Fault prediction of bearings based on LSTM and statistical process analysis

Liu, Junqiang; Pan, Chunlu; Fan, Lei; Hu, Dongbin; Zuo, Hongfu

doi:10.1016/j.ress.2021.107646

Cited by 82 publications

(27 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…NASA and FEMTO-ST Research Institute have verified the effectiveness of this method. It has been demonstrated that the proposed method is feasible and has a higher prediction accuracy than recurrent neural network (RNN) and support vector regression (SVR) [25]. Based on the historical maintenance data and GIS data, Chen et al [26] proposed a merged-LSTM network for the RUL prediction of the automobile.…”

Section: Machine Learning For Predictive Maintenancementioning

confidence: 99%

A deep learning-based approach for electrical equipment remaining useful life prediction

Liu

2022

Auton. Intell. Syst.

View full text Add to dashboard Cite

Electrical equipment maintenance is of vital importance to management companies. Efficient maintenance can significantly reduce business costs and avoid safety accidents caused by catastrophic equipment failures. In the current context, predictive maintenance (PdM) is becoming increasingly popular based on machine learning approaches, while its research on electrical equipment such as low-voltage contactors is in its infancy. The failure modes are mainly fusion welding and explosion, and a few are unable to switch on. In this study, a data-driven approach is proposed to predict the remaining useful life (RUL) of the low-voltage contactor. Firstly, the three-phase alternating voltage and current records the life of electrical equipment by tracking the number of times it has been operated. Secondly, the failure-relevant features are extracted by using the time domain, frequency domain, and wavelet methods. Then, a CNN-LSTM network is designed and used to train an electrical equipment RUL prediction model based on the extracted features. An experimental study based on ten datasets collected from low-voltage AC contactors reveals that the proposed method shows merits in comparison with the prevailing deep learning algorithms in terms of MAE and RMSE.

show abstract

Section: Machine Learning For Predictive Maintenancementioning

confidence: 99%

A deep learning-based approach for electrical equipment remaining useful life prediction

Liu

2022

Auton. Intell. Syst.

View full text Add to dashboard Cite

show abstract

“…LSTM has can be considered as the evolution of RNN which has ability to solve the gradient vanishing or explosion problem introduced in 1997, which has the capability to deal with the long and short term dependent problems 49,50 . The LSTM differs the RNN only in terms of the cell unit having memory which has been shown in Figure 16, where the cell structure consists of mainly three gates which are as follows 51 : Forget gate: It is first gate which decide the information that need to be removed or forgotten from the previous cell which can be expressed as:

{fg}_t=\sigma \bullet \left({W}_{fg}\times \left[{h}_{l_{t-1}},{d}_t\right]+{b}_{fg}\right)

here

{d}_t

denotes the input at the present state. Input gate: It exist between other two gates and decides which new information need to be retained or updated into the current state and is given as:

{ig}_t=\sigma \bullet \left({W}_{ig}\times \left[{h}_{l_{t-1}},{d}_t\right]+{b}_{ig}\right)

Output gate: It extracts the final updated information stored in the current cell which can be represented as:

{og}_t=\sigma \bullet \left({W}_{og}\times \left[{h}_{l_{t-1}},{d}_t\right]+{b}_{og}\right)

where,

{fg}_t

…”

Section: Forecasting ML Algorithm Usedmentioning

confidence: 99%

Hyper‐parametric improved machine learning models for solar radiation forecasting

Kumar

Namrata

Kumari

2022

Concurrency and Computation

View full text Add to dashboard Cite

Summary Spatiotemporal solar radiation forecasting is extremely challenging due to its dependence on metrological and environmental factors. Chaotic time‐varying and non‐linearity make the forecasting model more complex. To cater this crucial issue, the paper provides a comprehensive investigation of the deep learning framework for the prediction of the two components of solar irradiation, that is, Diffuse Horizontal Irradiance (DHI) and Direct Normal Irradiance (DNI). Through exploratory data analysis the three recent most prominent deep learning (DL) architecture have been developed and compared with the other classical machine learning (ML) models in terms of the statistical performance accuracy. In our study, DL architecture includes convolutional neural network (CNN) and recurrent neural network (RNN) whereas classical ML models include Random Forest (RF), Support Vector Regression (SVR), Multilayer Perceptron (MLP), Extreme Gradient Boosting (XGB), and K‐Nearest Neighbor (KNN). Additionally, three optimization techniques Grid Search (GS), Random Search (RS), and Bayesian Optimization (BO) have been incorporated for tuning the hyper parameters of the classical ML models to obtain the best results. Based on the rigorous comparative analysis it was found that the CNN model has outperformed all classical machine learning and DL models having lowest mean squared error and highest R‐Squared value with least computational time.

show abstract

“…From an application perspective, fault detection systems have been developed in many areas such as rolling bearing, machines, industrial systems, mechatronics systems, industrial cyber-physical systems, and industrial-scale telescopes, to name a few [15,[23][24][25][26][33][34][35]37,38,41,42]. Some of them describe some advantages and disadvantages over others in the applied methodology to obtain better results.…”

Section: Fault Detectionmentioning

confidence: 99%

“…For example, Yao Li [ 37 ] presented a branched Long-Short Term Memory (LSTM) model with an attention mechanism to discriminate multiple states of a system showing high performance in its prediction based on the F1-score metric. On the other hand, Liu et al [ 38 ] showed a strategy for failure prediction using the LSTM model in a multi-stage regression model to predict the trend; this is then used to classify the level of degradation by similarity with established failure profiles, achieving improvement estimates with better precision.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A RUL Estimation System from Clustered Run-to-Failure Degradation Signals

Cho

Carrasco

Ruz

2022

Sensors

View full text Add to dashboard Cite

The prognostics and health management disciplines provide an efficient solution to improve a system’s durability, taking advantage of its lifespan in functionality before a failure appears. Prognostics are performed to estimate the system or subsystem’s remaining useful life (RUL). This estimation can be used as a supply in decision-making within maintenance plans and procedures. This work focuses on prognostics by developing a recurrent neural network and a forecasting method called Prophet to measure the performance quality in RUL estimation. We apply this approach to degradation signals, which do not need to be monotonical. Finally, we test our system using data from new generation telescopes in real-world applications.

show abstract

Fault prediction of bearings based on LSTM and statistical process analysis

Cited by 82 publications

References 8 publications

A deep learning-based approach for electrical equipment remaining useful life prediction

A deep learning-based approach for electrical equipment remaining useful life prediction

Hyper‐parametric improved machine learning models for solar radiation forecasting

A RUL Estimation System from Clustered Run-to-Failure Degradation Signals

Contact Info

Product

Resources

About