Adoption of MEMS technology in e-maintenance systems for rotating machinery

Abstract

Microelectromechanical systems (MEMS)-based sensing networks with on-board signal processing capabilities are becoming very attractive for monitoring the condition of rotating and static equipment. Their advantages in cost and size are an important factor for deployment in a new generation of maintenance called e-maintenance. In this paper, an intelligent monitoring system for e-maintenance (IMSEM) was developed using MEMS accelerometers, a low-power microprocessor and a wireless communication module. The system has a compatible framework and interface with open system architecture for condition-based maintenance (OSA-CBM). It integrates OSA-CBM-defined functions, including a sensing module, signal processing, condition monitoring and health assessment. Thus, the developed system successfully reduced the monitoring complexity and communication overhead with human operators. The performance of IMSEM is evaluated by carrying out fault diagnostics on the rotating unbalance of a mechanical shaft driven by a direct current (DC) motor with varying load and speed. Five statistical features were calculated for 63 vibration datasets. 25 datasets were used to train a support vector machine, with a linear kernel, and the other 38 sets were used for binary classification. About 94.7% of unknown conditions were successfully classified as healthy/unhealthy based on all features, which was improved to 100% using the best three features. This has demonstrated the capability of the developed system in detecting faults and the severity of rotor unbalance, based on ISO 1940-1:2003.