CONFERENCE PROCEEDINGS
Advanced Search
Home > Proceedings > Volume 12800 > Article
Paper
11 October 2023 Research on energy-efficient speed control for automatic train operation based on dueling-DQN algorithm
Tian Lu, Bohong Liu, Yi Shi
Author Affiliations +
Proceedings Volume 12800, Sixth International Conference on Computer Information Science and Application Technology (CISAT 2023); 128006H (2023) https://doi.org/10.1117/12.3003921
Event: 6th International Conference on Computer Information Science and Application Technology (CISAT 2023), 2023, Hangzhou, China
Abstract
In order to realize a better train autopilot energy-saving operation control strategy, a train autopilot method based on Dueling-DQN algorithm is proposed with the train as the research object. Firstly, the train control model is established by considering the train operation demand comprehensively. Secondly, the idea of dueling network is introduced to change the structure of DQN network and prevent the problem of overestimation of value function. Finally, experimental simulations are conducted to compare with the DQN method and explore the feasibility of the method. The experiments are carried out to verify the train operation strategy method by simulating the actual line conditions. From the experimental results, it can be seen that the train operation meets the actual requirements. The energy consumption is 25.4% more energy-efficient than the actual operation, and the convergence speed of the algorithm is improved by about 40% compared with DQN. The Dueling-DQN method can improve the efficiency of the algorithm and can form an energy-efficient operation strategy that is better than the speed control in actual operation under the condition of satisfying the automatic train driving performance, which is meaningful for improving the intelligence of automatic train operation.
(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Citation Download Citation
Tian Lu, Bohong Liu, and Yi Shi "Research on energy-efficient speed control for automatic train operation based on dueling-DQN algorithm", Proc. SPIE 12800, Sixth International Conference on Computer Information Science and Application Technology (CISAT 2023), 128006H (11 October 2023); https://doi.org/10.1117/12.3003921
ACCESS THE FULL ARTICLE
ORGANIZATIONAL
Sign in with credentials provided by your organization.
INSTITUTIONAL
Select your institution to access the SPIE Digital Library.
SELECT YOUR INSTITUTION
PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
PERSONAL SIGN IN
No SPIE Account? Create one
PURCHASE THIS CONTENT
SUBSCRIBE TO DIGITAL LIBRARY
50 downloads per 1-year subscription
Members: $195
Non-members: $335 ADD TO CART
25 downloads per 1 - year subscription
Members: $145
Non-members: $250 ADD TO CART
PURCHASE SINGLE ARTICLE
Includes PDF, HTML & Video, when available
Members: $17.00
Non-members: $21.00 ADD TO CART
PROCEEDINGS
 6 PAGES
DOWNLOAD PAPER SAVE TO MY LIBRARY
GET CITATION
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Education and training
Evolutionary algorithms
Neural networks
Automatic control
Control systems
Motion models
Deep learning
RELATED CONTENT
Subscribe to Digital Library
Receive Erratum Email Alert
Back to Top