Abstract
A fundamental study for developing a fault diagnosis system of a pump is performed by using neural network. Acoustic signals were obtained and converted to frequency domain for normal products and artificially deformed products. The neural network model used in this study was 3-layer type composed of input, hidden, and output layer. The normalized amplitudes at the multiples of real driving frequency were chosen as units of input layer. And the codes of pump malfunctions were selected as units of output layer. Various sets of teach signals made from original data by eliminating some random cases were used in the training. The average errors were approximately proportional to the number of untaught data. Neural network trained by acoustic signals can detect malfunction or diagnose fault of a given machine from the results.
Similar content being viewed by others
References
Asakura, T., Kobayashi, T., Xu, B. and Hayashi, S., 2000, “Fault Diagnosis System for Machines Using Neural Networks,”JSME International Journal, Series C, Vol. 43, pp. 364–371.
Bae, Y. H. and Lee, S. K., 1998, “Multiple Fault Diagnosis Method by Modular Artificial Neural Network,”Journal of the Korean Society of Precision Engineering, Vol. 15, No. 2, pp. 35–44.
Chen, Z. and Mechefske, C., 2002, “Diagnosis of Machinery Fault Status using Transient Vibration Signal Parameters,”Journal of Vibration and Control, Vol. 8, pp. 321–335.
Chung, W. S., Lee, S. Y., Chung, T. J. and Lee, J. K., 2001, “Fault Diagnosis of a Pump by Using Vibration Signals,”Proc. of KSME 2001 Fall Annual Meeting, Vol. A, Jeonbuk national university, Korea, Nov. 1–3, pp. 590–595.
Danai, K. and Chin, H., 1991, “Fault Diagnosis with Process Uncertainty,”Journal of Dynamic Systems, Measurement and Control, Vol. 113, pp. 339–343.
Duffey, T. A., Doebling, S. W., Farrar, C. R., Baker, W. E. and Rhee, W. H., 2001, “Vibration-Based Damage Identification in Structures Exhibiting Axial and Torsional Response,”ASME, Journal of Vibration and Acoustics, Vol. 123, pp. 84–91.
Kirkegaard, P. H. and Rytter, A., 1994, “Use of Neural Networks for Damage Assessment in a Steel Mast,”Proc. of the 12thInternational Modal Analysis Conference by Society for Experimental Mechanics, Honolulu, HI, USA, Jan. 31–Feb. 3, pp. 1128–1134.
Lin, L. and Qu, L., 2000, “Feature Extraction Based on Morlet Wavelet and Its Application for Mechanical Fault Diagnosis,”Journal of Sound and Vibration, Vol. 234, pp. 135–148.
Na, E. G., Ono, K. and Lee, D. W., 2006, “Evaluation of Fracture Behavior of SA-516 Steel Welds Using Acoustic Emission Analysis,”KSME, J. of the Mechanical Science and Technology, Vol. 20, No. 2, pp. 197–204.
Staroswiecki, M., 2000, “Quantitative and Qualitative Models for Fault Detection and Isolation,”Mechanical Systems and Signal Processing, Vol. 14, pp. 301–325.
Staszewski, W., 1998, “Wavelet Based Compression and Feature Selection for Vibration Analysis,”Journal of Sound and Vibration, Vol. 211, pp. 735–760.
Stech, D. J., 1994, “Towards Real-time Continuous System Identification Using Modified Hopfield Neural Networks,”Proc. of the 12thInternational Modal Analysis Conference by Society for Experimental Mechanics, Honolulu, HI, USA, Jan. 31–Feb. 3, pp. 1135–1140.
Zang, C. and Imregun, M., 2001, “Structural Damage Detection Using Artificial Neural Networks and Measured FRF Data Reduced via Principal Component Projection,”Journal of Sound and Vibration, Vol. 242, pp. 813–827.
Zimmerman, D. C., Smith, S. W., Kim, H. M. and Bartkowicz, T., 1996, “An Experimental Study of Structural Health Monitoring Using Incomplete Measurements,”ASME, Journal of Vibration and Acoustics, Vol. 118, pp. 543–550.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Lee, SY. Acoustic diagnosis of a pump by using neural network. J Mech Sci Technol 20, 2079–2086 (2006). https://doi.org/10.1007/BF02916324
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF02916324