Failure Detection Techniques on the Demand Side of Smart and Sustainable Compressed Air Systems: A Systematic Review

Abstract

The industrial sector is a crucial economic pillar, seeing annual increases in the production output. In the last few years, a greater emphasis has been placed on the efficient and sustainable use of resources within industry. The use of compressed air in this field is hence gaining interest. These systems have numerous benefits, such as relative low investment costs and reliability; however, they suffer from low-energy efficiency and are highly susceptible to faults. Conventional detection systems, such as ultrasonic leak detection, can be used to identify faults. However, these methods are time consuming, meaning that leakages are often left unattended, contributing to additional energy wastage. Studies published in this area often focus on the supply side rather than the demand side of pneumatic systems. This paper offers a novel review based on the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology of fault detection methods on the demand side of compressed air systems, leading towards a comprehensive understanding of smart and sustainable pneumatic systems. Fifty-three studies were classified and reviewed under the following three areas: (a) demand parameters which help in identifying fault sources; (b) approaches taken to analyse the parametric data; and (c) the role of Artificial Intelligence (AI) in pneumatic fault monitoring systems. This review shows that fault detection on the demand side has received greater importance in the last five years and that data analysis is crucial for AI to be implemented correctly. Nevertheless, it is clear that further research in this sector is essential, in order to investigate more complex systems. It is envisaged that this study can promote the adoption of such systems, contributing to an energy-efficient and cost-effective industry.

Detection of Sensor Faults with or without Disturbance Using Analytical Redundancy Methods: An Application to Orifice Flowmeter

“…Fault isolation using a Kalman filter was reported in [ 5 ] for a flow meter, which was model-based fault diagnosis. An extensive review was carried out for the identification of faults in aircraft fuel systems using machine learning in [ 6 ] and for failure detection techniques for air systems in [ 7 ].…”

Low-cost Fault Diagnosis of Pneumatic Systems with Exergy and Machine Learning:

“…Compared with the hydraulic counterpart, the fault diagnosis of pneumatic systems is more complex and difficult due to the more significant nonlinearity caused by the high compressibility of compressed air, thereby leading to the lagging situation. Generally, most studies only investigate the single type of fault of a single pneumatic component, such as a valve or an actuator 3) . However, industrial pneumatic systems are much more complex and versatile.…”

Leakage Fault Diagnosis of Two Parallel Cylinders in Pneumatic System with a Minimal Number of Sensors

“…Thus, machine learning could also provide a new and feasible way for the fault diagnosis of pneumatic systems. Many studies have been conducted in this field [17]. For example, Feng and Yang [18] proposed a fault diagnosis method for pneumatic actuators based on adaptive multi-kernel multi-classification relevance vector machines.…”