Earticle

초록

영어

For the single source characteristics of the insufficient problem of nonlinear analog circuit soft fault diagnosis, we propose a new method that is based on dual Wiener core for fault diagnosis of intelligent information optimization fusion[1,2,3,4,5], firstly, the incentive is Gauss white noise, after sampling we obtain the Wiener core of circuit and power which is used from the discrete Wiener core, then use the improved genetic algorithm, make the feature selection and fusion combination as an optimization problem, propose intelligent optimization fusion extraction based on the improved genetic algorithm, the circuit set total Euclidean distance as the objective function optimizes, the different information in feature layer can be organic integration, then use the BP neural network for intelligent diagnosis. Experiments show that the method can effectively improve the accuracy of the diagnosis of nonlinear multiple soft faults.

목차

Abstract
 1. Introduction
 2. Intelligent Fault Diagnosis Based on Wiener Kernel Information Fusion
  2.1 The Acquisition of Weiner Core
  2.2 The Intelligent Optimization and Fusion Selection Dual Core Feature
  2.3 Neural Network Design and Training
  2.4 Test and Diagnosis of Actual Circuit
 3. Examples of Fault Diagnosis
 4. Experimental Results and Analysis
 5. Conclusions
 References

키워드

저자

• Haijun Lin [ Harbin University of Science and Technology, Harbin, China ]
• Jiren Han [ Harbin University of Science and Technology, Harbin, China ]
• Xuhui Zhang [ Harbin University of Science and Technology, Harbin, China ]
• Jingbo Xu [ Harbin University of Science and Technology, Harbin, China ]
• Yunfeng Liu [ Harbin University of Science and Technology, Harbin, China ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of u- and e- Service, Science and Technology

• 간기

  격월간

• pISSN

  2005-4246

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605