scholarly journals Equipment Failure Prediction based on the Improved Gray Prediction

2015 ◽  
Author(s):  
She Liu ◽  
Shijie Wang ◽  
Huizhi Ren
Keyword(s):  
Failure Prediction ◽  
Equipment Failure ◽  
Gray Prediction

A Study on Failure Prediction of Airborne Electronic Equipment

2007 ◽  
Vol 353-358 ◽  
pp. 2892-2895
Author(s):  
Hong Peng Li ◽  
Yu Ting He ◽  
Rong Shi ◽  
Heng Xi Zhang ◽  
Feng Li
Keyword(s):  
Support Vector Regression ◽  
Failure Probability ◽  
Failure Prediction ◽  
Working Time ◽  
Electronic Equipment ◽  
Support Vector ◽  
Airborne Radar ◽  
Equipment Failure ◽  
Maintenance System ◽  
Auto Regressive

The mostly working time of airborne electronic equipment is under preliminary depletion failure phase, and inspection & maintenance at intervals can’t lower the failure probability. In this paper, the law of airborne electronic equipment failure is introduced firstly. Then, methods for failure prediction are summarized and analyzed. Finally, an example for predicting the airborne radar failure using the Auto-Regressive (AR) and Support Vector Regression (SVR) model is presented. On this basis, it is possible to achieve the goal that increases the reliability in working phase and establish a more scientific maintenance system and to assure the safety of airborne electronic equipment.

Application of Improved BP Network in Failure Forecasting

2012 ◽  
Vol 490-495 ◽  
pp. 373-377
Author(s):  
Zhi Gang Li ◽  
Bo Wei Shi
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Predictive Power ◽  
Failure Prediction ◽  
Prediction Method ◽  
Equipment Failure ◽  
Bp Network ◽  
Neural Network Prediction ◽  
Neural Network Algorithm ◽  
Network Prediction

An improved BP neural network prediction method is used for collecting pipe equipment failure prediction and comparing with the improved BP neural network in front, which demonstrates that the improved BP neural network algorithm to the collecting pipe failures has better predictive power.

Sign in / Sign up

Export Citation Format

Share Document