CN116226784A - Federal domain adaptive fault diagnosis method based on statistical feature fusion - Google Patents
Federal domain adaptive fault diagnosis method based on statistical feature fusion Download PDFInfo
- Publication number
- CN116226784A CN116226784A CN202310124876.6A CN202310124876A CN116226784A CN 116226784 A CN116226784 A CN 116226784A CN 202310124876 A CN202310124876 A CN 202310124876A CN 116226784 A CN116226784 A CN 116226784A
- Authority
- CN
- China
- Prior art keywords
- domain
- fault diagnosis
- source domain
- data
- statistical
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003745 diagnosis Methods 0.000 title claims abstract description 64
- 238000000034 method Methods 0.000 title claims abstract description 49
- 230000003044 adaptive effect Effects 0.000 title claims abstract description 23
- 230000004927 fusion Effects 0.000 title claims abstract description 22
- 238000012549 training Methods 0.000 claims abstract description 19
- 230000002776 aggregation Effects 0.000 claims abstract description 5
- 238000004220 aggregation Methods 0.000 claims abstract description 5
- 238000000605 extraction Methods 0.000 claims description 29
- 238000011176 pooling Methods 0.000 claims description 10
- 238000012937 correction Methods 0.000 claims description 5
- 238000012360 testing method Methods 0.000 claims description 4
- 238000012935 Averaging Methods 0.000 claims description 3
- 238000009826 distribution Methods 0.000 abstract description 8
- 235000014653 Carica parviflora Nutrition 0.000 description 9
- 241000243321 Cnidaria Species 0.000 description 9
- 230000006978 adaptation Effects 0.000 description 7
- 238000013508 migration Methods 0.000 description 6
- 230000005012 migration Effects 0.000 description 6
- 238000010606 normalization Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 4
- 238000013526 transfer learning Methods 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 3
- 238000005096 rolling process Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Classifications
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Test And Diagnosis Of Digital Computers (AREA)
Abstract
The invention discloses a federal domain adaptive fault diagnosis method based on statistical feature fusion, wherein a source domain client receives statistical features of a target domain client and statistical features of active domain data and respectively performs data standardization on a source domain data set; the central server sends the fault diagnosis model to all source domain clients, and then the source domain clients train the received global model in the source domain clients by using two standardized source domain data as input; the trained models are returned to a central server, and the central server carries out global model aggregation on the received models of all source domain clients; when the training round number reaches a set value, the training is finished to obtain a final fault diagnosis model, the final fault diagnosis model is sent to a target domain client, the target domain client obtains mechanical fault data to be diagnosed, and a fault diagnosis result is obtained through the fault diagnosis model. The invention utilizes the statistical distribution difference of the data between the target domain and the source domain to improve the generalization capability of the fault diagnosis model in the target domain.
Description
Technical Field
The invention relates to a fault diagnosis technology, in particular to a federal domain adaptive fault diagnosis method based on statistical feature fusion.
Background
The rotating machinery data are usually from equipment with different models and working conditions and different operating and using environments, and a fault diagnosis model cooperatively trained by using the data has low prediction accuracy and poor generalization capability on new data.
Document "Toward Secure Data Fusion in Industrial IoT Using Transfer Learning" proposes that domain generalization and domain adaptation methods in transfer learning can solve the domain drift problem by spatially aligning data features. Document "Deep Domain Generalization Combining A Priori Diagnosis Knowledge Toward Cross-Domain Fault Diagnosis of Rolling Bearing" proposes a rolling bearing fault diagnosis method based on domain generalization. The method eliminates potential differences among a plurality of domains under the condition that the target domain has only healthy samples, and realizes high-efficiency fault diagnosis. Document "Conditional Adversarial Domain Generalization With a Single Discriminator for Bearing Fault Diagnosis" proposes a condition-resistant domain generalization method with a discriminator, which aims to extract domain-invariant features from data of different working conditions and to popularize these features into new fault data. In order to realize condition countermeasure training, a new condition countermeasure strategy is designed, namely, a feature extractor can make the discriminators distinguish fault categories, but cannot distinguish domains so as to better confuse the discriminators and generalize features. Document "Intelligent Fault Identification Based on Multisource Domain Generalization Towards Actual Diagnosis Scenario" proposes a new intelligent fault identification method based on multiple source domains. The method uses local Fisher discriminant analysis to describe the discriminant structure of each source domain as a point of the Grassmann manifold. By preserving local structures within the class, local Fisher discriminant analysis can learn effective discriminants from multi-modal fault data. Document "ANew Multiple Source Domain Adaptation Fault Diagnosis Method Between Different Rotating Machines" proposes a multi-source domain-based adaptive migration learning method. The method uses a multi-challenge learning strategy to obtain a domain-aligned feature representation while having discriminant for the target domain. Document "Deep Adversarial Domain Adaptation Model for Bearing Fault Diagnosis" proposes a depth-directed domain adaptive model for fault diagnosis of rolling bearings. The model builds a reactive domain adaptation network to solve the problem of inconsistent characteristic distribution of a source domain and a target domain.
The data is the basis of a deep learning fault diagnosis algorithm, and in order to ensure the effectiveness of deep learning, as much data as possible needs to be aggregated for use. In order to safely and effectively aggregate and use the data of different clients, the problem of 'data island' in the deep learning process is solved, and federal learning is generated. The learning task in federal learning is solved in a loose federal form by multiple participating devices (i.e., clients) under the coordination of a central server. Federal learning uses collaborative training of models of data from different clients, but because of the different working conditions or models, these data often have domain drift problems, and therefore federal migration learning is attracting more and more attention from researchers.
Document "Federated Transfer Learning for Intelligent Fault Diagnostics Using Deep Adversarial Networks With Data Privacy" proposes a federal migration learning method for fault diagnosis, which designs different network model structures for different edges and implements federal communications using deep challenge learning. Document "Data privacy preserving federated transfer learning in machinery fault diagnostics using prior distributions. Structure Health Monitoring" proposes a federal migration learning method for mechanical failure diagnosis. The method proposes to indirectly solve the domain drift problem by using prior distribution, and to perform fault diagnosis by extracting domain invariant features of different users.
While federal migration learning achieves comparable performance in terms of fault diagnosis as migration learning, existing federal domain adaptation methods typically require feature data for all clients to be transmitted to a central server to achieve feature space alignment, which increases the cost of communication between the client and the model. In addition, the existing federal domain adaptation method lacks research on a client multi-sensor input signal feature fusion method.
Disclosure of Invention
In order to solve the defects in the prior art, the invention aims to provide a federal domain adaptive fault diagnosis method based on statistical feature fusion.
In order to achieve the purpose of the invention, the technical scheme adopted by the invention is as follows:
a federal domain adaptive fault diagnosis method based on statistical feature fusion comprises the following steps:
(1) The target domain client transmits the statistical features of the unlabeled fault data to the central server, and the central server transmits the statistical features to all source domain clients; the source domain client uses the received statistical characteristics and the statistical characteristics of the active domain data to respectively carry out data standardization on the source domain data set;
(2) The fault diagnosis model of the central server comprises a feature extraction network and a classification network, the central server sends a global model to all source domain clients, and then the source domain clients use two standardized source domain data as input and train the received global model in the source domain clients based on a correlation alignment method;
(3) After the models of all source domain clients are trained for one round, the trained models are sent to a central server, and the central server carries out global model aggregation on the received models of all source domain clients; then the training data are sent to all source domain clients to carry out the next training, and when the training round number reaches a set value, the training task is ended, so that a final fault diagnosis model is obtained;
(4) In the test stage, the central server sends the trained fault diagnosis model to the target domain client, the target domain client acquires mechanical fault data to be diagnosed, and a fault diagnosis result is obtained through the fault diagnosis model.
Further, in the step (1), the statistical characteristics are mean and standard deviation.
Further, in the step (2), in the feature extraction network, the statistical feature exchange of different feature extraction channels is adopted to realize the standardization of the output features of the channel, and the features of exchange standardization are adopted as the input of the classification network.
Further, in step (2), the global model received by the source domain client includes a feature extraction network and a classification network.
Further, the received global model is trained in the source domain client based on the correlation alignment method, specifically, the source domain client further comprises feature space metrics, and the feature space metrics constraint distances between different features of the same sensor data by using the correlation alignment method.
Further, the feature space metric is input by using the statistical feature exchange of different feature extraction channels to realize the standardized features.
Further, in step (3), the global model on the central server is aggregated into,
feature extractor for N global models on N source domain clients
Classifier of N global models on N source domain clients +.>
After averaging, the feature extractor of the global model on the central server is updated +.>
And classifier->
Wherein (1)>
Feature extractor for global model on ith source domain client,/i>
A classifier that is a global model on the ith source domain client.
Further, in step (4), the model received by the target domain client includes a feature extraction network and a classification network.
Further, the two channels of the characteristic extraction network have the same structure, and the characteristic extraction network consists of three groups of convolution layers, a regularization layer, a linear correction unit and a maximum pooling layer which are sequentially connected; the input of the feature extraction network first enters the first set of convolution layers, the first set of largest pooling layers is connected to the second set of convolution layers, and the second set of largest pooling layers is connected to the third set of convolution layers.
Further, the classification network is composed of a flattening layer, a first full-connection layer, a regularization layer, a correction linear unit layer, a second full-connection layer and a softmax function layer which are connected in sequence.
Compared with the prior art, the federal domain adaptive fault diagnosis method based on statistical feature fusion has the beneficial effects that the generalization capability of a fault diagnosis model in a target domain is improved by utilizing the statistical distribution difference of data between the target domain and a source domain and the statistical distribution difference of multi-sensor signals of the source domain data. In the invention, only the statistical characteristics and the like of the target domain data are transmitted to each source domain client, so that the communication burden is reduced. In addition, at the source domain client, the statistical features of the multi-sensor data features will be exchanged with each other, achieving feature domain space enhancement.
Drawings
FIG. 1 is a flow chart of a federal domain adaptive fault diagnosis method based on statistical feature fusion according to the present invention;
FIG. 2 is a schematic diagram of a feature extraction network;
fig. 3 is a schematic diagram of a client training model.
Detailed Description
The technical scheme of the invention is further described below with reference to the accompanying drawings and examples. The following examples are only for more clearly illustrating the technical solutions of the present invention and are not intended to limit the scope of protection of the present application.
As shown in fig. 1, the federal domain adaptive fault diagnosis method based on statistical feature fusion of the present invention includes the following steps:
(1) Firstly, standardizing source domain data, specifically, sending statistical features (mean value and standard deviation) of unlabeled fault data to a central server by a target domain client, and then sending the statistical features to all source domain clients by the central server; the source domain client uses the received statistical characteristics and the statistical characteristics of the active domain data to respectively carry out data standardization on the source domain data set;
let N data sets in N source domain clients be
The data set in the source domain client k is
Wherein m is k For the number of data samples contained in the source domain client k,/for the number of data samples contained in the source domain client k>
For the jth data sample in the kth source domain client,/for the kth source domain client>
Is the label of the jth data sample in the kth source domain client.
Data set of target domain client
In the n+1th client, N t For the number of target field samples, < > and->
Is the i-th sample in the target domain client. Let the mean of the target domain dataset be +.>
Standard deviation->
The normalized target domain data is:
the target domain client will mu t And delta t And the source domain client sends the source domain client to a central server, and the central server sends the source domain client to each source domain client. In the kth source domain client,
from mu t And delta t Randomly select a group of mu i ,δ i For->
Normalization is performed, namely:
In addition, set up
Mean and standard deviation of +.>
Use->
And->
Standardization->
The result of (2) is:
Standardized source domain data
And->
For training a fault diagnosis model in a source domain client.
(2) The source domain client uses two standardized source domain data as input, and trains a fault diagnosis model in the source domain client based on a correlation alignment (Correlation Alignment, CORAL) method;
the fault diagnosis model of the central server includes a feature extraction network (feature extractor) and a classification network (classifier).
As shown in fig. 3, the model received by the source domain client includes a feature extraction network and a classification network; the source domain client also includes a feature distance measurement method CORAL that acts to limit the distance between different features of the same type of sensor data.
The feature extraction network and the classification network on the central server are respectively marked as
And->
In training the model, the central server will first +.>
And->
Is sent to all source domain clients and then source domain client k trains the received global model using its local training data set.
In the source domain client k,
and->
Will be respectively taken as +.>
And->
Is input to the computer.
From the current data->
And vibration data->
Composition, likewise, < >>
From the current data->
And vibration data->
Composition is prepared.
As shown in fig. 2, in the feature extraction network, feature domain adaptation is enhanced by exchanging statistical features of different sensor data. Feature extraction network
There are two feature extraction channels, the input of channel 1 is current data and the input of channel 2 is vibration data. The characteristics of the channel 1 and channel 2 outputs will be normalized using the statistics of the two channel exchanges. The feature exchange normalization of the outputs of channel 1 and channel 2 is then used as a classification network +.>
And the input of CORAL.
wherein,,
true tag for data sample j, +.>
The prediction of data sample j by the classification network in source domain client k.
In addition, to constrain the distance between different features of the same sensor data, feature distance metric loss, based on correlation alignment (Correlation Alignment, CORAL) is used 1,CORAL ，loss 2,CORAL The calculation process is as follows:
wherein,,
and C 1,g Respectively normalized +.>
Is a characteristic covariance matrix of>
And C 2,g Respectively normalized +.>
Is a feature covariance matrix of (1); d represents the dimension of the feature and, I.I F Representing the Frobenius norm.
Thus, loss of k A weighted sum of classification loss and feature distance metric loss in source domain client k containing the source domain dataset, namely:
wherein loss is k Representing lossesThe sum of the two is lost,
representing class loss in source domain client k, loss 1,CORAL Loss of feature distance metric representing current data, loss of loss 2,CORAL Characteristic distance metric loss of vibration data is represented, β=0.01.
(3) After the models of all source domain clients are trained for one round, all the global models trained on the source domain clients are sent to a central server; the central server averages the received fault diagnosis models of all source domain clients to obtain a final fault diagnosis model;
global model aggregation on a central server, feature extractors for N global models on N source domain clients
Classifier of N global models on N source domain clients +.>
After averaging, the feature extractor of the global model on the central server is updated +.>
And classifier->
Wherein (1)>
Feature extractor for global model on ith source domain client,/i>
A classifier that is a global model on the ith source domain client.
In this embodiment, the global model is not trained further on the central server, but is sent to all source domain clients for the next round of training.
(4) In the test stage, the central server sends the trained fault diagnosis model to the target domain client for fault diagnosis.
When the training round number reaches a set value, the training task is ended, the central server sends the global model to the target domain client for fault diagnosis, the target domain client obtains mechanical fault data to be diagnosed, and a fault diagnosis result is obtained through the global model sent by the central server.
The model received by the target domain client includes a feature extraction network and a classification network.
The two channels of the characteristic extraction network have the same structure, and the characteristic extraction network consists of three groups of convolution layers, a regularization layer, a linear correction unit and a maximum pooling layer which are connected in sequence; the input of the feature extraction network first enters the first set of convolution layers, the first set of largest pooling layers is connected to the second set of convolution layers, and the second set of largest pooling layers is connected to the third set of convolution layers. The convolution kernels of the three convolution layers are 128, and the convolution kernels of the convolution layers in the first group, the second group and the third group are 17, 17 and 3 respectively; the parameters of the largest pooling layer in the first, second and third groups are 16, 16 and 2 in order.
The classification network consists of a flattening layer, a first full-connection layer, a regularization layer, a linear correction unit layer, a second full-connection layer and a softmax function layer which are connected in sequence; the parameters of the first full connection layer are 512, and the parameters of the second full connection layer are the fault type number.
The invention is described in detail below in the Paderbonn university bearing failure column.
The dataset used in the experiment was a Paderborn dataset. The bearing numbers used are detailed in table 1. The sensor data for each bearing includes vibration data and current data.
The dataset contains bearings in three different states: an inner ring failure (IR), an outer ring failure (OR), and a health status (H). The data sets are from bearings operating at different rotational speeds, radial forces and load torques. The working conditions of the bearing used in the invention are shown in Table 2.
The present invention assumes A, B, C, D is distributed among four clients and uses two or three of them as source domain clients to cooperatively train a model without generating data aggregation based on the proposed federal domain adaptive fault diagnosis method (FDG) based on statistical feature fusion. The trained model will be tested on the target domain client.
Table 1 Paderborn dataset experimental bearing code number
| Bearing code | Bearing state |
| KA15,KA16,KA30,KA04,KA22 | OR |
| KI14,KI17,KI21,KI16,KI18 | IR |
| K001,K005,K002,K004,K003 | H |
TABLE 2 Paderborn dataset under different conditions
| Data set code | Rotating speed (rpm) | Radial force (N) | Load torque (Nm) |
| A | 1500 | 1000 | 0.7 |
| B | 1500 | 1000 | 0.1 |
| C | 1500 | 400 | 0.7 |
| D | 900 | 1000 | 0.7 |
The results of the present invention and comparisons with other methods on the Paderbonn dataset are shown in Table 3.
TABLE 3 Paderborrn dataset experimental results
| Source domain data set | Test data set | FedAvg | FDG |
| A,B | C | 0.8842 | 0.9072 |
| B,D | C | 0.9117 | 0.9373 |
| A,B,D | C | 0.9137 | 0.9422 |
| B,C,D | A | 0.9978 | 1.0 |
| A,C,D | B | 0.9942 | 1.0 |
The method proposed by the present invention gives better results than federal average (FedAVg). This illustrates that compared with other methods, the method provided by the invention has better generalization capability, which means that the model trained on the source domain client by the method provided by the invention can adapt to other fields.
Compared with the prior art, the federal domain adaptive fault diagnosis method based on statistical feature fusion has the beneficial effects that the generalization capability of a fault diagnosis model in a target domain is improved by utilizing the statistical distribution difference of data between the target domain and a source domain and the statistical distribution difference of multi-sensor signals of the source domain data. In the invention, only the statistical characteristics and the like of the target domain data are transmitted to each source domain client, so that the communication burden is reduced. In addition, at the source domain client, the statistical features of the multi-sensor data features will be exchanged with each other, achieving feature domain space enhancement.
While the applicant has described and illustrated the embodiments of the present invention in detail with reference to the drawings, it should be understood by those skilled in the art that the above embodiments are only preferred embodiments of the present invention, and the detailed description is only for the purpose of helping the reader to better understand the spirit of the present invention, and not to limit the scope of the present invention, but any improvements or modifications based on the spirit of the present invention should fall within the scope of the present invention.
Claims (10)
1. A federal domain adaptive fault diagnosis method based on statistical feature fusion is characterized by comprising the following steps:
(1) The target domain client transmits the statistical features of the unlabeled fault data to the central server, and the central server transmits the statistical features to all source domain clients; the source domain client uses the received statistical characteristics and the statistical characteristics of the active domain data to respectively carry out data standardization on the source domain data set;
(2) The fault diagnosis model of the central server comprises a feature extraction network and a classification network, the central server sends a global model to all source domain clients, and then the source domain clients use two standardized source domain data as input and train the received global model in the source domain clients based on a correlation alignment method;
(3) After the models of all source domain clients are trained for one round, the trained models are sent to a central server, and the central server carries out global model aggregation on the received models of all source domain clients; then the training data are sent to all source domain clients to carry out the next training, and when the training round number reaches a set value, the training task is ended, so that a final fault diagnosis model is obtained;
(4) In the test stage, the central server sends the trained fault diagnosis model to the target domain client, the target domain client acquires mechanical fault data to be diagnosed, and a fault diagnosis result is obtained through the fault diagnosis model.
2. The federal domain adaptive fault diagnosis method based on statistical feature fusion according to claim 1, wherein in step (1), the statistical features are mean and standard deviation.
3. The federal domain adaptive fault diagnosis method based on statistical feature fusion according to claim 1, wherein in step (2), in the feature extraction network, the standardization of the output features of the present channel is achieved by adopting the statistical feature exchange of different feature extraction channels, and the features of the exchange standardization are adopted as the input of the classification network.
4. The federal domain adaptive fault diagnosis method based on statistical feature fusion according to claim 1, wherein in step (2), the global model received by the source domain client includes a feature extraction network and a classification network.
5. The federal domain adaptive fault diagnosis method based on statistical feature fusion according to claim 4, wherein the received global model is trained in the source domain client based on a correlation alignment method, in particular, the source domain client further comprises feature space metrics, which constrain the distance between different features of the same sensor data using the correlation alignment method.
6. The federal domain adaptive fault diagnosis method based on statistical feature fusion according to claim 5, wherein the input of feature space metrics is to implement standardized features using statistical feature exchange of different feature extraction channels.
7. The federal domain adaptive fault diagnosis method based on statistical feature fusion according to claim 1, wherein in step (3), the global model on the central server is aggregated as,
feature extractor for N global models on N source domain clients
Classifier of N global models on N source domain clients +.>
After averaging, the feature extractor of the global model on the central server is updated +.>
And classifier->
Wherein (1)>
Feature extractor for global model on ith source domain client,/i>
A classifier that is a global model on the ith source domain client.
8. The federal domain adaptive fault diagnosis method based on statistical feature fusion according to claim 1, wherein in step (4), the model received by the target domain client includes a feature extraction network and a classification network.
9. The federal domain adaptive fault diagnosis method based on statistical feature fusion according to claim 8, wherein the two channels of the feature extraction network have the same structure, and the feature extraction network is composed of three groups of convolution layers, regularization layers, linear correction units and a maximum pooling layer which are sequentially connected; the input of the feature extraction network first enters the first set of convolution layers, the first set of largest pooling layers is connected to the second set of convolution layers, and the second set of largest pooling layers is connected to the third set of convolution layers.
10. The federal domain adaptive fault diagnosis method based on statistical feature fusion according to claim 8, wherein the classification network is composed of a flattening layer, a first fully-connected layer, a regularization layer, a modified linear unit layer, a second fully-connected layer and a softmax function layer, which are sequentially connected.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310124876.6A CN116226784A (en) | 2023-02-03 | 2023-02-03 | Federal domain adaptive fault diagnosis method based on statistical feature fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310124876.6A CN116226784A (en) | 2023-02-03 | 2023-02-03 | Federal domain adaptive fault diagnosis method based on statistical feature fusion |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116226784A true CN116226784A (en) | 2023-06-06 |
Family
ID=86585262
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310124876.6A Pending CN116226784A (en) | 2023-02-03 | 2023-02-03 | Federal domain adaptive fault diagnosis method based on statistical feature fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116226784A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116992336A (en) * | 2023-09-04 | 2023-11-03 | 南京理工大学 | Bearing fault diagnosis method based on federal local migration learning |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102387663B1 (en) * | 2021-08-30 | 2022-04-19 | 서울대학교산학협력단 | Apparatus for fault diagnosis using domain adaptation with semantic clustering algorithm and method for fault diagnosis using the same |
| CN114818996A (en) * | 2022-06-28 | 2022-07-29 | 山东大学 | Method and system for diagnosing mechanical fault based on federal domain generalization |
| WO2022206498A1 (en) * | 2021-03-31 | 2022-10-06 | 华为技术有限公司 | Federated transfer learning-based model training method and computing nodes |
| CN115328691A (en) * | 2022-10-14 | 2022-11-11 | 山东大学 | Fault diagnosis method, system, storage medium and equipment based on model difference |
| CN115560983A (en) * | 2022-09-30 | 2023-01-03 | 哈尔滨理工大学 | Rolling bearing fault diagnosis method and system under different working conditions based on federal feature transfer learning |
| CN115600150A (en) * | 2022-09-26 | 2023-01-13 | 郑州大学（Cn） | Multi-mode gearbox fault diagnosis method based on deep migration learning |
-
2023
- 2023-02-03 CN CN202310124876.6A patent/CN116226784A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022206498A1 (en) * | 2021-03-31 | 2022-10-06 | 华为技术有限公司 | Federated transfer learning-based model training method and computing nodes |
| KR102387663B1 (en) * | 2021-08-30 | 2022-04-19 | 서울대학교산학협력단 | Apparatus for fault diagnosis using domain adaptation with semantic clustering algorithm and method for fault diagnosis using the same |
| CN114818996A (en) * | 2022-06-28 | 2022-07-29 | 山东大学 | Method and system for diagnosing mechanical fault based on federal domain generalization |
| CN115600150A (en) * | 2022-09-26 | 2023-01-13 | 郑州大学（Cn） | Multi-mode gearbox fault diagnosis method based on deep migration learning |
| CN115560983A (en) * | 2022-09-30 | 2023-01-03 | 哈尔滨理工大学 | Rolling bearing fault diagnosis method and system under different working conditions based on federal feature transfer learning |
| CN115328691A (en) * | 2022-10-14 | 2022-11-11 | 山东大学 | Fault diagnosis method, system, storage medium and equipment based on model difference |
Non-Patent Citations (4)
| Title |
|---|
| GAOWEI XU ET.AL.: ""A Compressed Unsupervised Deep Domain Adaptation Model for Efficient Cross-Domain Fault Diagnosis"", 《 IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS》, vol. 19, no. 5, pages 6741, XP011939965, DOI: 10.1109/TII.2022.3183225 * |
| 孙洁娣等: ""类别标签辅助改进稠密网络的变工况轴承故障诊断"", 《振动与冲击》, vol. 41, no. 17, pages 204 - 212 * |
| 李萍;倪志伟;朱旭辉;宋娟;: "联合类间及域间分布适配的迁移学习方法", 模式识别与人工智能, no. 01, pages 6 - 15 * |
| 郭斌: "《人机物融合群智计算》", 30 June 2022, 机械工业出版社, pages: 301 - 302 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116992336A (en) * | 2023-09-04 | 2023-11-03 | 南京理工大学 | Bearing fault diagnosis method based on federal local migration learning |
| CN116992336B (en) * | 2023-09-04 | 2024-02-13 | 南京理工大学 | Bearing fault diagnosis method based on federal local migration learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114818996B (en) | Method and system for diagnosing mechanical fault based on federal domain generalization | |
| Wang et al. | A novel deep metric learning model for imbalanced fault diagnosis and toward open-set classification | |
| Liu et al. | A stacked auto-encoder based partial adversarial domain adaptation model for intelligent fault diagnosis of rotating machines | |
| CN111709448A (en) | Mechanical fault diagnosis method based on migration relation network | |
| Ning et al. | Malware traffic classification using domain adaptation and ladder network for secure industrial internet of things | |
| CN115328691B (en) | Fault diagnosis method, system, storage medium and equipment based on model difference | |
| CN110555060A (en) | Transfer learning method based on paired sample matching | |
| CN112906859B (en) | Federal learning method for bearing fault diagnosis | |
| CN116226784A (en) | Federal domain adaptive fault diagnosis method based on statistical feature fusion | |
| CN115560983A (en) | Rolling bearing fault diagnosis method and system under different working conditions based on federal feature transfer learning | |
| CN116894215B (en) | Gear box fault diagnosis method based on semi-supervised dynamic graph attention | |
| CN115358259A (en) | Self-learning-based unsupervised cross-working-condition bearing fault diagnosis method | |
| Zhao et al. | Intelligent fault diagnosis of reciprocating compressor based on attention mechanism assisted convolutional neural network via vibration signal rearrangement | |
| CN111310719A (en) | Unknown radiation source individual identification and detection method | |
| CN116992336B (en) | Bearing fault diagnosis method based on federal local migration learning | |
| CN102664771A (en) | Network agent action detection system and detection method based on SVM (Support Vector Machine) | |
| CN117349749B (en) | Multi-source domain bearing fault diagnosis method based on mixed convolution | |
| CN115952442B (en) | Global robust weighting-based federal domain generalized fault diagnosis method and system | |
| CN112800471A (en) | Countermeasure domain self-adaptive differential privacy protection method in multi-source domain migration | |
| CN117008570A (en) | Cross-working condition fault diagnosis method and system based on open set federation reactance domain adaptation | |
| CN116244640A (en) | Unbalanced bearing fault diagnosis method and system based on federal learning | |
| Xiong et al. | Anomaly network traffic detection based on deep transfer learning | |
| CN117235490A (en) | Fault self-adaptive diagnosis method integrating deep volume and self-attention network | |
| Chen et al. | An Anomaly Detection Scheme with K-means aided Extended Isolation Forest in RSS-based Wireless Positioning System | |
| Yan et al. | FTSDC: A novel federated transfer learning strategy for bearing cross-machine fault diagnosis based on dual-correction training |
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 |