CN116699243B - Intelligent analysis method and system for antistatic product performance - Google Patents
Intelligent analysis method and system for antistatic product performance Download PDFInfo
- Publication number
- CN116699243B CN116699243B CN202310667167.2A CN202310667167A CN116699243B CN 116699243 B CN116699243 B CN 116699243B CN 202310667167 A CN202310667167 A CN 202310667167A CN 116699243 B CN116699243 B CN 116699243B
- Authority
- CN
- China
- Prior art keywords
- product
- antistatic
- flatness
- coefficient
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 119
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 19
- 238000010521 absorption reaction Methods 0.000 claims abstract description 18
- 238000001514 detection method Methods 0.000 claims abstract description 11
- 238000000034 method Methods 0.000 claims abstract description 11
- 238000012360 testing method Methods 0.000 claims abstract description 10
- 238000004364 calculation method Methods 0.000 claims description 29
- 238000012549 training Methods 0.000 claims description 20
- 238000012795 verification Methods 0.000 claims description 12
- 238000013527 convolutional neural network Methods 0.000 claims description 10
- 238000010276 construction Methods 0.000 claims description 4
- 230000006870 function Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/30—Measuring arrangements characterised by the use of optical techniques for measuring roughness or irregularity of surfaces
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N13/00—Investigating surface or boundary effects, e.g. wetting power; Investigating diffusion effects; Analysing materials by determining surface, boundary, or diffusion effects
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R27/00—Arrangements for measuring resistance, reactance, impedance, or electric characteristics derived therefrom
- G01R27/02—Measuring real or complex resistance, reactance, impedance, or other two-pole characteristics derived therefrom, e.g. time constant
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/53—Querying
- G06F16/532—Query formulation, e.g. graphical querying
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The application relates to the technical field of product detection, and provides an intelligent analysis method and system for antistatic product performance, comprising the following steps: obtaining the surface resistance value of a target antistatic product; grading the antistatic performance to obtain an antistatic coefficient; performing multi-angle image acquisition, and inputting an image acquisition result into a surface flatness analysis model to obtain a flatness analysis result; performing a water absorption expansion test to obtain a moisture resistance coefficient; initial weight distribution is carried out on antistatic performance, flatness and moisture resistance according to a product expert system; weighting and calculating an antistatic coefficient, a flatness coefficient and a moisture-proof coefficient to obtain a coefficient of performance; and (5) carrying out level division to obtain the target antistatic product level. The method can solve the problem that the traditional antistatic product performance analysis method has lower accuracy of product performance analysis due to the fact that indexes are too single, and can improve the accuracy of product performance analysis by comprehensively analyzing multiple performance indexes of a target antistatic product.
Description
Technical Field
The application relates to the technical field of product detection, in particular to an intelligent analysis method and system for antistatic product performance.
Background
The antistatic floor is also called a dissipation static floor, and when the antistatic floor is grounded or connected to any lower potential point, charges can be dissipated, and the antistatic floor can play a role in antistatic, and is widely applied to a plurality of areas such as computer rooms, data processing centers, laboratories, central control rooms and the like. The traditional antistatic floor performance analysis method generally only analyzes the antistatic performance of the floor, and does not consider the performance of the antistatic floor in other aspects, so that the antistatic floor performance analysis accuracy is low.
In summary, in the prior art, the conventional antistatic product performance analysis method has the problem that the accuracy of product performance analysis is low due to the fact that indexes are too single.
Disclosure of Invention
Based on the above, it is necessary to provide an intelligent analysis method and system for the performance of antistatic products.
An intelligent analysis method for antistatic product performance, the method comprising: carrying out surface resistance detection on a target antistatic product to obtain a surface resistance value of the target antistatic product; grading the antistatic performance according to the surface resistance value to obtain an antistatic coefficient of the target antistatic product; performing multi-angle image acquisition on the target antistatic product through an image acquisition device, and inputting an image acquisition result into a surface flatness analysis model to obtain a flatness analysis result, wherein the flatness analysis result comprises a flatness coefficient; carrying out a water absorption expansion test on the target antistatic product, and obtaining the moisture resistance coefficient of the target antistatic product according to the water absorption expansion result; constructing a product expert system, and carrying out initial weight distribution on antistatic performance, flatness and moisture resistance according to the product expert system to obtain an initial weight value; based on the initial weight value, carrying out weighted calculation on the antistatic coefficient, the flatness coefficient and the moistureproof coefficient to obtain the performance coefficient of the target antistatic product; and based on the performance coefficient, classifying the target antistatic product according to a preset product classification rule to obtain the target antistatic product class.
An antistatic product performance intelligent analysis system, comprising:
the surface resistance detection module is used for detecting the surface resistance of a target antistatic product and obtaining the surface resistance value of the target antistatic product;
the antistatic performance grading module is used for grading the antistatic performance according to the surface resistance value to obtain the antistatic coefficient of the target antistatic product;
the flatness analysis result obtaining module is used for carrying out multi-angle image acquisition on the target antistatic product through the image acquisition device, inputting the image acquisition result into a surface flatness analysis model and obtaining a flatness analysis result, wherein the flatness analysis result comprises a flatness coefficient;
the moisture-proof coefficient obtaining module is used for carrying out a water absorption expansion test on the target antistatic product and obtaining the moisture-proof coefficient of the target antistatic product according to a water absorption expansion result;
the initial weight distribution module is used for constructing a product expert system, and carrying out initial weight distribution on antistatic performance, flatness and moisture resistance according to the product expert system to obtain an initial weight value;
the coefficient of performance obtaining module is used for carrying out weighted calculation on the antistatic coefficient, the flatness coefficient and the dampproof coefficient based on the initial weight value to obtain the coefficient of performance of the target antistatic product;
the target antistatic product grade obtaining module is used for carrying out grade division on the target antistatic product according to a preset product division rule based on the performance coefficient to obtain the target antistatic product grade.
The intelligent analysis method and the intelligent analysis system for the performance of the antistatic product can solve the problem that the accuracy of product performance analysis is low due to the fact that indexes are too single in the traditional analysis method for the performance of the antistatic product, and firstly, surface resistance detection is conducted on a target antistatic product to obtain the surface resistance value of the target antistatic product; grading the antistatic performance according to the surface resistance value to obtain an antistatic coefficient of the target antistatic product; performing multi-angle image acquisition on the target antistatic product through an image acquisition device, and inputting an image acquisition result into a surface flatness analysis model to obtain a flatness analysis result, wherein the flatness analysis result comprises a flatness coefficient; carrying out a water absorption expansion test on the target antistatic product, and obtaining the moisture resistance coefficient of the target antistatic product according to the water absorption expansion result; constructing a product expert system, and carrying out initial weight distribution on antistatic performance, flatness and moisture resistance according to the product expert system to obtain an initial weight value; based on the initial weight value, carrying out weighted calculation on the antistatic coefficient, the flatness coefficient and the moistureproof coefficient to obtain the performance coefficient of the target antistatic product; and based on the performance coefficient, classifying the target antistatic product according to a preset product classification rule to obtain the target antistatic product class. The accuracy of the product performance analysis can be improved by comprehensively analyzing the multiple performance indexes of the target antistatic product.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
Drawings
FIG. 1 is a schematic flow chart of an intelligent analysis method for the performance of an antistatic product;
FIG. 2 is a schematic flow chart of a flatness analysis result obtained in an intelligent analysis method for the performance of an antistatic product;
FIG. 3 is a schematic flow chart of a product expert system constructed in an intelligent analysis method for antistatic product performance;
fig. 4 is a schematic structural diagram of an intelligent analysis system for antistatic product performance.
Reference numerals illustrate: the system comprises a surface resistance detection module 1, an antistatic performance scoring module 2, a flatness analysis result obtaining module 3, a moisture-proof coefficient obtaining module 4, an initial weight distribution module 5, a performance coefficient obtaining module 6 and a target antistatic product level obtaining module 7.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
As shown in fig. 1, the application provides an intelligent analysis method for antistatic product performance, comprising the following steps:
step S100: carrying out surface resistance detection on a target antistatic product to obtain a surface resistance value of the target antistatic product;
specifically, firstly, two electrodes are arranged on a target antistatic product, and the surface resistance of the target antistatic product is detected by a resistance meter to obtain the surface resistance value of the target antistatic product. The target antistatic product is an antistatic floor. By obtaining the surface resistance value, support is provided for the next step of antistatic performance analysis of the target antistatic product.
Step S200: grading the antistatic performance according to the surface resistance value to obtain an antistatic coefficient of the target antistatic product;
as shown in fig. 2, in one embodiment, step S200 of the present application further includes:
step S210: acquiring an antistatic performance rule of a preset product;
step S220: inputting the surface resistance value into the preset product antistatic rule for matching, and obtaining the antistatic coefficient.
Specifically, the sheet resistance value is set to the valueThe target antistatic product performs antistatic performance analysis, and obtains preset product antistatic performance rules according to a plurality of historical surface resistance values, wherein the preset product antistatic performance rules can be set by a person skilled in the art according to surface resistance values in a self-defined manner, for example: according to the relevant regulations, the surface resistance of the antistatic floor needs to be 2.5X10 4 ~1.0×10 9 Between Ω, when the surface resistance is greater than 2.5X10 4 And when omega is, the floor has an antistatic function. At this time, the surface resistance is set to 1.0X10 5 When omega, the antistatic coefficient is 1; when the surface resistance is 1.0X10 6 When omega, the antistatic coefficient is 3; the larger the antistatic coefficient is, the better the antistatic performance of the antistatic floor is. And then inputting the surface resistance value into the preset product antistatic rule to perform surface resistance value matching, and obtaining an antistatic coefficient. By obtaining the antistatic coefficient, the antistatic performance of the target antistatic product can be obtained more intuitively and accurately.
Step S300: performing multi-angle image acquisition on the target antistatic product through an image acquisition device, and inputting an image acquisition result into a surface flatness analysis model to obtain a flatness analysis result, wherein the flatness analysis result comprises a flatness coefficient;
as shown in fig. 3, in one embodiment, the step S300 of the present application further includes:
step S310: the method comprises the steps that an image acquisition device acquires images of a target antistatic product from a first angle and a second angle respectively to obtain a first image and a second image, wherein the first angle is parallel to the target antistatic product, and the second angle is perpendicular to the target antistatic product;
step S320: based on big data, carrying out image data query by taking the target antistatic product as a search condition to obtain a plurality of historical product images and a plurality of flatness scores, wherein the historical product images and the flatness scores have a corresponding relationship;
step S330: classifying the plurality of historical product images according to an image acquisition angle to obtain a plurality of historical product first images and a plurality of historical product second images;
step S340: constructing a sample dataset based on the plurality of historical product first images, the plurality of first flatness scores and the plurality of historical product second images, the plurality of second flatness scores;
specifically, image acquisition is performed on the target antistatic product from a first angle and a second angle through an image acquisition device, wherein the image acquisition device is equipment with a photographing function, for example: an industrial camera. The first angle is parallel to the target antistatic product, the second angle is perpendicular to the target antistatic product, a first image and a second image are obtained, the first image is an image shot through the first angle, and the second image is an image shot through the second angle.
Based on a big data technology, carrying out related image data query by taking the target antistatic product as a search condition to obtain a plurality of historical product images and a plurality of flatness scores, wherein the historical product images and the flatness scores have a corresponding relationship. The flatness score is used for expressing the flatness of the product, and the higher the flatness is, the higher the flatness score is. And classifying the plurality of historical product images according to the first angle and the second angle of image acquisition to obtain a plurality of historical product first images and a plurality of historical product second images. And constructing a sample data set according to the plurality of historical product first images, the plurality of historical product second images, the corresponding plurality of first scores and the corresponding plurality of second scores. The first score is a flatness score of the first image of the historical product, and the second score is a flatness score of the second image of the historical product. By obtaining the sample data set, training data support is provided for the next step of supervised training of the model.
Step S350: based on a convolutional neural network, constructing a surface flatness analysis model, and training and verifying the surface flatness analysis model through the sample data set to obtain the surface flatness analysis model;
in one embodiment, step S350 of the present application further includes:
step S351: based on a convolutional neural network, a surface flatness analysis model is constructed, wherein the surface flatness analysis model comprises a first channel, a second channel, a calculation channel and an output channel;
step S352: the first channel is used for inputting the first image, the second channel is used for inputting the image, the calculating channel is used for calculating a first flatness score and a second flatness score, and the output channel is used for outputting a flatness analysis result;
step S353: acquiring a preset data dividing ratio, and dividing the sample data set into a sample training set and a sample verification set;
step S354: and training and verifying the surface flatness analysis model through the sample training set and the sample verification set to obtain the surface flatness analysis model.
Step S360: and outputting the first image and the second image to the surface flatness analysis model to obtain the flatness analysis result.
Specifically, a surface flatness analysis model is constructed based on a convolutional neural network, wherein the surface flatness analysis model is a neural network model which can be continuously subjected to iterative optimization in machine learning, and is obtained through supervised training by a training data set. The surface flatness analysis model comprises a first channel, a second channel, a calculation channel and an output channel. The first channel is used for inputting the first image, the second channel is used for inputting the image, the calculating channel is used for calculating a first flatness score and a second flatness score, and the output channel is used for outputting a flatness analysis result.
Obtaining a preset data dividing ratio, wherein the preset data dividing ratio can be set in a self-defined manner, for example: 90%, 10%. And dividing the sample data set into a sample training set and a sample verification set according to the preset data dividing proportion. Performing supervision training on the surface evenness analysis model through the sample data set, verifying an output result of the surface evenness analysis model through the sample verification set, and presetting a verification accuracy index, for example: 96%, when the accuracy of the model output result is greater than the preset verification accuracy index, obtaining the surface flatness analysis model.
Inputting the first image into a first channel to obtain a first flatness score of the first image; inputting the second image into a second channel to obtain a second flatness score of the second image, and then inputting the first flatness score and the second flatness score into the calculation channel to perform weighted calculation, wherein the calculation channel is embedded with weight ratios of the first image and the second image, and the weight ratios can be custom set by a person skilled in the art based on practical situations, for example: 40% and 60%. And carrying out weighted calculation on the first flatness score and the second flatness score according to the weight ratio, taking the sum of weighted calculation as the flatness coefficient, and outputting the flatness coefficient through the output channel to obtain a flatness analysis result. By constructing a surface flatness analysis model based on a convolutional neural network and setting a first channel and a second channel in the surface flatness analysis model, accuracy and efficiency of obtaining flatness coefficients can be improved.
Step S400: carrying out a water absorption expansion test on the target antistatic product, and obtaining the moisture resistance coefficient of the target antistatic product according to the water absorption expansion result;
specifically, coefficient expansion test is carried out on the target antistatic product, the water absorption expansion test refers to that the target antistatic floor is placed in a water tank with the temperature of 25 ℃ for standing for 30 minutes, then the thickness change condition of the target antistatic floor is observed, the thickness change condition is represented by water absorption expansion rate, the larger the water absorption expansion rate is, the worse the moisture resistance of the target antistatic floor is, the moisture resistance is used for representing the moisture resistance of the floor, and the better the moisture resistance is, the higher the moisture resistance is, and the moisture resistance of the target antistatic product is obtained. By obtaining the moisture-proof coefficient, the moisture-proof performance of the target antistatic product can be accurately known.
Step S500: constructing a product expert system, and carrying out initial weight distribution on antistatic performance, flatness and moisture resistance according to the product expert system to obtain an initial weight value;
in one embodiment, step S500 of the present application further includes:
step S510: obtaining a plurality of product experts and a plurality of product expert basic information, wherein the product expert basic information comprises the age of a practitioner, the academic, and the achievement;
step S520: carrying out trust degree scoring on the plurality of product experts based on the plurality of product expert basic information to obtain a plurality of trust degrees corresponding to the plurality of product experts;
step S530: the product expert system is constructed based on the plurality of product experts and the plurality of trustworthiness.
Specifically, a plurality of domain experts of the target antistatic product and basic information of the domain experts are obtained, wherein the basic information includes a practitioner age, an academic, and an achievement, which is achievement in the field of the target antistatic product, for example: publication amount of paper, etc. And grading the credibility of the plurality of product experts according to the basic information of the plurality of product experts, wherein the credibility grading rule can be set in a self-defined way, and the longer the year, the higher the learning, the more achievements are obtained, the higher the credibility is. And obtaining a plurality of trust degrees corresponding to the plurality of product experts. And identifying the plurality of experts according to the plurality of trust levels, and constructing the product expert system according to the identified plurality of product experts. By constructing the product expert system, the accuracy of obtaining the performance coefficient of the target antistatic product can be improved.
In one embodiment, step S500 of the present application further includes:
step S510: grading the antistatic performance, flatness and moisture resistance of the target antistatic product according to a plurality of product experts of the product expert system to obtain a plurality of antistatic performance grades, a plurality of flatness grades and a plurality of moisture resistance grades;
step S520: and carrying out weighted calculation on the antistatic performance scores, the flatness scores and the dampproof performance scores based on the trust degrees, and taking an average value of weighted calculation results as an initial weight to obtain the initial weight value.
Specifically, performance index scoring is performed on the antistatic performance, flatness and moisture resistance of the target antistatic product according to a plurality of product experts of the product expert system, and a plurality of antistatic performance scores, a plurality of flatness scores and a plurality of moisture resistance scores are obtained. And then carrying out weighted calculation on the antistatic performance scores, the flatness scores and the dampproof performance scores according to the trust degrees to obtain weighted calculation results, wherein the weighted calculation results are products of the performance scores multiplied by the trust degrees, then carrying out mean processing on the weighted calculation results to obtain an antistatic performance mean value score, a flatness mean value score and a dampproof performance mean value score, taking the mean scores as initial weights to obtain initial weight values, and providing support for carrying out comprehensive analysis on the performance of a target antistatic product in the next step by obtaining the initial weight values.
Step S600: based on the initial weight value, carrying out weighted calculation on the antistatic coefficient, the flatness coefficient and the moistureproof coefficient to obtain the performance coefficient of the target antistatic product;
specifically, according to the initial weight value, the antistatic coefficient, the flatness coefficient and the moistureproof coefficient are subjected to weighted calculation, weighted calculation results are added and summed, and the obtained sum is used as the coefficient of performance of the target antistatic product. By obtaining the coefficient of performance, the performance of the target antistatic product can be clearly and accurately known.
Step S700: and based on the performance coefficient, classifying the target antistatic product according to a preset product classification rule to obtain the target antistatic product class.
Specifically, a preset product division rule is obtained, and the preset product division rule can be set by a person skilled in the art based on the performance coefficient in a self-defining manner, for example: the coefficient of performance is less than or equal to 80, and is a first-grade product; the coefficient of performance is more than 80 and less than or equal to 120, and is a secondary product; the coefficient of performance is more than 120 and less than or equal to 140, and is a three-stage product. Inputting the performance index of the target antistatic product into the preset product division rule for matching, and obtaining the grade of the target antistatic product. The method solves the problem that the traditional antistatic product performance analysis method has lower accuracy of product performance analysis due to the fact that indexes are too single, and can improve the accuracy of product performance analysis by comprehensively analyzing multiple performance indexes of the target antistatic product.
In one embodiment, as shown in FIG. 4, an intelligent antistatic product performance analysis system is provided, comprising: the surface resistance detection module 1, the antistatic performance scoring module 2, the flatness analysis result obtaining module 3, the moisture-proof coefficient obtaining module 4, the initial weight distribution module 5, the performance coefficient obtaining module 6, the target antistatic product grade obtaining module 7, wherein:
the surface resistance detection module 1 is used for detecting the surface resistance of a target antistatic product to obtain the surface resistance value of the target antistatic product;
the antistatic performance grading module 2 is used for grading the antistatic performance according to the surface resistance value to obtain the antistatic coefficient of the target antistatic product;
the flatness analysis result obtaining module 3 is used for collecting the multi-angle image of the target antistatic product through the image collecting device, inputting the image collecting result into the surface flatness analysis model to obtain a flatness analysis result, wherein the flatness analysis result comprises a flatness coefficient;
the moisture-proof coefficient obtaining module 4 is used for carrying out a water absorption expansion test on the target antistatic product and obtaining the moisture-proof coefficient of the target antistatic product according to a water absorption expansion result;
the initial weight distribution module 5 is used for constructing a product expert system, and carrying out initial weight distribution on antistatic performance, flatness and moisture resistance according to the product expert system to obtain an initial weight value;
the coefficient of performance obtaining module 6 is configured to perform weighted calculation on the antistatic coefficient, the flatness coefficient and the moisture-proof coefficient based on the initial weight value, so as to obtain a coefficient of performance of the target antistatic product;
the target antistatic product level obtaining module 7 is configured to perform level division on the target antistatic product according to a preset product division rule based on the performance coefficient, so as to obtain the target antistatic product level.
In one embodiment, the system further comprises:
the preset product antistatic performance rule acquisition module is used for acquiring the preset product antistatic performance rule;
the antistatic coefficient obtaining module is used for inputting the surface resistance value into the antistatic rule of the preset product for matching, and obtaining the antistatic coefficient.
In one embodiment, the system further comprises:
the image acquisition module is used for acquiring images of the target antistatic product from a first angle and a second angle through the image acquisition device respectively to obtain a first image and a second image, wherein the first angle is an angle parallel to the target antistatic product, and the second angle is an angle perpendicular to the target antistatic product;
the image data query module is used for performing image data query by taking the target antistatic product as a search condition based on big data to obtain a plurality of historical product images and a plurality of flatness scores, wherein the historical product images and the flatness scores have a corresponding relationship;
the image classification module is used for classifying the plurality of historical product images according to an image acquisition angle to obtain a plurality of historical product first images and a plurality of historical product second images;
a sample data set construction module for constructing a sample data set based on the plurality of historical product first images, the plurality of first flatness scores, and the plurality of historical product second images, the plurality of second flatness scores;
the surface flatness analysis model obtaining module is used for constructing a surface flatness analysis model based on a convolutional neural network, training and verifying the surface flatness analysis model through the sample data set, and obtaining the surface flatness analysis model;
and the flatness analysis result obtaining module is used for outputting the first image and the second image to the surface flatness analysis model to obtain the flatness analysis result.
In one embodiment, the system further comprises:
the surface flatness analysis model construction module is used for constructing a surface flatness analysis model based on a convolutional neural network, and comprises a first channel, a second channel, a calculation channel and an output channel;
the model introduction module is used for inputting the first image through the first channel, inputting the image through the second channel, calculating the first flatness score and the second flatness score through the calculation channel, and outputting a flatness analysis result through the output channel;
the system comprises a preset data dividing ratio acquisition module, a sample data dividing ratio acquisition module and a sample verification module, wherein the preset data dividing ratio acquisition module is used for acquiring a preset data dividing ratio and dividing the sample data set into a sample training set and a sample verification set;
and the training verification module is used for training and verifying the surface flatness analysis model through the sample training set and the sample verification set to obtain the surface flatness analysis model.
In one embodiment, the system further comprises:
the product expert obtaining module is used for obtaining a plurality of product experts and a plurality of product expert basic information, wherein the product expert basic information comprises the age of a practitioner, the academic, and the achievement;
the trust degree obtaining module is used for scoring the trust degrees of the product experts based on the basic information of the product experts to obtain a plurality of trust degrees corresponding to the product experts;
and the product expert system construction module is used for constructing the product expert system based on the plurality of product experts and the plurality of credibility.
In one embodiment, the system further comprises:
the performance scoring module is used for scoring the antistatic performance, the flatness and the moisture resistance of the target antistatic product according to a plurality of product experts of the product expert system to obtain a plurality of antistatic performance scores, a plurality of flatness scores and a plurality of moisture resistance scores;
the initial weight value obtaining module is used for carrying out weighted calculation on the antistatic performance scores, the flatness scores and the dampproof performance scores based on the trust degrees, and taking the average value of weighted calculation results as initial weight to obtain the initial weight value.
In summary, the application provides an intelligent analysis method and system for antistatic product performance, which have the following technical effects:
1. the problem that the accuracy of product performance analysis is low due to the fact that indexes are too single in a traditional antistatic product performance analysis method is solved, and the accuracy of product performance analysis can be improved by comprehensively analyzing multiple performance indexes of a target antistatic product.
2. By obtaining the antistatic coefficient, the antistatic performance of the target antistatic product can be obtained more intuitively and accurately.
3. By constructing a surface flatness analysis model based on a convolutional neural network and setting a first channel and a second channel in the surface flatness analysis model, accuracy and efficiency of obtaining flatness coefficients can be improved.
4. By constructing the product expert system, the accuracy of obtaining the performance coefficient of the target antistatic product can be improved.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of protection of the present application is to be determined by the appended claims.
Claims (6)
1. An intelligent analysis method for the performance of an antistatic product is characterized by comprising the following steps:
carrying out surface resistance detection on a target antistatic product to obtain a surface resistance value of the target antistatic product;
grading the antistatic performance according to the surface resistance value to obtain an antistatic coefficient of the target antistatic product;
performing multi-angle image acquisition on the target antistatic product through an image acquisition device, and inputting an image acquisition result into a surface flatness analysis model to obtain a flatness analysis result, wherein the flatness analysis result comprises a flatness coefficient;
carrying out a water absorption expansion test on the target antistatic product, and obtaining the moisture resistance coefficient of the target antistatic product according to the water absorption expansion result;
constructing a product expert system, and carrying out initial weight distribution on antistatic performance, flatness and moisture resistance according to the product expert system to obtain an initial weight value;
based on the initial weight value, carrying out weighted calculation on the antistatic coefficient, the flatness coefficient and the moistureproof coefficient to obtain the performance coefficient of the target antistatic product;
based on the performance coefficient, classifying the target antistatic product according to a preset product classification rule to obtain the target antistatic product class;
the image acquisition device acquires the multi-angle image of the target antistatic product, inputs the image acquisition result into the surface flatness analysis model to obtain a flatness analysis result, and further comprises:
the method comprises the steps that an image acquisition device acquires images of a target antistatic product from a first angle and a second angle respectively to obtain a first image and a second image, wherein the first angle is parallel to the target antistatic product, and the second angle is perpendicular to the target antistatic product;
based on big data, carrying out image data query by taking the target antistatic product as a search condition to obtain a plurality of historical product images and a plurality of flatness scores, wherein the historical product images and the flatness scores have a corresponding relationship;
classifying the plurality of historical product images according to an image acquisition angle to obtain a plurality of historical product first images and a plurality of historical product second images;
constructing a sample dataset based on the plurality of historical product first images, the plurality of first flatness scores and the plurality of historical product second images, the plurality of second flatness scores;
based on a convolutional neural network, constructing a surface flatness analysis model, and training and verifying the surface flatness analysis model through the sample data set to obtain the surface flatness analysis model;
and outputting the first image and the second image to the surface flatness analysis model to obtain the flatness analysis result.
2. The method of claim 1, wherein said scoring antistatic properties based on said surface resistance value to obtain an antistatic coefficient for said target antistatic product, further comprising:
acquiring an antistatic performance rule of a preset product;
inputting the surface resistance value into the preset product antistatic rule for matching, and obtaining the antistatic coefficient.
3. The method of claim 1, wherein the method further comprises:
based on a convolutional neural network, a surface flatness analysis model is constructed, wherein the surface flatness analysis model comprises a first channel, a second channel, a calculation channel and an output channel;
the first channel is used for inputting the first image, the second channel is used for inputting the image, the calculating channel is used for calculating a first flatness score and a second flatness score, and the output channel is used for outputting a flatness analysis result;
acquiring a preset data dividing ratio, and dividing the sample data set into a sample training set and a sample verification set;
and training and verifying the surface flatness analysis model through the sample training set and the sample verification set to obtain the surface flatness analysis model.
4. The method of claim 1, wherein the constructing a product expert system further comprises:
obtaining a plurality of product experts and a plurality of product expert basic information, wherein the product expert basic information comprises the age of a practitioner, the academic, and the achievement;
carrying out trust degree scoring on the plurality of product experts based on the plurality of product expert basic information to obtain a plurality of trust degrees corresponding to the plurality of product experts;
the product expert system is constructed based on the plurality of product experts and the plurality of trustworthiness.
5. The method of claim 4, wherein the method further comprises:
grading the antistatic performance, flatness and moisture resistance of the target antistatic product according to a plurality of product experts of the product expert system to obtain a plurality of antistatic performance grades, a plurality of flatness grades and a plurality of moisture resistance grades;
and carrying out weighted calculation on the antistatic performance scores, the flatness scores and the dampproof performance scores based on the trust degrees, and taking an average value of weighted calculation results as an initial weight to obtain the initial weight value.
6. An intelligent analysis system for antistatic product performance, the system comprising:
the surface resistance detection module is used for detecting the surface resistance of a target antistatic product and obtaining the surface resistance value of the target antistatic product;
the antistatic performance grading module is used for grading the antistatic performance according to the surface resistance value to obtain the antistatic coefficient of the target antistatic product;
the flatness analysis result obtaining module is used for carrying out multi-angle image acquisition on the target antistatic product through the image acquisition device, inputting the image acquisition result into a surface flatness analysis model and obtaining a flatness analysis result, wherein the flatness analysis result comprises a flatness coefficient;
the moisture-proof coefficient obtaining module is used for carrying out a water absorption expansion test on the target antistatic product and obtaining the moisture-proof coefficient of the target antistatic product according to a water absorption expansion result;
the initial weight distribution module is used for constructing a product expert system, and carrying out initial weight distribution on antistatic performance, flatness and moisture resistance according to the product expert system to obtain an initial weight value;
the coefficient of performance obtaining module is used for carrying out weighted calculation on the antistatic coefficient, the flatness coefficient and the dampproof coefficient based on the initial weight value to obtain the coefficient of performance of the target antistatic product;
the target antistatic product level obtaining module is used for carrying out level division on the target antistatic product according to a preset product division rule based on the performance coefficient to obtain the target antistatic product level;
the image acquisition module is used for acquiring images of the target antistatic product from a first angle and a second angle through the image acquisition device respectively to obtain a first image and a second image, wherein the first angle is an angle parallel to the target antistatic product, and the second angle is an angle perpendicular to the target antistatic product;
the image data query module is used for performing image data query by taking the target antistatic product as a search condition based on big data to obtain a plurality of historical product images and a plurality of flatness scores, wherein the historical product images and the flatness scores have a corresponding relationship;
the image classification module is used for classifying the plurality of historical product images according to an image acquisition angle to obtain a plurality of historical product first images and a plurality of historical product second images;
a sample data set construction module for constructing a sample data set based on the plurality of historical product first images, the plurality of first flatness scores, and the plurality of historical product second images, the plurality of second flatness scores;
the surface flatness analysis model obtaining module is used for constructing a surface flatness analysis model based on a convolutional neural network, training and verifying the surface flatness analysis model through the sample data set, and obtaining the surface flatness analysis model;
and the flatness analysis result obtaining module is used for outputting the first image and the second image to the surface flatness analysis model to obtain the flatness analysis result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310667167.2A CN116699243B (en) | 2023-06-07 | 2023-06-07 | Intelligent analysis method and system for antistatic product performance |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310667167.2A CN116699243B (en) | 2023-06-07 | 2023-06-07 | Intelligent analysis method and system for antistatic product performance |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116699243A CN116699243A (en) | 2023-09-05 |
CN116699243B true CN116699243B (en) | 2023-12-05 |
Family
ID=87830668
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310667167.2A Active CN116699243B (en) | 2023-06-07 | 2023-06-07 | Intelligent analysis method and system for antistatic product performance |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116699243B (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2016127295A (en) * | 2014-12-26 | 2016-07-11 | 三菱電機株式会社 | Image processing apparatus, image processing method, image reader, and image processing program |
CN115144029A (en) * | 2022-07-01 | 2022-10-04 | 上海交通大学 | Evaluation method and monitoring device for electrostatic micro-lubrication effectiveness |
CN115613155A (en) * | 2022-11-18 | 2023-01-17 | 北京微构工场生物技术有限公司 | Filament or staple fiber and preparation method thereof |
CN115933574A (en) * | 2023-01-09 | 2023-04-07 | 浙江聚优非织造材料科技有限公司 | Intelligent control method and system for producing non-woven products |
CN116069002A (en) * | 2023-03-22 | 2023-05-05 | 常州市诺七微电子科技有限公司 | Motor controller rotation speed balance test method and system |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110297141A (en) * | 2019-07-01 | 2019-10-01 | 武汉大学 | Fault Locating Method and system based on multilayer assessment models |
-
2023
- 2023-06-07 CN CN202310667167.2A patent/CN116699243B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2016127295A (en) * | 2014-12-26 | 2016-07-11 | 三菱電機株式会社 | Image processing apparatus, image processing method, image reader, and image processing program |
CN115144029A (en) * | 2022-07-01 | 2022-10-04 | 上海交通大学 | Evaluation method and monitoring device for electrostatic micro-lubrication effectiveness |
CN115613155A (en) * | 2022-11-18 | 2023-01-17 | 北京微构工场生物技术有限公司 | Filament or staple fiber and preparation method thereof |
CN115933574A (en) * | 2023-01-09 | 2023-04-07 | 浙江聚优非织造材料科技有限公司 | Intelligent control method and system for producing non-woven products |
CN116069002A (en) * | 2023-03-22 | 2023-05-05 | 常州市诺七微电子科技有限公司 | Motor controller rotation speed balance test method and system |
Non-Patent Citations (1)
Title |
---|
棉型阻燃织物性能及在消防服中的应用研究;杨柳;中国优秀硕士学位论文全文数据库(第6期);第1-4章 * |
Also Published As
Publication number | Publication date |
---|---|
CN116699243A (en) | 2023-09-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20180349384A1 (en) | Differentially private database queries involving rank statistics | |
CN105930976B (en) | Node voltage sag severity comprehensive evaluation method based on weighted ideal point method | |
CN111914090B (en) | Method and device for enterprise industry classification identification and characteristic pollutant identification | |
WO2019223384A1 (en) | Feature interpretation method and device for gbdt model | |
CN108921206A (en) | A kind of image classification method, device, electronic equipment and storage medium | |
CN109783879B (en) | Radar radiation source signal identification efficiency evaluation method and system | |
CN113780443B (en) | Threat detection-oriented network security situation assessment method | |
US20140372444A1 (en) | Data clustering apparatus and method | |
CN112990330A (en) | User energy abnormal data detection method and device | |
CN107016416B (en) | Data classification prediction method based on neighborhood rough set and PCA fusion | |
CN110324178B (en) | Network intrusion detection method based on multi-experience nuclear learning | |
CN116699243B (en) | Intelligent analysis method and system for antistatic product performance | |
CN117332287A (en) | Evaluation index weight data processing method based on cluster analysis | |
Zhang et al. | DDoS attack security situation assessment model using fusion feature based on fuzzy C-means clustering algorithm | |
Obadinma et al. | Class-wise Calibration: A Case Study on COVID-19 Hate Speech. | |
CN116415836A (en) | Security evaluation method for intelligent power grid information system | |
CN107423319B (en) | Junk web page detection method | |
CN106709598B (en) | Voltage stability prediction and judgment method based on single-class samples | |
CN112613231B (en) | Track training data perturbation mechanism with balanced privacy in machine learning | |
CN112418313B (en) | Big data online noise filtering system and method | |
CN114818945A (en) | Small sample image classification method and device integrating category adaptive metric learning | |
Wang et al. | Intelligent weight generation algorithm based on binary isolation tree | |
CN108053093A (en) | A kind of k- neighbour's method for diagnosing faults based on the conversion of average influence Value Data | |
CN114021905A (en) | Credit risk evaluation method for small and medium-sized enterprises | |
CN114329966A (en) | Method and system for evaluating health degree of remote control system of natural gas pipeline |
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 |