论文信息 - Decentralized microsystem-based diagnostics of bearings of an electric motor

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.

[1] Wolf-Joachim Fischer,et al. Local Parameter Estimation Performed by Tailor-Made Microsystems , 1997 .

[2] T. Kohonen. Self-organized formation of topology correct feature maps , 1982 .

[3] Czesław Cempel. Vibroacoustic condition monitoring : Ellis Horwood, 212pp. (1991) , 1991 .

[4] H. Saunders,et al. Machinery Noise and Diagnostics , 1987 .

[5] T. Kohonen. Self-Organized Formation of Correct Feature Maps , 1982 .

[6] U. Marschner,et al. Low expense architectures for a dynamic spectrum analyzer based on SC-filters , 1998, ISCAS '98. Proceedings of the 1998 IEEE International Symposium on Circuits and Systems (Cat. No.98CH36187).

[7] R. J. Patton,et al. Fault detection, supervision, and safety for technical processes 1997 (SAFEPROCESS '97) : a proceedings volume from the 3rd IFAC symposium, Kingston Upon Hull, UK, 26-28 August 1997 , 1998 .