Using abductive machine learning for online vibration monitoring of turbo molecular pumps

Turbo molecular vacuum pumps constitute a critical component in many accelerator installations, where failures can be costly in terms of both money and lost beam time. Catastrophic failures can be averted if prior warning is given through a continuous online monitoring scheme. This paper describes the use of modern machine learning techniques for online monitoring of the pump condition through the measurement and analysis of pump vibrations. Abductive machine learning is used for modeling the pump status as ‘good’ or ‘bad’ using both radial and axial vibration signals measured close to the pump bearing. Compared to other statistical methods and neural network techniques, this approach offers faster and highly automated model synthesis, requiring little or no user intervention. Normalized 50-channel spectra derived from the low frequency region (0–10 kHz) of the pump vibration spectra provided data inputs for model development. Models derived by training on only 10 observations predict the correct value of the logical pump status output with 100% accuracy for an evaluation population as large as 500 cases. Radial vibration signals lead to simpler models and smaller errors in the computed value of the status output. Performance is comparable with literature data on a similar diagnosis scheme for compressor valves using neural networks.

[1]  M. Gusarova,et al.  Nuclear Instruments and Methods in Physics Research , 2009 .

[2]  C. Charalambous,et al.  Conjugate gradient algorithm for efficient training of artifi-cial neural networks , 1990 .

[3]  R. V. Poore,et al.  The XSYS Data Acquisition System at Triangle Universities Nuclear Laboratory , 1981, IEEE Transactions on Nuclear Science.

[4]  R. E. Abdel-Aal,et al.  A machine-learning approach to modelling and forecasting the minimum temperature at Dhahran, Saudi Arabia , 1994 .

[5]  Keith C. Drake,et al.  Abductive networks , 1990, Defense, Security, and Sensing.

[6]  G. Blume,et al.  350 keV accelerator facility for the University of Petroleum and Minerals , 1987 .

[7]  Q Zhuge,et al.  Signature Analysis for Reciprocating Machinery with Adaptive Signal Processing , 1991 .

[8]  I W Mayes.  Use of Neutral Networks for on-Line Vibration Monitoring , 1994 .

[9]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[10]  Philip D. Wasserman,et al.  Neural computing - theory and practice , 1989 .

[11]  Hidetoshi Shimodaira,et al.  Application of neural computation to sound analysis for valve diagnosis , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[12]  John Burrows,et al.  On-line condition monitoring of rotating equipment using neural networks , 1994 .

[13]  Sholom M. Weiss,et al.  Computer Systems That Learn , 1990 .

[14]  Manabu Kotani,et al.  Acoustic diagnosis for compressor with hybrid neural network , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[15]  E. A. Page,et al.  Improve predictive maintenance with HFE monitoring , 1994 .

[16]  Gérard Dreyfus,et al.  Single-layer learning revisited: a stepwise procedure for building and training a neural network , 1989, NATO Neurocomputing.

[17]  S. J. Farlow.  SEARCHING FOR STRUCTURE: THE GMDH ALGORITHM , 1984 .

[18]  A. G. Ivakhnenko,et al.  Polynomial Theory of Complex Systems , 1971, IEEE Trans. Syst. Man Cybern..