- Operation and Control
Automated machine learning for train A/C operation models that adapt to changes in the environment
This technology helps to provide comfortable spaces on trains in keeping with changes in the environment (e.g., seasonal changes).
- Automates train crew’s operation of train air conditioning (target temperature correction, circulation fans) through supervised learning (decision tree).
- Builds an automatic learning system that picks up data from trains and sends it to ground systems, creates decision tree models, and reflects results in the train’s operations.
- Confirmed effects in commercial trains through technology verification tests in FY2019.
Applications
- Railway ground systems (learning servers), On-board systems (A/C control, TCMS: Train Control and Monitoring System)
Benchmarks, strengths, and track record
- Some degree of effects verified on actual commercial train lines.
Inquiries
Please include the title “Toshiba AI Technology Catalog: Automated machine learning for train A/C operation models that adapt to changes in the environment” or the URL in the inquiry text.
Please note that because this technology is currently the subject of R&D activities, immediate responses to inquiries may not be possible.
References:
- “Automated machine learning for train A/C operation models that adapt to changes in the environment”; 58th Symposium on Railway Cybernetics, No. 524 (2021)
- “Technical information: Automated machine learning for A/C operation models that adapt to changes in the environment”; Cybernetics Vol. 27 – No 2. 2022, pp. 45-49.