Time Series Multiple Channel Convolutional Neural Network with Attention-Based Long Short-Term Memory for Predicting Bearing Remaining Useful Life

Jiang, Jehn-Ruey; Lee, Juei En; Zeng, Yi

doi:10.3390/s20010166

Cited by 87 publications

(53 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The monthly transaction volume data is not enough to guarantee the accuracy and objectivity of empirical conclusions. Therefore, the weekly trading volume will be used as an independent variable of the mathematical model established in this white paper, and its ability to explain the weekly forecasted rate of return will be analyzed [26][27].…”

Section: Yieldmentioning

confidence: 99%

Retracted: Mathematical Model of Yield Forecast Based on Long and Short-Term Memory Image Neural Network

2024

View full text Add to dashboard Cite

Yield prediction has always been the focus of stock investors' attention in stock investment. This research uses the virtual stock scene constructed by VR technology to explore the mathematical model of return rate prediction. First, neural nodes, activation functions and output functions are designed under the LSTM framework, and a recurrent neural network that can handle long-term sequences is constructed. Use VR technology to simulate stock data and extract key frames from the image sequence. Aiming at the timing of key curve nodes, this study uses a long and short-term memory neural network that is good at processing time series data to classify curve trends, and realizes the identification of abnormal fluctuations in virtual scenes of stock images. Then, according to the existing probability control asset allocation theory, the index of investment allocation is adjusted from the entire time series to a dynamic time series. According to the stock price decomposition of EEMD, the EEMD-LSTM model is constructed to predict the stock market price. Use EEMD to decompose the original sequence to obtain IMF and trend items containing various timescale characteristics. Then, the LSTM neural network is used to predict and analyze each rate of return, and the analysis software Python is used to process and count the predicted results. At the same time, retrospective restrictions are regarded as riskier assets. Finally, the investment is made under conditions that do not allow shorting in the VR simulation scenario. The accuracy of the calculation is more than 70% except for the Shanghai and Shenzhen 300 Index reaching 66%. The research results show that in the case of different stock price forecasts, the prediction ability of LSTM neural network has been greatly improved compared with that of support vector machine, which fully reflects the advantages of LSTM in time series prediction.

show abstract

Section: Yieldmentioning

confidence: 99%

Retracted: Mathematical Model of Yield Forecast Based on Long and Short-Term Memory Image Neural Network

2024

View full text Add to dashboard Cite

show abstract

“…Zhu et al [26] predicted raw RUL by combining the features of different layers of 2D-CNN and using them as the input of the flatten layer. Hinchi et al [27] and Jiang et al [28] predicted raw RUL using CNN-LSTM and time-series of vibration acceleration or statistical features of vibration acceleration as inputs, respectively. Wang et al…”

Section: Related Workmentioning

confidence: 99%

“…Also, [15], [18], [19], and [23] - [26] did not consider the past conditions of degradation, and RUL prediction error may increase if the fluctuation of vibration features becomes large. Then, [15], [27], [28], and [29] considered RUL degradation by using LSTM or GRU but did not consider its monotonicity. Furthermore, the abovementioned papers ( [15], [18], [19], [23], and [25]-[29]) did not investigated the RUL of rolling bearings that are used even under the defect progression.…”

Section: Related Workmentioning

confidence: 99%

A Framework for Predicting Remaining Useful Life Curve of Rolling Bearings Under Defect Progression Based on Neural Network and Bayesian Method

et al. 2021

View full text Add to dashboard Cite

In order to improve Remaining Useful Life (RUL) prediction accuracy for rolling bearings under defect progressing, the robustness for individual differences and the fluctuation of vibration features are challenging issues. In this research, we propose a novel RUL prediction framework based on a Convolutional Neural Network (CNN) and Hierarchical Bayesian Regression (HBR) for considering the degradation conditions and individual differences of RUL to improve the prediction accuracy. The characteristics of the proposed framework are: (1) In order to reduce the effect of the fluctuation of vibration features, the proposed framework uses an intermediate variable indicating the degradation condition instead of predicting RUL from vibration features. (2) The proposed framework considers not only present but also past degradation conditions in CNN. We conducted the experiment on rolling bearings under defect progression and evaluated the RUL prediction accuracy of the proposed framework. The proposed framework can generate a monotonous RUL prediction curve with a probability distribution and improve the RUL prediction accuracy under defect progression.

show abstract

“…Some researchers forego feature engineering altogether and use the raw signal directly (Khelif et al, 2017;C. Liu, Zhang, & Wu, 2019;Verstraete, Droguett, & Modarres, 2019;Jiang, Lee, & Zeng, 2019;Zhang, Hutchinson, Lieven, & Nunez-Yanez, 2020;B. Wang, Lei, Yan, Li, & Guo, 2020).…”

Section: Reportingmentioning

confidence: 99%

Remaining Useful Life Estimation of Bearings

Ferreira

Sousa

2021

IJPHM

View full text Add to dashboard Cite

In the domain of predictive maintenance, when trying to repli- cate and compare research in remaining useful life estimation (RUL), several inconsistencies and errors were identified in the experimental methodology used by various researchers. This makes the replication and the comparison of results diffi- cult, thus severely hindering both progress in this research do- main and its practical application to industry. We survey the literature to evaluate the experimental procedures that were used, and identify the most common errors and omission in both experimental procedures and reporting. A total of 70 papers on RUL were audited. From this meta- analysis we estimate that approximately 11% of the papers present work that will allow for replication and comparison. Surprisingly, only about 24.3% (17 of the 70 articles) com- pared their results with previous work. Of the remaining work, 41.4% generated and compared several models of their own and, somewhat unsettling, 31.4% of the researchers made no comparison whatsoever. The remaining 2.9% did not use the same data set for comparisons. The results of this study were also aggregated into 3 categories: problem class selec- tion, model fitting best practices and evaluation best practices. We conclude that model evaluation is the most problematic one. The main contribution of the article is a proposal of an ex- perimental protocol and several recommendations that specif- ically target model evaluation. Adherence to this protocol should substantially facilitate the research and application of RUL prediction models. The goals are to promote the collab- oration between scholars and practitioners alike and advance the research in this domain.

show abstract

Time Series Multiple Channel Convolutional Neural Network with Attention-Based Long Short-Term Memory for Predicting Bearing Remaining Useful Life

Cited by 87 publications

References 48 publications

Retracted: Mathematical Model of Yield Forecast Based on Long and Short-Term Memory Image Neural Network

Retracted: Mathematical Model of Yield Forecast Based on Long and Short-Term Memory Image Neural Network

A Framework for Predicting Remaining Useful Life Curve of Rolling Bearings Under Defect Progression Based on Neural Network and Bayesian Method

Remaining Useful Life Estimation of Bearings

Contact Info

Product

Resources

About