principal component analysis method, and constructing a sample data set for identifying the defects of the experimental instrument according to the low-dimensional data set.
In this scheme, a defect detection model is established based on a convolutional neural network, and the experimental instruments are subjected to a first classification through the defect detection model, specifically:
acquiring a sample data set for identifying defects of the experimental instrument, taking 70% of sample data in the sample data set as a training set, and performing a verification set on 30% of sample data;
constructing a defect detection model based on a Tensorflow framework, and inputting ultrasonic image information of each experimental instrument in a training set into a convolutional neural network training classifier;
classifying through a trained classifier to generate a classification result, carrying out accuracy inspection according to the classification result, and calculating the deviation rate of the classification result and sample data in a verification set;
judging whether the deviation rate is smaller than a preset deviation rate threshold value or not, if so, proving that the precision of the classifier meets a preset standard, and outputting a defect detection model;
and judging whether the experimental instrument has defects through the defect detection model, and performing first classification on the experimental instrument according to the judgment result.
In this scheme, still include:
obtaining an ultrasonic image data set of the experimental instrument containing the defect according to the classification result of the first classification, obtaining a defect image target area, and obtaining defect contour characteristics through the defect image target area;
and acquiring the size of an image pixel according to the defect contour feature, and acquiring the size information of the defect according to the mapping relation between the size of the image pixel and the actual proportion.
In this scheme, the evaluating the experimental instrument with defects according to the defect information to generate an evaluation score, and determining the defect grade information according to the evaluation score specifically includes:
constructing an evaluation index system of the defect, extracting a defect evaluation index through the evaluation index system, and acquiring the defect attribute of the experimental instrument according to the defect information;
determining index score information of a defect evaluation index according to the defect attribute, and calculating weight information of the evaluation index according to an analytic hierarchy process;
obtaining an evaluation score of the experimental instrument with defects according to the index score information and the weight information;
presetting a defect grade division standard, and determining defect grade information of the experimental instrument according to the range of the interval within which the evaluation score falls;
the defect grades are divided into fine defects, micro defects, general defects, and severe defects.
In this embodiment, the determining the service life of the experimental apparatus having the defect according to the defect level information, and writing the service life information into the defect label information specifically includes:
presetting a defect grade threshold, comparing the defect grade of the experimental instrument containing the defects with the defect grade threshold, and judging whether the defect grade information is smaller than the preset threshold;
if the defect size information is smaller than or equal to the defect size information, extracting the defect size information of the experimental instrument according to the defect information, acquiring defect increment information according to historical defect information, and matching the defect increment information with the average use frequency to generate an increment curve;
acquiring the service life of the experimental instrument with the defects according to the incremental curve, writing the service life information into the defect label information, and performing scrap early warning according to a preset mode;
and if the defect is larger than the preset value, marking the scrapped laboratory instrument with the defect.
The second aspect of the present invention also provides a system for identifying and classifying defects of laboratory instruments, which comprises: the defect identification and classification method program of the experimental instrument is executed by the processor to realize the following steps:
acquiring ultrasonic image information of an experimental instrument, and preprocessing the ultrasonic image information;
establishing a defect detection model based on a convolutional neural network, judging whether the experimental instrument has defect information according to the defect detection model, and performing first classification on the experimental instrument according to a judgment result;
evaluating the experimental instrument containing the defects according to the defect information to generate an evaluation score, and determining defect grade information according to the evaluation score;
performing second classification on the experimental instrument containing the defects according to the defect grade information, and generating defect label information according to a second classification result;
and determining the service life of the experimental instrument containing the defects according to the defect grade information, and writing the service life information into the defect label information.
In this scheme, the ultrasonic image information of the experimental instrument is obtained, and the ultrasonic image information is preprocessed, specifically:
filtering and denoising the ultrasonic image information, and performing image enhancement on the denoised ultrasonic image information to obtain an enhanced ultrasonic image;
carrying out image segmentation on the enhanced ultrasonic image information, and carrying out binarization processing to obtain preprocessed ultrasonic image information;
acquiring image characteristics according to the preprocessed ultrasonic image information, wherein the image characteristics comprise a gray level co-occurrence matrix and a geometric invariant matrix;
and converting the image characteristics into a low-dimensional data set by using a principal component analysis method, and constructing a sample data set for identifying the defects of the experimental instrument according to the low-dimensional data set.
In this scheme, a defect detection model is established based on a convolutional neural network, and the experimental instruments are subjected to a first classification through the defect detection model, specifically:
acquiring a sample data set for identifying defects of the experimental instrument, taking 70% of sample data in the sample data set as a training set, and performing a verification set on 30% of sample data;
constructing a defect detection model based on a Tensorflow framework, and inputting ultrasonic image information of each experimental instrument in a training set into a convolutional neural network training classifier;
classifying through a trained classifier to generate a classification result, carrying out accuracy inspection according to the classification result, and calculating the deviation rate of the classification result and sample data in a verification set;
judging whether the deviation rate is smaller than a preset deviation rate threshold value or not, if so, proving that the precision of the classifier meets a preset standard, and outputting a defect detection model;
and judging whether the experimental instrument has defects through the defect detection model, and performing first classification on the experimental instrument according to the judgment result.
In this scheme, still include:
obtaining an ultrasonic image data set of the experimental instrument containing the defect according to the classification result of the first classification, obtaining a defect image target area, and obtaining defect contour characteristics through the defect image target area;
and acquiring the size of an image pixel according to the defect contour feature, and acquiring the size information of the defect according to the mapping relation between the size of the image pixel and the actual proportion.
In this scheme, the evaluating the experimental instrument with defects according to the defect information to generate an evaluation score, and determining the defect grade information according to the evaluation score specifically includes:
constructing an evaluation index system of the defect, extracting a defect evaluation index through the evaluation index system, and acquiring the defect attribute of the experimental instrument according to the defect information;
determining index score information of a defect evaluation index according to the defect attribute, and calculating weight information of the evaluation index according to an analytic hierarchy process;
obtaining an evaluation score of the experimental instrument with defects according to the index score information and the weight information;
presetting a defect grade division standard, and determining defect grade information of the experimental instrument according to the range of the interval within which the evaluation score falls;
the defect grades are divided into fine defects, micro defects, general defects, and severe defects.
In this embodiment, the determining the service life of the experimental apparatus having the defect according to the defect level information, and writing the service life information into the defect label information specifically includes:
presetting a defect grade threshold, comparing the defect grade of the experimental instrument containing the defects with the defect grade threshold, and judging whether the defect grade information is smaller than the preset threshold;
if the defect size information is smaller than or equal to the defect size information, extracting the defect size information of the experimental instrument according to the defect information, acquiring defect increment information according to historical defect information, and matching the defect increment information with the average use frequency to generate an increment curve;
acquiring the service life of the experimental instrument with the defects according to the incremental curve, writing the service life information into the defect label information, and performing scrap early warning according to a preset mode;
and if the defect is larger than the preset value, marking the scrapped laboratory instrument with the defect.
The invention discloses a method and a system for identifying and classifying defects of experimental instruments, which relate to the field of experimental instrument management, wherein the method for identifying and classifying the defects of the experimental instruments comprises the following steps: acquiring ultrasonic image information of an experimental instrument, establishing a defect detection model based on a convolutional neural network, judging whether the experimental instrument has defect information according to the defect detection model, and performing first classification; evaluating the experimental instrument containing the defects according to the defect information to generate an evaluation score, and determining defect grade information according to the evaluation score; performing second classification on the experimental instrument containing the defects according to the defect grade information, and generating defect label information according to a second classification result; and determining the service life of the experimental instrument containing the defects according to the defect grade information, and writing the service life information into the defect label information. In the invention, the defect detection and classification are carried out on the experimental instrument through the defect detection model, so that the potential danger caused by the internal defect of the experimental instrument is eliminated.
Drawings
FIG. 1 is a flow chart of a method for identifying and classifying defects of a laboratory instrument according to the present invention;
FIG. 2 is a flow chart of a method of establishing a defect detection model for a first classification according to the present invention;
FIG. 3 is a flow chart illustrating a method of determining laboratory instrument defect level information based on an evaluation score according to the present invention;
FIG. 4 is a block diagram of a system for identifying and classifying defects of laboratory instruments according to the present invention.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described herein, and therefore the scope of the present invention is not limited by the specific embodiments disclosed below.
FIG. 1 is a flow chart of a method for identifying and classifying defects of a laboratory instrument according to the present invention.
As shown in fig. 1, a first aspect of the present invention provides a method for identifying and classifying defects of a laboratory instrument, including:
s102, acquiring ultrasonic image information of an experimental instrument, and preprocessing the ultrasonic image information;
s104, establishing a defect detection model based on the convolutional neural network, judging whether the experimental instrument has defect information according to the defect detection model, and performing first classification on the experimental instrument according to the judgment result;
s106, evaluating the experimental instrument with the defects according to the defect information to generate an evaluation score, and determining defect grade information according to the evaluation score;
s108, performing second classification on the experimental instrument with the defects according to the defect grade information, and generating defect label information according to a second classification result;
and S110, determining the service life of the experimental instrument containing the defects according to the defect grade information, and writing the service life information into the defect label information.
It should be noted that, the acquiring of the ultrasonic image information of the experimental apparatus and the preprocessing of the ultrasonic image information specifically include:
filtering and denoising the ultrasonic image information, and performing image enhancement on the denoised ultrasonic image information to obtain an enhanced ultrasonic image;
carrying out image segmentation on the enhanced ultrasonic image information, and carrying out binarization processing to obtain preprocessed ultrasonic image information;
acquiring image characteristics according to the preprocessed ultrasonic image information, wherein the image characteristics comprise a gray level co-occurrence matrix and a geometric invariant matrix;
and converting the image characteristics into a low-dimensional data set by using a principal component analysis method, and constructing a sample data set for identifying the defects of the experimental instrument according to the low-dimensional data set.
FIG. 2 is a flow chart of a method for establishing a defect detection model for a first classification according to the present invention.
According to the embodiment of the invention, a defect detection model is established based on a convolutional neural network, and the experimental instruments are subjected to first classification through the defect detection model, specifically:
s202, acquiring a sample data set for identifying defects of the experimental instrument, taking 70% of sample data in the sample data set as a training set, and performing a verification set on 30% of sample data;
s204, constructing a defect detection model based on a Tensorflow framework, and inputting ultrasonic image information of each experimental instrument in a training set into a convolutional neural network training classifier;
s206, classifying through a trained classifier to generate a classification result, carrying out accuracy inspection according to the classification result, and calculating the deviation rate of the classification result and sample data in a verification set;
s208, judging whether the deviation rate is smaller than a preset deviation rate threshold value or not, if so, proving that the precision of the classifier meets a preset standard, and outputting a defect detection model;
s210, judging whether the experimental instrument has defects through the defect detection model, and carrying out first classification on the experimental instrument according to the judgment result.
The defect detection model is constructed based on a Tensorflow framework, the Tensorflow is a Google open-source machine learning framework based on a data flow graph, the Tensorflow is widely used in the field of intelligent machine learning such as image recognition and voice, and supports various mainstream deep learning models such as CNN, RNN and LSTM. The size of an input ultrasonic image is adjusted through an input layer, different numbers of convolution layers and pooling layers are arranged in a defect detection model, defect detection models with different depths are built, a convolution kernel of 3 x 3 is used in each convolution layer, the convolution step length is 1, 512 nerve units are arranged in a full-connection layer, an output vector is calculated through a Softmax function, and a classification result is obtained.
The method includes inputting a training set into a defect detection model, performing convolution calculation and maximum pooling on image data input into the defect detection model by using an initial convolution kernel and an initial bias matrix of each convolution layer in the defect detection model to obtain a first feature image of sample data in the training set, performing pooling operation on the first feature image of the obtained sample data again to obtain a second feature image of the sample data, determining a feature vector of each sample data according to the second feature image of the sample data in the training set, processing the obtained feature vector through the initial bias matrix and the initial weight matrix to obtain a classification vector of the sample data in the training set, calculating to obtain a category error according to the classification vector of the sample data in the training set and an initial category of each sample data, performing correlation adjustment on the convolution kernel of the defect detection model according to the obtained category error, and continuously adjusting relevant parameters of the defect detection model according to the plurality of sample data and the adjusted convolution kernel parameters, and performing multiple iterations until the error reaches an ideal value and then stopping training the defect detection model.
It should be noted that, acquiring the defect size information of the experimental instrument specifically includes:
obtaining an ultrasonic image data set of the experimental instrument containing the defect according to the classification result of the first classification, obtaining a defect image target area, and obtaining defect contour characteristics through the defect image target area;
and acquiring the size of an image pixel according to the defect contour feature, and acquiring the size information of the defect according to the mapping relation between the size of the image pixel and the actual proportion.
FIG. 3 is a flow chart illustrating a method for determining laboratory instrument defect level information based on the evaluation score according to the present invention.
According to the embodiment of the invention, the evaluating the experimental instrument containing the defect according to the defect information to generate the evaluation score, and determining the defect grade information according to the evaluation score specifically comprises the following steps:
s302, constructing an evaluation index system of the defect, extracting a defect evaluation index through the evaluation index system, and acquiring the defect attribute of the experimental instrument according to the defect information;
s304, determining index score information of a defect evaluation index according to the defect attribute, and calculating weight information of the evaluation index according to an analytic hierarchy process;
s306, obtaining the evaluation score of the experimental instrument with defects according to the index score information and the weight information;
s308, presetting a defect grade division standard, and determining defect grade information of the experimental instrument according to the range of the interval within which the evaluation score falls;
the defect grades are divided into fine defects, micro defects, general defects, and severe defects.
It should be noted that the formula for calculating the evaluation score of the experimental instrument with defects specifically includes:
wherein the content of the first and second substances,
an evaluation score of the laboratory instrument containing the defect is represented,
the number of the evaluation indexes is shown,
the information of the mark score is represented,
weight information indicating an evaluation index.
It should be noted that, the determining the service life of the experimental instrument containing the defect according to the defect level information, and writing the service life information into the defect label information specifically includes:
presetting a defect grade threshold, comparing the defect grade of the experimental instrument containing the defects with the defect grade threshold, and judging whether the defect grade information is smaller than the preset threshold;
if the defect size information is smaller than or equal to the defect size information, extracting the defect size information of the experimental instrument according to the defect information, acquiring defect increment information according to historical defect information, and matching the defect increment information with the average use frequency to generate an increment curve;
acquiring the service life of the experimental instrument with the defects according to the incremental curve, writing the service life information into the defect label information, and performing scrap early warning according to a preset mode;
and if the defect is larger than the preset value, marking the scrapped laboratory instrument with the defect.
According to the embodiment of the invention, the method further comprises the steps of obtaining material information of the experimental instrument to be detected according to the ultrasonic wave, and judging the service life of the experimental instrument to be detected according to the material information, wherein the steps are as follows:
acquiring ultrasonic curve information of an experimental instrument to be detected, and extracting curve characteristics of the ultrasonic curve;
establishing an index tag according to the curve characteristics, and establishing retrieval in an ultrasonic waveform database according to the index tag by a big data analysis method;
calculating the matching degree of the waveform data of the ultrasonic waveform database and the index tag, presetting a matching degree threshold value, and marking the waveform data if the matching degree is greater than the matching degree threshold value;
aggregating the marked waveform data to generate a waveform data set, and calculating the matching degree score of each waveform data in the waveform data set;
taking material information corresponding to the waveform data with the highest matching degree score as material information of the experimental instrument to be detected;
and acquiring material characteristics according to the material information, and calculating the service life of the experimental instrument containing the defects according to the matching of the material characteristics, the defect size information and the use frequency.
According to the embodiment of the invention, a laboratory instrument management database is established, the use information and the defect information of the laboratory instrument are stored in the laboratory instrument management database, and scrap early warning is carried out through the laboratory instrument management database, which specifically comprises the following steps:
setting identity label information of the experimental instrument, generating a mapping relation between the identity label information and detection identification data of the defect detection model, and matching use information of the experimental instrument with the mapping relation;
establishing a laboratory instrument management database, and storing the mapping relation according to a time sequence;
if the experimental instrument requested by the user has defect information, generating defect reminding information and use notice by the experimental instrument management database, and displaying the defect reminding information and the use notice according to a preset mode;
meanwhile, the experimental instrument management data updates the service life of the experimental instrument according to the detection identification result and the use information of the defect detection model and carries out early warning, and when the service life of the experimental instrument is smaller than a preset service life threshold value, the experimental instrument is marked to be scrapped;
the usage information of the experimental instrument comprises usage duration information and experimental project information, and the usage duration information is acquired by lending registration time and warehousing registration time.
FIG. 4 is a block diagram of a system for identifying and classifying defects of laboratory instruments according to the present invention.
The second aspect of the present invention also provides a system 4 for identifying and classifying defects of laboratory instruments, which comprises: a memory 41 and a processor 42, wherein the memory includes a program for a defect identification and classification method of a laboratory instrument, and the program for the defect identification and classification method of the laboratory instrument realizes the following steps when being executed by the processor:
acquiring ultrasonic image information of an experimental instrument, and preprocessing the ultrasonic image information;
establishing a defect detection model based on a convolutional neural network, judging whether the experimental instrument has defect information according to the defect detection model, and performing first classification on the experimental instrument according to a judgment result;
evaluating the experimental instrument containing the defects according to the defect information to generate an evaluation score, and determining defect grade information according to the evaluation score;
performing second classification on the experimental instrument containing the defects according to the defect grade information, and generating defect label information according to a second classification result;
and determining the service life of the experimental instrument containing the defects according to the defect grade information, and writing the service life information into the defect label information.
It should be noted that, the acquiring of the ultrasonic image information of the experimental apparatus and the preprocessing of the ultrasonic image information specifically include:
filtering and denoising the ultrasonic image information, and performing image enhancement on the denoised ultrasonic image information to obtain an enhanced ultrasonic image;
carrying out image segmentation on the enhanced ultrasonic image information, and carrying out binarization processing to obtain preprocessed ultrasonic image information;
acquiring image characteristics according to the preprocessed ultrasonic image information, wherein the image characteristics comprise a gray level co-occurrence matrix and a geometric invariant matrix;
and converting the image characteristics into a low-dimensional data set by using a principal component analysis method, and constructing a sample data set for identifying the defects of the experimental instrument according to the low-dimensional data set.
According to the embodiment of the invention, a defect detection model is established based on a convolutional neural network, and the experimental instruments are subjected to first classification through the defect detection model, specifically:
acquiring a sample data set for identifying defects of the experimental instrument, taking 70% of sample data in the sample data set as a training set, and performing a verification set on 30% of sample data;
constructing a defect detection model based on a Tensorflow framework, and inputting ultrasonic image information of each experimental instrument in a training set into a convolutional neural network training classifier;
classifying through a trained classifier to generate a classification result, carrying out accuracy inspection according to the classification result, and calculating the deviation rate of the classification result and sample data in a verification set;
judging whether the deviation rate is smaller than a preset deviation rate threshold value or not, if so, proving that the precision of the classifier meets a preset standard, and outputting a defect detection model;
and judging whether the experimental instrument has defects through the defect detection model, and performing first classification on the experimental instrument according to the judgment result.
The defect detection model is constructed based on a Tensorflow framework, the Tensorflow is a Google open-source machine learning framework based on a data flow graph, the Tensorflow is widely used in the field of intelligent machine learning such as image recognition and voice, and supports various mainstream deep learning models such as CNN, RNN and LSTM. The size of an input ultrasonic image is adjusted through an input layer, different numbers of convolution layers and pooling layers are arranged in a defect detection model, defect detection models with different depths are built, a convolution kernel of 3 x 3 is used in each convolution layer, the convolution step length is 1, 512 nerve units are arranged in a full-connection layer, an output vector is calculated through a Softmax function, and a classification result is obtained.
The method includes inputting a training set into a defect detection model, performing convolution calculation and maximum pooling on image data input into the defect detection model by using an initial convolution kernel and an initial bias matrix of each convolution layer in the defect detection model to obtain a first feature image of sample data in the training set, performing pooling operation on the first feature image of the obtained sample data again to obtain a second feature image of the sample data, determining a feature vector of each sample data according to the second feature image of the sample data in the training set, processing the obtained feature vector through the initial bias matrix and the initial weight matrix to obtain a classification vector of the sample data in the training set, calculating to obtain a category error according to the classification vector of the sample data in the training set and an initial category of each sample data, performing correlation adjustment on the convolution kernel of the defect detection model according to the obtained category error, and continuously adjusting relevant parameters of the defect detection model according to the plurality of sample data and the adjusted convolution kernel parameters, and performing multiple iterations until the error reaches an ideal value and then stopping training the defect detection model.
It should be noted that, acquiring the defect size information of the experimental instrument specifically includes:
obtaining an ultrasonic image data set of the experimental instrument containing the defect according to the classification result of the first classification, obtaining a defect image target area, and obtaining defect contour characteristics through the defect image target area;
and acquiring the size of an image pixel according to the defect contour feature, and acquiring the size information of the defect according to the mapping relation between the size of the image pixel and the actual proportion.
According to the embodiment of the invention, the evaluating the experimental instrument containing the defect according to the defect information to generate the evaluation score, and determining the defect grade information according to the evaluation score specifically comprises the following steps:
constructing an evaluation index system of the defect, extracting a defect evaluation index through the evaluation index system, and acquiring the defect attribute of the experimental instrument according to the defect information;
determining index score information of a defect evaluation index according to the defect attribute, and calculating weight information of the evaluation index according to an analytic hierarchy process;
obtaining an evaluation score of the experimental instrument with defects according to the index score information and the weight information;
presetting a defect grade division standard, and determining defect grade information of the experimental instrument according to the range of the interval within which the evaluation score falls;
the defect grades are divided into fine defects, micro defects, general defects, and severe defects.
It should be noted that the formula for calculating the evaluation score of the experimental instrument with defects specifically includes:
wherein the content of the first and second substances,
an evaluation score of the laboratory instrument containing the defect is represented,
the number of the evaluation indexes is shown,
the information of the mark score is represented,
weight information indicating an evaluation index.
It should be noted that, the determining the service life of the experimental instrument containing the defect according to the defect level information, and writing the service life information into the defect label information specifically includes:
presetting a defect grade threshold, comparing the defect grade of the experimental instrument containing the defects with the defect grade threshold, and judging whether the defect grade information is smaller than the preset threshold;
if the defect size information is smaller than or equal to the defect size information, extracting the defect size information of the experimental instrument according to the defect information, acquiring defect increment information according to historical defect information, and matching the defect increment information with the average use frequency to generate an increment curve;
acquiring the service life of the experimental instrument with the defects according to the incremental curve, writing the service life information into the defect label information, and performing scrap early warning according to a preset mode;
and if the defect is larger than the preset value, marking the scrapped laboratory instrument with the defect.
According to the embodiment of the invention, the method further comprises the steps of obtaining material information of the experimental instrument to be detected according to the ultrasonic wave, and judging the service life of the experimental instrument to be detected according to the material information, wherein the steps are as follows:
acquiring ultrasonic curve information of an experimental instrument to be detected, and extracting curve characteristics of the ultrasonic curve;
establishing an index tag according to the curve characteristics, and establishing retrieval in an ultrasonic waveform database according to the index tag by a big data analysis method;
calculating the matching degree of the waveform data of the ultrasonic waveform database and the index tag, presetting a matching degree threshold value, and marking the waveform data if the matching degree is greater than the matching degree threshold value;
aggregating the marked waveform data to generate a waveform data set, and calculating the matching degree score of each waveform data in the waveform data set;
taking material information corresponding to the waveform data with the highest matching degree score as material information of the experimental instrument to be detected;
and acquiring material characteristics according to the material information, and calculating the service life of the experimental instrument containing the defects according to the matching of the material characteristics, the defect size information and the use frequency.
According to the embodiment of the invention, a laboratory instrument management database is established, the use information and the defect information of the laboratory instrument are stored in the laboratory instrument management database, and scrap early warning is carried out through the laboratory instrument management database, which specifically comprises the following steps:
setting identity label information of the experimental instrument, generating a mapping relation between the identity label information and detection identification data of the defect detection model, and matching use information of the experimental instrument with the mapping relation;
establishing a laboratory instrument management database, and storing the mapping relation according to a time sequence;
if the experimental instrument requested by the user has defect information, generating defect reminding information and use notice by the experimental instrument management database, and displaying the defect reminding information and the use notice according to a preset mode;
meanwhile, the experimental instrument management data updates the service life of the experimental instrument according to the detection identification result and the use information of the defect detection model and carries out early warning, and when the service life of the experimental instrument is smaller than a preset service life threshold value, the experimental instrument is marked to be scrapped;
the usage information of the experimental instrument comprises usage duration information and experimental project information, and the usage duration information is acquired by lending registration time and warehousing registration time.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described device embodiments are merely illustrative, for example, the division of the unit is only a logical functional division, and there may be other division ways in actual implementation, such as: multiple units or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or units may be electrical, mechanical or other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units; can be located in one place or distributed on a plurality of network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, all the functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately regarded as one unit, or two or more units may be integrated into one unit; the integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
Those of ordinary skill in the art will understand that: all or part of the steps for realizing the method embodiments can be completed by hardware related to program instructions, the program can be stored in a computer readable storage medium, and the program executes the steps comprising the method embodiments when executed; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Alternatively, the integrated unit of the present invention may be stored in a computer-readable storage medium if it is implemented in the form of a software functional module and sold or used as a separate product. Based on such understanding, the technical solutions of the embodiments of the present invention may be essentially implemented or a part contributing to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, a ROM, a RAM, a magnetic or optical disk, or various other media that can store program code.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (10)
1. A defect identification and classification method for experimental instruments is characterized by comprising the following steps:
acquiring ultrasonic image information of an experimental instrument, and preprocessing the ultrasonic image information;
establishing a defect detection model based on a convolutional neural network, judging whether the experimental instrument has defect information according to the defect detection model, and performing first classification on the experimental instrument according to a judgment result;
evaluating the experimental instrument containing the defects according to the defect information to generate an evaluation score, and determining defect grade information according to the evaluation score;
performing second classification on the experimental instrument containing the defects according to the defect grade information, and generating defect label information according to a second classification result;
and determining the service life of the experimental instrument containing the defects according to the defect grade information, and writing the service life information into the defect label information.
2. The method for identifying and classifying defects of laboratory instruments according to claim 1, wherein the step of obtaining ultrasonic image information of the laboratory instruments and preprocessing the ultrasonic image information comprises:
filtering and denoising the ultrasonic image information, and performing image enhancement on the denoised ultrasonic image information to obtain an enhanced ultrasonic image;
carrying out image segmentation on the enhanced ultrasonic image information, and carrying out binarization processing to obtain preprocessed ultrasonic image information;
acquiring image characteristics according to the preprocessed ultrasonic image information, wherein the image characteristics comprise a gray level co-occurrence matrix and a geometric invariant matrix;
and converting the image characteristics into a low-dimensional data set by using a principal component analysis method, and constructing a sample data set for identifying the defects of the experimental instrument according to the low-dimensional data set.
3. The method for identifying and classifying the defects of the experimental instruments according to claim 1, wherein a defect detection model is established based on a convolutional neural network, and the experimental instruments are subjected to a first classification through the defect detection model, specifically:
acquiring a sample data set for identifying defects of the experimental instrument, taking 70% of sample data in the sample data set as a training set, and performing a verification set on 30% of sample data;
constructing a defect detection model based on a Tensorflow framework, and inputting ultrasonic image information of each experimental instrument in a training set into a convolutional neural network training classifier;
classifying through a trained classifier to generate a classification result, carrying out accuracy inspection according to the classification result, and calculating the deviation rate of the classification result and sample data in a verification set;
judging whether the deviation rate is smaller than a preset deviation rate threshold value or not, if so, proving that the precision of the classifier meets a preset standard, and outputting a defect detection model;
and judging whether the experimental instrument has defects through the defect detection model, and performing first classification on the experimental instrument according to the judgment result.
4. The method for identifying and classifying defects of laboratory instruments according to claim 3, further comprising:
obtaining an ultrasonic image data set of the experimental instrument containing the defect according to the classification result of the first classification, obtaining a defect image target area, and obtaining defect contour characteristics through the defect image target area;
and acquiring the size of an image pixel according to the defect contour feature, and acquiring the size information of the defect according to the mapping relation between the size of the image pixel and the actual proportion.
5. The method for identifying and classifying the defects of the experimental instrument as claimed in claim 1, wherein the experimental instrument with the defects is evaluated according to the defect information to generate an evaluation score, and the defect grade information is determined according to the evaluation score, specifically:
constructing an evaluation index system of the defect, extracting a defect evaluation index through the evaluation index system, and acquiring the defect attribute of the experimental instrument according to the defect information;
determining index score information of a defect evaluation index according to the defect attribute, and calculating weight information of the evaluation index according to an analytic hierarchy process;
obtaining an evaluation score of the experimental instrument with defects according to the index score information and the weight information;
presetting a defect grade division standard, and determining defect grade information of the experimental instrument according to the range of the interval within which the evaluation score falls;
the defect grades are divided into fine defects, micro defects, general defects, and severe defects.
6. The method as claimed in claim 1, wherein the step of determining the lifetime of the testing apparatus having the defect according to the defect class information and writing the lifetime information into the defect label information comprises:
presetting a defect grade threshold, comparing the defect grade of the experimental instrument containing the defects with the defect grade threshold, and judging whether the defect grade information is smaller than the preset threshold;
if the defect size information is smaller than or equal to the defect size information, extracting the defect size information of the experimental instrument according to the defect information, acquiring defect increment information according to historical defect information, and matching the defect increment information with the average use frequency to generate an increment curve;
acquiring the service life of the experimental instrument with the defects according to the incremental curve, writing the service life information into the defect label information, and performing scrap early warning according to a preset mode;
and if the defect is larger than the preset value, marking the scrapped laboratory instrument with the defect.
7. A system for identifying and classifying defects of laboratory instruments, comprising: the memory comprises a program of a method for identifying and classifying defects of the experimental instrument, and the program of the method for identifying and classifying defects of the experimental instrument realizes the following steps when being executed by the processor:
acquiring ultrasonic image information of an experimental instrument, and preprocessing the ultrasonic image information;
establishing a defect detection model based on a convolutional neural network, judging whether the experimental instrument has defect information according to the defect detection model, and performing first classification on the experimental instrument according to a judgment result;
evaluating the experimental instrument containing the defects according to the defect information to generate an evaluation score, and determining defect grade information according to the evaluation score;
performing second classification on the experimental instrument containing the defects according to the defect grade information, and generating defect label information according to a second classification result;
and determining the service life of the experimental instrument containing the defects according to the defect grade information, and writing the service life information into the defect label information.
8. The system for identifying and classifying defects of laboratory instruments according to claim 7, wherein a defect detection model is established based on a convolutional neural network, and the laboratory instruments are classified by the defect detection model for the first time, specifically:
acquiring a sample data set for identifying defects of the experimental instrument, taking 70% of sample data in the sample data set as a training set, and performing a verification set on 30% of sample data;
constructing a defect detection model based on a Tensorflow framework, and inputting ultrasonic image information of each experimental instrument in a training set into a convolutional neural network training classifier;
classifying through a trained classifier to generate a classification result, carrying out accuracy inspection according to the classification result, and calculating the deviation rate of the classification result and sample data in a verification set;
judging whether the deviation rate is smaller than a preset deviation rate threshold value or not, if so, proving that the precision of the classifier meets a preset standard, and outputting a defect detection model;
and judging whether the experimental instrument has defects through the defect detection model, and performing first classification on the experimental instrument according to the judgment result.
9. The system of claim 7, wherein the laboratory instrument with defects is evaluated according to the defect information to generate an evaluation score, and the defect grade information is determined according to the evaluation score, and specifically comprises:
constructing an evaluation index system of the defect, extracting a defect evaluation index through the evaluation index system, and acquiring the defect attribute of the experimental instrument according to the defect information;
determining index score information of a defect evaluation index according to the defect attribute, and calculating weight information of the evaluation index according to an analytic hierarchy process;
obtaining an evaluation score of the experimental instrument with defects according to the index score information and the weight information;
presetting a defect grade division standard, and determining defect grade information of the experimental instrument according to the range of the interval within which the evaluation score falls;
the defect grades are divided into fine defects, micro defects, general defects, and severe defects.
10. The system as claimed in claim 7, wherein the step of determining the lifetime of the testing apparatus having the defect according to the defect class information and writing the lifetime information into the defect label information comprises:
presetting a defect grade threshold, comparing the defect grade of the experimental instrument containing the defects with the defect grade threshold, and judging whether the defect grade information is smaller than the preset threshold;
if the defect size information is smaller than or equal to the defect size information, extracting the defect size information of the experimental instrument according to the defect information, acquiring defect increment information according to historical defect information, and matching the defect increment information with the average use frequency to generate an increment curve;
acquiring the service life of the experimental instrument with the defects according to the incremental curve, writing the service life information into the defect label information, and performing scrap early warning according to a preset mode;
and if the defect is larger than the preset value, marking the scrapped laboratory instrument with the defect.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111344664.6A CN113793332B (en) | 2021-11-15 | 2021-11-15 | Experimental instrument defect identification and classification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111344664.6A CN113793332B (en) | 2021-11-15 | 2021-11-15 | Experimental instrument defect identification and classification method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113793332A true CN113793332A (en) | 2021-12-14 |
| CN113793332B CN113793332B (en) | 2022-02-08 |
Family
ID=78955151
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111344664.6A Active CN113793332B (en) | 2021-11-15 | 2021-11-15 | Experimental instrument defect identification and classification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113793332B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115586256A (en) * | 2022-12-09 | 2023-01-10 | 成都西交智汇大数据科技有限公司 | Method, device and equipment for detecting cleaning grade of experimental equipment and storage medium |
| CN115661762A (en) * | 2022-12-15 | 2023-01-31 | 山东德普检测技术有限公司 | Library environment intelligent monitoring management system and method |
| CN118169547A (en) * | 2024-05-13 | 2024-06-11 | 常州忆隆信息科技有限公司 | Single-use circuit detection method and system for electric anastomat |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108074231A (en) * | 2017-12-18 | 2018-05-25 | 浙江工业大学 | Magnetic sheet surface defect detection method based on convolutional neural network |
| CN108171707A (en) * | 2018-01-23 | 2018-06-15 | 武汉精测电子集团股份有限公司 | A kind of Mura defects level evaluation method and device based on deep learning |
| US20200175666A1 (en) * | 2017-06-14 | 2020-06-04 | Nikon-Trimble Co., Ltd. | Calculation system, calculation method, program, and target |
| CN112488983A (en) * | 2019-09-11 | 2021-03-12 | 中信戴卡股份有限公司 | Defect identification network obtaining method, defect identification method and grade determining method |
| CN112581001A (en) * | 2020-12-24 | 2021-03-30 | 成都安易迅科技有限公司 | Device evaluation method and device, electronic device and readable storage medium |
| CN113269727A (en) * | 2021-05-08 | 2021-08-17 | 深圳市深视创新科技有限公司 | Transparent glass material defect visual detection method |
| CN113269775A (en) * | 2021-06-11 | 2021-08-17 | 河南理工大学 | Defect detection method and device based on multi-scale feature fusion SSD |
-
2021
- 2021-11-15 CN CN202111344664.6A patent/CN113793332B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200175666A1 (en) * | 2017-06-14 | 2020-06-04 | Nikon-Trimble Co., Ltd. | Calculation system, calculation method, program, and target |
| CN108074231A (en) * | 2017-12-18 | 2018-05-25 | 浙江工业大学 | Magnetic sheet surface defect detection method based on convolutional neural network |
| CN108171707A (en) * | 2018-01-23 | 2018-06-15 | 武汉精测电子集团股份有限公司 | A kind of Mura defects level evaluation method and device based on deep learning |
| CN112488983A (en) * | 2019-09-11 | 2021-03-12 | 中信戴卡股份有限公司 | Defect identification network obtaining method, defect identification method and grade determining method |
| CN112581001A (en) * | 2020-12-24 | 2021-03-30 | 成都安易迅科技有限公司 | Device evaluation method and device, electronic device and readable storage medium |
| CN113269727A (en) * | 2021-05-08 | 2021-08-17 | 深圳市深视创新科技有限公司 | Transparent glass material defect visual detection method |
| CN113269775A (en) * | 2021-06-11 | 2021-08-17 | 河南理工大学 | Defect detection method and device based on multi-scale feature fusion SSD |
Non-Patent Citations (2)
| Title |
|---|
| DENYS HAVRYLIV ET AL.: "Defect detection on the surface of the technical ceramics using image processing and deep learning algorithms", 《2020 21ST INTERNATIONAL CONFERENCE ON RESEARCH AND EDUCATION IN MECHATRONICS (REM)》 * |
| 曹晓杰: "基于卷积神经网络的超声无损检测图像缺陷识别研究", 《中国优秀硕士学位论文全文数据库 (信息科技辑)》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115586256A (en) * | 2022-12-09 | 2023-01-10 | 成都西交智汇大数据科技有限公司 | Method, device and equipment for detecting cleaning grade of experimental equipment and storage medium |
| CN115661762A (en) * | 2022-12-15 | 2023-01-31 | 山东德普检测技术有限公司 | Library environment intelligent monitoring management system and method |
| CN118169547A (en) * | 2024-05-13 | 2024-06-11 | 常州忆隆信息科技有限公司 | Single-use circuit detection method and system for electric anastomat |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113793332B (en) | 2022-02-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113793332B (en) | Experimental instrument defect identification and classification method and system | |
| CN113159147B (en) | Image recognition method and device based on neural network and electronic equipment | |
| CN109284372B (en) | User operation behavior analysis method, electronic device and computer readable storage medium | |
| Ahmadi et al. | An integrated machine learning model for automatic road crack detection and classification in urban areas | |
| CN117152123B (en) | Detection positioning optimization method, system and storage medium for solder paste printing | |
| CN106372624A (en) | Human face recognition method and human face recognition system | |
| CN112765003B (en) | Risk prediction method based on APP behavior log | |
| CN112270596A (en) | Risk control system and method based on user portrait construction | |
| CN114694178A (en) | Method and system for monitoring safety helmet in power operation based on fast-RCNN algorithm | |
| CN117011274A (en) | Automatic glass bottle detection system and method thereof | |
| CN115393351A (en) | Method and device for judging cornea immune state based on Langerhans cells | |
| CN114462469A (en) | Training method of target detection model, target detection method and related device | |
| CN111488927B (en) | Classification threshold determining method, device, electronic equipment and storage medium | |
| CN112990792A (en) | Method and device for automatically detecting infringement risk and electronic equipment | |
| CN111784053A (en) | Transaction risk detection method, device and readable storage medium | |
| CN117235608A (en) | Risk detection method, risk detection device, electronic equipment and storage medium | |
| CN110543910A (en) | Credit state monitoring system and monitoring method | |
| CN113177603B (en) | Training method of classification model, video classification method and related equipment | |
| Zhang et al. | A YOLOv3‐Based Industrial Instrument Classification and Reading Recognition Method | |
| CN116245630A (en) | Anti-fraud detection method and device, electronic equipment and medium | |
| CN109190489A (en) | A kind of abnormal face detecting method based on reparation autocoder residual error | |
| CN109840479B (en) | Health state matching method and device | |
| CN114462510A (en) | Equipment classification method and system for precise protection of Internet of things | |
| CN113239031A (en) | Big data denoising processing method | |
| CN113515771A (en) | Data sensitivity determination method, electronic device, and computer-readable storage medium |
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 |