---

概要

Abstract: Many intelligent diagnosis methods, such as neural networks, genetic algorithms, etc., have been proposed in the field of mechanical fault diagnosis. These methods require a large number of training data and highly sensitive symptom parameters (SPs). However, in many cases of condition diagnosis for rotating machinery, because the training data cannot be easily acquired in a real plant, and SPs are not highly sensitive, the intelligent methods, namely neural networks, genetic algorithms, etc., often cannot converge when learning. In order to solve these problems, this paper proposes a new intelligent method by which the fault of rotating machinery can by sensitively detected and diagnosed by using Support Vector Machine (SVM) and symptom parameters in time domain. We have used the method to diagnose structural faults of rotating machinery, and the efficiency of the proposed method is verified by practical examples of the condition diagnosis.

---

全文掲載のPDFファイルダウンロード

• PDFファイルダウンロード