摘要
为了降低插电式混合动力汽车(Plug-in Hybrid Electric Vehicle,PHEV)在驾驶过程中的能耗,本文对插电式混合动力汽车绿色路径规划问题(Plug-in Hybrid Electric Vehicle Green Routing Problem,PHEVGRP)进行了研究。基于脉冲耦合神经网络提出了用时间依赖中继神经网络求解时间依赖车辆路径规划问题。基于可实时获取的道路交通状态量建立PHEV能耗计算模型。采用硬参数共享多任务学习建立道路交通状态量的预测模型。结合两个模型,将时间依赖中继神经网络应用于PHEVGRP的求解。采用真实数据进行试验,结果表明所提出的方法能够求得PHEVGRP的基于预测模型的最优解且求解速度优于启发式算法。
In order to reduce the energy consumption of plug-in hybrid electric vehicle(PHEV)during driving,this paper studies the Plug-in Hybrid Electric Vehicle Green Routing Problem(PHEVGRP).A time-dependent relay neural network based on pulse-coupled neural network is proposed to solve time-dependent vehicle routing problem.Based on the road traffic status data that can be acquired in real time,a PHEV energy consumption calculation model is established.Hard parameter sharing multi-task learning is used to establish a prediction model of road traffic status.Combining the two models,the time-dependent relay neural network is applied to the solve PHEVGRP.By using real data for experiments,the result show that the proposed method can obtain the optimal solution of PHEVGRP and is faster than heuristic algorithm.
作者
何智杨
丁烨
HE Zhiyang;DING Ye(Dongguan University of Technology,Dongguan Guangdong 523808,China)
出处
《交通节能与环保》
2023年第5期1-6,共6页
Transport Energy Conservation & Environmental Protection
基金
国家自然科学基金项目(61976051)
国家自然科学基金联合基金重点支持项目(U19A2067)。
