Application of Neural Network to Fault Diagnosis ofElectro-Mechanical System
Access this Article
Search this Article
In this paper, neuro based intelligent diagnosis methods for electro-mechanical controlsystem are proposed. A self organizing map neural network (SOM) is used to classifymeasured data of the target system as a qualitative diagnostic method. Besides of the aboveprocedure, it is expected to attain more efficient maintenance by a quantitative estimationof failure. For the purpose, new method is proposed using a hierarchical neural network(HNN). In the method, classified results by SOM are processed for the quantitative diagnosis.Hierarchical neural network can identify inner structure of the relations between failurecauses and its results that enables a quantitative diagnosis.
- Memoirs of the Faculty of Engineering, Okayama University
Memoirs of the Faculty of Engineering, Okayama University 39(1), 21-27, 2005-01
Faculty of Engineering, Okayama University