Cost-sensitive large margin distribution machine for fault detection of wind turbines

Given the importance of the class-imbalanced data and misclassified unequal costs in large wind turbine datasets, this paper proposes a cost-sensitive large margin distribution machine (CLDM) for fault detection of wind turbines. The margin mean and margin variance are use to characterize the margin distribution. The objective function and constraints of the large margin distribution machine (LDM) are modified to be cost-sensitive. The class-imbalanced data and misclassified unequal costs are solved by selecting the appropriately cost-sensitive parameters. Then CLDM is designed to train and test data from wind turbines in a wind farm. In order to verify the effectiveness of CLDM, it is compared with support vector machine (SVM), cost-sensitive SVM, and LDM. Comprehensive experiments on 7 datasets from a benchmark model of wind turbines and 5 datasets from a real wind farm show that CLDM has better sensitivity, gMean and average misclassified cost than the other methods.

[1]  Andrew Kusiak,et al.  The prediction and diagnosis of wind turbine faults , 2011 .

[2]  Iury Valente de Bessa,et al.  Data-driven fault detection and isolation scheme for a wind turbine benchmark , 2016 .

[3]  Francisco Charte,et al.  MLSMOTE: Approaching imbalanced multilabel learning through synthetic instance generation , 2015, Knowl. Based Syst..

[4]  Xiao Lei,et al.  A generalized model for wind turbine anomaly identification based on SCADA data , 2016 .

[5]  Tadeusz Uhl,et al.  Condition monitoring and fault detection in wind turbines based on cointegration analysis of SCADA data , 2018 .

[6]  Juan José Rodríguez Diez,et al.  Random Balance: Ensembles of variable priors classifiers for imbalanced data , 2015, Knowl. Based Syst..

[7]  Yang Wang,et al.  Cost-sensitive boosting for classification of imbalanced data , 2007, Pattern Recognit..

[8]  Nitesh V. Chawla,et al.  Editorial: special issue on learning from imbalanced data sets , 2004, SKDD.

[9]  Abdul Qayyum Khan,et al.  Observer-based FDI Schemes for Wind Turbine Benchmark , 2011 .

[10]  Zhihua Xia,et al.  Steganalysis of least significant bit matching using multi-order differences , 2014, Secur. Commun. Networks.

[11]  Naixue Xiong,et al.  Steganalysis of LSB matching using differences between nonadjacent pixels , 2016, Multimedia Tools and Applications.

[12]  Han Jiguang,et al.  Wind turbine fault diagnosis method based on diagonal spectrum and clustering binary tree SVM , 2013 .

[13]  Victor S. Sheng,et al.  Cost-Sensitive Learning , 2009, Encyclopedia of Data Warehousing and Mining.

[14]  M. Davenport.  The 2nu-SVM: A Cost-Sensitive Extension of the nu-SVM , 2005 .

[15]  Jing Zhang,et al.  Cost-Sensitive Large margin Distribution Machine for classification of imbalanced data , 2016, Pattern Recognit. Lett..

[16]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[17]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[18]  Taghi M. Khoshgoftaar,et al.  RUSBoost: A Hybrid Approach to Alleviating Class Imbalance , 2010, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[19]  Chih-Jen Lin,et al.  A dual coordinate descent method for large-scale linear SVM , 2008, ICML '08.

[20]  Jian Hou,et al.  Recent advances on SVM based fault diagnosis and process monitoring in complicated industrial processes , 2016, Neurocomputing.

[21]  Vicenç Puig,et al.  Robust Fault Diagnosis of Nonlinear Systems Using Interval Constraint Satisfaction and Analytical Redundancy Relations , 2014, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[22]  Wei Chen,et al.  Intelligent fault diagnosis of rotating machinery using support vector machine with ant colony algorithm for synchronous feature selection and parameter optimization , 2015, Neurocomputing.

[23]  Chengsheng Yuan,et al.  Fingerprint liveness detection based on multi-scale LPQ and PCA , 2016, China Communications.

[24]  Youmin Zhang,et al.  Fault-tolerant cooperative control in an offshore wind farm using model-free and model-based fault detection and diagnosis approaches ☆ , 2017 .

[25]  Hojjat Adeli,et al.  Concept Drift-Oriented Adaptive and Dynamic Support Vector Machine Ensemble With Time Window in Corporate Financial Risk Prediction , 2013, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[26]  Bin Gu,et al.  A Robust Regularization Path Algorithm for $\nu $ -Support Vector Classification , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[27]  Anthony Widjaja,et al.  Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond , 2003, IEEE Transactions on Neural Networks.

[28]  XiongNaixue,et al.  Steganalysis of LSB matching using differences between nonadjacent pixels , 2016 .

[29]  Halil Ceylan,et al.  A survey of health monitoring systems for wind turbines , 2015 .

[30]  Taghi M. Khoshgoftaar,et al.  Comparing Boosting and Bagging Techniques With Noisy and Imbalanced Data , 2011, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[31]  Moamar Sayed Mouchaweh,et al.  Hybrid dynamic classifier for drift-like fault diagnosis in a class of hybrid dynamic systems: Application to wind turbine converters , 2016, Neurocomputing.

[32]  Peter Fogh Odgaard,et al.  Fault Detection of Wind Turbines with Uncertain Parameters: A Set-Membership Approach , 2012 .

[33]  Zhi-Hua Zhou,et al.  On the doubt about margin explanation of boosting , 2010, Artif. Intell..

[34]  Xingming Sun,et al.  Structural Minimax Probability Machine , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[35]  Zhi-Hua Zhou,et al.  Large margin distribution machine , 2013, KDD.

[36]  Henry Hong,et al.  Wind Turbine Fault Diagnosis and Fault-Tolerant Torque Load Control Against Actuator Faults , 2015, IEEE Transactions on Control Systems Technology.

[37]  Bin Gu,et al.  Incremental Support Vector Learning for Ordinal Regression , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[38]  Bin Gu,et al.  Incremental learning for ν-Support Vector Regression , 2015, Neural Networks.

[39]  Peter Fogh Odgaard,et al.  Fault-Tolerant Control of Wind Turbines: A Benchmark Model , 2009, IEEE Transactions on Control Systems Technology.

[40]  Youmin Zhang,et al.  Fuzzy gain-scheduled active fault-tolerant control of a wind turbine , 2014, J. Frankl. Inst..

[41]  Hisao Ishibuchi,et al.  Imbalanced TSK Fuzzy Classifier by Cross-Class Bayesian Fuzzy Clustering and Imbalance Learning , 2017, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[42]  Torsten Jeinsch,et al.  A data-driven approach for sensor fault diagnosis in gearbox of wind energy conversion system , 2013, 2013 10th IEEE International Conference on Control and Automation (ICCA).

[43]  Chia-Hua Ho,et al.  Recent Advances of Large-Scale Linear Classification , 2012, Proceedings of the IEEE.

[44]  Francisco Herrera,et al.  A Review on Ensembles for the Class Imbalance Problem: Bagging-, Boosting-, and Hybrid-Based Approaches , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[45]  Nuno Vasconcelos,et al.  Cost-Sensitive Support Vector Machines , 2012, Neurocomputing.