Anomaly Detection of Servomotors Subject to Highly Accelerated Limit Testing
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Abstract
Companies utilize highly accelerated limit testing (HALT) to ensure efficient product development by accelerating loading conditions in the qualification process. The aim of qualitative accelerated testing such as HALT is to properly identify early behavioral anomalies. To this end, this study utilizes machine learning techniques for detecting anomalies in servomotors in electronic products subjected to HALT. A case study was conducted using a programmable robot kit with 12 servomotors. HALT comprises five types of stress: thermal conditioning (cold and heat), rapid thermal change, vibration, and combined stresses. The anomalous behavior of a servomotor can be identified using a k-nearest neighbor algorithm and verified by inspection using the loading conditions and electrical responses. In addition, anomalous behaviors among servomotors and a control board are assessed using a Gaussian graph model approach. Changes in the Gaussian graph are assessed as anomaly scores using Kullback–Leibler divergence. The anomaly score increased earlier than the operating limit defined by inspection, i.e., the deviation from the initial position of the shaft. The machine learning algorithm successfully identified the failure precursor of the unit. The proposed approach of HALT with the machine learning algorithm supports prognostic health management of servomotors.
##plugins.themes.bootstrap3.article.details##
Highly accelerated limit test, Anomaly detection, Prognostics health management, Machine learning, k-nearest neighbor algorithm, Gaussian graphical model
Aoki, Y., Doertenbach, N., Hirata, T., & Pihet, R. (2019, January). Experiments Comparing the Efficacy of HALT vs. Traditional Stress Testing. In 2019 Annual Reliability and Maintainability Symposium (RAMS) (pp. 1-7). IEEE. DOI: 10.1109/RAMS.2019.8769044
Catelani, M., & Ciani, L. (2014, May). Highly accelerated life testing for avionics devices. In 2014 IEEE Metrology for Aerospace (MetroAeroSpace) (pp. 418-422). IEEE. DOI: 10.1109/MetroAeroSpace.2014.6865961
Charki, A., Laronde, R., Guérin, F., Bigaud, D. & Coadou, F. (2011). Robustness evaluation using highly accelerated life testing. The International Journal of Advanced Manufacturing Technology, Vol. 56, pp. 1253-1261. DOI: 10.1007/s00170-011-3264-z
He, Q. P., & Wang, J. (2007). Fault detection using the k-nearest neighbor rule for semiconductor manufacturing processes. IEEE Transactions on Semiconductor Manufacturing, Vol. 20(4), pp. 345-354. DOI: 10.1109/TSM.2007.907607
Gray, K. A., & Paschkewitz, J. J. (2016). Next generation HALT and HASS: robust design of electronics and systems. John Wiley & Sons.
Hobbs, G. K. (2000). Accelerated reliability engineering: HALT and HASS. John Wiley & Sons Incorporated.
Ide, T. (2015). Introduction to Anomaly Detection Using Machine Learning, CORONA Publishing Co. Ltd., 2015 (in Japanese).
International Electrotechnical Commission, “Methods for product accelerated testing”, IEC62506:2013, 2013.
Kang, M., Ramaswami, G. K., Hodkiewicz, M., Cripps, E., Kim, J. M., & Pecht, M. (2016, June). A sequential K-nearest neighbor classification approach for data-driven fault diagnosis using distance-and density-based affinity measures. In International Conference on Data Mining and Big Data (pp. 253-261). Springer, Cham.
Kwon, D., Hodkiewicz, M. R., Fan, J., Shibutani, T., & Pecht, M. G. (2016). IoT-based prognostics and systems health management for industrial applications. IEEE Access, Vol. 4, pp. 3659-3670. DOI: 10.1109/ACCESS.2016.2587754
Li, W., & Feng, R. C. (2006, October). Highly accelerated life test for the reliability assessment of the lead-free SMT mainboard. In 2006 International Microsystems, Package, Assembly Conference Taiwan (pp. 1-4). IEEE. DOI: 10.1109/IMPACT.2006.312176
Munikoti, R., & Dhar, P. (1988). Highly accelerated life testing (HALT) for multilayer ceramic capacitor qualification. IEEE Transactions on Components, Hybrids, and Manufacturing Technology, Vol. 11(4), pp. 342-345. DOI: 10.1109/33.16665
Muja, M., Lowe, D., & Yee, J. (2017). rflann: Basic R Interface to the 'FLANN' C++ Library, R package, 2017-1-28.
Nesreen, K. A., Amir F. A., Neamat E. G. & Hisham E. (2010). An Empirical Comparison of Machine Learning Models for Time Series Forecasting, Econometric Reviews, Vol. 29(5-6), pp. 594-621. DOI: 10.1080/07474938.2010.481556
Omar, Y. (2015). Efficient machine learning for big data: A review. Big Data Research, Vol. 2(3), pp. 87-93. DOI: 10.1016/j.bdr.2015.04.001
Pecht, M. (2009). Prognostics and health management of electronics. Encyclopedia of structural health monitoring. John Wiley, 2008.
Prakash, S. (1998). The application of HALT and HASS principles in a high‐volume manufacturing environment. Quality and Reliability Engineering International, Vol. 14(6), pp. 385-392. DOI: 10.1002/(SICI)1099-1638(199811/12)14:6<385::AID-QRE217>3.0.CO;2-E
Sakamoto, J., Hirata, R., & Shibutani, T. (2018). Potential failure mode identification of operational amplifier circuit board by using high accelerated limit test. Microelectronics Reliability, Vol. 85, pp. 19-24. DOI: 10.1016/j.microrel.2018.04.005
Shiroishi, Y., Uchiyama, K., & Suzuki, N. (2018). Society 5.0: For human security and well-being. Computer, Vol. 51(7), pp. 91-95. DOI: 10.1109/MC.2018.3011041
Tian, J., Morillo, C., Azarian, M. H., & Pecht, M. (2015). Motor bearing fault detection using spectral kurtosis-based feature extraction coupled with K-nearest neighbor distance analysis. IEEE Transactions on Industrial Electronics, Vol. 63(3), pp. 1793-1803. DOI: 10.1109/TIE.2015.2509913
Yao, B., Chen, H., He, X. Q., Xiao, Q. Z., & Kuang, X. J. (2013, July). Reliability and failure analysis of DC/DC converter and case studies. In 2013 International Conference on Quality, Reliability, Risk, Maintenance, and Safety Engineering (QR2MSE) (pp. 1133-1135). IEEE. DOI: 10.1109/QR2MSE.2013.6625766