Domain adaptive deep belief network for rolling bearing fault diagnosis

Che, Changchang; Wang, Huawei; Ni, Xiaomei; Fu, Qiang

doi:10.1016/j.cie.2020.106427

Cited by 132 publications

(42 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The characteristics of fault depend on motor speed, the geometry of the bearing, and also the location of the fault. Many works in literature have focused on bearing fault diagnostics [43], [44] , [45] , [46] , [47] In the last decade, there has been a continuous growth in research paper publications in DL. It presents the trend in publications cited by Google scholar for literary works in this scope in The dataset formation is the first step towards the solution using the DL approach.…”

Section: DL For Fault Diagnostics Of Bearingsmentioning

confidence: 99%

Deep Learning for Fault Diagnostics in Bearings, Insulators, PV Panels, Power Lines, and Electric Vehicle Applications—The State-of-the-Art Approaches

et al. 2021

View full text Add to dashboard Cite

Deep learning (DL) is an exciting field of interest for many researchers and business. Due to a massive leap in DL based research, many domains like Business, science and government sectors make use of DL for various applications. This work puts forward the importance of DL and its application in a few critical electrical segments. Initially, an introduction to Artificial Intelligence (AI) and Machine Learning (ML) is presented. Then the need for DL and the popular architectures, algorithms and frameworks used are presented. A summary of different techniques used in DL is outlined, and finally, a review on the application of deep learning techniques in some popular electrical applications is presented. Five critical electrical applications, namely identification of bearing faults, hot spots on the surface of PV panels, insulator faults, an inspection of power lines and Electric vehicles have been considered for review in this work. The primary aim of this work is to present chronologically, a survey of different areas in which it applies DL along with their architectures, frameworks and techniques to provide a deeper understanding of DL for widespread use in real-time applications.

show abstract

Section: DL For Fault Diagnostics Of Bearingsmentioning

confidence: 99%

Deep Learning for Fault Diagnostics in Bearings, Insulators, PV Panels, Power Lines, and Electric Vehicle Applications—The State-of-the-Art Approaches

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Moreover, researchers are now showing more and more interest in seeking new ideas for better performance in FDD. For example, Yao et al [95] propose to use state information imaging where gray-images representing operating transients are analyzed and fed into a neural network while Peng et al [140] suggest a deep belief network along with correction analysis achieves better results than backpropagation network or SVM and many other upgraded deep belief networks, such as domain adaptive deep belief network, have been proven effective in FDD of other industries [141], [142] which is a considerable achievement for further development of FDD in NPPs. Some researchers, however, put their focus on improving condition monitoring capability to provide more accurate information on NPP devices [143], [144].…”

Section: ) Fault Detection and Diagnosismentioning

confidence: 99%

Nuclear Power Plants With Artificial Intelligence in Industry 4.0 Era: Top-Level Design and Current Applications—A Systemic Review

Lyu

Zhang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Nuclear energy can make an important contribution to low-carbon energy supply for Industry 4.0, while Industry 4.0 can reform this industry in return. As a typical and complex man-machine-network integration system, various faults, insufficient automation and stressed human operators limit the further popularization of nuclear power plants (NPPs) while these issues can be addressed by the aid of artificial intelligence (AI) technologies. In this work, we try to present a systemic review of how AI can benefit NPPs in a top-to-down fashion. We discuss limitations in current NPPs and introduce the concept of Nuclear Power Plant Human-Cyber-Physical System (NPPHCPS) as the top-level design. Then, we category AI-related nuclear power applications into Physical-Plant-Centered and Human-Operator-Centered technologies and review research works from 7 typical NPP functional scenarios in the recent two decades. In each NPP functional scenario, how researchers integrate AI into NPPs is presented following timeline. We hope this review can be used as the guideline for NPPs' Design in the future and contribute to green Industry 4.0.

show abstract

“…The difference-based approach mainly adopts the idea that the untagged target domain data also follows the tagged source domain data for common training. Then various feature alignment methods are used in the high-dimensional space to align the differentiated distribution features of the source domain and the target domain so as to realize the transfer diagnosis of the target domain [20]. For example, Yang et al [21] innovatively proposed a polynomial kernel induced maximum mean discrepancy method to extract domain invariant features, thus realizing transfer diagnosis.…”

Section: Introductionmentioning

confidence: 99%

Siamese Distinguishing Features Attentional Enhancement Transfer Fault Diagnosis Method for Variable Rotational Speed

Xu¹,

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Transfer learning is widely used in artificial intelligence fault diagnosis field because it can solve the problem of label missing in rotating parts at varying speeds. However, the domain adaptive method in transfer learning is not suitable for real transfer fault diagnosis scenarios, and the adaptive enhancement of fault characteristics is not realized in the transfer process. To solve these thorny problems, a novel method called Siamese Distinguishing features Attentional Enhancement Transfer fault diagnosis (SDAET) has been proposed. The body of SDAET model adopts the dual-branch convolutional neural network architecture with shared weights. It mainly uses the contrast loss function in the siamese feature contrast network to extract the domain invariant features at two rotational speeds, and then applies it to the transfer diagnosis at other rotational speeds, so as to meet the more real transfer diagnosis scenarios. The distinguishing features attentional enhancement network is designed to adaptively enhance the differentiated domain invariant features at different rotational speeds. Furthermore, various feature visualization techniques are used to further explain the features learned from the black box neural network. The diagnostic results on two kinds of test datasets show that the proposed model has higher diagnostic accuracy. The technique of siamese distinguishing features attentional enhancement provides a new and better way to solve the transfer diagnosis problem.

show abstract

Domain adaptive deep belief network for rolling bearing fault diagnosis

Cited by 132 publications

References 46 publications

Deep Learning for Fault Diagnostics in Bearings, Insulators, PV Panels, Power Lines, and Electric Vehicle Applications—The State-of-the-Art Approaches

Deep Learning for Fault Diagnostics in Bearings, Insulators, PV Panels, Power Lines, and Electric Vehicle Applications—The State-of-the-Art Approaches

Nuclear Power Plants With Artificial Intelligence in Industry 4.0 Era: Top-Level Design and Current Applications—A Systemic Review

Siamese Distinguishing Features Attentional Enhancement Transfer Fault Diagnosis Method for Variable Rotational Speed

Contact Info

Product

Resources

About