Transfer Learning Based Fault Diagnosis with Missing Data Due to Multi-Rate Sampling

Chen, Danmin; Yang, Shuai; Zhou, Funa

doi:10.3390/s19081826

Cited by 41 publications

(22 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Data may also be subject to problems like incompleteness, heterogeneity, low signal to noise ratio, exhibition of certain topology, etc. Chen et al attempted to conquer the incomplete data problem caused by multi-rate sampling by using transfer learning [168]. They proposed a framework enabling a portion of the structure and parameters to be transferred between the model of structurally complete data and the model of incomplete data.…”

Section: ) Structured Datamentioning

confidence: 99%

A Review on Deep Learning Applications in Prognostics and Health Management

et al. 2019

View full text Add to dashboard Cite

Deep learning has attracted intense interest in Prognostics and Health Management (PHM), because of its enormous representing power, automated feature learning capability and best-in-class performance in solving complex problems. This paper surveys recent advancements in PHM methodologies using deep learning with the aim of identifying research gaps and suggesting further improvements. After a brief introduction to several deep learning models, we review and analyze applications of fault detection, diagnosis and prognosis using deep learning. The survey validates the universal applicability of deep learning to various types of input in PHM, including vibration, imagery, time-series and structured data. It also reveals that deep learning provides a one-fits-all framework for the primary PHM subfields: fault detection uses either reconstruction error or stacks a binary classifier on top of the network to detect anomalies; fault diagnosis typically adds a soft-max layer to perform multi-class classification; prognosis adds a continuous regression layer to predict remaining useful life. The general framework suggests the possibility of transfer learning across PHM applications. The survey reveals some common properties and identifies the research gaps in each PHM subfield. It concludes by summarizing some major challenges and potential opportunities in the domain.

show abstract

Section: ) Structured Datamentioning

confidence: 99%

A Review on Deep Learning Applications in Prognostics and Health Management

et al. 2019

View full text Add to dashboard Cite

show abstract

“…To understand the memory-cell operations of LSTM, assuming at time and input in (11), the forget gate of the first layer can be represented as that removes information of the memory cell once required and saves the previous state of information before emptying the memory.…”

Section: Figure 5 Lstm-memory Cellmentioning

confidence: 99%

“…The vibration signal has been broadly and revealed acceptable performance [9]. DL is used in fault diagnosis of mechanical equipment such as gear transmission [10,11], bearing [12], and multi-joint industrial robots [13]. In [14], an intelligent fault diagnosis was proposed based on a deep echo state network (ESN) and a hybrid evolutionary algorithm.…”

Section: Introductionmentioning

confidence: 99%

A Novel Deep Learning Framework Based RNN-SAE for Fault Detection of Electrical Gas Generator

2021

View full text Add to dashboard Cite

The electrical generator is the key part of the electrical generation system for the oil and gas industry, and it is easy to fail, which disturbs the availability and reliability of the electrical generation in the power industry. Therefore, extracting and diagnosing the fault features from the process signals are useful to diagnose the status of the machine. Though, a common challenge in many applied applications is the practical knowledge about the risk of failure or historical records, which is totally unlabeled and difficult to be identified by traditional fault approaches. Hence, in the present study, a novel deep learning (DL) framework is proposed to fill the gap by balancing the three stages of fault feature extraction, fault detection, and parameter optimization based on the long short term memory-recurrent neural networks (RNN-LSTM), stacked autoencoders (SAE), and particle swarm optimization (PSO) techniques. The suggested framework focuses on failure detection through a sequence of numerous features for the unlabeled historical data and unknown anomaly. To validate the effectiveness of the proposed DL framework, an experiment for failure detection of the electrical generator was conducted for the data of risky environment at Yemen oil and gas plant. The experimental results compared with the earlier studies validate that, the DL framework can address the faults for vibration signals of the electrical generator in a well-diagnosis performance effectively. INDEX TERMSDeep learning (DL), Fault detection, Long short-term memory (LSTM), Oil and gas plant, Recurrent neural networks (RNN), Stacked autoencoders (SAE) This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.

show abstract

“…There may be such diagnosis scenarios that massive training data with incomplete information are available. Several research works discussed how to utilize these incomplete samples of source domain to facilitate the target diagnosis task through transfer learning methods [90]- [93], [107], [108].…”

Section: E: Motivation 5: Leveraging Knowledge From the Source With Imentioning

confidence: 99%

“…Besides, reference [107] proposed a fault diagnosis framework that uses structurally incomplete samples to facilitate the model training of the target domain. They declared that a large number of incomplete samples also contain useful information, and transferring them to target diagnosis task is helpful.…”

Section: E: Motivation 5: Leveraging Knowledge From the Source With Imentioning

confidence: 99%

Cross-Domain Fault Diagnosis Using Knowledge Transfer Strategy: A Review

et al. 2019

View full text Add to dashboard Cite

Data-driven fault diagnosis has been a hot topic in recent years with the development of machine learning techniques. However, the prerequisite that the training data and the test data should follow an identical distribution prevents the conventional data-driven diagnosis methods from being applied to the engineering diagnosis problems. To tackle this dilemma, cross-domain fault diagnosis using knowledge transfer strategy is becoming popular in the past five years. The diagnosis methods based on transfer learning aim to build models that can perform well on target tasks by leveraging knowledge from semantic related but distribution different source domains. This paper for the first time summarizes the state-of-art cross-domain fault diagnosis research works. The literatures are introduced from three different viewpoints: research motivations, cross-domain strategies, and application objects. In addition, the corresponding open-source fault datasets and several future directions are also presented. The survey provides readers a framework for better understanding and identifying the research status, challenges and future directions of cross-domain fault diagnosis. INDEX TERMS Cross-domain, domain adaptation, fault diagnosis, review, transfer learning.

show abstract

Transfer Learning Based Fault Diagnosis with Missing Data Due to Multi-Rate Sampling

Cited by 41 publications

References 46 publications

A Review on Deep Learning Applications in Prognostics and Health Management

A Review on Deep Learning Applications in Prognostics and Health Management

A Novel Deep Learning Framework Based RNN-SAE for Fault Detection of Electrical Gas Generator

Cross-Domain Fault Diagnosis Using Knowledge Transfer Strategy: A Review

Contact Info

Product

Resources

About