A Genetic Algorithm Optimized RNN-LSTM Model for Remaining Useful Life Prediction of Turbofan Engine

• Published in: Electronics (Basel) Vol. 10; no. 3; p. 285
• Main Authors: Chui, Kwok Tai, Gupta, Brij B., Vasant, Pandian
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.02.2021
• Subjects: Approximation; Artificial intelligence; Datasets; Decomposition; Deep learning; Downtime; Empirical analysis; Failure; Feature extraction; Genetic algorithms; Internet of Things; Life prediction; Maintenance costs; Maintenance management; Neural networks; Optimization algorithms; Performance evaluation; Prediction models; Predictive maintenance; Preventive maintenance; Recurrent neural networks; Root-mean-square errors; Sorting algorithms; Turbofan engines; Useful life; Wavelet transforms
• ISSN: 2079-9292; 2079-9292
• DOI: 10.3390/electronics10030285

Understanding the remaining useful life (RUL) of equipment is crucial for optimal predictive maintenance (PdM). This addresses the issues of equipment downtime and unnecessary maintenance checks in run-to-failure maintenance and preventive maintenance. Both feature extraction and prediction algorithm have played crucial roles on the performance of RUL prediction models. A benchmark dataset, namely Turbofan Engine Degradation Simulation Dataset, was selected for performance analysis and evaluation. The proposal of the combination of complete ensemble empirical mode decomposition and wavelet packet transform for feature extraction could reduce the average root-mean-square error (RMSE) by 5.14–27.15% compared with six approaches. When it comes to the prediction algorithm, the results of the RUL prediction model could be that the equipment needs to be repaired or replaced within a shorter or a longer period of time. Incorporating this characteristic could enhance the performance of the RUL prediction model. In this paper, we have proposed the RUL prediction algorithm in combination with recurrent neural network (RNN) and long short-term memory (LSTM). The former takes the advantages of short-term prediction whereas the latter manages better in long-term prediction. The weights to combine RNN and LSTM were designed by non-dominated sorting genetic algorithm II (NSGA-II). It achieved average RMSE of 17.2. It improved the RMSE by 6.07–14.72% compared with baseline models, stand-alone RNN, and stand-alone LSTM. Compared with existing works, the RMSE improvement by proposed work is 12.95–39.32%.