Prediction and Evaluation of the Comfort of a Passenger in a High-Speed Maglev System Based on a Neural Network Algorithm

The comfort of a passenger is related to vehicle speed and line condition, which represents the comprehensive value of acceleration perceived by passengers. Shanghai Maglev demonstration line is the longest test line in the world, and its mainline is less than 30 km, which cannot support the test or operation of the maglev system with a speed of more than 500 km/h. Therefore, it is necessary to scientifically predict the comfort parameters of the maglev system operating at higher speeds through the existing test data when the test conditions are not available. Therefore, it is necessary to scientifically predict the technical parameters of the maglev system operating at a higher speed through the existing test data when the test conditions are not available. Based on the passenger comfort test data of 430 km/h high-speed maglev vehicle on Shanghai Maglev demonstration line, the relationship between the comfort measurement value and historical data such as running speed, line, and vehicle condition is studied. The relationship between the weight of the relevant factors affecting the vehicle comfort and vehicle speed is analyzed. The improved Elman neural network algorithm is used to predict and evaluate the comfort of 600 km/h vehicle by taking the speed and line condition as input value and the comfort of a passenger as an output value. The above research provides theoretical support for the design of a maglev system operating at 600 km/h or even higher speed.

Language

  • English

Media Info

  • Media Type: Web
  • Pagination: pp 1080-1088
  • Monograph Title: CICTP 2020: Transportation Evolution Impacting Future Mobility

Subject/Index Terms

Filing Info

  • Accession Number: 01767390
  • Record Type: Publication
  • ISBN: 9780784483053
  • Files: TRIS, ASCE
  • Created Date: Dec 9 2020 3:02PM