订单需求预测的低偏差序列混合遗传粒子群优化算法  

Hybrid Genetic Particle Swarm Optimization Algorithm for Forecast of Orders Demand Based on Low Discrepancy Sequence

作　　者：黄建强 张爱军 赵梗明[1] HUANG Jianqiang;ZHANG Aijun;ZHAO Gengming(College of Information, Mechanical and Electrical Engineering, Shanghai Normal University, Shanghai 200030, China)

机构地区：[1]上海师范大学信息与机电工程学院,上海200030

出　　处：《宜宾学院学报》2018年第12期38-40,共3页Journal of Yibin University

摘　　要：传统启发式搜索算法存在易陷入局部最优的缺点,因此其优化的灰色神经网络不能准确预测冰箱订单需求.为了提高订单需求的预测精度,提出了基于低偏差序列的遗传粒子群优化算法对灰色神经网络参数进行优化.仿真实验结果表明,改进后的混合遗传粒子群优化灰色神经网络的预测精度更高.The traditional heuristic search algorithm has the disadvantage of falling into local minimization,its optimized grey neural network cannot forecast the refrigerator orders demand accurately.In order to improve the forecast accuracy of the orders demand,hybrid genetic particle swarm optimization algorithm was proposed to optimize the parameters of the grey neural network based on low discrepancy sequence.The results of simulation experiments show that the forecast accuracy of the improved grey neural network with hybrid genetic particle swarm optimization is higher than that before.

关 键 词：灰色神经网络 遗传粒子群算法 预测模型 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]