A Remaining Useful Life Prediction Method of Rolling Bearings Based on Deep Reinforcement Learning.
Guokang ZhengYasong LiZheng ZhouRuqiang YanPublished in: IEEE Internet Things J. (2024)
Keyphrases
- reinforcement learning
- neural network
- significant improvement
- detection method
- support vector machine
- preprocessing
- support vector machine svm
- state space
- probabilistic model
- high accuracy
- cost function
- prior knowledge
- mathematical model
- correlation coefficient
- prediction error
- prediction algorithm
- synthetic data
- segmentation method
- dynamic programming
- classification accuracy
- computational cost
- k means
- pairwise
- computational complexity
- multiscale
- similarity measure
- image sequences
- genetic algorithm
- machine learning