CN111791090B - Cutter life abrasion judgment method based on edge calculation and particle swarm optimization - Google Patents
Cutter life abrasion judgment method based on edge calculation and particle swarm optimization Download PDFInfo
- Publication number
- CN111791090B CN111791090B CN202010633618.7A CN202010633618A CN111791090B CN 111791090 B CN111791090 B CN 111791090B CN 202010633618 A CN202010633618 A CN 202010633618A CN 111791090 B CN111791090 B CN 111791090B
- Authority
- CN
- China
- Prior art keywords
- particle swarm
- feature
- data
- support vector
- vector machine
- 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
- 239000002245 particle Substances 0.000 title claims abstract description 51
- 238000000034 method Methods 0.000 title claims abstract description 16
- 238000005299 abrasion Methods 0.000 title claims abstract description 12
- 238000004364 calculation method Methods 0.000 title claims abstract description 10
- 238000005457 optimization Methods 0.000 title claims description 19
- 238000012706 support-vector machine Methods 0.000 claims abstract description 24
- 238000005516 engineering process Methods 0.000 claims abstract description 5
- 230000008030 elimination Effects 0.000 claims abstract description 4
- 238000003379 elimination reaction Methods 0.000 claims abstract description 4
- 238000001914 filtration Methods 0.000 claims abstract description 4
- 239000013589 supplement Substances 0.000 claims abstract description 4
- 230000006870 function Effects 0.000 claims description 21
- 239000011159 matrix material Substances 0.000 claims description 20
- 238000012549 training Methods 0.000 claims description 10
- 238000012360 testing method Methods 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 5
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 230000006872 improvement Effects 0.000 claims description 3
- 238000010297 mechanical methods and process Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 239000013598 vector Substances 0.000 claims description 3
- 238000000513 principal component analysis Methods 0.000 abstract description 6
- 238000013145 classification model Methods 0.000 abstract 1
- 238000010606 normalization Methods 0.000 abstract 1
- 238000003754 machining Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23Q—DETAILS, COMPONENTS, OR ACCESSORIES FOR MACHINE TOOLS, e.g. ARRANGEMENTS FOR COPYING OR CONTROLLING; MACHINE TOOLS IN GENERAL CHARACTERISED BY THE CONSTRUCTION OF PARTICULAR DETAILS OR COMPONENTS; COMBINATIONS OR ASSOCIATIONS OF METAL-WORKING MACHINES, NOT DIRECTED TO A PARTICULAR RESULT
- B23Q17/00—Arrangements for observing, indicating or measuring on machine tools
- B23Q17/09—Arrangements for observing, indicating or measuring on machine tools for indicating or measuring cutting pressure or for determining cutting-tool condition, e.g. cutting ability, load on tool
- B23Q17/0952—Arrangements for observing, indicating or measuring on machine tools for indicating or measuring cutting pressure or for determining cutting-tool condition, e.g. cutting ability, load on tool during machining
- B23Q17/0957—Detection of tool breakage
-
- 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
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Biophysics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Mechanical Engineering (AREA)
- Feedback Control In General (AREA)
Abstract
The invention relates to a cutter service life abrasion judgment method based on edge calculation and a particle swarm algorithm, and belongs to the field of numerical control machines. The method comprises the steps of firstly carrying out operations of outlier elimination, missing value supplement and wavelet threshold noise filtering on original signals on an edge side, then utilizing a Pearson correlation coefficient to extract characteristics closely related to a tool life wear state, then carrying out normalization processing on the characteristics, further reducing characteristic dimensionality of processed data by adopting a PCA (principal component analysis) technology, then uploading the characteristic set to a cloud server, and dividing the data processed on the edge side in the cloud server and constructing a support vector machine classification model. Aiming at the problem that the parameters of the existing support vector machine model are difficult to select, an improved particle swarm algorithm is provided for optimizing the parameters of the support vector machine model, and the cutter service life abrasion judgment method based on edge calculation and the particle swarm algorithm is realized.
Description
Technical Field
The invention belongs to the field of numerical control machines and relates to a cutter service life abrasion judging method based on edge calculation and a particle swarm algorithm.
Background
In recent years, with the rapid development of the mechanical field, the number and types of the tools applied to machining are increasing, and whether the tool state can be accurately predicted is an important factor influencing the purchase of the number of the tools, the cost budget of the tool and the setting of cutting parameters by enterprises. Because the factors influencing the state of the tool are complex and cannot depend on experience or some specific formulas, the effective prediction of the state of the tool becomes a troublesome problem in the field of machining.
In the machining process of the numerical control machine tool, a large amount of tool state data can be collected through the sensor, and if the data are uploaded to the cloud server, the requirements on network bandwidth and the performance of the cloud server are very strict. In the face of such a scene, the edge calculation embodies the advantages thereof, and since the edge calculation is deployed near the equipment side, the decision can be fed back in real time through an algorithm, most data can be filtered, and the load of the cloud end is effectively reduced.
The support vector machine is originally proposed to be used for performing two-classification, and with continuous and deep development, the current support vector machine model can effectively solve the complex classification problem. The particle swarm optimization is an algorithm for solving the optimal problem, has the advantages of few changeable parameters, simple structure and the like, can effectively avoid the problem that parameters in the support vector machine are difficult to set by optimizing the parameters of the support vector machine by the particle swarm optimization, and greatly improves the precision of the model.
Disclosure of Invention
In view of the above, the present invention provides a method for determining tool life wear based on edge calculation and particle swarm optimization.
In order to achieve the purpose, the invention provides the following technical scheme:
a cutter service life abrasion judging method based on edge calculation and particle swarm optimization comprises the following steps:
step 1, preprocessing cutter data and extracting characteristics on the edge side;
step 2, dividing the characteristic matrix obtained in the step 1 in a cloud server and establishing a corresponding SVM model;
step 3, optimizing parameters of the SVM model by using the improved particle swarm algorithm and training set data in the cloud server;
and 4, judging the service life of the cutter on the optimized support vector machine model by using the test set in the cloud server.
Optionally, in step 1, the preprocessing of tool data and the feature extraction specifically include:
step 1.1, carrying out operations of abnormal value elimination, missing value supplement and wavelet threshold noise filtering on an original signal;
step 1.2, analyzing the noise-filtered signals by using a Pearson correlation coefficient, and selecting variables closely related to cutter abrasion to construct a feature set;
step 1.3, the feature set obtained in step 1.2 is normalized, and the formula is as follows:
in the formula:
the ith data representing the normalized kth dimension features,
the ith data representing the feature of the kth dimension,
the maximum value of the feature of the k-th dimension is represented,
representing the minimum of the k-dimensional feature.
Step 1.4, the feature set processed in step 1.3 is subjected to feature extraction by using a PCA technology, and the specific steps comprise:
step 1.4.1, subtracting the mean value of each dimension from each dimension of feature data;
step 1.4.2, calculating a characteristic covariance matrix;
step 1.4.3, calculating an eigenvalue and an eigenvector of the covariance matrix;
step 1.4.4, sorting the eigenvalues in descending order, taking the first K eigenvalues, and then taking eigenvectors corresponding to the K eigenvalues as column vectors to form an eigenvector matrix;
step 1.4.5, selecting K mainly depends on the variance and the ratio after dimensionality reduction, and the larger the proportion is, the more information is kept;
and step 1.5, uploading the feature matrix obtained in the step 1.4 to a cloud server.
Optionally, in step 2, the dividing, in the cloud server, the feature matrix obtained in S1 specifically includes: dividing the feature matrix uploaded on the edge side into a training set and a test set in a ratio of 4:1 in a cloud server, wherein training set data are used for SVM parameter optimization and optimal SVM model establishment, and test set data are used for cutter life abrasion judgment on the optimal SVM model;
the SVM is a support vector machine model, is a mechanical method based on a statistical learning theory, maps linear inseparable data of a low-dimensional space to a high-dimensional space, constructs an optimal classification hyperplane in the high-dimensional space to distinguish the data, and maximizes a classification interval; the type of the kernel function in the support vector machine model is selected as a radial basis kernel function, and after the kernel function is determined, two optimal kernel function combinations, a kernel function parameter g and a penalty parameter c need to be determined.
Optionally, in step 3, the parameter of the support vector machine optimized by using the improved particle swarm optimization algorithm in the cloud server includes two parts,
the first part is an improvement to the particle swarm algorithm, comprising the steps of:
step 3.1 the traditional particle swarm algorithm formula is:
in the formula, ω represents an inertial weight, c1And c2Is the learning factor of the learning factor,
respectively representing the position and velocity of the d-th dimension in the k-th iteration of the i-th particle, and rand () being 0,1]The random numbers are uniformly distributed in the range,
a d-dimension representing the individual optimal position of the ith particle,
and d dimension representing historical optimal positions of the particle swarm.
Step 3.2: the principle ω based on particle swarm algorithm should be continuously reduced as the search proceeds, so a formula for dynamically adjusting ω size is adopted as follows:
wherein, ω ismaxRepresenting the maximum value of the inertial weight, ωminRepresents the minimum value of the inertia weight, and k represents when
Number of previous iterations, kmaxIndicating the maximum number of iterations
Step 3.3 learning factor c1And c2The capability of approaching the particles to the individual optimal solution and the global optimal solution is embodied,
therefore, a dynamic adjustment c is designed1And c2The formula for the size is:
where k denotes the current number of iterations, kmaxIndicating the maximum number of iterations.
The second part is to optimize the parameters of the support vector machine by using the improved particle swarm optimization, and the optimization process comprises the following steps:
step 3.4 parameter initialization. Setting the population size, the maximum iteration times, defining a fitness function, initializing the maximum value and the minimum value of the weight omega, the maximum iteration times, the position and the speed of each particle, and the value ranges of a kernel function parameter g and a penalty factor c;
step 3.5, calculating the fitness value of each particle, and updating the individual optimal value and the global historical optimal value;
step 3.6 update the velocity and position of the particles by step 3.1, step 3.2, step 3.3;
and 3.7, judging whether the maximum iteration number is reached, if so, outputting the optimal parameters of the support vector machine, and otherwise, returning to the step 3.5.
The invention has the beneficial effects that: and preprocessing the cutter data and extracting effective characteristics at the edge side, optimizing a support vector machine model by using an improved particle swarm algorithm at a cloud server, and judging the service life abrasion of the cutter by using the obtained model.
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention. The objectives and other advantages of the invention may be realized and attained by the means of the instrumentalities and combinations particularly pointed out hereinafter.
Drawings
For the purposes of promoting a better understanding of the objects, aspects and advantages of the invention, reference will now be made to the following detailed description taken in conjunction with the accompanying drawings in which:
FIG. 1 is a flow chart of an algorithm according to the present invention;
FIG. 2 is a flow chart of the improved particle swarm optimization for optimizing the parameters of the support vector machine model.
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention in a schematic way, and the features in the following embodiments and examples may be combined with each other without conflict.
Wherein the showings are for the purpose of illustrating the invention only and not for the purpose of limiting the same, and in which there is shown by way of illustration only and not in the drawings in which there is no intention to limit the invention thereto; to better illustrate the embodiments of the present invention, some parts of the drawings may be omitted, enlarged or reduced, and do not represent the size of an actual product; it will be understood by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
The same or similar reference numerals in the drawings of the embodiments of the present invention correspond to the same or similar components; in the description of the present invention, it should be understood that if there is an orientation or positional relationship indicated by terms such as "upper", "lower", "left", "right", "front", "rear", etc., based on the orientation or positional relationship shown in the drawings, it is only for convenience of description and simplification of description, but it is not an indication or suggestion that the referred device or element must have a specific orientation, be constructed in a specific orientation, and be operated, and therefore, the terms describing the positional relationship in the drawings are only used for illustrative purposes, and are not to be construed as limiting the present invention, and the specific meaning of the terms may be understood by those skilled in the art according to specific situations.
FIG. 1 is a flow chart of the algorithm of the present invention;
the first step is as follows: and preprocessing the acquired data, including abnormal value elimination, missing value supplement and wavelet threshold noise filtering.
The second step is that: performing feature extraction on the preprocessed data, wherein the specific method is as follows: firstly, analyzing data by using a Pearson correlation coefficient, selecting data closely related to the service life wear of a cutter to construct a feature set, then normalizing the feature set, and finally further reducing the dimensionality of the feature set by using a PCA (principal component analysis) technology, wherein the specific steps of reducing the dimensionality by using the PCA technology comprise:
2.1, subtracting the average value of each dimension from each dimension of feature data;
step 2.2, calculating a characteristic covariance matrix;
step 2.3, calculating an eigenvalue and an eigenvector of the covariance matrix;
step 2.4, sorting the eigenvalues in descending order, taking the first K eigenvalues, and then taking eigenvectors corresponding to the K eigenvalues as column vectors to form an eigenvector matrix;
and 2.5, selecting K mainly depends on the variance and the ratio after dimensionality reduction, and the larger the proportion is, the more information is kept.
And 2.6, uploading the feature matrix obtained in the step 2.4 to a cloud server.
The third step: dividing the feature matrix obtained in the second step and establishing a corresponding SVM model, wherein the method comprises the following steps: dividing the feature matrix uploaded on the edge side into a training set and a test set in a ratio of 4:1 in a cloud server, wherein training set data are used for SVM parameter optimization and optimal SVM model establishment, and test set data are used for accuracy test of the optimal SVM model.
The SVM is a mechanical method based on a statistical learning theory, and the core idea of the SVM is to map linear inseparable data of a low-dimensional space to a high-dimensional space, construct an optimal classification hyperplane in the high-dimensional space to distinguish the data, and maximize a classification interval. The type of the kernel function in the support vector machine model is selected as a radial basis kernel function, and after the kernel function is determined, two optimal kernel function combinations, a kernel function parameter g and a penalty parameter c need to be determined.
The fourth step: the method comprises the following steps of optimizing parameters of the SVM model by using an improved particle swarm algorithm and training set data.
The first part is an improvement to the particle swarm algorithm, comprising the steps of:
step 4.1 the traditional particle swarm algorithm formula is:
in the formula, ω represents an inertial weight, c1And c2Is the learning factor of the learning factor,
respectively representThe position and velocity of the d-th dimension in the k-th iteration of the ith particle, rand () is 0,1]The random numbers are uniformly distributed in the range,
a d-dimension representing the individual optimal position of the ith particle,
and d dimension representing historical optimal positions of the particle swarm.
Step 4.2 should be continuously reduced as the search proceeds based on the principle ω of particle swarm algorithm, so a formula for dynamically adjusting the size of ω is adopted as follows:
wherein, ω ismaxRepresenting the maximum value of the inertial weight, ωminRepresents the minimum value of the inertia weight, and k represents when
Number of previous iterations, kmaxIndicating the maximum number of iterations
Step 4.3 learning factor c1And c2Embodies the capability of approaching the particles to the individual optimal solution and the global optimal solution, so a dynamic adjustment c is designed1And c2The formula for the size is:
where k denotes the current number of iterations, kmaxIndicating the maximum number of iterations.
The second part is to optimize the parameters of the support vector machine by using the improved particle swarm optimization, as shown in fig. 2, the optimization process comprises the following steps:
step 4.4 parameter initialization. And initializing parameters. Setting the population size m to be 50, the maximum iteration number k to be 100, and omegamax＝0.9，ωmin0.4, penalty parameter C ∈ [0.1, 100 ∈ [ ]]The kernel function parameter g ∈ [0.01, 100 ]]Defining a fitness function as the minimum mean square error of a training set under 10 times of cross validation, and initializing the speed and the position of a particle;
step 4.5, calculating the fitness value of each particle, and updating the individual optimal value and the global historical optimal value;
step 4.6 update the velocity and position of the particles by step 4.1, step 4.2, step 4.3;
and 4.7, judging whether the maximum iteration number is reached, if so, outputting the optimal parameters of the support vector machine, and otherwise, returning to the step 4.5.
The fifth step: and judging the tool wear by using the obtained optimal SVM model.
Finally, the above embodiments are only intended to illustrate the technical solutions of the present invention and not to limit the present invention, and although the present invention has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions, and all of them should be covered by the claims of the present invention.
Claims (1)
1. A cutter service life abrasion judging method based on edge calculation and particle swarm optimization is characterized in that: the method comprises the following steps:
step 1, preprocessing cutter data and extracting characteristics on the edge side;
step 2, dividing the characteristic matrix obtained in the step 1 in a cloud server and establishing a corresponding SVM model;
step 3, optimizing parameters of the SVM model by using the improved particle swarm algorithm and training set data in the cloud server;
step 4, using a test set in the cloud server to judge the tool life wear of the optimized support vector machine model;
in the step 1, the tool data preprocessing and feature extraction specifically includes:
step 1.1, carrying out operations of abnormal value elimination, missing value supplement and wavelet threshold noise filtering on an original signal;
step 1.2, analyzing the noise-filtered signals by using a Pearson correlation coefficient, and selecting variables closely related to cutter abrasion to construct a feature set;
step 1.3, the feature set obtained in step 1.2 is normalized, and the formula is as follows:
in the formula:
the ith data representing the normalized kth dimension features,
the ith data representing the feature of the kth dimension,
the maximum value of the feature of the k-th dimension is represented,
a minimum value representing a feature of the k-th dimension;
step 1.4, the feature set processed in step 1.3 is subjected to feature extraction by using a PCA technology, and the specific steps comprise:
step 1.4.1, subtracting the mean value of each dimension from each dimension of feature data;
step 1.4.2, calculating a characteristic covariance matrix;
step 1.4.3, calculating an eigenvalue and an eigenvector of the covariance matrix;
step 1.4.4, sorting the eigenvalues in descending order, taking the first K eigenvalues, and then taking eigenvectors corresponding to the K eigenvalues as column vectors to form an eigenvector matrix;
step 1.4.5, selecting K mainly depends on the variance and the ratio after dimensionality reduction, and the larger the proportion is, the more information is kept;
step 1.5, uploading the eigenvector matrix obtained in the step 1.4 to a cloud server;
in the step 2, the dividing, in the cloud server, the feature matrix obtained in S1 specifically includes: dividing the feature matrix uploaded on the edge side into a training set and a test set in a ratio of 4:1 in a cloud server, wherein training set data are used for SVM parameter optimization and establishment of an optimized SVM model, and test set data are used for cutter life abrasion judgment of the optimized SVM model;
the SVM is a support vector machine model, is a mechanical method based on a statistical learning theory, maps linear inseparable data of a low-dimensional space to a high-dimensional space, constructs an optimal classification hyperplane in the high-dimensional space to distinguish the data, and maximizes a classification interval; selecting the type of a kernel function in a support vector machine model as a radial basis kernel function, and determining two optimal kernel function combinations, a kernel function parameter g and a penalty parameter c after determining the kernel function;
in the step 3, the parameters of the support vector machine optimized by using the improved particle swarm optimization in the cloud server comprise two parts,
the first part is an improvement to the particle swarm algorithm, comprising the steps of:
step 3.1 the traditional particle swarm algorithm formula is:
in the formula, ω represents an inertial weight, c1And c2Is the learning factor of the learning factor,
respectively representing the position and velocity of the d-th dimension in the k-th iteration of the i-th particle, and rand () being 0,1]The random numbers are uniformly distributed in the range,
a d-dimension representing the individual optimal position of the ith particle,
a d dimension representing historical optimal positions of the particle swarm;
step 3.2: the principle ω based on particle swarm algorithm should be continuously reduced as the search proceeds, so a formula for dynamically adjusting ω size is adopted as follows:
wherein, ω ismaxRepresenting the maximum value of the inertial weight, ωminRepresents the minimum value of the inertia weight, and k represents when
Number of previous iterations, kmaxIndicating the maximum number of iterations
Step 3.3 learning factor c1And c2The capability of approaching the particles to the individual optimal solution and the global optimal solution is embodied,
therefore, a dynamic adjustment c is designed1And c2The formula for the size is:
where k denotes the current number of iterations, kmaxRepresenting the maximum number of iterations;
the second part is to optimize the parameters of the support vector machine by using the improved particle swarm optimization, and the optimization process comprises the following steps:
step 3.4, initializing parameters; setting the population size, the maximum iteration times, defining a fitness function, initializing the maximum value and the minimum value of the weight omega, initializing the position and the speed of each particle, and setting the value ranges of a kernel function parameter g and a penalty factor c;
step 3.5, calculating the fitness value of each particle, and updating the individual optimal value and the global historical optimal value;
step 3.6 update the velocity and position of the particles by step 3.1, step 3.2, step 3.3;
and 3.7, judging whether the maximum iteration number is reached, if so, outputting the optimal parameters of the support vector machine, and otherwise, returning to the step 3.5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010633618.7A CN111791090B (en) | 2020-07-02 | 2020-07-02 | Cutter life abrasion judgment method based on edge calculation and particle swarm optimization |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010633618.7A CN111791090B (en) | 2020-07-02 | 2020-07-02 | Cutter life abrasion judgment method based on edge calculation and particle swarm optimization |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111791090A CN111791090A (en) | 2020-10-20 |
| CN111791090B true CN111791090B (en) | 2022-03-29 |
Family
ID=72810064
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010633618.7A Active CN111791090B (en) | 2020-07-02 | 2020-07-02 | Cutter life abrasion judgment method based on edge calculation and particle swarm optimization |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111791090B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112706001A (en) * | 2020-12-23 | 2021-04-27 | 重庆邮电大学 | Machine tool cutter wear prediction method based on edge data processing and BiGRU-CNN network |
| CN113408182B (en) * | 2021-07-16 | 2022-05-06 | 山东大学 | Tool life full-cycle wear diagnosis method, device and storage medium based on multiple wavelet optimal features and neural network |
| CN113673845B (en) * | 2021-08-04 | 2023-11-14 | 上海航天精密机械研究所 | Hole machining sequencing method and system based on centralized utilization of cutters |
| CN116681901B (en) * | 2023-07-31 | 2023-10-31 | 山东捷瑞数字科技股份有限公司 | Method for predicting residual life of glass push broach tool bit based on industrial vision |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105740887A (en) * | 2016-01-26 | 2016-07-06 | 杭州电子科技大学 | Electroencephalogram feature classification method based on PSO-SVM (Particle Swarm Optimization-Support Vector Machine) |
| CN107378641B (en) * | 2017-08-23 | 2019-02-01 | 东北电力大学 | A kind of Monitoring Tool Wear States in Turning based on characteristics of image and LLTSA algorithm |
| CN107547457A (en) * | 2017-09-15 | 2018-01-05 | 重庆大学 | A kind of approach for blind channel equalization based on Modified particle swarm optimization BP neural network |
| CN108107838A (en) * | 2017-12-27 | 2018-06-01 | 山东大学 | A kind of numerical control equipment tool wear monitoring method based on cloud knowledge base and machine learning |
| CN109033730A (en) * | 2018-09-30 | 2018-12-18 | 北京工业大学 | A kind of tool wear prediction technique based on improved particle swarm optimization algorithm |
| CN109605127A (en) * | 2019-01-21 | 2019-04-12 | 南京航空航天大学 | A kind of cutting-tool wear state recognition methods and system |
| CN110303380B (en) * | 2019-07-05 | 2021-04-16 | 重庆邮电大学 | Method for predicting residual life of cutter of numerical control machine tool |
| CN110653661A (en) * | 2019-09-30 | 2020-01-07 | 山东大学 | Cutter state monitoring and identifying method based on signal fusion and multi-fractal spectrum algorithm |
-
2020
- 2020-07-02 CN CN202010633618.7A patent/CN111791090B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111791090A (en) | 2020-10-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111791090B (en) | Cutter life abrasion judgment method based on edge calculation and particle swarm optimization | |
| CN106371610B (en) | Electroencephalogram signal-based driving fatigue detection method | |
| Sun et al. | Multiclassification of tool wear with support vector machine by manufacturing loss consideration | |
| CN103839033A (en) | Face identification method based on fuzzy rule | |
| CN103544499A (en) | Method for reducing dimensions of texture features for surface defect detection on basis of machine vision | |
| CN102103691A (en) | Identification method for analyzing face based on principal component | |
| CN104616319A (en) | Multi-feature selection target tracking method based on support vector machine | |
| CN104268507A (en) | Manual alphabet identification method based on RGB-D image | |
| CN110728694A (en) | Long-term visual target tracking method based on continuous learning | |
| CN105809113A (en) | Three-dimensional human face identification method and data processing apparatus using the same | |
| CN111730412A (en) | Ant colony optimization algorithm-based micro milling cutter wear state monitoring method of support vector machine | |
| Singh et al. | Speaker specific feature based clustering and its applications in language independent forensic speaker recognition | |
| CN113989747A (en) | Terminal area meteorological scene recognition system | |
| CN114639238B (en) | Urban expressway traffic state estimation method based on normalized spectral clustering algorithm | |
| CN113316080B (en) | Indoor positioning method based on Wi-Fi and image fusion fingerprint | |
| CN112804650B (en) | Channel state information data dimension reduction method and intelligent indoor positioning method | |
| CN113989676A (en) | Terminal area meteorological scene identification method for improving deep convolutional self-coding embedded clustering | |
| Campos et al. | Global localization with non-quantized local image features | |
| Wu et al. | Real-time compressive tracking with motion estimation | |
| CN114861756A (en) | Driving behavior mode real-time classification method and system based on short-term observation | |
| CN113591780A (en) | Method and system for identifying driving risk of driver | |
| CN114093055A (en) | Road spectrum generation method and device, electronic equipment and medium | |
| CN113936246A (en) | Unsupervised target pedestrian re-identification method based on joint local feature discriminant learning | |
| CN112668446A (en) | Flower pollination algorithm-based method for monitoring wear state of micro milling cutter by optimizing SVM (support vector machine) | |
| Dougherty et al. | Feature extraction and selection |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240425 Address after: 400020 12-1 to 12-12, building 1, No. 8, West Ring Road, Jiangbei District, Chongqing Patentee after: Chongqing ruanjiang Turing Artificial Intelligence Technology Co.,Ltd. Country or region after: China Address before: 400065 Chongqing Nan'an District huangjuezhen pass Chongwen Road No. 2 Patentee before: CHONGQING University OF POSTS AND TELECOMMUNICATIONS Country or region before: China |