基于Gray-Markov的电力设备物流量多目标组合估计  

Multi-objective combination estimation of power equipment material flow based on Gray-Markov

作　　者：陈耀标 CHEN Yaobiao(Zhejiang Power Transmission and Transformation Engineering Co.,Ltd.,Hangzhou 310020,China)

机构地区：[1]浙江省送变电工程有限公司,浙江杭州310020

出　　处：《电子设计工程》2024年第19期86-89,93,共5页Electronic Design Engineering

基　　金：浙江省送变电工程有限公司科研项目(7190213JS2022)。

摘　　要：电力设备物流量较多且所涉及到的环节较为复杂,导致物流量多目标组合估计误差增加,所以设计基于Gray-Markov的电力设备物流量多目标组合估计方法。利用数据录入模块、数据分析处理模块搭建数据采集平台,实现电力设备物流量数据采集。改进卷积神经网络,构建深度空洞卷积去噪模型,对采集到的数据实施去噪处理。结合BP神经网络与Gray-Markov实现电力设备物流量多目标组合估计。测试结果表明,该方法的绝对误差平均值最低仅为1 025.21,平均相对误差百分比一直低于1.8%,估计误差比较小,精度较高。Due to the large logistics volume of power equipment and the complex links involved,the multi-objective combination estimation error of logistics volume increases.Therefore,a multi-objective combination estimation method of power equipment material flow based on Gray-Markov is designed.Use the data entry module and data analysis and processing module to build a data collection platform to realize the data collection of electric equipment logistics volume.The convolution neural network is improved,the deep hole convolution denoising model is constructed,and the collected data is de-noised.Combining BP neural network and Gray-Markov to realize multi-objective combined estimation of power equipment material flow.The test results show that the average absolute error of this method is only 1025.21,and the average relative error percentage is always lower than 1.8%.The estimation error is relatively small and the accuracy is high.

关 键 词：Gray-Markov 电力设备 多目标 组合估计 BP神经网络 

分 类 号：U291.5[交通运输工程—交通运输规划与管理] TN-9[交通运输工程—道路与铁道工程]