Remaining useful life prediction for rolling bearings using multi-layer grid search and LSTM

Chang, Zihan; Wei, Yuan; Huang, Kou

doi:10.1016/j.compeleceng.2022.108083

Cited by 31 publications

(10 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wang et al [22] proposed an adaptive self-attentive LSTM network that allows the extraction of indirect health indicators with better results. Chang et al [23] used multi-layer grid search and LSTM to predict RUL. The method integrates feature data and effectively predicts the non-stationary degradation of bearings.…”

Section: Related Workmentioning

confidence: 99%

ODDformer: odd–even de-stationary and decomposition techniques transformer for aircraft engine remaining useful life prediction

Yi,

Han,

Liang

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

In the aerospace industry, accurately predicting the remaining useful life (RUL) of aircraft engines is critical to reduce mainte-nance costs and increase safety. Existing RUL prediction algorithms fail to account for global temporal factors, overlook the non-stationary nature of monitored data, and neglect critical trends and seasonal characteristics. These factors directly affect the sensi-tivity of the forecast model to changes in the system state. In light of this, this study introduces an innovative end-to-end deep learning model, called Odd-even De-stationary and Decomposition Transformer (ODDformer), specifically designed for accurate RUL prediction. By incorporating global time embedding, our model demonstrates improved temporal awareness. We propose an innovative odd-even sequence normalization technique, enhancing data stability. Our method incorporates advanced odd-even de-stationary attention to capture crucial dynamic features, deepening model understanding of data evolution. Simultaneously, our channel-independent series decomposition modules extract reliable trend and seasonal features for each sensor. Finally, the two feature sets are fused to obtain the final prediction results. Experimental results on the N-CMPASS dataset demonstrate a 50.89% reduction in RMSE for ODDformer compared to the baseline and a 59.08% reduction for Score. Ablation experiments have validated the efficacy of these components. Our findings offer promising potential for improving tasks like fault diagnosis and anomaly detection in prognostics and health management.

show abstract

Section: Related Workmentioning

confidence: 99%

ODDformer: odd–even de-stationary and decomposition techniques transformer for aircraft engine remaining useful life prediction

Yi,

Han,

Liang

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…(1) Create a random vector of the direction for the beetle antennae and normalize it: rely on the temporal feature in signals [25]; limited accuracy [41] Illustrative example 1: Atamuradov et al [29] proposed a new health indicator construction method for point machine prognostics composed of a hybrid feature selection, which extracted 8 time-domain features from the point machine sliding-chair CM data. Illustrative example 2: in study [36], the FFT method is applied to extract 12 time-frequency domain feature data, including root mean square, peak, and mean, from the vibration signal to fully mine the data information. Ten, the PCA is used to calculate the eigenvalues of the multidimensional data index covariance matrix and feature vector as the new comprehensive index data, which be used as input data in the prediction model.…”

Section: Rul Predictionmentioning

confidence: 99%

Discovering New Prognostic Features for the Harmonic Reducer in Remaining Useful Life Prediction

Jiang

et al. 2023

Shock and Vibration

View full text Add to dashboard Cite

Vibration and current signals are widely used in fault diagnosis and life prediction of electromechanical transmission systems. However, due to the complex working environment of harmonic reducer in the industrial robot, using a single signal for failure analysis or life prediction may risk to false alarming due to lacking of fault information. In the early operation stage of equipment, fault information contained in the signal is too weak to be extracted. In addition, there is certain correlation among the features, which can lead to meaningless superposition of the calculation process. Therefore, a new health index construction method is proposed integrating the current signal and vibration signal and reducing the redundancy among the features in multidomains and can effectively enhance the fault information. In addition, in view of the local optimum and slow speed caused by the random initialization of the network model, an improved life prediction method is proposed to optimize BP neural network to improve the prediction performance. The proposed method is verified by the test data of the harmonic reducer. Results show that the proposed method can predict the remaining useful life of the harmonic reducer more accurately and effectively.

show abstract

“…Unlike modelbased methods, data-driven methods do not depend on specific physical or expert knowledge, and have the capability to uncover nonlinear relationships between input data and objectives, revealing hidden correlations. Therefore, datadriven methods can overcome certain challenges faced by model-based methods in the context of RUL prediction [9,10]. Within data-driven approaches, machine learning techniques are recognized as powerful and efficient solutions for adaptively modeling the degradation process using measurement data.…”

Section: Introductionmentioning

confidence: 99%

Remaining useful life prediction of bearings using a trend memory attention-based GRU network

Li,

Fan

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Remaining useful life prediction of bearings holds significant importance in enhancing the reliability and durability of rotating machinery. Bearings undergo a gradual degradation process that unfolds over multiple stages. In this paper, a novel framework for forecasting the remaining useful life of bearings is put forward, which includes the construction of a health indicator with a stage division algorithm and the estimation of the health indicator using a new trend memory attention-based gated recurrent unit (TMAGRU). The stage division algorithm, based on the K-Means++ algorithm and angle recognition algorithm, is introduced to distinguish the degradation stage based on the health indicator. Inspired by the double exponential smoothing technique and attention mechanism, the proposed TMAGRU network effectively incorporates both the historical health information in the slow degradation stage and its trend. Experimental results conducted on IEEE PHM Challenge 2012 dataset and XJTU-SY dataset demonstrate the superior predictive performance of the proposed approach compared to several state-of-the-art predictive networks.

show abstract

Remaining useful life prediction for rolling bearings using multi-layer grid search and LSTM

Cited by 31 publications

References 17 publications

ODDformer: odd–even de-stationary and decomposition techniques transformer for aircraft engine remaining useful life prediction

ODDformer: odd–even de-stationary and decomposition techniques transformer for aircraft engine remaining useful life prediction

Discovering New Prognostic Features for the Harmonic Reducer in Remaining Useful Life Prediction

Remaining useful life prediction of bearings using a trend memory attention-based GRU network

Contact Info

Product

Resources

About