This content is not included in your SAE MOBILUS subscription, or you are not logged in.
Failure Prediction for Robot Reducers by Combining Two Machine Learning Methods
ISSN: 0148-7191, e-ISSN: 2688-3627
Published April 2, 2019 by SAE International in United States
This content contains downloadable datasetsAnnotation ability available
There are many production robots used at car manufacturing plants, and each of them is fitted with several reducers. A breakdown of one of these reducers may cause a huge loss due to the stoppage of all production lines. Therefore, condition-based maintenance is currently being used to predict failures by predetermined thresholds for average and standard deviations. However, this method can cause many false alarms or some false negatives. There are some ways of suppressing false alarms, such as detecting a change in the probability density function. However, when false alarms are suppressed using the probability density function in the operational range, some false negatives may occur, leading to a breakdown of a reducer and huge loss. A false negative is caused by overlooking an anomaly with slight changes and it is difficult to detect using only the probability density function. Therefore, we developed the Difference Signum Method (DSM) to detect an anomaly with slight changes by focusing on such changes. Although DSM reduces false negatives, it can cause many false alarms. This paper proposes a new failure prediction method using ensemble learning of the probability density function and DSM in order to reduce both false positives and false negatives. Using this new failure prediction method, the number of alerts is now fewer than four times/week, a substantial reduction from nine times/week with the previous method. The number of false negatives reached the target value of zero times/year from two times/year using the probability density function. Therefore, the performance of this new failure prediction method makes it applicable to actual production lines.
CitationTanaka, Y. and Takagi, T., "Failure Prediction for Robot Reducers by Combining Two Machine Learning Methods," SAE Technical Paper 2019-01-0508, 2019, https://doi.org/10.4271/2019-01-0508.
Data Sets - Support Documents
|[Unnamed Dataset 1]|
|[Unnamed Dataset 2]|
|[Unnamed Dataset 3]|
|[Unnamed Dataset 4]|
|[Unnamed Dataset 5]|
- Claudiu-Florinel, B., Medhi, C., Alain, G., and Jean-Yves, K., “Dynamic Behavior Analysis for a Six Axis Industrial Machining Robot,” Journal of Advanced Materials Research 423:65-76, 2012.
- Lars, C., Alexander, F., Bernd, O., and Jörg, N., “Improved Diagnosis by Combining Structural and Process Knowledge,” in Emerging Technologies Factory Automation (ETFA), 2011 IEEE 16th Conference, 1-8, doi:10.1109/ETFA.2011.6059056.
- Stefan, W. and Oliver N., “Efficient Fault Detection for Industrial Automation Processes with Observable Process Variables,” in 2015 IEEE 13th International Conference on Industrial Informatics (INDIN), 2015, 121-126.
- Lisowski, E. and Fabiś, J., “Prediction of Potential Failures in Hydraulic Gear Pumps,” Archives of Foundry Engineering 10(3):73-76, 2010.
- Rosmaini, A. and Shahrul, K., “A Review of Condition-Based Maintenance Decision-Making,” European J of Industrial Engineering 6(5):519-541, 2012.
- Abeer, A., Zhigang, T., and Tongdan, J., “Condition Based Maintenance of Wind Turbine Systems Considering Different Turbine Types,” in IEEE Quality, Reliability, Risk, Maintenance, and Safety Engineering (ICQR2MSE), 2011 International Conference, 2011, 596-600, doi:10.1109/ICQR2MSE.2011.5976683.
- Mitchell, L., Katherine, M., Robert, C., Carl, B. et al., “Review of Vibration Analysis Methods for Gearbox Diagnostics and Prognostics,” in Proceedings of the 54th Meeting of the Society for Machinery Failure Prevention Technology, Virginia Beach, VA, May 1-4, 2000, 623-634.
- Dalpiaz, G., Rivola, A., and Rubini, R., “Gear Fault Monitoring: Comparison of Vibration Analysis Techniques,” in Proc. of the 3rd Int. Conf. on Acoustical and Vibratory Surveillance Methods and Diagnostic Techniques, Senlis, France, Ed. Société Française des Mécaniciens, Courbevole, 1, 1998, 263-272.
- Alvarez, E.J. and Ribaric, A.P., “An Improved-Accuracy Method for Fatigue Load Analysis of Wind Turbine Gearbox Based on SCADA,” Renewable Energy 115:391-399, 2018.
- Montaña, M.M. and Sanz-Bobi, M.A., “Anomaly Detection Indicators of a Wind Turbine Gearbox Based on Feature Extraction from its Vibration Performance,” European Conference of the Prognostics and Health Management Society 4(1):1-8, 2018.
- Kato, T. and Kuroshita, T., “Method of Diagnosing Abnormality of Reduction Gear and Apparatus for Carry Out the Method,” U.S. Patent 20080215292, July 23, 2007.
- Sugiyama, M., Suzuki, T., and Kanamori, T., “Density Ratio Estimation: A Comprehensive Review,” 2011, https://pdfs.semanticscholar.org/fb36/1d6104b3f158ab4e74aa89779f0600ff6512.pdf.
- Kanamori, T., Hido, S., and Sugiyama, M., “Efficient Direct Density Ratio Estimation for Non-stationarity Adaptation and Outlier Detection,” in Conference: Advances in Neural Information Processing, 2008.
- Härdle, W., Nonparametric and Semiparametric Models (Berlin: Springer, 2004), 76-113, doi:10.1007/978-3-642-17146-8.
- Ishibashi, T., Bing, H., and Kawai, T., “Rotating Machinery Library for Diagnosis,” in The 12th International Modelica Conference, 2017.