车辆路径问题的混沌神经网络解法

摘要/Abstract

摘要： 利用混沌神经网络在解组合优化问题时具有的随机性和确定性并存的优点，对一类随机需求服从泊松分布的车辆选径问题进行了求解，提出了一种混沌神经网络求解算法，并与平均场退火算法和模拟退火算法进行了比较。结果表明，该算法具有很强的避免陷入局部极小点的能力和较强的全局搜索能力，较大地提高了优化的时间性能和求解质量，是求解车辆选径问题的有效方法。

关键词: 组合优化, 混沌, 神经网络, 车辆选径问题

Abstract: By making full use of coexistence of randomicity with deterministic property in a chaotic neural network, a novel solution to a combinatorial optimization problem was proposed. For a class of Vehicle Routing Problems (VRP) with Poisson-distributed stochastic demands, a model was first set up to solve the problem and the solution was then compared with those obtained by the existing mean field annealing approach and simulated annealing approach. Results from case studies showed that the proposed algorithm could avoid getting stuck in local minima and has better global-search capability. The proposed algorithm has greatly improved optimization time property and solution quality, and it was an effective method to solve Stochastic VRP problems.

Key words: combinatorial optimization, chaos, neural network, vehicle routing problem

中图分类号:

O24
U116

王德东，郑丕谔. 车辆路径问题的混沌神经网络解法[J]. .

WANG De-dong ,ZHENG Pi-e. Chaotic neural network-based solution to vehicle routing problem[J]. .

参考文献

［1］ DANTZIG G B, RAMSER K B. The truck dispatch Problem ［J］. Management Science, 1959, 12(1): 80-91.

[2] LAPORTE G, LOUVEAUX F V, MERCURE H. The vehicle routing problem with stochastic travel times［J］. Transportation Science,1992,26（3）:161-170.

[3] TEODOROVIC D, PAVKOVIC G. A simulated annealing technique approach to the vehicle routing problem in the case of stochastic demand［J］. Transportation Planning and Technology, 1992, 16(1): 261-273.

[4] POPOVIC J. Vehicle routing in the case of uncertain demand: a Bayesian approach［J］. Transportation Planning and Technology, 1995, 19(1): 19-29.

[5] MILOSAVLJEVIC N, TEODOROVIC D. A fuzzy approach to the vehicle assignment problem［J］. Transportation Planning and Technology, 1996, 20(1): 33-47.

[6] GOLDEN B L, LAPORTE G,TAILLAND E D. An adaptive memory heuristic for a class of vehicle routing problems with minmax objective［J］. Computers Ops Res, 1997, 24(5): 445-452.

[7] YUAN Jian, LIU Jin. A hopfield neural network approach to the vehicle routing problem with stochastic demands［J］. Transactions of Nanjing University of Aeronautics and Astronautics, 2000, 32(5):579-503 (in Chinese).［袁健，刘晋.随机需求情形VRP的Hopfield神经网络解法［J］. 南京航天航空大学学报，2000, 32(5):579-203.］

[8] YUAN Jian, LIU Jin, LU Houqing. Annealed neural networks approach to the vehicle routing problem with stochastic demands［J］.System Engineering-Theory & Practice, 2002, 22(3):109-113(in Chinese).［袁健，刘晋，卢厚清.随机需求情形VRP的退火网络解法［J］. 系统工程理论与应用，2002，22(3)：109-113.］

[9] WANG Ling, ZHENG Dazhong. A kind of chaotic neural network optimization algorithm based on annealing strategy［J］.Control Theory and Applications, 2000,17(1):139-142(in Chinese).［王凌，郑大钟.一种基于退火策略的混沌神经网络优化算法［J］. 控制理论与应用，2000，17(1): 139-142.］

[10] HOPFIELD J J, TANK D W.“Neural” computation of decisions in optimization problem ［J］. Biological Cybernetics，1985, 52(8): 141-152.

[1]	孙笑笑,侯文杰,沈沪军,应钰柯,俞东进. 基于上下文感知的多角度业务流程在线异常检测方法[J]. 计算机集成制造系统, 2021, 27(9): 2532-2541.
[2]	田钰. 基于多元特征感知网络的高考成绩预测[J]. 计算机集成制造系统, 2021, 27(9): 2741-2748.
[3]	冯国奇,崔东亮,代学武,俞胜平. 数据视角下神经网络增量学习支持的涡轮盘多目标优化[J]. 计算机集成制造系统, 2021, 27(8): 2393-2404.
[4]	郭羽含,于俊宇,刘万军,张宇,张美琪. 制造业可持续供应链网络建模及求解[J]. 计算机集成制造系统, 2021, 27(7): 2112-2133.
[5]	杨通,姚山,薛凯华. 用于增材制造的点云直接分层算法[J]. 计算机集成制造系统, 2021, 27(5): 1371-1381.
[6]	杜彦斌,吴国奥,许磊. 基于神经网络和再制造因子的再制造机床可靠性分配方法[J]. 计算机集成制造系统, 2021, 27(4): 1052-1061.
[7]	程永胜,徐骁琪,陈国强,孙利,吴俭涛. 基于神经网络的电动汽车造型意象预测模型[J]. 计算机集成制造系统, 2021, 27(4): 1135-1145.
[8]	王民,刘利明,宋铠钰,杨斌,王琛. 基于主轴驱动电流杂波的立铣刀复杂工况下磨损状态辨识[J]. 计算机集成制造系统, 2021, 27(12): 3429-3438.
[9]	王欢,张春,张宁,陈耀华. 具有强泛化性的高铁逆变器开路故障诊断算法[J]. 计算机集成制造系统, 2021, 27(11): 3236-3246.
[10]	徐彦伟,蔡薇薇,颉潭成,陈立海,刘明明. 变工况下基于信息融合的地铁牵引电机轴承故障智能诊断[J]. 计算机集成制造系统, 2021, 27(11): 3247-3258.
[11]	任春华,孙林夫,韩敏. 面向多价值链的汽车配件需求预测模型[J]. 计算机集成制造系统, 2021, 27(10): 2786-2800.
[12]	刘辉,张超勇,戴稳. 基于堆叠稀疏去噪自动编码网络与多隐层反向传播神经网络的铣刀磨损预测模型[J]. 计算机集成制造系统, 2021, 27(10): 2801-2812.
[13]	李丽丽,陈琨,高建民,李辉,冯增行,张建. 采用优化概率神经网络的质量异常识别方法[J]. 计算机集成制造系统, 2021, 27(10): 2813-2821.
[14]	陈德蕾,王成,曾煜,李海波,赖雄鸣,陈叶旺. 基于神经网络和模型迁移学习的不相关多源频域载荷识别[J]. 计算机集成制造系统, 2021, 27(10): 2961-2969.
[15]	陈耶拉,耿秀丽. 基于改进协同过滤的个性化产品服务系统方案推荐[J]. 计算机集成制造系统, 2021, 27(1): 240-248.