Asia Pacific Journal of Multidisciplinary Research, Vol. 5, No. 1, February 2017 _______________________________________________________________________________________________________________ 103 P-ISSN 2350-7756 | E-ISSN 2350-8442 | www.apjmr.com Vibration Feature Extraction and Analysis for Fault Diagnosis of Rotating Machinery-A Literature Survey Saleem Riaz 1 , Hassan Elahi 2,3 , Kashif Javaid 1 , Tufail Shahzad 4 1 Northwestern Polytechnical University, Xi’an, China; 2 La Sapienza University of Rome, Rome, Italy; 2 Department of Mechanical Engineering, Institute of Space Technology, Islamabad, Pakistan; 3 Advanced Master in Ship Design (EMSHIP: Erasmus Mundus) University of Liege, Liege, Belgium saleemriaznwpu@yahoo.com, hassanelahi_uet@yahoo.com Date Received: August 10, 2016; Date Revised: January 4, 2017 Asia Pacific Journal of Multidisciplinary Research Vol. 5 No.1, 103-110 February 2017 P-ISSN 2350-7756 E-ISSN 2350-8442 www.apjmr.com Abstract – Safety, reliability, efficiency and performance of rotating machinery in all industrial applications are the main concerns. Rotating machines are widely used in various industrial applications. Condition monitoring and fault diagnosis of rotating machinery faults are very important and often complex and labor-intensive. Feature extraction techniques play a vital role for a reliable, effective and efficient feature extraction for the diagnosis of rotating machinery. Therefore, developing effective bearing fault diagnostic method using different fault features at different steps becomes more attractive. Bearings are widely used in medical applications, food processing industries, semi-conductor industries, paper making industries and aircraft components. This paper review has demonstrated that the latest reviews applied to rotating machinery on the available a variety of vibration feature extraction. Generally literature is classified into two main groups: frequency domain, time frequency analysis. However, fault detection and diagnosis of rotating machine vibration signal processing methods to present their own limitations. In practice, most healthy ingredients faulty vibration signal from background noise and mechanical vibration signals are buried. This paper also reviews that how the advanced signal processing methods, empirical mode decomposition and interference cancellation algorithm has been investigated and developed. The condition for rotating machines based rehabilitation, prevent failures increase the availability and reduce the cost of maintenance is becoming necessary too. Rotating machine fault detection and diagnostics in developing algorithms signal processing based on a key problem is the fault feature extraction or quantification. Currently, vibration signal, fault detection and diagnosis of rotating machinery based techniques most widely used techniques. Furthermore, the researchers are widely interested to make automatic procedures for fault extraction techniques. Such expert systems, neural networks, artificial intelligence and system devices and most powerful methods described above in conjunction with some of the techniques being used fuzzy inference system. Keywords – Condition monitoring, rotating machinery faults, fault diagnostic method, fault features extraction, advanced signal processing methods, frequency domain, time frequency analysis. INTRODUCTION Machinery rotating mass often with very demanding performance standards, some of which are complex used in the industry today. Machine failure, a failure of a reliable lead-time is not able to predict, without effective evaluation. Thus resulting in costly downtime can be devastating. Therefore, effective and efficient condition monitoring and fault diagnosis is essential for the industry. However, the diagnosis of faults in rotating machinery is often a labor-intensive and time-consuming. Effective and efficient fault diagnosis is always a challenging task for the technicians and plant diagnostics. Fault diagnosis is usually done in the following steps: data acquisition, feature extraction, and fault detection and identification structure. Vibration signals collected and processed by the sensor are often contaminated by noise and thus unusable for direct machine faults diagnose. Properties (signatures and characteristics) can go undetected without the help of special techniques. Feature extraction techniques can increase the signal to noise ratio to detect machine faults signal for help or find some ingredients. Several vibration of rotating machinery fault diagnosis techniques have