Integrated Hilbert Huang technique for bearing defects detection

Abstract

Nowadays, the modern rotating machinery industries, such as automotive industries, aerospace turbo machinery, chemical plants, and power stations, are rapidly increasing in complexity and in their everyday operations, which demand the system to operate in higher reliability, extreme safety, and with lower cost of production and maintenance. Therefore accurate fault diagnosis of machine failure is vital to the operation and production departments. The majority of Machine imperfections and malfunctions have been related to bearings faults. Many researchers are still exploring to find suitable diagnosis strategies and techniques to detect incipient bearing faults. A new integrated Hilbert-Huang technique (iHT) is proposed in this paper for bearing fault detection. The iHT takes two processes; firstly: representative signatures are extracted and secondly the resulting selected features are employed to highlight defect-related impulses for incipient bearing fault detection. A novel Jarque-Bera analysis method is suggested to select most prominent characteristic feature functions and the signals are integrated to enhance the features of the condition related function. The effectiveness of the proposed iHT technique is verified by a series of experimental tests corresponding to different bearing health conditions.