Deep neural networks: A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data

Jia, Feng; Lei, Yaguo; Lin, Jing; Zhou, Xin; Lü, Na

doi:10.1016/j.ymssp.2015.10.025

Cited by 1,443 publications

(701 citation statements)

References 31 publications

Supporting

Mentioning

690

Contrasting

Unclassified

Order By: Relevance

“…For the noise datasets, 1% and 5% Gaussian noises are added to first seven frequencies and the associated mode shapes respectively with consideration of structural frequencies measured more accurately as reported in [21]. Besides, 1% uncertainty is considered in the stiffness parameters to simulate the finite element modelling errors.…”

Section: Data Generationmentioning

confidence: 99%

A Novel Parallel Auto-Encoder Framework for Multi-Scale Data in Civil Structural Health Monitoring

Wang

2018

Algorithms

View full text Add to dashboard Cite

Abstract:In this paper, damage detection/identification for a seven-storey steel structure is investigated via using the vibration signals and deep learning techniques. Vibration characteristics, such as natural frequencies and mode shapes are captured and utilized as input for a deep learning network while the output vector represents the structural damage associated with locations. The deep auto-encoder with sparsity constraint is used for effective feature extraction for different types of signals and another deep auto-encoder is used to learn the relationship of different signals for final regression. The existing SAF model in a recent research study for the same problem processed all signals in one serial auto-encoder model. That kind of models have the following difficulties: (1) the natural frequencies and mode shapes are in different magnitude scales and it is not logical to normalize them in the same scale in building the models with training samples; (2) some frequencies and mode shapes may not be related to each other and it is not fair to use them for dimension reduction together. To tackle the above-mentioned problems for the multi-scale dataset in SHM, a novel parallel auto-encoder framework (Para-AF) is proposed in this paper. It processes the frequency signals and mode shapes separately for feature selection via dimension reduction and then combine these features together in relationship learning for regression. Furthermore, we introduce sparsity constraint in model reduction stage for performance improvement. Two experiments are conducted on performance evaluation and our results show the significant advantages of the proposed model in comparison with the existing approaches.

show abstract

Section: Data Generationmentioning

confidence: 99%

A Novel Parallel Auto-Encoder Framework for Multi-Scale Data in Civil Structural Health Monitoring

Wang

2018

Algorithms

View full text Add to dashboard Cite

show abstract

“…Although ANNs require supervised learning, DNNs work well with the help of unsupervised learning. DNN with the deep architectures can adaptively capture the representative information from raw signal via multiple nonlinear transformations and approximate complex nonlinear functions with a low error [208]. DBN uses a hierarchical structure with multiple stacked restricted Boltzmann machines and works by a layer-by-layer successive learning process [23].…”

Section: Deep Learningmentioning

confidence: 99%

Basic research on machinery fault diagnostics: Past, present, and future trends

et al. 2017

View full text Add to dashboard Cite

Machinery fault diagnosis has progressed over the past decades with the evolution of machineries in terms of complexity and scale. High-value machineries require condition monitoring and fault diagnosis to guarantee their designed functions and performance throughout their lifetime. Research on machinery Fault diagnostics has grown rapidly in recent years. This paper attempts to summarize and review the recent R&D trends in the basic research field of machinery fault diagnosis in terms of four main aspects: Fault mechanism, sensor technique and signal acquisition, signal processing, and intelligent diagnostics. The review discusses the special contributions of Chinese scholars to machinery fault diagnostics. On the basis of the review of basic theory of machinery fault diagnosis and its practical applications in engineering, the paper concludes with a brief discussion on the future trends and challenges in machinery fault diagnosis.

show abstract

“…First, extraction and selection of features depend largely on the prior knowledge of signal-processing technique and diagnosis experience, and generalization is weak. Second, ANN adopts a shallow structure, which also limits ANN to learn complex nonlinear structures in fault diagnosis [32]. Deep neural network (DNN) is developed based on deep learning theory, which can enhance the accuracy of big data classification [33] and effectively overcome the preceding shortcomings.…”

Section: Artificial Neural Network (Ann)mentioning

confidence: 99%

“…Guo, et al [36], developed a hierarchical adaptive deep convolutional neural network for bearing fault diagnosis. Jia, et al [32], used DNN for intelligence fault diagnosis in rotating machinery, especially in the case when the vibration data were massive. ELM has been extensively applied and popularized in the fault diagnosis of mechanical system in recent years.…”

Section: Artificial Neural Network (Ann)mentioning

confidence: 99%

Comprehensive Overview on Computational Intelligence Techniques for Machinery Condition Monitoring and Fault Diagnosis

Zhang

Jia

Zhu

et al. 2017

Chin. J. Mech. Eng.

View full text Add to dashboard Cite

Computational intelligence is one of the most powerful data processing tools to solve complex nonlinear problems, and thus plays a significant role in intelligent fault diagnosis and prediction. However, only few comprehensive reviews have summarized the ongoing efforts of computational intelligence in machinery condition monitoring and fault diagnosis. The recent research and development of computational intelligence techniques in fault diagnosis, prediction and optimal sensor placement are reviewed. The advantages and limitations of computational intelligence techniques in practical applications are discussed. The characteristics of different algorithms are compared, and application situations of these methods are summarized. Computational intelligence methods need to be further studied in deep understanding algorithm mechanism, improving algorithm efficiency and enhancing engineering application. This review may be considered as a useful guidance for researchers in selecting a suitable method for a specific situation and pointing out potential research directions.

show abstract

Deep neural networks: A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data

Cited by 1,443 publications

References 31 publications

A Novel Parallel Auto-Encoder Framework for Multi-Scale Data in Civil Structural Health Monitoring

A Novel Parallel Auto-Encoder Framework for Multi-Scale Data in Civil Structural Health Monitoring

Basic research on machinery fault diagnostics: Past, present, and future trends

Comprehensive Overview on Computational Intelligence Techniques for Machinery Condition Monitoring and Fault Diagnosis

Contact Info

Product

Resources

About