| Bayesian Diagnostic Network： A Powerful Model for Representation and Reasoning of Engineering Diagnostic Knowledge |
| |
| 引用本文： | HUZhao-yong. Bayesian Diagnostic Network： A Powerful Model for Representation and Reasoning of Engineering Diagnostic Knowledge[J]. 国际设备工程与管理, 2005, 10(1): 28-35 |
| |
| 作者姓名： | HUZhao-yong |
| |
| 作者单位： | ResearchInstituteofDiagnosticsandCybernetics,Xi＇anJiaotongUniversity,Xi＇an710049,P.R.China |
| |
| 基金项目： | NaturalScienceFoundationofChinaunderGrantNo. 50335030 |
| |
| 摘 要： | Engineering diagnosis is essential to the operation of industrial equipment. The key to successful diagnosis is correct knowledge representation and reasoning. The Bayesian network is a powerful tool for it. This paper utilizes the Bayesian network to represent and reason diagnostic knowledge, named Bayesian diagnostic network. It provides a three-layer topologic structure based on operating conditions, possible faults and corresponding symptoms. The paper also discusses an approximate stochastic sampling algorithm. Then a practical Bayesian network for gas turbine diagnosis is constructed on a platform developed under a Visual C environment. It shows that theBayesian net work is a powerful model for representation and reasoning of diagnostic knowledge. The three-layer structure and the approximate algorithm are effective also.
|
| 关 键 词： | 贝叶斯神经网络 知识推理 工程诊断 专家系统 |
Bayesian Diagnostic Network: A Powerful Model for Representation and Reasoning of Engineering Diagnostic Knowledge |
| |
| Abstract: | Engineering diagnosis is essential to the operation of industrial equipment. The key to successful diagnosis is correct knowledge representation and reasoning. The Bayesian network is a powerful tool for it. This paper utilizes the Bayesian network to represent and reason diagnostic knowledge, named Bayesian diagnostic network. It provides a three-layer topologic structure based on operating conditions, possible faults and corresponding symptoms. The paper also discusses an approximate stochastic sampling algorithm. Then a practical Bayesian network for gas turbine diagnosis is constructed on a platform developed under a Visual C++ environment. It shows that the Bayesian network is a powerful model for representation and reasoning of diagnostic knowledge. The three- layer structure and the approximate algorithm are effective also. |
| |
| Keywords: | engineering diagnosis Bayesian network reasoning knowledge representation |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
