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) p… Show more
“…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.…”
Section: Comparison Experimentsmentioning
confidence: 99%
“…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].…”
Section: Introductionmentioning
confidence: 99%
“…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].…”
With the continuous progress of technology, the structure of modern industrial equipment is becoming increasingly complex. Complex industrial processes often have multivariable, nonlinear, variable operating conditions and intense noise, making it a challenging research direction to establish accurate residual service life prediction models.
This paper constructs a life prediction model based on two-way convolution, attention mechanisms, and a two-way short-term memory network. The front end of the model uses a two-way convolution scale and attention module to mine critical fault information of bearings, improve the anti-noise ability of the model, and use adaptive batch normalization (AdaBN) and Meta-Aconc activation function to adaptively adjust neurons to enhance the generalization ability of the model, At the back end of the model, the bidirectional long-term and short-term memory network is used to memorize the degradation information of the bearing and the residual service life of the bearing is predicted.
Finally, it has a high prediction accuracy in noise interference and condition migration scenarios using the root mean square error (RMSE), average absolute error (MAE), and other prediction indicators.
This model provides a method reference for predicting the lifespan of rotating machinery under intense noise and variable operating conditions.
“…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.…”
Section: Comparison Experimentsmentioning
confidence: 99%
“…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].…”
Section: Introductionmentioning
confidence: 99%
“…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].…”
With the continuous progress of technology, the structure of modern industrial equipment is becoming increasingly complex. Complex industrial processes often have multivariable, nonlinear, variable operating conditions and intense noise, making it a challenging research direction to establish accurate residual service life prediction models.
This paper constructs a life prediction model based on two-way convolution, attention mechanisms, and a two-way short-term memory network. The front end of the model uses a two-way convolution scale and attention module to mine critical fault information of bearings, improve the anti-noise ability of the model, and use adaptive batch normalization (AdaBN) and Meta-Aconc activation function to adaptively adjust neurons to enhance the generalization ability of the model, At the back end of the model, the bidirectional long-term and short-term memory network is used to memorize the degradation information of the bearing and the residual service life of the bearing is predicted.
Finally, it has a high prediction accuracy in noise interference and condition migration scenarios using the root mean square error (RMSE), average absolute error (MAE), and other prediction indicators.
This model provides a method reference for predicting the lifespan of rotating machinery under intense noise and variable operating conditions.
“…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).…”
Historical condition monitoring data from technical systems can be utilized to develop data-driven models for predicting the remaining useful life (RUL) of similar systems, whereas the Health Index (HI) often is a crucial component. The development of robust and accurate models requires meaningful features that reflect the system’s degradation process, enabling an accurate prediction of the system's HI. Traditionally, the identification of those is supported by one of various feature ranking methods. In literature, feature interdependencies and their transferability across various similar systems are not sufficiently considered in feature selection, exacerbating the challenge of HI prediction posed by the scarcity of data and system diversity in real-world applications. This work addresses this gaps by demonstrating how filter-based feature selection, incorporating failure thresholds and cross correlations, enhances feature selection leading to improved HI prediction. The proposed methodology is applied to a novel dataset* obtained from run-to-failure experiments on geared motors conducted as part of this study, which presents the aforementioned challenges. It is revealed that classical feature selection, consisting of feature ranking only, leaves potential untapped, which is utilized by the proposed selection methodology. It is shown that the proposed feature selection methodology leads to the best result with a RMSE of 0.14 in predicting the HI of a constructive different gearbox, while the features, determined by classical feature selection, lead to a RMSE of 0.19 at best.
“…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…”
This paper presents a comprehensive study on diagnosing a spacecraft propulsion system utilizing data provided by the Prognostics and Health Management (PHM) society, specifically obtained as part of the Asia-Pacific PHM conference’s data challenge 2023. The objective of the challenge is to identify and diagnose known faults as well as unknown anomalies in the spacecraft’s propulsion system, which is critical for ensuring the spacecraft’s proper functionality and safety. To address this challenge, the proposed method follows a systematic approach of feature extraction, feature selection, and model development. The models employed in this study are kMeans clustering and decision trees combined to ensembles, enriched with expert knowledge. With the method presented, our team was capable of reaching high accuracy in identifying anomalies as well as diagnosing faults, resulting in attaining the seventh place with a score of 93.08 %.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.