An algorithm for modelling escalator fixed loss energy for PHM and sustainable energy usage

Abstract

Fixed loss energy of escalators denotes the energy consumption of an unloaded escalator. Fixed loss energy fluctuates over time indicating varying operation conditions. We propose an algorithm (named the Optimization approach) to compute daily fixed loss energy based on energy consumption sensor data and validate our algorithm by comparing it to two benchmark methods (named the Classical and Engineering approaches) using a set of experimental data. Our evaluation includes a discussion of the advantages and disadvantages of each approach, ultimately recommending our method due to its nearly 20 times smaller bias. Our optimization approach shows significant improvement (p-value=0.022): error declines from 2.87 for the classical approach to -0.11 for our approach. To further highlight the practical application within Prognostic Health Management (PHM), we design an Exponential Weighted Moving Average (EWMA) chart for monitoring the fixed loss over time and illustrate the potential of this approach in reducing energy usage and costs associated with escalator operation. We estimate that 5 Wh of energy every minute can be saved, which roughly equals 10% of the fixed loss energy of the escalator in our example. This study enables us to support health status assessment of escalators, and provides valuable insights into maintenance effectiveness, as well as identifying excessive energy consumption.