Statistically Optimal Vibration Feature Selection for Fault Diagnosis in Wind Turbine Blade

Ahmed Ali Farhan Ogaili, Alaa Abdulhady Jaber, Mohsin Noori Hamzah

Abstract


 The present study identifies various faults in wind turbine blades from the ?acquired vibration signals. Various statistically obtained features were computed from time-domain vibration signatures, including kurtosis, skewness, standard deviation, variation, root mean square, and crest factor. To identify faults in wind turbines, a comparison was made with the performance of two classification models, Random Forest (RF) and Support Vector Machine (SVM), using the feature set obtained from the time-domain vibration signals. The results demonstrate these classifiers for fault diagnosis. The use of chi-square (x2) statistical feature selection techniques has been found to improve classification accuracy. To test the efficacy of this approach, we compared the proposed model with traditional models using several performance measurements. The findings confirmed that when chi-square (x2) is used in conjunction with RF, the proposed model achieved a significant improvement in precision, increasing from 75.3% to 83.315%. These results suggest that the chi-square (x2) can be valuable for optimizing feature selection and improving classification accuracy in machine learning models. ?


Keywords


Machine learning, Random Forest (RF), ?2, SVM, Vibration signal?

Full Text:

PDF

References


?[1]? C. Amer and M. Sahin, "Structural analysis of a ?composite wind turbine blade," International Journal of ?Aerospace and Mechanical Engineering, vol. 8, no. 7, pp. ??1264-1270, 2014.?

?[2]? A. A. F. Ogaili, M. N. Hamzah and A. A. Jaber, ??"Integration of Machine Learning (ML) and Finite ?Element Analysis (FEA) for Predicting the Failure Modes ?of a Small Horizontal Composite Blade," International ?Journal of Renewable Energy Research (IJRER), vol. 12, ?no. 4, pp. 2168-2179, 2022.?

?[3]? Ogaili, A.A.F., Hamzah, M.N., Jaber, AA "Free Vibration ?Analysis of a Wind Turbine ?Blade Made of Composite ?Materials" International Middle Eastern Simulation ?and ?Modeling Conference 2022, MESM 2022, 2022, pp. ??203–209.?

?[4]? Lu, B., Li, Y., Wu, X. and Yang, Z.: 'A review of recent ?advances in wind turbine condition monitoring and fault ?diagnosis, 2009 IEEE power electronics and Machines in ?wind applications, 2009, pp. 1-7 ?

?[5]? Z. Hameed, Y. Hong, Y. Cho, S. Ahn, and C. Song, ??"Condition monitoring and fault detection of wind ?turbines and related algorithms: A review," Renewable ?and Sustainable Energy Reviews, vol. 13, no. 1, pp. 1-39, ??2009.?

?[6]? S. K. Abraham, V. Sugumaran, and M. Amarnath, ??"Acoustic signal based condition monitoring of gearbox ?using wavelets and decision tree classifier," Indian ?Journal of Science and Technology, vol. 9, no. 33, pp. 1-??9, 2016.?

?[7]? F. P. G. Márquez, A. M. Tobias, J. M. P. Pérez, and M. ?Papaelias, "Condition monitoring of wind turbines: ?Techniques and methods," Renewable energy, vol. 46, ?pp. 169-178, 2012.?

?[8]? W. Y. Liu, B. P. Tang, J. G. Han, X. N. Lu, N. N. Hu, and ?Z. Z. He, "The structure healthy condition monitoring ?and fault diagnosis methods in wind ?turbines: A review," ?Renewable and Sustainable Energy Reviews, Volume 44, ??April 2015, Pages 466-472.? ?

?[9]? ? A. Joshuva and V. Sugumaran, "A data-driven ?approach for condition monitoring of ?wind turbine blade ?using vibration signals through the best-first tree ?algorithm and ?functional trees algorithm: a comparative ?study," ISA (Instrum. Soc. Am.) Trans. ??67 (2017) 160- ??172.?

?[10]? A. Joshuva and V. Sugumaran, "Fault Diagnosis for ?Wind TurbineBlade through ?Vibration Signals Using ?Statistical Features and Random Forest Algorithm," ?IJPT, ?Vol. 9, April-2017.?

?[11]? Joshuva, A., Kumar, R. S., Sivakumar, S., ?Deenadayalan, G. & Vishnuvardhan, R. ??(2020). An in-?depth look at VMD to diagnose wind turbine blade faults ?using C4. ??5 as feature selection and discriminating ?through multilayer ?perceptron. Alexandria Engineering ?Journal, 59(5), 3863-3879.?

?[12]? K.F. Abdulraheem, G. Al-Kindi, A Simplified Wind ?Turbine Blade Crack ?Identification Using Experimental ?Modal Analysis (EMA), Int. J. Renew. Energy ?Research ??(IJRER) 7 (2) (2017)715–722.?

?[13]? ? D. Tcherniak, L.L. Mlgaard, Active vibration-based ?structuralhealth monitoring ?system for wind turbine ?blade: demonstration on an operating Vestas V27 wind ??turbine, Structural Health Monitoring. 16 (5) (2017) 536–??550.?

?[14]? Sahoo, S.; Kushwah, K.; Sunaniya, A.K. Health ?Monitoring of Wind Turbine Blades ?Through Vibration ?Signal Using Advanced Signal Processing Techniques. In ??Proceedings of the 2020 Advanced Communication ?Technologies and Signal ?Processing (ACTS), Silchar, ?India, 4–6 December 2020; pp. 1–6.?

?[15]? Yang Tao, Ren Yong, Liu Xia et al. Research on ?modeling and simulation of wind ?turbine rotor imbalance ?fault [J]. Journal of Mechanical Engineering, 2012, ???48(6):130-135.?

?[16]? Ren Yong. Modeling and Simulation of the Unbalance ?of wind turbine ?blade[D].Wuhan: Huazhong University ?of Science and Technology,2012?

?[17]? Gupta DL, Malviya AK, Singh S (2012) Performance ?analysis of classification tree ?learningalgorithms. Int J ?Comput Appl 55(6):0975–8887?

?[18]? ? Amarnath M, Sugumaran V, Kumar H (2013) ?Exploiting sound signals for fault ?diagnosis of bearings ?using decision tree. Measurement 46:1250–1256.?

?[19]? L. Breiman, Random forests, Machine Learning ??45(1)(2001), 3-52.?

?[20]? Yang, B. S., Di, X., & Han, T. (2008). Random forests ?classifier for machine fault ?diagnosis. Journal of ?Mechanical Science and technology, 22, 1716-1725.?

?[21]? M. Cerrada, G. Zurita, D. Cabrera, RR Sanchez, M. Art' ?es'?? ?and C. Li, Fault diagnosis ?in spur gears based on ?genetic? ?algorithm and random forest, Mechanical ?Systems ?and Signal Processin 70 (2016), 87–103?

?[22]? Vapnik VN (1998) Statistical learning theory. Wiley, New ?York

?[23]? Maria Navin, JR, Pankaja, R., 2016. Performance ?Analysis of Text Classification ?Algorithms Using ?Confusion Matrix.?

?[24]? Hossin, M., Sulaiman, M.N., 2015. Review of evaluation ?metrics for data ?classification evaluations. International ?Journal of Data Mining & Knowledge ?Management ?Process 5 (2), 1.?

?[25]? Tilaki-Hajian, K., 2013. Receiver Operating ?Characteristics (ROC) Curve Analysis ?Formal Diagnostic ?Test Evaluation. Caspian Journal of internal medicine 4 ??(2), ??627.?

?[26]? Antariksa, G., Muammar, R., & Lee, J. (2022). ?Performance evaluation of machine ?learning-based ?classification with rock physics analysis of geological ?lithofacies in ?the Tarakan Basin, Indonesia. Journal of ?Petroleum Science and Engineering, 208, ??109250.?

?[27]? Jaber, A.A.; Bicker, R. A simulation of nonstationary ?signal analysis using wavelet ?transform based on ?LabVIEW and Matlab. In Proceedings of the UKSim-?AMSS ??8th European Modeling Symposium on ?Computer Modelling and Simulation,EMS ??2014,Pisa, ?Italy, 21–23 October 2014; pp. 138–144. ??https://doi.org/10.1109/EMS.2014.38.?

?[28]? Vakharia, V., Gupta, V. K. & Kankar, P. K. (2017). ?Efficient Ball Bearing Failure Diagnosis using ?ReliefF ?and Random Forest Classifier. Journal of the Brazilian ?Society of ?Mechanical Sciences and Engineering, 39(8), ??2969-2982.?

?[29]? Ali, L.; Zhu, C.; Zhou, M.; Liu, Y. Early diagnosis of ?Parkinson's disease from ?multiple voice recordings by ?simultaneous sample selection and features. Expert ?Syst. ?Appl. 2019, 137, 22–28. ?

?[30]? ? Liu, H.; Setiono, R. Chi2: Feature selection and ?discretization of numeric attributes. ?In Proceedings of the ??7th IEEE International Conference on Tools with ?Artificial ?Intelligence, Herndon, VA, USA, 5–8 November ??1995; pp. 388–391.?

?[31]? Al-Haddad, Luttfi A. and Alaa Abdulhady Jaber. 2023. ??"An Intelligent Fault ?Diagnosis Approach for Multirotor ?UAVs Based on Deep Neural Network of ?Multi-?Reduction Transform Features" Drones 7, no. 2: 82. ??https://doi.org/10.3390/drones7020082.?




DOI (PDF): https://doi.org/10.20508/ijrer.v13i3.14096.g8782

Refbacks

  • There are currently no refbacks.


Online ISSN: 1309-0127

Publisher: Gazi University

IJRER is cited in SCOPUS, EBSCO, WEB of SCIENCE (Clarivate Analytics);

IJRER has been cited in Emerging Sources Citation Index from 2016 in web of science.

WEB of SCIENCE in 2025; 

h=35,

Average citation per item=6.59

Last three Years Impact Factor=(1947+1753+1586)/(146+201+78)=5286/425=12.43

Category Quartile:Q4