摘要
电子产品涉及的配件较多,每种配件均有多种品牌与型号,给CTO订单的确定带来较大的困难。针对上述问题,以功能定位目标贴近度为优化目标,加工成本和产品功耗为约束条件,建立了一种电子产品CTO订单推荐(CTO order recommendation,CTOR)模型,并提出一种改进的遗传算法来求解该模型。仿真结果验证了改进算法的有效性:自适应遗传算子提高了算法的收敛精度和速度,而种群的多样性维护策略在一定程度上降低了算法陷入局部最优的可能性。
Configure-to-order(CTO)is an effective way to meet the personalized needs of users.There are many accessories involved in electronic products,and each kind of accessories has a variety of brands and models,thus very difficult to determine the order of CTO.In order to solve the above problems,a CTO order recommendation(CTOR)model for electronic products is established with function proximity as optimization target in processing cost and product power consumption as constraints.An improved genetic algorithm is proposed to solve the model.The simulation results verify the effectiveness of the improved algorithm.Adaptive genetic operator improves the convergence accuracy and speed of the algorithm.The diversity maintenance strategy of the population reduces the possibility of the algorithm falling into the local optimum to some extent.
作者
韩海峰
叶恒舟
张路
HAN Hai-feng;YE Heng-zhou;ZHANG Lu(Guangxi Key Laboratory of Embedded Technology and Intelligent System,Guilin University of Technology,Guilin 541006,China)
出处
《桂林理工大学学报》
CAS
北大核心
2020年第2期409-414,共6页
Journal of Guilin University of Technology
基金
国家自然科学基金项目(51365010)
广西科技重大专项(桂科AA19046004)
广西嵌入式技术与智能系统重点实验室项目(2019-01-10)。
关键词
CTO订单推荐
自适应
遗传算法
种群多样性
CTO order recommendation
adaptive
genetic algorithm
population diversity
