ABSTRACT
To increase overall passenger satisfaction, the comfort of railways was reconsidered from a passenger perspective. We twice conducted a web-based survey (February and November 2020) on passenger comfort during several representative travel phases (from planning to destination) and developed a draft evaluation index to estimate the overall comfort from the comfort of each travel phase. We confirm that this draft evaluation index created in the first survey shows 70 to 80% estimation accuracy against the second survey data affected by COVID-19, and that the overall comfort can be stably estimated from the comfort of each travel phase. © 2022 Ken-yusha Inc.. All rights reserved.
ABSTRACT
Passenger comfort systems such as Heating, Ventilation, and Air-Conditioning units (HVACs) usually lack the data monitoring quality enjoyed by mission-critical systems in trains. But climate change, in addition to the high ventilation standards enforced by authorities due to the COVID pandemic, have increased the importance of HVACs worldwide. We propose a machine learning (ML) approach to the challenge of failure detection from incomplete data, consisting of two steps: 1. human-annotation bootstrapping, on a fraction of temperature data, to detect ongoing functional loss and build an artificial ground truth (AGT);2. failure prediction from digital-data, using the AGT to train an ML model based on failure diagnose codes to foretell functional loss. We exercise our approach in trains of Dutch Railways, showing its implementation, ML-predictive capabilities (the ML model for the AGT can detect HVAC malfunctions online), limitations (we could not foretell failures from our digital data), and discussing its application to other assets. © 2022, Springer Nature Switzerland AG.