APPLICATION OF MEMS SENSOR BASED SMART SENSORS IN TARGET MACHINE FAULT CLASSIFICATION

摘要

In recent years, wireless smart sensors show huge attraction in machine condition monitoring, which have advantages in power, size, cost, mobility and flexibility. They can integrate with MEMS sensors; MEMS accelerometer, MEMS current, and MEMS temperature etc. MEMS sensors are batch product. So the prices are cheap. And the suitability of it for condition monitoring is researched by experimental study. Hence MEMS sensor based smart sensors are powerful tools for cost-effective maintenance.This paper presents a development of wireless smart sensors for intelligent fault diagnosis and a novel application of smarts sensors in target machine fault classification by 3 intelligent classifiers. We attempt to signal validation of smart sensor accuracy and reliability. And performance comparisons of classifiers are conducted. MEMS accelerometer and MEMS current sensors are employed for experiment test. In addition, a simple self-diagnosis strategy was applied to make sure smart sensor reliability. The result of application is good for using fault classification