A Parameter Identification Method of Train Basic Resistance Based on Improved White Shark Algorithm

ABSTRACT Nowadays, the development of automatic train operation technology has promoted the popularization and application of high‐level automatic train control equipment. The higher‐level automatic train control equipment requires more accurate operational parameters as data support to ensure the safety and efficiency of train operation. The train basic resistance parameters cannot be directly measured and must be obtained by establishing train dynamics models and applying parameter identification methods. At present, the existing methods are difficult to balance the generality, identification efficiency, and robustness in parameter identification of train basic resistance. In this research, an identification framework based on train single‐mass dynamics model is firstly established to transform the parameter identification problem into a parameter optimization problem. Subsequently, an improved white shark algorithm incorporating logistic chaos map, time‐varying inertia weight, and Gaussian random walk is designed to solve the problem. The proposed algorithm achieves an optimal mean square error value of 0.002189 with a maximum error of 0.1248 km/h. Finally, using the real operational data from a specific line of the Beijing Subway System, comparative validation, ablation study, and robustness testing against Genetic Algorithm and the original White Shark Algorithm demonstrate the efficacy and robustness of the proposed framework and method.