Failure analysis on a water pump based on a low-cost MEMS accelerometer and machine learning classifiers
DOI:
https://doi.org/10.5433/1679-0375.2020v41n2p171Keywords:
MEMS Accelerometer. Diagnosis by Vibration. Diagnostic Classifiers. Logistic Regression. Linear SVM. ANN-MLPAbstract
This work presents a failure diagnosis tool for a water pump using a low-cost MEMS accelerometer. It was inserted three types of failures: rotor blade (new and damaged), pump soleplate tightness (stiff or loose), and cavitation, in this case on three conditions: none, incipient and severe, totaling twelve fault combinations. These conditions were tested under two different speeds to perform the diagnosis, totaling twenty-four tests. In all cases, the vibration signals from axes X, Y, and Z were acquired. Some features extracted from the vibration spectra from X-axis were used to compose the dataset. These data were analyzed employing logistic regression, a linear support vector machine (SVM), and an artificial neural network multilayer perceptron (ANN-MLP). We compared these three techniques of machine learning and evaluated which one was able to obtain the most accurate result. Using the ANN-MLP, the system was able to detect all three types of failures inserted, with about 100% of accuracy on the rotor blade condition, 92% for anchorage faults, and about 99% accuracy on cavitation state. As a conclusion, it is demonstrated that this classifier algorithm can be used to process the data from the low-cost MEMS accelerometer in predictive maintenance as an accurate tool.Downloads
Download data is not yet available.
References
AUGUSTYN, T. Energy efficiency and savings in pumping Systems: the holistic approach. Southern African Energy Efficiency Convention, Johannesburg, p. 1-7, 2012.
BAZANINI, G. Cavitation erosion pits and craters in metals. Semina: Ciências Exatas e Tecnológicas, Londrina, v. 38, n. 2, p. 43, 2018
BRAUM, S. G. Mechanical signature analysis: theory and applications. London: Academic Press, 1986.
CYBENKO, G. Approximation by superpositions of a sigmoidal function. Mathematics of Control, Signals and Systems, Piscataway, v. 2, n. 4, p. 303-314, Dec. 1989.
DUTTA, N.; UMASHANKAR, S.; SHANKAR, V. K. A; et al. Centrifugal pump cavitation detection using machine learning algorithm technique. IEEE International Conference on Environment and Electrical Engineering and 2018 IEEE Industrial and Commercial Power Systems Europe, Palermo, p. 1–6, 2018.
FLORINO, J. A. C.; MELLO, L. F.; CARAZZAI, R. F. Redução de custos operacionais em indústrias de manufatura de MDF. Semina: Ciências Exatas e Tecnológicas, Londrina, v. 35, n. 1, p. 77, 2014.
GOLDBERG, Y.; HIRST, G. Neural network methods in natural language processing. Williston: Morgan & Claypool, 2017.
HAMOND, O.; ALABIED, S.; XU, Y.; DARAZ, A. et al., Vibration based centrifugal pump fault diagnosis based on modulation signal bispectrum analysis. In:CONFERENCE ON AUTOMATION AND COMPUTING (ICAC), 23., Huddersfield, 2017. Proceedings [. . . ]. Huddersfield, ICAC, 2017. p. 1-5.
HARRELL JUNIOR, R. F. E. Regression modeling strategies: with applications to linear models, logistic and ordinal regression, and survival analysis. New York: SpringerVerlag, 2001.
HAYKIN, S. Neural networks: a comprehensive foundation. 2. ed. New Jersey: Prentice Hall, 1998.
HAYKIN, S. Neural networks and learning machines. 3. ed. New Jersey: Prentice-Hall, 2008.
IEEE Guide for Induction Machinery Maintenance Testing and Failure Analysis. IEEE, [textitS. l.], p. 1-68, Apr. 2007.
JARDINE, A. K. S.; LIN, D.; BANJEVIC, D. A review on machinery diagnostics and prognostics implementing condition-based maintenance. Mechanical Systems and Signal Processing, London, v. 20, n. 7, p. 1483-1510, 2006.
KAYA, D.; YAGMUR, E. A.; YIGIT, K. S.; KILIC, F. C. Kilic et al. Energy efficiency in pumps. Energy Conversion and Management, Amsterdam, v. 49, n. 6, p. 1662-1673, 2008.
KERAS. The Python Deep Learning library. 2017. Available from: <https://keras:io/>. Access in: Aug. 2018.
KNAPP, R. T.; DAILY, J. W.; HAMMIT, F. G. Cavitation. San Francisco: McGraw-Hill, 1970.
LAROSE, D. T. Logistic regression. In: LAROSE, D. T. Data Mining Methods and Models. New Jersey: JOHN WILEY, 2006. p. 155-199.
MATTOS, E. E.; FALCO, R. Industrial Pumps. 2. ed. Rio de Janeiro: Editora Interciência, 1998.
NAIR, V.; HINTON, G. E. Rectified linear units improve restricted boltzmann machines. In: INTERNATIONAL CONFERENCE ON MACHINE LEARNING, 27, Haifa, 2010. Proceedings [. . . ].Haifa: ICML, 2010.
NAKAJIMA, S. Introduction to TPM: total productive maintenance (preventative maintenance series). [S. l.]: Eleventh Printing edition, 1988.
NASIRI, M. R.; MAHJOOB, M. J.; VAHID-ALIZADEH, H. Vibration signature analysis for detecting cavitation in centrifugal pumps using neural networks. In: INTERNATIONAL CONFERENCE ON MECHATRONICS, 2011, Istanbul. Proceedings [. . . ]. Istanbul: IEEE, 2011. p. 632-
635.
NORTON, M.; KARCZUB, D. Fundamentals of noise and vibration analysis for engineers. 2. ed. Cambridge: University Press, 1994.
NXP. MMA8451Q, 3-axis, 14-bit/8-bit digital accelerometer. Netherlands: NXP, 2018. Available from: <https://www:nxp:com/docs/en/datasheet/MMA8451Q:pdf>. Access in: Aug. 2018.
NXP, MMA8451Q: ±2g/±4g/±8g, Low g, 14-bit Digital Accelerometer. Netherlands: NXP, 2017. Available from: <http://www.nxp.com/products/sensors/accelerometers/3-axis-accelerometers/2g-4g-8g-low-g-14-bit-digitalaccelerometer:MMA8451Q?tab=Buy_Parametric_Ta>. Access in: Mar. 2017.
NXP, i.MX 8M Quad Power Consumption Measurement. Netherlands: NXP, 2020. Available from: <https://www.nxp.com/docs/en/nxp/application-notes/AN12118.pdf>. Access in: Nov. 2020.
PEDOTTI, L. A. S.; ZAGO, R. M; FRUETT, F. Fault diagnostics in rotary machines through spectral vibration analysis using low-cost MEMS devices. IEEE Instrumentation & Measurement Magazine, New York, v. 20, n. 6, p. 39-44, 2017.
PEDOTTI, L. A. S. Dispositivo IoT de baixo custo para Diagnóstico de Falhas em Máquinas Rotativas. 2019. Tese (Doutorado) - Faculdade de Engenharia Elétrica e de Computação, Universidade Estadual de Campinas, Campinas, 2019.
POWERS, D.M.W. Evaluation: from precision, recall and F-mesaure to ROC, informedness, markedness & correlation. Journal of Machine learning Technologies, Singapore, v. 2, n. 1, p-37-63, 2011.
RAO, S. Mechanical vibrations. 5. ed. New Jersey: Prentice Hall, 2010.
ROJAS, R. Neural networks: a systematic introduction. New-York: Springer-Verlag, 1996.
ROJO-ÁLVAREZ, J. L.; MARTINEZ-RAMÓN, M.; MUÑOZ-MARÍ, J.; CAMPS-VALLS, G. Support Vector Machine and Kernel Classification Algorithms. Digital Signal Processing with Kernel Methods, [S. l.], p. 433-502, 2018.
SÁNCHEZ, W.; CARVAJAL, C.; POALACIN, J. et al. Detection of cavitation in centrifugal pump for vibration Analysis. INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION AND ROBOTICS (ICCAR), 4., 2018, Auckland. Proceedings [. . . ]. Auckland: ICCAR, 2018. p.460-464.
SCIKIT-LEARN. An introduction to machine learning with scikit-learn. 2018. Available from: <http://scikitlearn:
org/stable/tutorial/basic/tutorial:html>. Access in: Aug. 2018.
SCIKIT-LEARN developers. Ascikit-learn: Machine Learning in Python. Available from: <https://scikitlearn.org/stable/>. Access in: Nov. 2020.
STEEGE, P. Overall equipment effectiveness in resist processing equipment. In: ADVANCED SEMICONDUCTOR MANUFACTURING CONFERENCE AND WORKSHOP – ASMC, San Diego, 1996. Proceedings [. . . ].San Diego: IEEE, 1996. p. 76-79.
STOPA, M. M; CARDOSO FILHO, B. J.; MARTINEZ, C. B. Incipient Detection of Cavitation Phenomenon in Centrifugal Pumps. IEEE Transactions on Industry Applications, New York, v. 50, n. 1, p. 120-126, 2014.
SCHRODER, F; LUCCA, Y.; DALFRÉ FILHO, J. G. Bearing Temperature effect analysis of centrifuge pumps operating with moderate cavitation. American Journal of Hydropower, Water and Environment Systems, [S. l.], 2015.
TENSORFLOW.ORG. An open source machine learning framework for everyone. 2018. Available from: https://github.com/tensorflow/tensorflow>. Acess in: 4 Nov. 2020.
WHITE, F. M. Fluid Mechanics, 8. ed. Island: University of Rhode Island, 2016.
WOWK, V. Machinery vibration: measurement and analysis. New York, McGraw-Hill, 1991.
BAZANINI, G. Cavitation erosion pits and craters in metals. Semina: Ciências Exatas e Tecnológicas, Londrina, v. 38, n. 2, p. 43, 2018
BRAUM, S. G. Mechanical signature analysis: theory and applications. London: Academic Press, 1986.
CYBENKO, G. Approximation by superpositions of a sigmoidal function. Mathematics of Control, Signals and Systems, Piscataway, v. 2, n. 4, p. 303-314, Dec. 1989.
DUTTA, N.; UMASHANKAR, S.; SHANKAR, V. K. A; et al. Centrifugal pump cavitation detection using machine learning algorithm technique. IEEE International Conference on Environment and Electrical Engineering and 2018 IEEE Industrial and Commercial Power Systems Europe, Palermo, p. 1–6, 2018.
FLORINO, J. A. C.; MELLO, L. F.; CARAZZAI, R. F. Redução de custos operacionais em indústrias de manufatura de MDF. Semina: Ciências Exatas e Tecnológicas, Londrina, v. 35, n. 1, p. 77, 2014.
GOLDBERG, Y.; HIRST, G. Neural network methods in natural language processing. Williston: Morgan & Claypool, 2017.
HAMOND, O.; ALABIED, S.; XU, Y.; DARAZ, A. et al., Vibration based centrifugal pump fault diagnosis based on modulation signal bispectrum analysis. In:CONFERENCE ON AUTOMATION AND COMPUTING (ICAC), 23., Huddersfield, 2017. Proceedings [. . . ]. Huddersfield, ICAC, 2017. p. 1-5.
HARRELL JUNIOR, R. F. E. Regression modeling strategies: with applications to linear models, logistic and ordinal regression, and survival analysis. New York: SpringerVerlag, 2001.
HAYKIN, S. Neural networks: a comprehensive foundation. 2. ed. New Jersey: Prentice Hall, 1998.
HAYKIN, S. Neural networks and learning machines. 3. ed. New Jersey: Prentice-Hall, 2008.
IEEE Guide for Induction Machinery Maintenance Testing and Failure Analysis. IEEE, [textitS. l.], p. 1-68, Apr. 2007.
JARDINE, A. K. S.; LIN, D.; BANJEVIC, D. A review on machinery diagnostics and prognostics implementing condition-based maintenance. Mechanical Systems and Signal Processing, London, v. 20, n. 7, p. 1483-1510, 2006.
KAYA, D.; YAGMUR, E. A.; YIGIT, K. S.; KILIC, F. C. Kilic et al. Energy efficiency in pumps. Energy Conversion and Management, Amsterdam, v. 49, n. 6, p. 1662-1673, 2008.
KERAS. The Python Deep Learning library. 2017. Available from: <https://keras:io/>. Access in: Aug. 2018.
KNAPP, R. T.; DAILY, J. W.; HAMMIT, F. G. Cavitation. San Francisco: McGraw-Hill, 1970.
LAROSE, D. T. Logistic regression. In: LAROSE, D. T. Data Mining Methods and Models. New Jersey: JOHN WILEY, 2006. p. 155-199.
MATTOS, E. E.; FALCO, R. Industrial Pumps. 2. ed. Rio de Janeiro: Editora Interciência, 1998.
NAIR, V.; HINTON, G. E. Rectified linear units improve restricted boltzmann machines. In: INTERNATIONAL CONFERENCE ON MACHINE LEARNING, 27, Haifa, 2010. Proceedings [. . . ].Haifa: ICML, 2010.
NAKAJIMA, S. Introduction to TPM: total productive maintenance (preventative maintenance series). [S. l.]: Eleventh Printing edition, 1988.
NASIRI, M. R.; MAHJOOB, M. J.; VAHID-ALIZADEH, H. Vibration signature analysis for detecting cavitation in centrifugal pumps using neural networks. In: INTERNATIONAL CONFERENCE ON MECHATRONICS, 2011, Istanbul. Proceedings [. . . ]. Istanbul: IEEE, 2011. p. 632-
635.
NORTON, M.; KARCZUB, D. Fundamentals of noise and vibration analysis for engineers. 2. ed. Cambridge: University Press, 1994.
NXP. MMA8451Q, 3-axis, 14-bit/8-bit digital accelerometer. Netherlands: NXP, 2018. Available from: <https://www:nxp:com/docs/en/datasheet/MMA8451Q:pdf>. Access in: Aug. 2018.
NXP, MMA8451Q: ±2g/±4g/±8g, Low g, 14-bit Digital Accelerometer. Netherlands: NXP, 2017. Available from: <http://www.nxp.com/products/sensors/accelerometers/3-axis-accelerometers/2g-4g-8g-low-g-14-bit-digitalaccelerometer:MMA8451Q?tab=Buy_Parametric_Ta>. Access in: Mar. 2017.
NXP, i.MX 8M Quad Power Consumption Measurement. Netherlands: NXP, 2020. Available from: <https://www.nxp.com/docs/en/nxp/application-notes/AN12118.pdf>. Access in: Nov. 2020.
PEDOTTI, L. A. S.; ZAGO, R. M; FRUETT, F. Fault diagnostics in rotary machines through spectral vibration analysis using low-cost MEMS devices. IEEE Instrumentation & Measurement Magazine, New York, v. 20, n. 6, p. 39-44, 2017.
PEDOTTI, L. A. S. Dispositivo IoT de baixo custo para Diagnóstico de Falhas em Máquinas Rotativas. 2019. Tese (Doutorado) - Faculdade de Engenharia Elétrica e de Computação, Universidade Estadual de Campinas, Campinas, 2019.
POWERS, D.M.W. Evaluation: from precision, recall and F-mesaure to ROC, informedness, markedness & correlation. Journal of Machine learning Technologies, Singapore, v. 2, n. 1, p-37-63, 2011.
RAO, S. Mechanical vibrations. 5. ed. New Jersey: Prentice Hall, 2010.
ROJAS, R. Neural networks: a systematic introduction. New-York: Springer-Verlag, 1996.
ROJO-ÁLVAREZ, J. L.; MARTINEZ-RAMÓN, M.; MUÑOZ-MARÍ, J.; CAMPS-VALLS, G. Support Vector Machine and Kernel Classification Algorithms. Digital Signal Processing with Kernel Methods, [S. l.], p. 433-502, 2018.
SÁNCHEZ, W.; CARVAJAL, C.; POALACIN, J. et al. Detection of cavitation in centrifugal pump for vibration Analysis. INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION AND ROBOTICS (ICCAR), 4., 2018, Auckland. Proceedings [. . . ]. Auckland: ICCAR, 2018. p.460-464.
SCIKIT-LEARN. An introduction to machine learning with scikit-learn. 2018. Available from: <http://scikitlearn:
org/stable/tutorial/basic/tutorial:html>. Access in: Aug. 2018.
SCIKIT-LEARN developers. Ascikit-learn: Machine Learning in Python. Available from: <https://scikitlearn.org/stable/>. Access in: Nov. 2020.
STEEGE, P. Overall equipment effectiveness in resist processing equipment. In: ADVANCED SEMICONDUCTOR MANUFACTURING CONFERENCE AND WORKSHOP – ASMC, San Diego, 1996. Proceedings [. . . ].San Diego: IEEE, 1996. p. 76-79.
STOPA, M. M; CARDOSO FILHO, B. J.; MARTINEZ, C. B. Incipient Detection of Cavitation Phenomenon in Centrifugal Pumps. IEEE Transactions on Industry Applications, New York, v. 50, n. 1, p. 120-126, 2014.
SCHRODER, F; LUCCA, Y.; DALFRÉ FILHO, J. G. Bearing Temperature effect analysis of centrifuge pumps operating with moderate cavitation. American Journal of Hydropower, Water and Environment Systems, [S. l.], 2015.
TENSORFLOW.ORG. An open source machine learning framework for everyone. 2018. Available from: https://github.com/tensorflow/tensorflow>. Acess in: 4 Nov. 2020.
WHITE, F. M. Fluid Mechanics, 8. ed. Island: University of Rhode Island, 2016.
WOWK, V. Machinery vibration: measurement and analysis. New York, McGraw-Hill, 1991.
Downloads
Published
2020-12-11
How to Cite
Pedotti, L. A. dos S., Zago, R. M., Rocha, J. C., Dalfré Filho, J. G., Giesbrecht, M., & Fruett, F. (2020). Failure analysis on a water pump based on a low-cost MEMS accelerometer and machine learning classifiers. Semina: Ciências Exatas E Tecnológicas, 41(2), 171–184. https://doi.org/10.5433/1679-0375.2020v41n2p171
Issue
Section
Original Article
License
The Copyright Declaration for articles published in this journal is the author’s right. Since manuscripts are published in an open access Journal, they are free to use, with their own attributions, in educational and non-commercial applications. The Journal has the right to make, in the original document, changes regarding linguistic norms, orthography, and grammar, with the purpose of ensuring the standard norms of the language and the credibility of the Journal. It will, however, respect the writing style of the authors. When necessary, conceptual changes, corrections, or suggestions will be forwarded to the authors. In such cases, the manuscript shall be subjected to a new evaluation after revision. Responsibility for the opinions expressed in the manuscripts lies entirely with the authors.
This journal is licensed with a license Creative Commons Attribution-NonCommercial 4.0 International.
