Research on Reliability Evaluation Method of Sanitation Vehicles under Small Sample Data. Issue 1 (January 2021)

• Record Type: Journal Article
• Authors: He, YuLong
• Is Part Of: IOP conference series. Volume 647:Issue 1(2021)
• Publication Date: 2021-01
• Subjects: Earth sciences -- Periodicals; Environmental sciences -- Congresses; Environmental sciences -- Periodicals; 550.5
• DOI: 10.1088/1755-1315/647/1/012171
• Languages: English
• ISSNs: 1755-1307

Abstract

Abstract: Aiming at the problem of insufficient failure data of sanitation vehicles, a data expansion model based on gray neural network is proposed. First, the gray model is used to predict the error sequence between the true value and the predicted value; input the error sequence into the neural network, and calculate the error prediction sequence by adjusting parameters such as neurons and weights; the predicted error sequence is multiplied by the weight coefficient and subtracted from the prediction result of the gray model to obtain the final prediction result. The results show that the combined forecasting model is more accurate. This method enlarges the number of fault data samples while maintaining the original data distribution law to determine the reliability distribution model.