A comprehensive review on convolutional neural network in machine fault diagnosis

For the data-driven remaining useful life (RUL) prediction for rolling bearings, the traditional machine learning-based methods generally provide insufficient feature representation and adaptive extraction. Although deep learning-based RUL prediction methods can solve these problems to some extent, they still do not yield satisfactory predictive results due to less degradation data and inconsistent data distribution among different bearings. To solve these problems, a new RUL prediction method based on deep feature representation and transfer learning is proposed in this paper. This method includes an off-line stage and an online stage. In the off-line stage, the Hilbert–Huang transform marginal spectra of the raw vibration signal of auxiliary bearings are first calculated as the input, and then contractive denoising autoencoder is introduced to extract deep features with good and stable fault representation. Second, by using the obtained deep features and Pearson’s correlation coefficient, a new health condition assessment method is proposed to divide the whole life of each bearing into a normal state and a fast-degradation state. Finally, using the extracted deep features and their RUL values, an RUL prediction model for the fast-degradation state is trained by means of a least-square support vector machine. In the online stage, a kind of transfer learning algorithm, i.e., transfer component analysis, is introduced to sequentially adjust the features of target bearing from auxiliary bearings, and then the corresponding RUL is predicted using the corrected features. Results using the PHM Challenging 2012 data set show a significant performance improvement when using the proposed method in terms of predictive accuracy and numerical stability.

Predicting Remaining Useful Life of Rolling Bearings Based on Deep Feature Representation and Transfer Learning

A large number of intelligent algorithms based on social intelligent behavior have been extensively researched in the past few decades, through the study of natural creatures, and applied to various optimization fields. The learning-based intelligent optimization algorithm (LIOA) refers to an intelligent optimization algorithm with a certain learning ability. This is how the traditional intelligent optimization algorithm combines learning operators or specific learning mechanisms to give itself some learning ability, thereby achieving better optimization behavior. We conduct a comprehensive survey of LIOAs in this paper. The research includes the following sections: Statistical analysis about LIOAs, classification of LIOA learning method, application of LIOAs in complex optimization scenarios, and LIOAs in engineering applications. The future insights and development direction of LIOAs are also discussed.

A Survey of Learning-Based Intelligent Optimization Algorithms

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.

/pdf/a-review-on-deep-learning-applications-in-prognostics-and-3cw1pwlic5.pdf

A Review on Deep Learning Applications in Prognostics and Health Management

Elephant herding optimization (EHO) is a nature-inspired metaheuristic optimization algorithm based on the herding behavior of elephants. EHO uses a clan operator to update the distance of the elephants in each clan with respect to the position of a matriarch elephant. The superiority of the EHO method to several state-of-the-art metaheuristic algorithms has been demonstrated for many benchmark problems and in various application areas. A comprehensive review for the EHO-based algorithms and their applications are presented in this paper. Various aspects of the EHO variants for continuous optimization, combinatorial optimization, constrained optimization, and multi-objective optimization are reviewed. Future directions for research in the area of EHO are further discussed.

https://www.mdpi.com/2227-7390/8/9/1415/pdf

Elephant Herding Optimization: Variants, Hybrids, and Applications

For bearing remaining useful life prediction problem, the traditional machine-learning-based methods are generally short of feature representation ability and incapable of adaptive feature extracti...

https://journals.sagepub.com/doi/pdf/10.1177/1687814018817184

Jiamei Tang

Papers

Predicting remaining useful life of rolling bearings based on deep feature representation and long short-term memory neural network: