Digital twin updating method of railway vehicle bogies based on hybrid whale sea-horse optimization

Abstract

Railway vehicle bogies run continuously under complex and changeable working conditions for a long time, and the friction and wear of parts, performance degradation and failure occur, resulting in the difficulty of synchronous mapping between digital twin model and physical entity, which seriously affects the accuracy of condition monitoring and fault diagnosis. In order to solve this problem, this paper proposes a digital twin updating method for railway vehicle bogies based on hybrid whale sea-horse optimization (HWSHO), which is used for fault identification under varying working conditions. A comprehensive index of signal characteristics is constructed, and a multi-strategy optimization method of digital twin agent model is proposed. The HWSHO algorithm is proposed, which uses sin chaotic mapping and opposition learning, dynamic adaptive transformation probability, local exploration of whale bubble spiral motion and adaptive T-distribution variation. The digital twin update is realized by real-time sensor data, and the real-time fault defect size of the mapping is obtained. The effectiveness of the proposed method is proved by the data of spalling defects of bogie gears. The results show that the proposed digital twin update method realizes digital twin synchronous mapping and can accurately identify the fault size under different working conditions.