CN113780208A - Cutter wear state prediction method and device based on anti-migration learning - Google Patents

Cutter wear state prediction method and device based on anti-migration learning Download PDF

Info

Publication number
CN113780208A
CN113780208A CN202111085598.5A CN202111085598A CN113780208A CN 113780208 A CN113780208 A CN 113780208A CN 202111085598 A CN202111085598 A CN 202111085598A CN 113780208 A CN113780208 A CN 113780208A
Authority
CN
China
Prior art keywords
data set
domain data
tool
wear state
domain
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202111085598.5A
Other languages
Chinese (zh)
Inventor
李伟业
贺松平
余凡
李斌
裘超超
刘红奇
毛新勇
梁焜
赵尊元
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Wuhan Qingyi Intelligent Manufacturing Co.,Ltd.
Original Assignee
Huazhong University of Science and Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Huazhong University of Science and Technology filed Critical Huazhong University of Science and Technology
Priority to CN202111085598.5A priority Critical patent/CN113780208A/en
Publication of CN113780208A publication Critical patent/CN113780208A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/02—Preprocessing
    • G06F2218/04—Denoising
    • G06F2218/06—Denoising by applying a scale-space analysis, e.g. using wavelet analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/08—Feature extraction
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/12—Classification; Matching

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Business, Economics & Management (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Strategic Management (AREA)
  • Human Resources & Organizations (AREA)
  • Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Economics (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Development Economics (AREA)
  • Signal Processing (AREA)
  • Game Theory and Decision Science (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Feedback Control In General (AREA)

Abstract

The invention discloses a tool wear state prediction method and device based on anti-migration learning, and belongs to the technical field of tool wear state prediction of a numerical control machining center. The method combines dynamic distribution self-adaptation and anti-migration learning, and firstly obtains and processes a source domain data set and a target domain data set with labels; then, constructing an anti-migration learning model comprising a feature extraction network, a label classifier, a global area discriminator and a local area discriminator; and finally, training the anti-migration learning model based on the source domain data set and the target domain data set by taking the loss of the anti-migration learning model as a target to be minimized. Therefore, the method can assist in establishing the anti-migration learning model under other scenes by utilizing the existing labeled tool wear monitoring data (source domain data), so that the problem of wear state prediction of tools with different diameters can be solved by only needing less labeled target domain data.

Description

Cutter wear state prediction method and device based on anti-migration learning
Technical Field
The invention belongs to the technical field of tool wear state prediction of a numerical control machining center, and particularly relates to a tool wear state prediction method and device based on anti-migration learning.
Background
The abrasion of the cutter has important influence on the machining precision and the surface quality of parts, and the establishment of an effective cutter abrasion prediction model can improve the product percent of pass and reduce the production cost. The data of different types of tool machining are greatly different from the training data distribution of the existing model, and the model needs to be retrained by the data of the type of tool with a wear value or a wear state label. However, the data with the labels acquired in the actual processing scene is expensive and very difficult, and currently, some transfer learning methods can be used for predicting the wear states of tools with the same type and different diameters. However, for the wear state prediction of different types of tools, the difference between the wear processes of the source tool and the target tool is large, the adaptation between the fields is difficult to perform, and the wear state prediction is difficult.
Therefore, in the field, research on different types of tool wear prediction models in a scene with few label data is needed by means of labeled tool wear monitoring data and prediction models in an existing scene, so as to solve the problem of predicting the wear states of different types of tools in milling of a numerical control machine.
Disclosure of Invention
Aiming at the defects or improvement requirements of the prior art, the invention provides a tool wear state prediction method and device based on anti-migration learning, and aims to solve the technical problem that when tool wear prediction is performed in a new scene, enough tool wear state or wear value labels corresponding to monitoring signals are difficult to obtain and are used for wear state prediction model training.
In order to achieve the above object, the present invention provides a tool wear state prediction method based on anti-migration learning, comprising the steps of:
s1, obtaining vibration signals and tool wear values of the source tool and the target tool; preprocessing the vibration signal, and corresponding the processed signal to a tool wear value to obtain a source domain data set and a target domain data set with labels;
s2, constructing an antagonistic transfer learning model comprising a feature extraction network, a label classifier, a global area discriminator and a local area discriminator; the feature extraction network is used for performing feature extraction on the source domain data set and the target domain data set to obtain sample features; the label classifier predicts the wear state of the sample according to the sample characteristics; the global area discriminator predicts the domain category of the sample according to the sample characteristics; the local area discriminator firstly predicts the wear state of the sample based on the label classifier and then judges the area type of the sample with the predicted wear state;
s3, training the anti-migration learning model based on the source domain data set and the target domain data set with the aim of minimizing the loss of the anti-migration learning model; and the target tool wear state prediction is realized by utilizing a trained antagonistic transfer learning model.
Further, the loss function of the migration-resistant learning model is:
Figure BDA0003265569640000021
wherein the content of the first and second substances,
Figure BDA0003265569640000022
network weight parameters of the feature extraction network, the label classifier, the global domain discriminator and the local domain discriminator are respectively obtained; c is the type number of the cutter wearing state, and C is the type number of the cutter wearing state; l iscFor source domain classification loss, LgFor global adaptive loss, LlFor local adaptive loss, λ is a weight coefficient, and ω is a dynamic factor;
Figure BDA0003265569640000023
Figure BDA0003265569640000024
Figure BDA0003265569640000025
in the formula (I), the compound is shown in the specification,
Figure BDA0003265569640000026
in the form of a source-domain data set,
Figure BDA0003265569640000027
for the target domain data set, ysA source domain data tag; x is the number ofiIs a data sample, and
Figure BDA0003265569640000028
ns、ntthe number of data set samples in source domain and target domain, Gf(xi) For the sample features extracted by the feature extraction network, Gd(Gf(xi) Represents the domain class predicted by the global domain arbiter,
Figure BDA0003265569640000031
representing the sample wear state predicted by the label classifier,
Figure BDA0003265569640000032
representing the domain class predicted by the local domain discriminator, diIs a domain category label.
Further, the dynamic factor ω is:
Figure BDA0003265569640000033
in the formula (I), the compound is shown in the specification,
Figure BDA0003265569640000034
further, in S1, acquiring vibration signals and tool wear values of the source tool and the target tool includes: arranging a vibration sensor near a machine tool spindle, and acquiring spindle vibration signals in the machining process through a Dewesoft acquisition instrument; and (4) photographing by using a microscope to mark the cutter wear value label.
Further, in S1, the preprocessing the vibration signal includes: and denoising and wavelet decomposition and reconstruction are carried out on the vibration signal.
Further, in S2, the feature extraction network is a depth feature extraction network of a residual network structure.
In order to achieve the above object, the present invention further provides a tool wear state prediction device based on anti-migration learning, including:
the data acquisition and preprocessing module is used for acquiring vibration signals and tool wear values of a source tool and a target tool; preprocessing the vibration signal, and corresponding the processed signal to a tool wear value to obtain a source domain data set and a target domain data set with labels;
the system comprises an antagonistic transfer learning model construction module, a label classification module, a global area discriminator, a local area discriminator and a local area discriminator, wherein the antagonistic transfer learning model construction module is used for constructing an antagonistic transfer learning model comprising a feature extraction network, a label classifier, the global area discriminator and the local area discriminator; the feature extraction network is used for performing feature extraction on the source domain data set and the target domain data set to obtain sample features; the label classifier predicts the wear state of the sample according to the sample characteristics; the global area discriminator predicts the domain category of the sample according to the sample characteristics; the local area discriminator firstly predicts the wear state of the sample based on the label classifier and then judges the area type of the sample with the predicted wear state;
a migration-resistant learning model training module for training the migration-resistant learning model based on the source domain data set and the target domain data set with the goal of minimizing the loss of the migration-resistant learning model; and the target tool wear state prediction is realized by utilizing a trained antagonistic transfer learning model.
Generally, by the above technical solution conceived by the present invention, the following beneficial effects can be obtained:
(1) the method combines dynamic distribution self-adaptation and anti-migration learning, and firstly obtains and processes a source domain data set and a target domain data set with labels; then, constructing an anti-migration learning model comprising a feature extraction network, a label classifier, a global area discriminator and a local area discriminator; and finally, training the anti-migration learning model based on the source domain data set and the target domain data set by taking the loss of the anti-migration learning model as a target to be minimized. Therefore, the method can assist in establishing the anti-migration learning model under other scenes by utilizing the existing labeled tool wear monitoring data (source domain data), so that the problem of wear state prediction of tools with different diameters can be solved by only needing less labeled target domain data.
(2) The method can effectively carry out source domain and target domain adaptation from condition distribution and edge distribution respectively, thereby improving the accuracy of the wear prediction of different types of cutters.
(3) When the anti-migration learning model is trained, the loss function related to domain self-adaptation is designed, a multi-stage learning rate curve adjusted according to requirements is adopted, the optimizer is a random gradient descent method, the model training speed is high, and the prediction effect on the wear states of the source cutter and the target cutter is good.
Drawings
FIG. 1 is a flowchart of a tool wear state prediction method based on anti-migration learning according to an embodiment of the present invention;
FIG. 2 is a diagram of two types of tools according to an embodiment of the present invention, wherein (a) is an 8mm end mill milling tool and (b) is a 2mm injection mold finishing tool;
FIG. 3 is a diagram of the time domain and frequency domain components of the vibration signals of different types of tool machining spindles according to an embodiment of the present invention, where (a) is a 8mm milling tool machining vibration time domain signal, (b) is an 8mm milling tool machining vibration signal frequency spectrum, (c) is a mold finishing tool machining vibration time domain signal, and (d) is a mold finishing tool machining vibration signal frequency spectrum;
FIG. 4 is a diagram illustrating a structure of an anti-migration learning model according to an embodiment of the present invention;
FIG. 5 is a graph illustrating model learning rate settings according to an exemplary embodiment of the present invention;
FIG. 6 is a confusion matrix of source domain 8mm diameter end mill test data predictions according to an embodiment of the present invention;
FIG. 7 is a matrix of confusion of data predictions for a target field 2mm injection mold finishing tool according to an embodiment of the present invention;
FIG. 8 is a graph illustrating the variation of the dynamic countermeasure factor ω during the model training process according to an embodiment of the present invention;
fig. 9 is a block diagram of a tool wear state prediction apparatus based on anti-migration learning according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
In the present application, the terms "first," "second," and the like (if any) in the description and the drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.
Fig. 1 is a flowchart of a tool wear state prediction method based on learning against migration according to an embodiment of the present invention, where the detection method includes operations S1-S3.
Operation S1, obtaining vibration signals and tool wear values of the source tool and the target tool; and preprocessing the vibration signal, and corresponding the processed signal with a tool wear value to obtain a source domain data set and a target domain data set with labels. Specifically, the method comprises the following steps:
the source domain data set and the target domain data set are respectively obtained through the following steps:
s11, respectively building different types of cutter milling abrasion experiment platforms of the numerical control machine tool, arranging a vibration sensor near a main shaft of a machining center, and collecting main shaft vibration signals in the machining process through a Dewesoft acquisition instrument;
s12, shooting each cutting edge abrasion picture by adopting a portable microscope under the condition that the cutter is not detached, and marking the cutter abrasion value by magnification;
and S13, denoising the original vibration signal, obtaining a reconstructed signal through wavelet decomposition, and establishing a source domain data set and a target domain data set.
The source cutter is a cutter with enough labeled cutter wear monitoring data, and the target cutter is a cutter to be predicted.
Operation S2, constructing an antagonistic migration learning model including a feature extraction network, a label classifier, a global area discriminator, and a local area discriminator; the feature extraction network is used for performing feature extraction on the source domain data set and the target domain data set to obtain sample features; the label classifier predicts the wear state of the sample according to the sample characteristics; the global area discriminator predicts the domain category of the sample according to the sample characteristics; the local area discriminator predicts the wear state of the sample based on the label classifier, and then judges the area type of the sample with the predicted wear state. Specifically, the method comprises the following steps:
and establishing a transfer-resistant learning model, judging the data domain label, and realizing condition distribution and edge distribution self-adaptation of the source domain and target domain sample characteristics.
The loss function against the migration learning model is:
Figure BDA0003265569640000061
wherein the content of the first and second substances,
Figure BDA0003265569640000062
network weight parameters of the feature extraction network, the label classifier, the global domain discriminator and the local domain discriminator are respectively obtained; c is the type number of the cutter wearing state, and C is the type number of the cutter wearing state; l iscFor source domain classification loss, LgFor global adaptive loss, LlFor local adaptive loss, λ is a weight coefficient, and ω is a dynamic factor;
Figure BDA0003265569640000063
Figure BDA0003265569640000071
Figure BDA0003265569640000072
in the formula (I), the compound is shown in the specification,
Figure BDA0003265569640000073
in the form of a source-domain data set,
Figure BDA0003265569640000074
for the target domain data set, ysA source domain data tag; x is the number ofiIs a data sample, and
Figure BDA0003265569640000075
ns、ntthe number of data set samples in source domain and target domain, Gf(xi) For the sample features extracted by the feature extraction network, Gd(Gf(xi) Represents the domain class predicted by the global domain arbiter,
Figure BDA0003265569640000076
representing the sample wear state predicted by the label classifier,
Figure BDA0003265569640000077
representing the domain class predicted by the local domain discriminator, diIs a domain category label.
Meanwhile, the difference between the edge distribution and the condition distribution of the source domain and the target domain is different, and the importance degree of adaptation is inconsistent, so a dynamic factor omega is introduced and updated after each round of training, and the calculation method is as follows:
Figure BDA0003265569640000078
in the formula (I), the compound is shown in the specification,
Figure BDA0003265569640000079
furthermore, the feature extraction network is used for extracting deep features of the source domain data and the target domain data, and the input of the network is time domain and frequency domain components after the original vibration signal is subjected to noise reduction and time domain and frequency domain components of the wavelet decomposition reconstruction signal. The depth feature extraction network is built by adopting a residual error network structure. In the deep learning network, the depth of the network is increased to obtain better nonlinear mapping capability, so that the prediction effect of the model can be improved. However, increasing the depth of the network makes the parameters of the network more difficult to converge on one hand, and on the other hand, the gradient of the network gradually decreases during the back propagation process of a plurality of network layers, and when the network layers are too deep, the gradient may become zero, which may cause the model to fail. Therefore, the prediction effect cannot be improved by increasing the network depth without limit, the special structure of the residual error neural network enables a deeper network, and the gradient disappearance is avoided by adding the input to the output again, and the model effect is not influenced.
An operation S3 of training the anti-migration learning model based on the source domain data set and the target domain data set with a goal of minimizing a loss of the anti-migration learning model; and the target tool wear state prediction is realized by utilizing a trained antagonistic transfer learning model. Specifically, the method comprises the following steps:
and training the established anti-migration learning model on the source domain and target domain data sets by adopting a strategy of adjusting the learning rate as required to realize the prediction of the wear states of different types of cutters.
The learning rate in the training process adopts a strategy of adjusting according to requirements, which is divided into four stages, and different learning rates are respectively adopted in 0-100, 100-300, 300-600 and 600-1000 training rounds.
The model data input batch size is 64, the training iteration number (Epoch) is 1000, and the optimizer is a random gradient descent method.
The method of the present invention will be described below by taking a 8mm end mill machining tool and a 2mm injection mold finish machining tool as examples.
The embodiment of the invention comprises the following steps:
(1) experimental data acquisition and preprocessing
Acquiring spindle three-way vibration signals and tool wear values of a milling process of a 8mm end mill and a 2mm injection mold finish machining tool of a numerical control machine tool, and generating source domain and target domain data sets after performing vibration signal noise reduction and wavelet decomposition reconstruction on the two milling tools as shown in FIG. 2;
the specific data acquisition and preprocessing steps are as follows:
(1.1) building an 8mm end mill milling cutter abrasion experiment platform and a 2mm injection mold finish machining cutter abrasion experiment platform of a numerical control machine tool, arranging a vibration sensor near a main shaft of the machine tool, and acquiring a main shaft vibration signal in the machining process through a Dewesoft acquisition instrument, wherein time domain and frequency domain components of the vibration signal are shown in figure 3;
(1.2) measuring a tool wear value by adopting an automatic zooming three-dimensional measuring instrument as a data label;
and (1.3) denoising the original vibration signal, obtaining a reconstructed signal through wavelet decomposition, and establishing a source domain data set and a target domain data set.
(2) Construction of an antagonistic migration learning model
And establishing a transfer-resistant learning model, judging the data domain label, and realizing the condition distribution and edge distribution self-adaptation of the source domain and target domain signal characteristics.
The loss function against the migration learning model is:
Figure BDA0003265569640000091
wherein the content of the first and second substances,
Figure BDA0003265569640000092
network weight parameters of the feature extraction network, the label classifier, the global domain discriminator and the local domain discriminator are respectively obtained; c is the type number of the cutter wearing state, and C is the type number of the cutter wearing state; l iscFor source domain classification loss, LgFor global adaptive loss, LlFor local adaptive loss, λ is a weight coefficient, and ω is a dynamic factor;
Figure BDA0003265569640000093
Figure BDA0003265569640000094
Figure BDA0003265569640000095
in the formula (I), the compound is shown in the specification,
Figure BDA0003265569640000096
in the form of a source-domain data set,
Figure BDA0003265569640000097
for the target domain data set, ysA source domain data tag; x is the number ofiIs a data sample, and
Figure BDA0003265569640000098
ns、ntthe number of data set samples in source domain and target domain, Gf(xi) For the sample features extracted by the feature extraction network, Gd(Gf(xi) Represents the domain class predicted by the global domain arbiter,
Figure BDA0003265569640000099
representing the sample wear state predicted by the label classifier,
Figure BDA00032655696400000910
representing the domain class predicted by the local domain discriminator, diIs a domain category label.
Meanwhile, the difference between the edge distribution and the condition distribution of the source domain and the target domain is different, and the importance degree of adaptation is inconsistent, so a dynamic factor omega is introduced and updated after each round of training, and the calculation method is as follows:
Figure BDA00032655696400000911
in the formula (I), the compound is shown in the specification,
Figure BDA00032655696400000912
(3) model training
The structure of the constructed anti-migration learning model is shown in fig. 4, and the model consists of four parts: the first part is a model feature extraction part and adopts a residual error neural network; the second part is a classifier used for classifying the wear state of the cutter; the third and fourth parts are domain discrimination networks, and whether the input features come from domain source domain or target domain data is judged.
The learning rate in the training process adopts a strategy adjusted as required, as shown in fig. 5, which is divided into four stages, and different learning rates are respectively adopted in 0-100, 100-300, 300-600, and 600-1000 training rounds; the model data input batch size is 64, the training iteration number (Epoch) is 1000, and the optimizer is a random gradient descent method.
And training by adopting a strategy of adjusting the learning rate as required on the source domain data set and the target domain data set to realize the prediction of the wear states of different types of milling tools.
And performing model test by using the test data of the source domain, and finally reaching 94.7% of accuracy by comparing the actual label with the predicted label. The accuracy rates of the prediction of initial abrasion, normal abrasion and serious abrasion are respectively 97.1%, 92.9% and 94.0%. And outputting a prediction label of the source domain test data, and drawing a confusion matrix compared with a real label, as shown in FIG. 6.
And outputting the prediction result of the target domain, wherein the three states respectively have 600 samples and 1800 samples in total. The final accuracy was 71%. The accuracy of prediction of initial wear, normal wear and severe wear is 88.7%, 67.2% and 57.2%, respectively. And outputting a predicted label of the target domain test data, and drawing a confusion matrix by comparing the predicted label with the real label, as shown in fig. 7.
The dynamic countermeasure factor of the model, i.e., the dynamic factor ω measuring the dissimilarity of the condition distribution and the edge distribution, varies as shown in fig. 8, and eventually stabilizes at 0.66 as the model is iterated.
The source domain and target domain data are subjected to dimensionality reduction output after network feature extraction, visualization is carried out, and it can be obtained that the features of the source domain are divided into three parts and have obvious boundaries at the 100 th Epoch, but the feature distribution of the target domain is greatly different from the feature distribution of the source domain, the feature distribution of the source domain and the feature distribution of the target domain are approximately consistent at the 550 th Epoch, and the model is proved to be adaptive to the two domains.
Fig. 9 is a block diagram of a tool wear state prediction apparatus based on anti-migration learning according to an embodiment of the present invention. Referring to fig. 9, the prediction apparatus 900 includes a data acquisition and preprocessing module 910, an anti-migration learning model construction module 920, and an anti-migration learning model training module 930.
The data obtaining and preprocessing module 910, for example, performs operation S1 for obtaining vibration signals and tool wear values of the source tool and the target tool; preprocessing the vibration signal, and corresponding the processed signal to a tool wear value to obtain a source domain data set and a target domain data set with labels;
the antagonistic migration learning model building module 920 performs, for example, operation S2 for building an antagonistic migration learning model including a feature extraction network, a label classifier, a global domain discriminator, and a local domain discriminator; the feature extraction network is used for performing feature extraction on the source domain data set and the target domain data set to obtain sample features; the label classifier predicts the wear state of the sample according to the sample characteristics; the global area discriminator predicts the domain category of the sample according to the sample characteristics; the local area discriminator firstly predicts the wear state of the sample based on the label classifier and then judges the area type of the sample with the predicted wear state;
the anti-migration learning model training module 930 performs, for example, operation S3 for training the anti-migration learning model based on the source domain data set and the target domain data set with a goal of minimizing the loss of the anti-migration learning model; and the target tool wear state prediction is realized by utilizing a trained antagonistic transfer learning model.
The prediction apparatus 900 is used to perform the prediction method in the embodiment shown in fig. 1. For details that are not described in the present embodiment, please refer to the prediction method in the embodiment shown in fig. 1, which is not described herein again.
In conclusion, based on the method provided by the invention, after the noise reduction and reconstruction of the main shaft vibration signals in the milling process of different types of cutters of the numerical control machine tool, the main shaft vibration signals are input into the dynamic countermeasure migration learning model for training, and after the wear states of different types of cutters are identified, the method is found to have great significance for the research of the identification of the wear states of different types of cutters of the numerical control machine tool and the monitoring of the machine tool state no matter the method is from the accuracy of the identification of the wear states of different types of cutters or the effectiveness of the migration of different types of cutter models.
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.

Claims (7)

1. A tool wear state prediction method based on anti-migration learning is characterized by comprising the following steps:
s1, obtaining vibration signals and tool wear values of the source tool and the target tool; preprocessing the vibration signal, and corresponding the processed signal to a tool wear value to obtain a source domain data set and a target domain data set with labels;
s2, constructing an antagonistic transfer learning model comprising a feature extraction network, a label classifier, a global area discriminator and a local area discriminator; the feature extraction network is used for performing feature extraction on the source domain data set and the target domain data set to obtain sample features; the label classifier predicts the wear state of the sample according to the sample characteristics; the global area discriminator predicts the domain category of the sample according to the sample characteristics; the local area discriminator firstly predicts the wear state of the sample based on the label classifier and then judges the area type of the sample with the predicted wear state;
s3, training the anti-migration learning model based on the source domain data set and the target domain data set with the aim of minimizing the loss of the anti-migration learning model; and the target tool wear state prediction is realized by utilizing a trained antagonistic transfer learning model.
2. The tool wear state prediction method based on anti-migration learning of claim 1, wherein the loss function of the anti-migration learning model is:
Figure FDA0003265569630000011
wherein the content of the first and second substances,
Figure FDA0003265569630000012
network weight parameters of the feature extraction network, the label classifier, the global domain discriminator and the local domain discriminator are respectively obtained; c is the type number of the cutter wearing state, and C is the type number of the cutter wearing state; l iscFor source domain classification loss, LgFor global adaptive loss, LlFor local adaptive loss, λ is a weight coefficient, and ω is a dynamic factor;
Figure FDA0003265569630000013
Figure FDA0003265569630000014
Figure FDA0003265569630000021
in the formula (I), the compound is shown in the specification,
Figure FDA0003265569630000022
in the form of a source-domain data set,
Figure FDA0003265569630000023
for the target domain data set, ysA source domain data tag; x is the number ofiIs a data sample, and
Figure FDA0003265569630000024
ns、ntthe number of data set samples in source domain and target domain, Gf(xi) For the sample features extracted by the feature extraction network, Gd(Gf(xi) Represents the domain class predicted by the global domain arbiter,
Figure FDA0003265569630000025
representing the sample wear state predicted by the label classifier,
Figure FDA0003265569630000026
representing the domain class predicted by the local domain discriminator, diIs a domain category label.
3. The tool wear state prediction method based on the anti-migration learning according to claim 2, wherein the dynamic factor ω is:
Figure FDA0003265569630000027
in the formula (I), the compound is shown in the specification,
Figure FDA0003265569630000028
4. the tool wear state prediction method based on the learning against migration according to any one of claims 1 to 3, wherein in the step S1, obtaining the vibration signals and the tool wear values of the source tool and the target tool includes: arranging a vibration sensor near a machine tool spindle, and acquiring spindle vibration signals in the machining process through a Dewesoft acquisition instrument; and (4) photographing by using a microscope to mark the cutter wear value label.
5. The tool wear state prediction method based on learning against migration according to any one of claims 1 to 3, wherein in the step S1, the preprocessing of the vibration signal includes: and denoising and wavelet decomposition and reconstruction are carried out on the vibration signal.
6. The tool wear state prediction method based on learning against migration according to any one of claims 1 to 3, wherein in the step S2, the feature extraction network is a depth feature extraction network of a residual network structure.
7. A tool wear state prediction device based on anti-migration learning, comprising:
the data acquisition and preprocessing module is used for acquiring vibration signals and tool wear values of a source tool and a target tool; preprocessing the vibration signal, and corresponding the processed signal to a tool wear value to obtain a source domain data set and a target domain data set with labels;
the system comprises an antagonistic transfer learning model construction module, a label classification module, a global area discriminator, a local area discriminator and a local area discriminator, wherein the antagonistic transfer learning model construction module is used for constructing an antagonistic transfer learning model comprising a feature extraction network, a label classifier, the global area discriminator and the local area discriminator; the feature extraction network is used for performing feature extraction on the source domain data set and the target domain data set to obtain sample features; the label classifier predicts the wear state of the sample according to the sample characteristics; the global area discriminator predicts the domain category of the sample according to the sample characteristics; the local area discriminator firstly predicts the wear state of the sample based on the label classifier and then judges the area type of the sample with the predicted wear state;
a migration-resistant learning model training module for training the migration-resistant learning model based on the source domain data set and the target domain data set with the goal of minimizing the loss of the migration-resistant learning model; and the target tool wear state prediction is realized by utilizing a trained antagonistic transfer learning model.
CN202111085598.5A 2021-09-16 2021-09-16 Cutter wear state prediction method and device based on anti-migration learning Pending CN113780208A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111085598.5A CN113780208A (en) 2021-09-16 2021-09-16 Cutter wear state prediction method and device based on anti-migration learning

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111085598.5A CN113780208A (en) 2021-09-16 2021-09-16 Cutter wear state prediction method and device based on anti-migration learning

Publications (1)

Publication Number Publication Date
CN113780208A true CN113780208A (en) 2021-12-10

Family

ID=78844481

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111085598.5A Pending CN113780208A (en) 2021-09-16 2021-09-16 Cutter wear state prediction method and device based on anti-migration learning

Country Status (1)

Country Link
CN (1) CN113780208A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPWO2023276097A1 (en) * 2021-07-01 2023-01-05
CN115933531A (en) * 2023-01-09 2023-04-07 广东工业大学 Machine tool thermal error modeling method and system based on depth domain anti-migration
CN116070146A (en) * 2023-01-10 2023-05-05 西南石油大学 Pore structure analysis method integrating migration learning
CN116662768A (en) * 2023-08-02 2023-08-29 上海交通大学 Wear state online monitoring method and system based on migration learning and multisource information fusion

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108581633A (en) * 2018-04-11 2018-09-28 温州大学 A method of based on the more sensor monitoring cutting tool states of genetic algorithm optimization
CN111832624A (en) * 2020-06-12 2020-10-27 上海交通大学 Tool remaining life prediction method based on anti-migration learning
AU2020103905A4 (en) * 2020-12-04 2021-02-11 Chongqing Normal University Unsupervised cross-domain self-adaptive medical image segmentation method based on deep adversarial learning

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108581633A (en) * 2018-04-11 2018-09-28 温州大学 A method of based on the more sensor monitoring cutting tool states of genetic algorithm optimization
CN111832624A (en) * 2020-06-12 2020-10-27 上海交通大学 Tool remaining life prediction method based on anti-migration learning
AU2020103905A4 (en) * 2020-12-04 2021-02-11 Chongqing Normal University Unsupervised cross-domain self-adaptive medical image segmentation method based on deep adversarial learning

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
JINYANG JIAO 等: "A mixed adversarial adaptation network for intelligent fault diagnosis", JOURNAL OF INTELLIGENT MANUFACTURING, vol. 33, 29 April 2021 (2021-04-29), pages 2207 - 2222 *
沈长青等: "基于自适应流形嵌入动态分布对齐的轴承故障诊断", 电子测量与仪器学报, vol. 35, no. 2, 28 February 2021 (2021-02-28), pages 33 - 39 *

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPWO2023276097A1 (en) * 2021-07-01 2023-01-05
JP7325697B2 (en) 2021-07-01 2023-08-14 三菱電機株式会社 Transfer learning device and transfer learning method
CN115933531A (en) * 2023-01-09 2023-04-07 广东工业大学 Machine tool thermal error modeling method and system based on depth domain anti-migration
CN115933531B (en) * 2023-01-09 2024-04-05 广东工业大学 Machine tool thermal error modeling method and system based on depth domain countermeasure migration
CN116070146A (en) * 2023-01-10 2023-05-05 西南石油大学 Pore structure analysis method integrating migration learning
CN116070146B (en) * 2023-01-10 2023-09-26 西南石油大学 Pore structure analysis method integrating migration learning
CN116662768A (en) * 2023-08-02 2023-08-29 上海交通大学 Wear state online monitoring method and system based on migration learning and multisource information fusion
CN116662768B (en) * 2023-08-02 2023-10-24 上海交通大学 Wear state online monitoring method and system based on migration learning and multisource information fusion

Similar Documents

Publication Publication Date Title
CN113780208A (en) Cutter wear state prediction method and device based on anti-migration learning
CN109514349B (en) Tool wear state monitoring method based on vibration signal and Stacking integrated model
Dun et al. A chatter detection method in milling of thin-walled TC4 alloy workpiece based on auto-encoding and hybrid clustering
CN110647943B (en) Cutting tool wear monitoring method based on evolution data cluster analysis
CN112254964A (en) Rolling bearing fault diagnosis method based on rapid multi-scale convolution neural network
Ambadekar et al. CNN based tool monitoring system to predict life of cutting tool
CN111633467B (en) Cutter wear state monitoring method based on one-dimensional depth convolution automatic encoder
CN109158954B (en) Ultrasonic cutter wear state identification method and system based on acoustic signal detection
CN113567130A (en) Bearing fault diagnosis method based on multiple working conditions of equipment
CN111562108A (en) Rolling bearing intelligent fault diagnosis method based on CNN and FCMC
CN108197647B (en) Rapid clustering method for automobile starter endurance test data
CN111832432B (en) Cutter wear real-time prediction method based on wavelet packet decomposition and deep learning
Klancnik et al. Computer vision-based approach to end mill tool monitoring
CN110928237B (en) Vibration signal-based numerical control machining center flutter online identification method
CN106002490B (en) Milling workpiece roughness monitoring method based on Path and redundant eliminating
CN111145145B (en) Image surface defect detection method based on MobileNet
CN114346761B (en) Cutter abrasion condition detection method based on improved condition generation countermeasure network
CN113762182A (en) Milling cutter wear state prediction method and device based on depth network self-adaptation
CN110659682A (en) Data classification method based on MCWD-KSMOTE-AdaBoost-DenseNet algorithm
Jegorowa et al. Deep learning methods for drill wear classification based on images of holes drilled in melamine faced chipboard
CN114429152A (en) Rolling bearing fault diagnosis method based on dynamic index antagonism self-adaption
Kurek et al. Data augmentation techniques for transfer learning improvement in drill wear classification using convolutional neural network
CN113369993B (en) Method for monitoring tool wear state under small sample
CN113109782B (en) Classification method directly applied to radar radiation source amplitude sequence
CN112487406B (en) Network behavior analysis method based on machine learning

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
TA01 Transfer of patent application right

Effective date of registration: 20230524

Address after: 430206 No. 8, Ligou South Road, Donghu New Technology Development Zone, Wuhan City, Hubei Province

Applicant after: WUHAN INTELLIGENT EQUIPMENT INDUSTRIAL INSTITUTE Co.,Ltd.

Address before: 430074 Hubei Province, Wuhan city Hongshan District Luoyu Road No. 1037

Applicant before: HUAZHONG University OF SCIENCE AND TECHNOLOGY

TA01 Transfer of patent application right
TA01 Transfer of patent application right

Effective date of registration: 20231201

Address after: F2A206, 2nd Floor, Phase I, Wuhan Intelligent Equipment Park, No. 8 Ligou South Road, Donghu New Technology Development Zone, Wuhan City, Hubei Province (Wuhan Free Trade Zone)

Applicant after: Wuhan Qingyi Intelligent Manufacturing Co.,Ltd.

Address before: 430206 No. 8, Ligou South Road, Donghu New Technology Development Zone, Wuhan City, Hubei Province

Applicant before: WUHAN INTELLIGENT EQUIPMENT INDUSTRIAL INSTITUTE Co.,Ltd.

TA01 Transfer of patent application right