Deep reinforcement learning based preventive maintenance policy for serial production lines.
Jing HuangQing ChangJorge ArinezPublished in: Expert Syst. Appl. (2020)
Keyphrases
- preventive maintenance
- production line
- reinforcement learning
- optimal policy
- multistage
- policy search
- buffer allocation
- scheduling problem
- action selection
- production system
- markov decision processes
- flowshop
- reward function
- control policy
- production process
- state space
- maintenance cost
- function approximators
- infinite horizon
- policy gradient
- dynamic programming
- allocation strategy
- material handling
- machine learning
- sufficient conditions
- data mining
- computational complexity
- learning algorithm
- expert systems
- data model
- special case