Diagnosis, classification and prognosis of rotating machine using artificial intelligence

• Main Author: Mahamad, Abd Kadir
• Format: Thesis
• Language: English
• Published: 2010
• Subjects: QC Physics; QC251-338.5 Heat
• Online Access: http://eprints.uthm.edu.my/3637/

The demand for cost efficient, reliable and safe rotating machinery requires accurate fault diagnosis, classification and prognosis systems. Therefore these issues have become of paramount important so that the potential failures of rotating machinery can be managed properly. Various methods have been applied to tackle these issues, but the accuracy of those methods is just satisfactory only. This research, therefore propose appropriate methods for fault diagnosis, classification and prognosis systems. For fault diagnosis and classification, the vibration data was obtained from Western Reserved University. The vibration signal was processed through pre-processing stage, features extraction, features selection before the developed diagnosis and classification model were built. For fault prognosis systems, the acoustic emission and vibration signals were used as input signals. Furthermore, ANN was used as prognosis systems of rotating machinery failure. The simulation results for fault diagnosis, classification and prognosis systems show that proposed methods perform very well and accurate. The proposed model can be used as tools for diagnosing rotating machinery failures.