Abstract: The existing route search algorithm generally adopts traversal search. Starting from improving the search efficiency, the paper introduces an intelligent optimized particle swarm algorithm to follow the optimal particles in the solution space for search. For the application of particle swarm algorithm in route search, the iterative part of particle meaning and particle position are redefined. Considering the safety and efficiency of the search, the search is concluded by combining the number of iterations control and the accuracy control. Experimental simulation is carried out to test the feasibility of the algorithm and the optimal value of the core parameters, and the experimental results show that the inertia parameter is 0.3, the historical optimal parameter is 0.3, and the global optimal parameter is 0.4, which has the highest search efficiency, and the search algorithm takes about 0.5 s according to the search accuracy requirements, safely and efficiently completes the train route search, and provides a certain reference value for the application of the intelligent optimization algorithm in the railway station train route search.

Key words: route search, particle swarm algorithm, optimal parameter value, station-type data structure

摘要： 现有进路搜索算法普遍采用遍历搜索，从提高搜索效率出发，引入智能优化型的粒子群算法在解空间内追随最优粒子进行搜索。针对粒子群算法在进路搜索中的应用，对粒子含义与粒子位置迭代部分重新定义。从搜索的安全性与高效性等方面考虑，采用迭代次数控制与精度控制相结合的方式结束搜索。进行实验仿真，测试算法可行性与核心参数最优取值，实验结果表明：惯性参数为0.3，历史最优参数为0.3，全局最优参数为0.4，具有最高搜索效率，搜索算法按照搜索精度要求用时0.5 s左右，安全、高效地完成了列车进路搜索，为智能优化算法在铁路车站列车进路搜索的应用提供一定的参考价值。

关键词: 进路搜索, 粒子群算法, 参数最优取值, 站场型数据结构