Advancement and current status of wear debris analysis for machine condition monitoring: a review

Abstract

Purpose -The dependency on human expertise for analysis and interpretation is the main reason for wear debris analysis not being used in industry to its full potential and becoming one of the most powerful machine condition monitoring strategies. The dependency on human expertise makes the interpretation and result subjective in nature, costly and time consuming. The purpose of this paper is to review work being done to develop an automatic, reliable and objective wear particle classification system as a solution to the above problem. At the same time it also aims to discuss some common off line test methods being practiced for wear debris analysis. Design/methodology/approach -Computer image analysis is a solution for some of the problems associated with the conventional techniques. First it is tried to efficiently describe the characteristics of computer images of different types of wear debris using a few numerical parameters. Then using some Artificial Intelligence tools, the wear particle classification system can be developed. Findings -Many shape, size and surface parameters are discussed in the paper. Out of these, nine numerical parameters are selected to describe and distinguish six common type of wear debris. Once the type of debris is identified, the mode of wear and hence the machine condition can be assessed. Practical implications -The present process of fault and condition monitoring of an equipment by wear debris analysis involves human judgment of debris formations. A set-up standard for comparison of debris will enable the maintenance team to diagnose faults in a comparatively better way. Originality/value -The aim of this paper is to discuss the difficulties in identifying wear particles and finding out the exact health of equipment, which, due to its subjective nature, is influenced by human errors. An objective method with certain standards for classification of wear particles compatible with an artificial intelligence system will yield some flawless results of wear debris analysis, which has not been attempted in the past as per available literature.

Spectral kurtosis for fault detection, diagnosis and prognostics of rotating machines: A review with applications

“…A variety of methods have been developed and summarized for rotating machinery fault diagnostics, such as vibration analysis [2], acoustic emission (AE) [3], temperature trend analysis [4] and wear debris analysis [5]. Commonly used technique for fault detection is vibration-based signature analysis.…”

Photonic Low Cost Micro-Sensor for in-Line Wear Particle Detection in Flowing Lube Oils

“…The presence of solid particles in suspension in industrial fluids, such as lubricants or hydraulic fluids, is frequently an early warning of latent or imminent faults in the machines or processes where they are being used [1,2], as it can be seen in Figure 1, where the contaminated lubricant of a gearbox about to fail is displayed. Therefore, the early detection of the presence of these wear particles is a key objective in a proper predictive maintenance program, complementing other machine condition monitoring approaches (CMS) such as vibration analysis [3].…”

Characterising the friction and wear behaviour of lubricated metal‐metal pairings with an optical online particle detection system

“…Over the years, different lubricant‐based condition monitoring techniques (with their specific advantages and disadvantages) have been developed. Recent reviews on this topic can be found in the previous works …”