H Liu, B Li, F Yao, G Hu, L Xie - Reliability Engineering & System Safety, 2024 - Elsevier
… By employing a customized deepreinforcementlearning algorithm, … approach differs from previous research on maintenance optimization for balanced systems, the proposed method …
… applied to a system with four parallel units. In the second study, we delve into Deep ReinforcementLearning, developing a framework designed for multi-unit systems experiencing …
C Zhang, YF Li, DW Coit - IEEE Transactions on Reliability, 2022 - ieeexplore.ieee.org
… of the multi-component system. This article presents an … systems with load sharing, solved by a modified proximal policy optimization approach based on deepreinforcementlearning …
O Ogunfowora, H Najjaran - Journal of Manufacturing Systems, 2023 - Elsevier
… generally try to minimize maintenance costs for multi-unitsystems by developing … Reinforcementlearningmethods as you will see in the coming chapters use a synergistic approach …
J Chen, K Jiang, R Liang, J Wang, S Zheng… - … Conference on Data …, 2022 - Springer
… In this work we proposed an curriculum learningmethod based on interfering the opponent to solve an heterogeneous force combat. According to the empirical results, the two …
… policies for simplified multi-unitsystems, which impedes those methods from be generalized to … model of the system and derives a PM policy for a two-machine-one-buffer manufacturing …
S Gan, N Yousefi, DW Coit - International Journal of …, 2024 - inderscienceonline.com
… system using a reinforcementlearningapproach. The system utilises a critical machine with … for spares and imperfect maintenance based on the remaining life of multi-unitsystems. For …
… Multi-unit residential buildings … is called deepreinforcementlearning (DRL), which comes to handling large state spaces [33]. The DRL is a category of advanced machinelearning …
J Li, T Yu, X Zhang - … Journal of Electrical Power & Energy Systems, 2022 - Elsevier
… to the challenge caused by convergence in the multi-unit power grid. … deepreinforcement learning algorithm termed as the imitation guided-exploration multi-agent twin-delayed deep …