Title :
Prediction Model of Equipment Maintenance Materials Consumption Based on Improved BP Neural Network
Author :
Zhang, Lianghua ; Hu, Qiang ; Wu, Mingfei ; Gu, Jin
Author_Institution :
Staff Room of Inf. Technol. & Simulation, Inst. of Chem. Defense, Beijing, China
Abstract :
To make an accurate prediction about the amount of equipment maintenance materials consumption (EMMC), which plays an important role of equipment maintenance materials support, precondition and management, an LM algorithm prediction model of EMMC established based on the improved BP neural network algorithm by means of history data processing, and which has been discussed and verified through example analysis. Experimental results show that the LM prediction algorithm model provides better precision and performance result than the batch gradient descent method with momentum.
Keywords :
backpropagation; data handling; gradient methods; maintenance engineering; neural nets; production engineering computing; production equipment; Levenberg-Marquardt algorithm; backpropagation neural network; equipment maintenance materials consumption; history data processing; Artificial neural networks; Maintenance engineering; Materials; Mathematical model; Prediction algorithms; Predictive models; Training; Computing and algorithm; EMMC; Improved BP neural network; Prediction model;
Conference_Titel :
Computational and Information Sciences (ICCIS), 2010 International Conference on
Conference_Location :
Chengdu
Print_ISBN :
978-1-4244-8814-8
Electronic_ISBN :
978-0-7695-4270-6
DOI :
10.1109/ICCIS.2010.140
