Reliability research method of tractive power supply system based on small sample condition

Abstract

The invention discloses a reliability research method for a tractive power supply system based on a small sample condition, and the method carries out virtual augmentation of small sample data by a Bootstrap method, and effectively solves a problem that a Weibull distribution fitting effect is poor because the actual sample amount of related fault data is small in the prior art. Compared with a traditional SVM algorithm, an LSSVM algorithm has the advantages that the calculation complexity is simplified, and the algorithm convergence precision is improved. Advantages of easy implementation, high precision, fast convergence and the like of the particle swarm algorithm are combined. LSSVM model parameters are optimized by applying the designed PSOLSSVM algorithm, and the optimal parameters of the LSSVM are selected to configure. A tractive power supply system model established by adopting a fault tree analysis method and a BDD algorithm is effectively predicted. The reliability and average failure time of the traction power supply system equipment are obtained, and a reliable scientific basis is provided for an overall equipment maintenance plan of the traction power supply system.

Description

technical field [0001] The invention relates to the field of railway traction power supply, in particular to a reliability research method of traction power supply system based on small sample conditions. Background technique [0002] The traction power supply system is a key part of the high-speed railway system, and the speed increase of the train puts forward higher requirements for the traction power supply system. Conventional railway traction power supply system integration schemes (including technical specifications) can no longer meet the requirements for safe operation of the system. Reliable and safe operation of traction power supply systems is crucial to high-speed passenger dedicated lines, and it directly affects the safe and reliable operation of trains. The traction power supply system consists of a large number of catenary, cables, transformers, circuit breakers, isolating switches, transformers, lightning arresters and secondary equipment, etc., but the two...

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the deficiencies in the prior art, the present invention provides a reliability research method based on the traction power supply system under the condition of a small sample, and applies the Bootstrap method to virtual augment the "small sample" data, which effectively improves the correlation in the prior art. The actual sample size of the fault data is small, which leads to poor fitting effect on the Weibull distribution

Images