基于PSO算法的飞行保障车辆调度问题研究

计算机工程与应用 ›› 2012, Vol. 48 ›› Issue (1): 242-244.

基于PSO算法的飞行保障车辆调度问题研究

田丰1，邢清华1，张威2

1.空军工程大学导弹学院，陕西三原 713800
2.徐州空军学院航空兵军交运输指挥系，江苏徐州 221000

收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2012-01-01 发布日期:2012-01-01

Research on support vehicles scheduling problem in flight support process with PSO algorithm

TIAN Feng1, XING Qinghua1, ZHANG Wei2

1.Missile Institute, Air Force Engineering University, Sanyuan, Shaanxi 713800, China
2.Department of Aviation Military Transportation Command, Xuzhou Air-force College, Xuzhou, Jiangsu 221000, China

Received:1900-01-01 Revised:1900-01-01 Online:2012-01-01 Published:2012-01-01

摘要/Abstract

摘要： 通过对飞行保障车辆调度过程的分析，针对传统估算法依据指挥员经验进行飞行保障车辆调度效率低等缺点，提出了一种基于线性递减权重PSO的飞行保障车辆调度问题解决方案。根据飞行保障车辆调度问题解的特点，对粒子的编码及寻优操作进行了深入研究，提出适合飞行保障车辆调度问题的粒子编码和寻优方式，并将算法利用Matlab编程实现，应用于实际飞行保障车辆调度过程中。仿真结果表明，通过对算法参数的合理设置，可以快速地得到较优的飞机保障工序排序结果，该排序结果能够满足动态飞行保障车辆调度的需要。

关键词: 飞行保障系统, 车辆调度, 粒子群算法

Abstract: Considering the conventional anticipation method which depends on experience of the commander to schedule the aviation support vehicles, it has the disadvantage of low efficiency, PSO-based linearly decreasing weight to flight support vehicles is presented through analyzing the problem of support vehicle scheduling. According to the characteristics of the problem, the PSO coding and optimization are studied to determine the way of particles’ coding and operation, which is more adaptable to flight support vehicles scheduling. The support vehicles scheduling part of the flight support process is programmed based on the algorithm with software Matlab. Simulation results show that it can provide better plane support sequences to satisfy the requirement of dynamic flight support vehicles scheduling by setting the suitable parameters in algorithm.

Key words: flight support system, vehicle scheduling, Particle Swarm Optimization（PSO）

田丰1，邢清华1，张威2. 基于PSO算法的飞行保障车辆调度问题研究[J]. 计算机工程与应用, 2012, 48(1): 242-244.

TIAN Feng1, XING Qinghua1, ZHANG Wei2. Research on support vehicles scheduling problem in flight support process with PSO algorithm[J]. Computer Engineering and Applications, 2012, 48(1): 242-244.

[1]	史春天，曾艳阳，侯守明. 群体智能算法在图像分割中的应用综述[J]. 计算机工程与应用, 2021, 57(8): 36-47.
[2]	李静星，杨有龙. 针对高维数据的马尔科夫毯特征选择[J]. 计算机工程与应用, 2021, 57(6): 58-66.
[3]	朱佳莹，高茂庭. 融合粒子群与改进蚁群算法的AUV路径规划算法[J]. 计算机工程与应用, 2021, 57(6): 267-273.
[4]	王嘉月，史立. 考虑电池损耗的电动冷藏车路径及充电策略[J]. 计算机工程与应用, 2021, 57(24): 283-289.
[5]	林炜星，王宇嘉，陈万芬，梁海娜. 基于多因子粒子群的高维数据特征选择算法[J]. 计算机工程与应用, 2021, 57(22): 199-207.
[6]	李雨鑫，李悦悦. 面向JIT采购的多目标车辆调度[J]. 计算机工程与应用, 2021, 57(12): 263-272.
[7]	于国龙，赵勇，吴恋，崔忠伟. QPSO算法的改进及其在DBN参数优化中应用[J]. 计算机工程与应用, 2021, 57(10): 154-162.
[8]	周蓉，李俊，王浩. 基于灰狼优化的反向学习粒子群算法[J]. 计算机工程与应用, 2020, 56(7): 48-56.
[9]	杨华龙，陆婷，辛禹辰. 基于改进粒子群算法的异质车队二级IRP优化[J]. 计算机工程与应用, 2020, 56(22): 272-278.
[10]	覃凤婷，杨有龙，仇海全. 基于稀疏子空间的局部异常值检测算法[J]. 计算机工程与应用, 2020, 56(19): 152-159.
[11]	杨彦荣，宋荣杰，周兆永. 基于GAN-PSO-ELM的网络入侵检测方法[J]. 计算机工程与应用, 2020, 56(12): 66-72.
[12]	周琴，程立正. 层适应网格上求解奇异摄动问题的粒子群算法[J]. 计算机工程与应用, 2020, 56(11): 46-50.
[13]	胡雪娇，陈行健，赵南，薛卫. PSO_BFA优化词袋模型及蛋白质亚细胞定位预测[J]. 计算机工程与应用, 2020, 56(1): 165-171.
[14]	蒋丽1，2，叶润舟1，2，梁昌勇1，2，陆文星1，2. 改进的二阶振荡粒子群算法[J]. 计算机工程与应用, 2019, 55(9): 130-138.
[15]	张鑫1，邹德旋1，肖鹏1，喻秋2. 自适应简化粒子群优化算法及其应用[J]. 计算机工程与应用, 2019, 55(8): 250-263.