FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2989091336> ?p ?o ?g. }

• W2989091336 endingPage "105173" @default.
• W2989091336 startingPage "105173" @default.
• W2989091336 abstract "Electric locomotives provide high tractive power for fast acceleration of heavy-haul freight trains, and significantly reduce the energy consumption with regenerative braking. This paper proposes a reinforcement learning (RL) approach for the optimal control of multiple electric locomotives in a heavy-haul freight train, without using the prior knowledge of train dynamics and the pre-designed velocity profile. The optimization takes the velocity, energy consumption and coupler force as objectives, considering the constraints on locomotive notches and their change rates, speed restrictions, traction and regenerative braking. Besides, since the problem in this paper has continuous state space and large action space, and the adjacent actions’ influences on states share similarities, we propose a Double-Switch Q-network (DSQ-network) architecture to achieve fast approximation of the action-value function, which enhances the parameter sharing of states and actions, and denoises the action-value function. In the numerical experiments, we test DSQ-network in 28 cases using the data of China Railways HXD3B electric locomotive. The results indicate that compared with table-lookup Q-learning, DSQ-network converges much faster and uses less storage space in the optimal control of electric locomotives. Besides, we analyze 1)the influences of ramps and speed restrictions on the optimal policy, and 2)the inter-dependent and inter-conditioned relationships between multiple optimization objectives. Finally, the factors that influence the convergence rate and solution accuracy of DSQ-network are discussed based on the visualization of the high-dimensional value functions." @default.
• W2989091336 created "2019-11-22" @default.
• W2989091336 creator A5017774638 @default.
• W2989091336 creator A5056448190 @default.
• W2989091336 creator A5064239100 @default.
• W2989091336 creator A5079703112 @default.
• W2989091336 date "2020-02-01" @default.
• W2989091336 modified "2023-10-15" @default.
• W2989091336 title "Reinforcement learning approach for optimal control of multiple electric locomotives in a heavy-haul freight train:A Double-Switch-Q-network architecture" @default.
• W2989091336 cites W1852135537 @default.
• W2989091336 cites W1853065930 @default.
• W2989091336 cites W1969195578 @default.
• W2989091336 cites W1974589405 @default.
• W2989091336 cites W2009975158 @default.
• W2989091336 cites W2014158136 @default.
• W2989091336 cites W2015474962 @default.
• W2989091336 cites W2019917218 @default.
• W2989091336 cites W2022689755 @default.
• W2989091336 cites W2033250667 @default.
• W2989091336 cites W2046558083 @default.
• W2989091336 cites W2057211133 @default.
• W2989091336 cites W2064168989 @default.
• W2989091336 cites W2070392617 @default.
• W2989091336 cites W2072425957 @default.
• W2989091336 cites W2078644189 @default.
• W2989091336 cites W2079286168 @default.
• W2989091336 cites W2080324798 @default.
• W2989091336 cites W2082958903 @default.
• W2989091336 cites W2095113878 @default.
• W2989091336 cites W2104765758 @default.
• W2989091336 cites W2109028470 @default.
• W2989091336 cites W2116031712 @default.
• W2989091336 cites W2132311469 @default.
• W2989091336 cites W2144366468 @default.
• W2989091336 cites W2145339207 @default.
• W2989091336 cites W2155257334 @default.
• W2989091336 cites W2161260282 @default.
• W2989091336 cites W2244774950 @default.
• W2989091336 cites W2257979135 @default.
• W2989091336 cites W2337617318 @default.
• W2989091336 cites W2345991322 @default.
• W2989091336 cites W2432285071 @default.
• W2989091336 cites W2516895171 @default.
• W2989091336 cites W2526006345 @default.
• W2989091336 cites W2606446473 @default.
• W2989091336 cites W2623013179 @default.
• W2989091336 cites W2626769442 @default.
• W2989091336 cites W2746553466 @default.
• W2989091336 cites W2766282873 @default.
• W2989091336 cites W2766447205 @default.
• W2989091336 cites W2886157770 @default.
• W2989091336 cites W2903320160 @default.
• W2989091336 cites W2912406022 @default.
• W2989091336 cites W2913909435 @default.
• W2989091336 cites W4253791020 @default.
• W2989091336 doi "https://doi.org/10.1016/j.knosys.2019.105173" @default.
• W2989091336 hasPublicationYear "2020" @default.
• W2989091336 type Work @default.
• W2989091336 sameAs 2989091336 @default.
• W2989091336 citedByCount "24" @default.
• W2989091336 countsByYear W29890913362020 @default.
• W2989091336 countsByYear W29890913362021 @default.
• W2989091336 countsByYear W29890913362022 @default.
• W2989091336 countsByYear W29890913362023 @default.
• W2989091336 crossrefType "journal-article" @default.
• W2989091336 hasAuthorship W2989091336A5017774638 @default.
• W2989091336 hasAuthorship W2989091336A5056448190 @default.
• W2989091336 hasAuthorship W2989091336A5064239100 @default.
• W2989091336 hasAuthorship W2989091336A5079703112 @default.
• W2989091336 hasConcept C119599485 @default.
• W2989091336 hasConcept C127413603 @default.
• W2989091336 hasConcept C154945302 @default.
• W2989091336 hasConcept C162380856 @default.
• W2989091336 hasConcept C171146098 @default.
• W2989091336 hasConcept C190839683 @default.
• W2989091336 hasConcept C205649164 @default.
• W2989091336 hasConcept C2780165032 @default.
• W2989091336 hasConcept C2780999251 @default.
• W2989091336 hasConcept C41008148 @default.
• W2989091336 hasConcept C44154836 @default.
• W2989091336 hasConcept C58640448 @default.
• W2989091336 hasConcept C97541855 @default.
• W2989091336 hasConceptScore W2989091336C119599485 @default.
• W2989091336 hasConceptScore W2989091336C127413603 @default.
• W2989091336 hasConceptScore W2989091336C154945302 @default.
• W2989091336 hasConceptScore W2989091336C162380856 @default.
• W2989091336 hasConceptScore W2989091336C171146098 @default.
• W2989091336 hasConceptScore W2989091336C190839683 @default.
• W2989091336 hasConceptScore W2989091336C205649164 @default.
• W2989091336 hasConceptScore W2989091336C2780165032 @default.
• W2989091336 hasConceptScore W2989091336C2780999251 @default.
• W2989091336 hasConceptScore W2989091336C41008148 @default.
• W2989091336 hasConceptScore W2989091336C44154836 @default.
• W2989091336 hasConceptScore W2989091336C58640448 @default.
• W2989091336 hasConceptScore W2989091336C97541855 @default.
• W2989091336 hasFunder F4320321545 @default.
• W2989091336 hasFunder F4320335774 @default.
• W2989091336 hasLocation W29890913361 @default.

• next