Matches in SemOpenAlex for { <https://semopenalex.org/work/W4281710540> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4281710540 endingPage "108615" @default.
- W4281710540 startingPage "108615" @default.
- W4281710540 abstract "Developing optimal rail renewal and maintenance planning that minimizes long-term costs and risks of failure is of paramount importance for railroad industry. However, intrinsic uncertainty, presence of constraints, and curse of dimensionality induce a challenging engineering problem. Despite the potential capabilities of Deep Reinforcement Learning (DRL), there is very limited research in the area of employing DRL methods to solve renewal and maintenance planning. Inspired by the recent advances in the area of DRL, a DRL-based approach is developed to optimize maintenance and renewal planning. This approach optimizes renewal and maintenance planning over a planning horizon by considering cost-effectiveness and risk reduction. We consider both predictive and condition-based maintenance tasks and incorporate time, resource, and related engineering constraints into the model to capture realistic features of the problem. Available historic inspection and maintenance data is used to simulate the rail environment and feed into DRL method. A Double Deep Q-Network (DDQN) is applied to overcome the uncertainty of the environment. In addition, prioritized replay memory is applied which improves the feedback from the improvement by giving high weight to important experiences of the agent. The proposed DDQN approach is applied to a Class I railroad network to demonstrate the applicability and efficiency the approach. Our analyses demonstrate that the proposed approach develops an optimal policy that not only reduces budget consumption but also improves the reliability and safety of the network." @default.
- W4281710540 created "2022-06-13" @default.
- W4281710540 creator A5032410601 @default.
- W4281710540 creator A5054724725 @default.
- W4281710540 date "2022-09-01" @default.
- W4281710540 modified "2023-10-15" @default.
- W4281710540 title "A deep reinforcement learning approach for rail renewal and maintenance planning" @default.
- W4281710540 cites W2072911393 @default.
- W4281710540 cites W2145339207 @default.
- W4281710540 cites W2159185621 @default.
- W4281710540 cites W2746553466 @default.
- W4281710540 cites W2768978102 @default.
- W4281710540 cites W2794181575 @default.
- W4281710540 cites W2794204271 @default.
- W4281710540 cites W2898897140 @default.
- W4281710540 cites W2921732122 @default.
- W4281710540 cites W2922839280 @default.
- W4281710540 cites W2963426313 @default.
- W4281710540 cites W2985465748 @default.
- W4281710540 cites W2990681646 @default.
- W4281710540 cites W2991061473 @default.
- W4281710540 cites W3008516500 @default.
- W4281710540 cites W3026899377 @default.
- W4281710540 cites W3037319445 @default.
- W4281710540 cites W3037851088 @default.
- W4281710540 cites W3091780726 @default.
- W4281710540 cites W3134861104 @default.
- W4281710540 cites W3158411095 @default.
- W4281710540 cites W3167900848 @default.
- W4281710540 cites W3199652046 @default.
- W4281710540 doi "https://doi.org/10.1016/j.ress.2022.108615" @default.
- W4281710540 hasPublicationYear "2022" @default.
- W4281710540 type Work @default.
- W4281710540 citedByCount "19" @default.
- W4281710540 countsByYear W42817105402022 @default.
- W4281710540 countsByYear W42817105402023 @default.
- W4281710540 crossrefType "journal-article" @default.
- W4281710540 hasAuthorship W4281710540A5032410601 @default.
- W4281710540 hasAuthorship W4281710540A5054724725 @default.
- W4281710540 hasConcept C121332964 @default.
- W4281710540 hasConcept C126255220 @default.
- W4281710540 hasConcept C127413603 @default.
- W4281710540 hasConcept C154945302 @default.
- W4281710540 hasConcept C163258240 @default.
- W4281710540 hasConcept C200601418 @default.
- W4281710540 hasConcept C2776671899 @default.
- W4281710540 hasConcept C28761237 @default.
- W4281710540 hasConcept C33923547 @default.
- W4281710540 hasConcept C41008148 @default.
- W4281710540 hasConcept C42475967 @default.
- W4281710540 hasConcept C43214815 @default.
- W4281710540 hasConcept C62520636 @default.
- W4281710540 hasConcept C97541855 @default.
- W4281710540 hasConceptScore W4281710540C121332964 @default.
- W4281710540 hasConceptScore W4281710540C126255220 @default.
- W4281710540 hasConceptScore W4281710540C127413603 @default.
- W4281710540 hasConceptScore W4281710540C154945302 @default.
- W4281710540 hasConceptScore W4281710540C163258240 @default.
- W4281710540 hasConceptScore W4281710540C200601418 @default.
- W4281710540 hasConceptScore W4281710540C2776671899 @default.
- W4281710540 hasConceptScore W4281710540C28761237 @default.
- W4281710540 hasConceptScore W4281710540C33923547 @default.
- W4281710540 hasConceptScore W4281710540C41008148 @default.
- W4281710540 hasConceptScore W4281710540C42475967 @default.
- W4281710540 hasConceptScore W4281710540C43214815 @default.
- W4281710540 hasConceptScore W4281710540C62520636 @default.
- W4281710540 hasConceptScore W4281710540C97541855 @default.
- W4281710540 hasFunder F4320321001 @default.
- W4281710540 hasLocation W42817105401 @default.
- W4281710540 hasOpenAccess W4281710540 @default.
- W4281710540 hasPrimaryLocation W42817105401 @default.
- W4281710540 hasRelatedWork W1607054433 @default.
- W4281710540 hasRelatedWork W2033512842 @default.
- W4281710540 hasRelatedWork W2369695847 @default.
- W4281710540 hasRelatedWork W2374901194 @default.
- W4281710540 hasRelatedWork W2913665393 @default.
- W4281710540 hasRelatedWork W2994319598 @default.
- W4281710540 hasRelatedWork W3005535424 @default.
- W4281710540 hasRelatedWork W3116237489 @default.
- W4281710540 hasRelatedWork W4233600955 @default.
- W4281710540 hasRelatedWork W4322734194 @default.
- W4281710540 hasVolume "225" @default.
- W4281710540 isParatext "false" @default.
- W4281710540 isRetracted "false" @default.
- W4281710540 workType "article" @default.