Recent progress on intelligent fault diagnosis (IFD) has greatly depended on deep representation learning and plenty of labeled data. However, machines often operate with various working conditions, or the target task has different distributions with the collected data used for training (the domain shift problem). Besides, the newly collected test data in the target domain are usually unlabeled, leading to unsupervised deep transfer learning (UDTL)-based IFD problem. Although it has achieved huge development, a standard and open source code framework and a comparative study for UDTL-based IFD are not yet established. In this article, we construct a new taxonomy and perform a comprehensive review of UDTL-based IFD according to different tasks. Comparative analysis of some typical methods and datasets reveals some open and essential issues in UDTL-based IFD, which is rarely studied, including transferability of features, the influence of backbones, negative transfer, physical priors, and so on. To emphasize the importance and reproducibility of UDTL-based IFD, the whole test framework will be released to the research community to facilitate future research. In summary, the released framework and comparative study can serve as an extended interface and basic results to carry out new studies on UDTL-based IFD. The code framework is available at https://github.com/ZhaoZhibin/UDTL .

pdf/applications-of-unsupervised-deep-transfer-learning-to-1vjmkyvj6p.pdf

Applications of Unsupervised Deep Transfer Learning to Intelligent Fault Diagnosis: A Survey and Comparative Study

The data-driven methods in machinery fault diagnosis have become increasingly popular in the past two decades. However, the wide applications of this scheme are generally compromised in real-world conditions because of the discrepancy between the training data and testing data. Although the recently emerging transfer fault diagnosis can learn transferable features from relevant source data and adapt the diagnostic model to the target data, these methods still only work on the target domain with a priori data distribution. The generalization capability of the transferred model cannot be guaranteed for unseen domains. Since the working conditions of machinery are varying during operation, the generalization capability of the diagnosis methods is crucial in this case. To tackle this challenge, this article proposes a domain generalization-based hybrid diagnosis network for deploying to unseen working conditions. The main idea is to regularize the discriminant structure of the deep network with both intrinsic and extrinsic generalization objectives such that the diagnostic model can learn robust features and generalize to unseen domains. The triplet loss minimization of intrinsic multisource data is implemented to facilitate the intraclass compactness and the interclass separability at the class level, leading to a more generalized decision boundary. The extrinsic domain-level regularization is achieved by using adversarial training to further reduce the risk of overfitting. Extensive cross-domain diagnostic experiments on planetary gearbox demonstrate the effectiveness of the proposed method.

A Hybrid Generalization Network for Intelligent Fault Diagnosis of Rotating Machinery Under Unseen Working Conditions

Most data-driven methods for fault diagnostics rely on the assumption of independently and identically distributed data of training and testing. However, domain shift between the phases of training and testing is common in practice. Recently, domain generalization-based fault diagnosis (DGFD) has gained widespread attention for learning fault diagnosis knowledge from multiple source domains and applying it to unseen target domains. This paper summarizes the developments in DGFD from an application-oriented perspective. Firstly, basic definitions of DGFD and its variant applications are formulated. Then, motivations, goals, challenges and state-of-the-art solutions for different applications are discussed. The limitations of existing technologies are highlighted. A comprehensive benchmark study is carried out on eight open-source and two self-collected datasets to provide an understanding of the existing methods and a unified framework for researchers. Finally, several future directions are given. Our code is available at https://github.com/CHAOZHAO-1/DG-PHM. 

Domain Generalization for Cross-Domain Fault Diagnosis: an Application-oriented Perspective and a Benchmark Study

Data-driven fault diagnosis methods often require abundant labeled examples for each fault type. On the contrary, real-world data is often unlabeled and consists of mostly healthy observations and only few samples of faulty conditions. The lack of labels and fault samples imposes a significant challenge for existing data-driven fault diagnosis methods. In this paper, we aim to overcome this limitation by integrating expert knowledge with domain adaptation in a synthetic-to-real framework for unsupervised fault diagnosis. Motivated by the fact that domain experts often have a relatively good understanding on how different fault types affect healthy signals, in the first step of the proposed framework, a synthetic fault dataset is generated by augmenting real vibration samples of healthy bearings. This synthetic dataset integrates expert knowledge and encodes class information about the fault types. However, models trained solely based on the synthetic data often do not perform well because of the distinct distribution difference between the synthetically generated and real faults. To overcome this domain gap between the synthetic and real data, in the second step of the proposed framework, an imbalance-robust domain adaptation~(DA) approach is proposed to adapt the model from synthetic faults~(source) to the unlabeled real faults~(target) which suffer from severe class imbalance. The framework is evaluated on two unsupervised fault diagnosis cases for bearings, the CWRU laboratory dataset and a real-world wind-turbine dataset. Experimental results demonstrate that the generated faults are effective for encoding fault type information and the domain adaptation is robust against the different levels of class imbalance between faults. 

Integrating Expert Knowledge With Domain Adaptation for Unsupervised Fault Diagnosis

Fault diagnosis of mechanical equipment in high energy consumption industries in China: A review

Traditional deep learning assumes that the probability distributions of the test set and the training set are exactly the same. When the test samples and the training samples are from different working conditions, the distribution gap between different conditions might dramatically lower the accuracy. To address this problem, domain adaptation (DA) via joint using training and test sets is adopted to increase the final accuracy. The disadvantage of DA is that it requires test samples to participate in the training phase. However, sometimes it is impossible to collect the test samples beforehand. To solve this problem, this article proposes a conditional adversarial domain generalization with a single discriminator, which aims to extract domain-invariant features from different working conditions and generalize the features to unseen working conditions. To realize conditional adversarial training, a new conditional adversarial strategy that the feature extractor can allow the discriminator to distinguish the fault classes, but cannot distinguish the domains, is designed to better confuse the discriminator and generalize the features. Meanwhile, three loss functions, including mean square error (MSE), cross-entropy coupled with entropy, and cross-entropy combined with traditional adversarial methods, are proposed to achieve the new conditional adversarial strategy. The effectiveness of the conditional adversarial strategy is verified by training conditional generative adversarial networks (CGANs) on two image data sets, and the performance of the proposed domain generalization method for bearing fault diagnosis is also verified by bearing data sets. Compared with traditional conditional adversarial domain generalization, the proposed method can save computing resource consumption and improve accuracy that does not appear in the training phase.

Conditional Adversarial Domain Generalization With a Single Discriminator for Bearing Fault Diagnosis

The invention provides a motor rolling bearing fault diagnosis method and a diagnosis system thereof. The motor rolling bearing fault diagnosis method comprises the steps that a three-dimensional coordinate system in radial direction X, forward direction Y and vertical direction Z is used; a three-way acceleration sensor is arranged near a motor rolling bearing to acquire a three-way vibration signal; a rotational speed sensor and an ammeter are arranged to acquire the rotational speed pulse signal of the rolling bearing and measure the current signal of a motor stator; the maximum allowable deviation sigma I determining the current smoothness is set, and the maximum allowable deviation sigma V determining the rotational speed smoothness is set; during the time period T, vibration data under steady rotational speed and current are intercepted through predetermined conditions; valid three-way vibration data Acc in the time period T are extracted; the standard deviation of the three-wayvibration data is calculated, and composite time domain indexes in three directions are calculated; a threshold table is acquired through testing; and the acquired composite time domain indexes in three directions are compared with the threshold table to acquire the fault degree, and an alarm is given out.

Motor rolling bearing fault diagnosis method and diagnosis system thereof

The invention reveals an intelligent operation and maintenance management system for key equipment The system comprises a health management layer, an operation and maintenance layer and a coordination management layer Through the integration of the functions of all-time remote monitoring, fault diagnosis, service life prediction, operation and maintenance center and a coordination center of multiple devices and multiple parts, the system achieves the effective control of the operation states and change rules of the fixed facilities and moving equipment at an operation stage Moreover, multiple departments, multiple terminals and multiple stations cooperate with each other and are combined with the operation and maintenance, thereby forming the closed-loop circulation of the recognition,diagnosis, prediction and elimination of a safety risk source, and preventing the safety risk to the maximum degree Meanwhile, the system is based on data, and achieves a purpose that the upgrading of an industrial chain promotes the upgrading of equipment

Intelligent operation and maintenance management system for key equipment

The utility model discloses a motor rolling bearing fault diagnosis system, motor rolling bearing fault diagnosis system include data acquisition device (2), treater (4) and comparator (5) of the vibration data under measuring device (1), intercepting rotational speed and the steady operating mode of electric current, and measuring device (1) including setting up galvanometer (8) at motor antifriction bearing's three -dimensional acceleration sensor (6), speed sensor (7) and electricity connection stator, data acquisition device (2) record accords with predetermined condition's vibration vector matrix acc, rotational speed average value (img file='DDA0001588548300000011. TIF'wi='40'he='56' /) and electric current average value (img file='DDA0001588548300000012. TIF'wi='58'he='59' /) treater (4) are connected data acquisition device (2) and compound time domain index to comparator (5) of sending calculation, comparator (5), it must the degree of being out of order than pair recombination time domain index and reports to the police.

Motor rolling bearing fault diagnosis system

The invention discloses a method for improving the Lamb wave phased array focusing detection speed. The method comprises the steps that a first sensor array and a second sensor array are arranged on the surface of a detected structure in the vertical direction and the horizontal direction; the first sensor array generates a first excitation signal to simultaneously detect any two symmetric focuseson the surface of the detected structure by taking the first sensor array as a symmetric axis, and when the first sensor array receives a first echo signal, at least one of the two symmetric focusesis a damage point; the second sensor array generates a second excitation signal to respectively detect the symmetric focuses, and when the second sensor array receives a second echo signal from a certain focus in the symmetric focuses, the focus is a damage point; and the energy of the damage point is calculated, and the damage degree of the damage point is determined according to the energy.

Method for increasing Lamb wave phased array focusing detection speed

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Li Ming

Author Tools

Chat about Author