Analysis of factors affecting traction energy consumption of electric multiple unit trains based on data mining

Abstract

Traction energy accounts for a majority of energy consumed by electric multiple unit (EMU) trains. In this study, factors affecting the traction energy consumption of EMU trains are qualitatively and quantitatively analyzed to conserve energy and improve operational efficiency of high-speed railways. First, influencing factors are recognized and categorized into three groups. Then, quantitative analysis is performed using the self-organizing data mining method to analyze the factors affecting traction energy consumption of high-speed EMU trains based on data acquired from a joint debugging and commissioning conducted on EMU trains. The data mining and empirical results are compared for verification, revealing that self-organizing data mining is feasible and efficient to analyze the energy consumption of EMU trains and is better compared to empirical analysis. Because its parameters are dynamic, the self-organizing data mining results can be readily and accurately fit to independent and dependent variables based on the observed data and statistical analysis. Finally, the generality and significance of self-organizing data mining in analyzing the energy consumption of EMU trains considering a large amount of EMU train operation data is discussed.