Using Johnson Distribution for Automatic Threshold Setting in Wind Turbine Condition Monitoring System



Kun S. Marhadi Georgios Alexandros Skrimpas


Setting optimal alarm thresholds in vibration based condition monitoring system is inherently difficult. There are no established thresholds for many vibration based measurements. Most of the time, the thresholds are set based on statistics of the collected data available. Often times the underlying probability distribution that describes the data is not known. Choosing an incorrect distribution to describe the data and then setting up thresholds based on the chosen distribution could result in sub-optimal thresholds. Moreover, in wind turbine applications the collected data available may not represent the whole operating conditions of a turbine, which results in uncertainty in the parameters of the fitted probabil- ity distribution and the thresholds calculated. In this study Johnson distribution is used to identify shape, location, and scale parameters of distribution that can best fit vibration data. This study shows that using Johnson distribution can eliminate testing or fitting various distributions to the data, and have more direct approach to obtain optimal thresholds. To quantify uncertainty in the thresholds due to limited data, implementations with bootstrap method and Bayesian inference are investigated.

How to Cite

S. Marhadi, K., & Alexandros Skrimpas, . G. . (2014). Using Johnson Distribution for Automatic Threshold Setting in Wind Turbine Condition Monitoring System. Annual Conference of the PHM Society, 6(1).
Abstract 78 | PDF Downloads 50



Wind Turbine, Bayesian inference, Johnson distribution, automatic threshold setting

Andersson, C., Gutt, S., & Hastings, M. (2007). Cost- effective monitoring solution using external surveillance center. In The second world congress on engineering asset management and the forth international conference on condition monitoring. Harrogate, UK.

Bechhoefer, E., & Bernhard, A. P. (2004). Setting hums condition indicator thresholds by modeling aircraft and torque band variance. In Aerospace Conference, 2004. proceedings. 2004 IEEE (Vol. 6, pp. 3590–3595).

Bechhoefer, E., & Bernhard, A. P. (2005). Use of non-gaussian distribution for analysis of shaft components. In Aerospace Conference, 2006 ieee (pp. 9–pp).

Bechhoefer, E., He, D., & Dempsey, P. (2011). Gear health threshold setting based on a probability of false alarm. In Annual conference of the prognostics and health management society, September 25–20, Montreal, canada.

Cempel, C. (1987). Simple condition forecasting techniques in vibroacoustical diagnostics. Mechanical Systems and Signal Processing, 1(1), 75–82.

Cempel, C. (1990). Limit value in the practice of machine vibration diagnostics. Mechanical systems and signal processing, 4(6), 483–493.

Chernick, M. R. (1999). Bootstrap methods, a practitioners guide. John Wiley & Sons.

Crabtree, C. (2011). Condition monitoring techniques for wind turbines. Unpublished doctoral dissertation, Durham University.

DeBrota, D. J., Dittus, R. S., Swain, J. J., Roberts, S. D., & Wilson, J. R. (1989). Modeling input processes with johnson distributions. In Proceedings of the 21st conference on winter simulation (pp. 308–318).

DeBrota, D. J., Roberts, S. D., Swain, J. J., Dittus, R. S., Wil- son, J. R., & Venkatraman, S. (1988). Input modeling with the johnson system of distributions. In Proceedings of the 20th conference on winter simulation (pp. 165–179).

Enterprises, S. (2012). Scilab: Free and open source software for numerical computation [Computer software manual]. Orsay, France. Retrieved from

Hill, I., Hill, R., & Holder, R. (1976). Algorithm as 99: Fitting johnson curves by moments. Applied Statistics, 180–189.

Jablonski, A., Barszcz, T., Bielecka, M., & Breuhaus, P. (2013). Modeling of probability distribution functions for automatic threshold calculation in condition monitoring systems. Measurement, 46(1), 727–738.

Johnson, N. L. (1949). Systems of frequency curves generated by methods of translation. Biometrika, 16, 149– 176.

MacKay, D. J. C. (2003). Information theory, inference, and learning algorithms. Cambridge University Press.

Marhadi, K., & Hilmisson, R. (2013, 11–13 June). Simple and effective technique for early detection of rolling element bearing fault: A case study in wind turbine application. In International congress of condition monitoring and diagnostic engineering management (coma- dem). Helsinki, Finland.

Marhadi, K., Venkataraman, S., & Pai, S. S. (2012). Quantifying uncertainty in statistical distribution of small sample data using Bayesian inference of unbounded johnson distribution. International Journal of Reliability and Safety, 6(4), 311–337.

Tavner, P. (2012). Offshore wind turbines. The Institution of Engineering and Technology.
Technical Research Papers

Most read articles by the same author(s)