![open-access-img](/_next/image?url=/images/open-access.png&w=32&q=100)
![open-access-img](/_next/image?url=/images/open-access.png&w=32&q=100)
Author(s)
David Zhang,
Fengju Li,
Fengzhong Wang,
Xie Xin-peng
Publication year2019
Publication title
iop conference series. materials science and engineering
Resource typeJournals
PublisherIOP Publishing
According to the historical data characteristics of vehicle turnover equipment demand, a GM (1,1) - BP combined model is established. Firstly, GM (1,1) model is used to forecast the historical data of vehicle turnover equipment demand. On this basis, BP neural network is introduced to correct the residual of the prediction. It optimizes the forecasting method of vehicle turnover equipment demand, makes up the deficiency of single model, and enhances the accuracy of vehicle turnover equipment demand forecasting.
Subject(s)algorithm , artificial intelligence , artificial neural network , computer science , demand forecasting , econometrics , economics , engineering , operations research , residual
Language(s)English
eISSN1757-899X
pISSN1757-8981
DOI10.1088/1757-899x/688/5/055008
Seeing content that should not be on Zendy? Contact us.