Optimisation of current collection quality of high-speed pantograph-catenary system using the combination of artificial neural network and genetic algorithm

Abstract

In this paper, The combination of back-propagation neural network (BPNN) and genetic algorithm (GA) is used to optimize the current collection quality of the pantograph-catenary system. The contact force standard deviation (CFSD) between pantograph and catenary is utilized as the optimization index. The optimization works in this paper are as follows. 1. The equivalent mass, stiffness, and damping of the pantograph. 2. The distance between each dropper and the positioning point. 3. The length of each dropper. 4. The tension of contact wire, messenger wire, and stitch wire.  Firstly, a pantograph-catenary coupling simulation model verified by EN 50318: 2018 and the line experiment result is established in this paper. Then, the pantograph-catenary coupling simulations are conducted according to the experiments designed by center composite design (CCD). The BPNN models accurately reflecting the relationship between the optimized input parameters and the output CFSD are established. Subsequently, the minimum CFSD of the BPNN model and the corresponding optimal parameter combinations are searched through GA. Finally, an evaluation method based on the BPNN weight matrix and the Garson equation is used to quantify the relative importance of the input optimized parameters of the established BPNN.

KEYWORDS:

• Pantograph-catenary system
• contact force standard deviation
• current collection quality
• BP neural network
• genetic algorithm

Acknowledgements

This work was supported by National Natural Science Foundation of China (No. 52075457).

Disclosure statement

No potential conflict of interest was reported by the author(s).

Correction Statement

This article has been corrected with minor changes in Figure 2. These changes do not impact the academic content of the article.

Additional information

Funding

This work was supported by National Natural Science Foundation of China: [Grant Number 52075457].