A Multiagent Based Vehicle Engine Fault Diagnosis

  • Authors:

  • Xiaobing Wu;Xueshan Gao;Dharmendra Sharma

  • Affiliations:

  • Beijing Institute of Technology, 100081, Beijing, China;Beijing Institute of Technology, 100081, Beijing, China;University of Canberra, 2601, Canberra, Australia

  • Venue:
  • KES '07 Knowledge-Based Intelligent Information and Engineering Systems and the XVII Italian Workshop on Neural Networks on Proceedings of the 11th International Conference
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

A special two-level neural network Multiagent system is used in vehicle engine fault diagnosis. Each agent contains a neural network (NN) for its intelligent. The first level is used to acquire the reasons of the fault and the second level is used to classify the fault. There are a few advantages for using two-level NN multiagent system. When new knowledge of faults is acquired, only the first level needs to be retrained. An agent system is added into the second level of the whole system, and the main structure of the network need not be changed. Under the cooperation of the relative agent system, we can diagnose out complex faults and synthetic faults with less resource and better performance.