Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Low-Data Predictive Maintenance of Railway Station Doors and Elevators Using Bayesian Proxy Flow Modeling

Waldemar Bauer, Jerzy Baranowski

Abstract

This paper proposes a low-data predictive maintenance framework for automatic doors and elevators in a railway station building. The method is intended for assets without direct condition monitoring, where only aggregate passenger traffic information and expert knowledge about movement patterns are available. Passenger flows are modeled on a reduced station graph using a Bayesian formulation with uncertain totals and routing shares. The inferred flows are converted into approximate operating-cycle loads for doors and elevators through simple stochastic proxy relations. These loads are combined with uncertain age- and cycle-based maintenance thresholds to estimate the probability that predefined maintenance conditions have been reached. A cost-aware scheduling model is then used to align maintenance activities while accounting for service costs, disruption, delay penalties, and grouping opportunities within each asset class. The framework is illustrated on a simulated case study reflecting a real station layout. The results show that proxy operational data can support maintenance scheduling with low incremental implementation cost and can improve alignment relative to a calendar-based policy.

Low-Data Predictive Maintenance of Railway Station Doors and Elevators Using Bayesian Proxy Flow Modeling

Abstract

This paper proposes a low-data predictive maintenance framework for automatic doors and elevators in a railway station building. The method is intended for assets without direct condition monitoring, where only aggregate passenger traffic information and expert knowledge about movement patterns are available. Passenger flows are modeled on a reduced station graph using a Bayesian formulation with uncertain totals and routing shares. The inferred flows are converted into approximate operating-cycle loads for doors and elevators through simple stochastic proxy relations. These loads are combined with uncertain age- and cycle-based maintenance thresholds to estimate the probability that predefined maintenance conditions have been reached. A cost-aware scheduling model is then used to align maintenance activities while accounting for service costs, disruption, delay penalties, and grouping opportunities within each asset class. The framework is illustrated on a simulated case study reflecting a real station layout. The results show that proxy operational data can support maintenance scheduling with low incremental implementation cost and can improve alignment relative to a calendar-based policy.
Paper Structure (17 sections, 12 equations, 4 figures, 1 table)

This paper contains 17 sections, 12 equations, 4 figures, 1 table.

Table of Contents

  1. Introduction
  2. Proposed Framework
  3. Passenger Flow Model
  4. Device Load Estimation
  5. Maintenance-Condition Probability
  6. Maintenance Scheduling Model
  7. Scheduling Objective
  8. Cost Components
  9. Grouping Effect and Temporal Alignment
  10. Reference Calendar Policy
  11. Case Study and Simulation Setup
  12. Results and Discussion
  13. Passenger-Flow Inference on the Station Graph
  14. Estimated Loads of Doors and Elevators
  15. Maintenance-Condition Reaching Probabilities
  16. ...and 2 more sections

Figures (4)

  • Figure 1: View of the recently renovated Łódź Kaliska railway station, which provides the real architectural context for the illustrative case study considered in this paper. The analytical results presented later are based on synthetic numerical data consistent with this layout, since the operational data used in the underlying project are proprietary.
  • Figure 2: Illustrative passenger-flow intensity over the reduced station graph superimposed on the station floor plan.
  • Figure 3: Illustrative proxy-based cumulative estimated cycles since last relevant maintenance for selected doors and elevators, shown with uncertainty bands.
  • Figure 4: Illustrative maintenance-reaching probabilities for selected assets under uncertain cycle and age accumulation.