Multiobjective Deep Belief Networks Ensemble for Remaining Useful Life Estimation in Prognostics

By Chong Zhang, Pin Lim, A. K. Qin, Kay Chen Tan. IEEE Transactions on Neural Networks and Learning Systems, 2017

742 citations recorded by the source corpus.

Subfields: Control and Systems Engineering, Safety, Risk, Reliability and Quality

View Paper: https://www.semanticscholar.org/paper/f0959b291381e15ecc31502af6bad4f22cdd41f5

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Control and Systems Engineering

1. Xiang Li
2. Qian Ding
3. Ruqiang Yan
4. Ningbo Li
5. Naipeng Li
6. Cheng-Geng Huang
7. Hongzhong Huang
8. Yanfeng Li

In Safety, Risk, Reliability and Quality

1. Ningbo Li
2. Naipeng Li
3. Yaguo Lei
4. Cheng-Geng Huang
5. Hongzhong Huang
6. Yanfeng Li
7. Biao Wang

Citations in the corpus

• An Evolutionary Algorithm for Large-Scale Sparse Multiobjective Optimization Problems (2020, background): “In fact, few MOEAs are dedicated to solving sparse MOPs, while most work only adopts general MOEAs to solve them [19], [20].”
• Remaining useful life predictions for turbofan engine degradation using semi-supervised deep architecture (2019, background): “information regarding RUL predictions [19,33].”
• A Hybrid Prognostics Approach for Estimating Remaining Useful Life of Rolling Element Bearings (2020, methodology): “, artificial neural networks (ANNs) [10], [11], support vector machine (SVM) [12], [13], and relevance vector machine (RVM) [14], [15], to train a prediction model and then utilize the trained model to estimate the RUL of a bearing.”
• A Bidirectional LSTM Prognostics Method Under Multiple Operational Conditions (2019, methodology): “In addition, compared with recently developed approaches (e.g., DCNN [16] and MODBNE [20]), the results of the proposed method are also promising and competitive.”
• Machine Remaining Useful Life Prediction via an Attention-Based Deep Learning Approach (2021, methodology): “For the algorithms of SVR, RF, and CNN, we use the parameters in [23] and [26], which have carefully tuned the parameters of the models.”
• Remaining Useful Lifetime Prediction via Deep Domain Adaptation (2019, neutral): “[58].”
• Remaining useful life estimation in prognostics using deep convolution neural networks (2018, methodology): “That is because in many industrial applications, it is impossible to evaluate the precise health condition and estimate the RUL of the system at each time step without an accurate physics-based model [29].”
• A Survey on Evolutionary Neural Architecture Search (2020, neutral): “Other Memetic [134], [162] DE [48], [74] [89] [51] [163] HCA [31], [58], [79] CVOA [87] Hyper-heuristic [77] FA [76] AIS [75] Multiobjective EA [64], [72], [80], [100], [104], [106], [114], [114], [120], [128], [133], [136], [164]–[167] [54], [168] [169] [170], [171]”
• Deep Learning Enabled Fault Diagnosis Using Time-Frequency Image Analysis of Rolling Element Bearings (2017, methodology): “Although not dealing with rolling elements, Zhang [22] used a deep learning multiobjective deep belief network ensemble method to estimate the remaining useful life of NASA’s C-MAPSS data set.”