Remaining useful life prediction for rolling bearings based on similarity feature fusion and convolutional neural network

Abstract

As a critical content of condition-based maintenance (CBM) for mechanical systems, remaining useful life (RUL) prediction of rolling bearing attracts extensive attention to this day. Through mining the bearing degradation rule from operating data, the deep learning method is often used to perform RUL prediction. However, due to the complexity of operating data, it is usually difficult to establish a satisfactory deep learning model for accurate RUL prediction. Thus, a novel convolutional neural network (CNN) prediction method based on similarity feature fusion is proposed. In this paper, the similarity features are extracted based on the correlation between statistical features and time series. After sensitive feature screening, eligible features are applied to develop a health indicator (HI), which can be used to define the bearing failure stages and reduces the complexity of the CNN model. Subsequently, a one-dimensional CNN is established to predict the RUL of bearing, and the HI is utilized to train the prediction model. The proposed approach is verified by FEMTO bearing datasets and IMS bearing datasets. And the experimental results reveal the superiority and effectiveness of the feature fusion-based CNN method in constructing HI and accurate RUL prediction.

A lifetime prediction model based on two-path convolution with attention mechanism and bidirectional long short-term memory network

“…To further demonstrate the superiority of two-path convolutional scaling and attention mechanism, this paper uses CNN [7] (CNN, abbreviated net-1), extended short-term memory network [8] (LSTM, abbreviated net-2), bi-directional extended short-term memory network [9] (BiLSTM, abbreviated net-3) and convolutional extended short-term memory network [13] (CNN-LSTM, abbreviated as net-4) networks, these four network models are used as comparison models for bearing RUL prediction with the two-path convolution-Attention-BiLSTM-Network model in this paper, abbreviated as DABN model below.…”

“…Deep learning has achieved significant results in handling large-scale data and complex pattern recognition in recent years, offering fresh perspectives for solving bearing lifetime prediction problems [6]. Nie et al selected similar features based on the correlation between bearings and time series, feeding them into a convolutional neural network (CNN) to predict bearing life [7]. Yang et al proposed a method based on long short-term memory (LSTM) networks for bearing lifetime prediction, enhancing prediction accuracy by improving the Dropout module during training [8].…”

“…Although deep learning methods have achieved certain successes in bearing lifetime prediction, they exhibit limitations in practical applications, especially under conditions of noise interference and variable working conditions. For example, the CNN method is sensitive to environmental noise [7]. The EEMD-BiLSTM method shows predictive accuracy under different operating conditions but may be limited in dealing with complex noise [9].…”

Filter-based feature selection for prognostics incorporating cross correlations and failure thresholds

“…Feature ranking: Feature ranking is crucial in predictive analysis as it allows to identify the most relevant and informative features. Evaluation metrics employed typically encompass assessment of monotonicity and trendability analysis (Carino, Zurita, Delgado, Ortega, & Romero-Troncoso, 2015;Nie, Zhang, Xu, Cai, & Yang, 2022). Moreover, these metrics can be combined with a metric to consider the robustness (Chen, Xu, Wang, & Li, 2019;Zhang, Zhang, & Xu, 2016).…”

Expert-Informed Hierarchical Diagnostics of Multiple Fault Modes of a Spacecraft Propulsion System

“…Feature extraction is employed to unveil meaningful and significant underlying information from condition monitoring data. Commonly considered domains for extracting features from data of technical systems are time, frequency and timefrequency domain features (Kimotho & Sextro, 2014;Nie, Zhang, Xu, Cai, & Yang, 2022) (Pearson, 1900). The Chi-Square test statistic can be computed as…”