Decentralized microsystem-based diagnostics of bearings of an electric motor

A new microsystem is presented which is able to diagnose bearing faults completely autonomous using vibration and temperature measurements. The heart of the microsystem is a 16-Bit digital signal processor (DSP) which can operate up to 100 MIPS (million instructions per second). It is able to calculate the diagnosis result including necessary Fast Fourier Transforms (FFT), envelope calculations and the classification by a neural network within a few seconds. The extracted features are stored in a large non-volatile memory and are used for a long term trend analysis. Current or predicted faults are displayed locally and announced to the staff or a host computer via field bus or phone.