ISSN (Online) 2278-1021 ISSN (Print) 2319-5940 International Journal of Advanced Research in Computer and Communication Engineering Vol. 4, Issue 3, March 2015 Copyright to IJARCCE DOI 10.17148/IJARCCE.2015.4359 240 Techniques of Vibration Signature Analysis Sumit Kumar Sar 1 , Dr. Ramesh Kumar 2 P.hD Scholar, Department of Computer Science & Engineering, BIT, Durg, India 1 Department of Computer Science & Engineering, BIT, Durg, India 2 Abstract: This paper presents recent developments of techniques, based on vibration signature analysis to detect the fault in a machine. This paper shows vibration signature analysis implemented to detect fault in various machineries such as gear, rolling element bearing, journal bearing, induction motor, centrifugal pump and beam. The authors do not intend to provide an exhaustive discussion about machine faults but only detailed overview of rotating parts vulnerable to fault. In addition, advantages of advanced vibration signature analysis techniques over traditional one have also been discussed. Keywords: Machine fault, condition monitoring, vibration signature, preventive maintenance. I. INTRODUCTION The main objective of maintenance department is to keep machinery and plant equipments in good operating condition that prevents failure and production loss [1]. Monitoring of a rotating machine has been a challenging task for engineers and researchers especially in industries. There are many monitoring methods available which require expensive sensors and specialized tools. There was a need felt for a cheaper, yet more precise technique for identifying and preventing rather than curing problems resulting in shutdowns/breakdowns [2]. Breakdown Maintenance costs can be drastically cut with the help of Condition Based Monitoring (CBM). The idea of CBM is to perform maintenance only when there is an actual requirement, while ensuring safety, apparatus reliability and decrease in 1 total cost [3][4]. Vibration analysis is a powerful process of performing all of the following: a) Current machine Status. b) Diagnosing defects related with operational machines. c) Monitoring the overall condition of machines.[5] A complete vibration analysis consists of the following three components: a) Exact vibration determination b) Bearing condition determination c) FFT analysis This paper is divided into different sections, each dealing with various aspects of the subject. It begins with maintenance of machine followed by types of monitoring; vibration analysis uses in different machineries till date and general overview of the advanced techniques of signature analysis. II. MAINTENANCE PROCEDURE Definition: 1. Care or upkeep of machines is known as maintenance. 2. Activities required or undertaken to conserve as nearly, and as long as possible the original condition of an asset or resource while compensating for normal wear and tear. 3. Actions necessary for retaining or restoring a piece of equipment, machine, or system to the specified operable condition to achieve its maximum useful life. It includes corrective maintenance and preventive maintenance. Maintenance requires knowledge of science, a thought process and an artistic fervor. Maintenance requires understanding the real as well as literal meaning of the word maintenance. Effective maintenance is „Just –In- Time‟. [6] Types of Maintenance A. Breakdown maintenance B. Preventive maintenance a. Periodic maintenance b. Predictive Maintenance C. Corrective maintenance III. MONITORING TECHNIQUES Breakdown monitoring of machines is no longer a preferred method used in industries. Preventive and non destructive monitoring techniques are, thus, becoming more and more popular. The main benefits of such techniques are: Easy and early identification of fault. Almost total prevention of breakdown. Lesser loss of production time. Optimum utilization of machine life period. Condition-Based Monitoring has emerged as a precise and easily applicable technique of the others. A. Conditioning-Based Monitoring Def: Condition-Based Monitoring may be defined as the process of monitoring a parameter of condition of a machine, any impending technical failure or fault may become apparent. Predictive maintenance renders maintenance activities frequent and scheduled, such that any failure may be avoided at an early stage [7][8][9][10][11][12][13]. The following are some CBM techniques that have been developed in the recent past: