Jian Zhou
Editorial Notes
The editors have requested minor, non-substantive changes to the VoR and, in accordance with ACM policies, a Corrected VoR was published on March 5, 2021. For reference purposes the VoR may still be accessed via the Supplemental Material section on this page.
ABSTRACT
Fault detection is a difficult but important problem for a complex system. This paper presents a fault detection method based on data-driven key feature selection for the complex system abbreviated as FD-DKFS. By regarding the observable parameters as original features, FD-DKFS first finds the missing correlations among original features and constructs potentially useful features for fault detection. Next, FD-DKFS provides a filter feature selection method to find the best feature subset for fault detection. Then, these selected features are used to detect the fault in a certain complex system with conventional classifiers. Compared with the other methods, the results of the experiment show that the proposed method is more accurate for fault detection in the complex system.
Supplemental Material
Available for Download
Version of Record for "Data-driven Key Features Selection for Fault Detection in a Complex System" by Zhou et al., Proceedings of the 2020 4th International Conference on Electronic Information Technology and Computer Engineering (EITCE '20).
- Mei, S., Zarrabi, N., Lees, M., Sloot, P. M. A. (2015). Complex agent networks: an emerging approach for modeling complex systems. Applied Soft Computing, 37, 311--321.Google Scholar
Digital Library
- Liu, Z., Jia, Z., Vong, C. M., Bu, S., Han, J., & Tang, X.. (2017). Capturing high-discriminative fault features for electronics-rich analog system via deep learning. IEEE Transactions on Industrial Informatics, 1213--1226.Google ScholarCross Ref
- Betelin, V. B., Eskov, V. M., Galkin, V. A., & Gavrilenko, T. V.. (2017). Stochastic volatility in the dynamics of complex homeostatic systems. Doklady Mathematics, 95(1), 92--94.Google ScholarCross Ref
- Li, D., Zhou, Y., Hu, G., & Spanos, C. J.. (2016). Optimal sensor configuration and feature selection for ahu fault detection and diagnosis. IEEE Transactions on Industrial Informatics, 13(3), 1369--1380.Google ScholarCross Ref
- Wang, G., & Yin, S.. (2017). Quality-related fault detection approach based on orthogonal signal correction and modified pls. IEEE Transactions on Industrial Informatics, 11(2), 398--405.Google Scholar
- Wang, G., Yin, S., & Kaynak, O.. (2014). An lwpr-based data-driven fault detection approach for nonlinear process monitoring. Industrial Informatics IEEE Transactions on, 10(4), 2016--2023.Google ScholarCross Ref
- Guyon, I., & Elisseeff, André. (2003). An introduction to variable and feature selection. Journal of Machine Learning Research, 3(6), 1157--1182.Google ScholarDigital Library
- Chen, Q., Zhang, M., & Xue, B.. (2017). Genetic Programming with Embedded Feature Construction for High-Dimensional Symbolic Regression. Intelligent and Evolutionary Systems. Springer International Publishing.Google Scholar
- Liu, H., & Motoda, H.. (1999). Feature extraction construction and selection: a data mining perspective. Journal of the American Statistical Association, 94(448), 014004.Google Scholar
- Piramuthu, S., and Sikora, R. T. (2009). Iterative feature construction for improving inductive learning algorithms. Expert Systems with Applications, 36(2), 3401--3406.Google ScholarDigital Library
- Smith, M. G., & Bull, L.. (2005). Genetic programming with a genetic algorithm for feature construction and selection. Genetic Programming & Evolvable Machines, 6(3), 265--281.Google ScholarDigital Library
- Tang, J., Chai, T. Y., Yu, W., Liu, Z., Zhou, X. J. (2016). A comparative study that measures ball mill load parameters through different single-scale and multiscale frequency spectra-based approaches. IEEE Transactions on Industrial Informatics. 12(6), 2008--2019.Google ScholarCross Ref
- Georgoulas, G., Climente, V., Antonino-Daviu, J. A., Tsoumas, I., Stylios, C., Arkkio, A. and Nikolakopoulos, G. (2017). The use of a multi-label classification framework for the detection of broken bars and mixed eccentricity faults based on the start-up transient. IEEE Transactions on Industrial Informatics. 13(2), 625--634.Google ScholarCross Ref
- Rajput, D. S., Singh, P. K. and Bhattacharya, M. (2015). PROFIT: A Projected Clustering Technique. Real World Data Mining Applications, Springer International Publishing, 51--70.Google Scholar
- Liu, Z., Zhao, X., Zuo, M. J., & Xu, H.. (2014). Feature selection for fault level diagnosis of planetary gearboxes. Advances in Data Analysis & Classification, 8(4), 377--401.Google ScholarDigital Library
- Al-Otaibi, R., Jin, N., Wilcox, T., & Flach, P.. (2017). Feature construction and calibration for clustering daily load curves from smart-meter data. IEEE Transactions on Industrial Informatics, 12(2), 645--654.Google ScholarCross Ref
- Lillywhite, K., Lee, D. J., Tippetts, B., & Archibald, J.. (2013). A feature construction method for general object recognition. Pattern Recognition, 46(12), 3300--3314.Google ScholarDigital Library
- Saeys, Y., Inza, I. and Larraaga, P. (2007). A review of feature selection techniques in bioinformatics. Bioinformatics, 23(19), 2507--2517.Google ScholarDigital Library
- Chen, G. and Chen, J. (2015). A novel wrapper method for feature selection and its applications. Neurocomputing, 159(1), 219--226.Google ScholarDigital Library
- Khammassi, C., and Krichen, S. (2017). A GA-LR Wrapper Approach for Feature Selection in Network Intrusion Detection. Computers & Security, 70, 255--277.Google ScholarCross Ref
- Ferreira, A. J. and Figueiredo, M. A. T. (2014). Incremental filter and wrapper approaches for feature discretization. Neurocomputing, 123, 60--74.Google ScholarDigital Library
- Wang, A., An, N., Chen, G., Li, L., & Alterovitz, G.. (2015). Accelerating wrapper-based feature selection with k-nearest-neighbor. Knowledge-Based Systems, 83(1), 81--91.Google ScholarDigital Library
- Zhang, K., Li, Y., Scarf, P. and Ball A. (2011). Feature selection for high-dimensional machinery fault diagnosis data using multiple models and Radial Basis Function networks. Neurocomputing, 74(17), 2941--2952.Google ScholarDigital Library
- Yang, Y., Liao, Y., Meng, G. and Lee, J. (2011). A hybrid feature selection scheme for unsupervised learning and its application in bearing fault diagnosis. Expert Systems with Applications. 38(9), 11311--11320.Google ScholarDigital Library
- Yang, P., Zhou, B. B., Zhang, Z. and Zomaya, A. Y. (2010). A multi-filter enhanced genetic ensemble system for gene selection and sample classification of microarray data, BMC Bioinformatics, 11, 1--12.Google ScholarCross Ref
- Zhao, X., Zuo, M. J. and Patel, T. (2010). EMD, ranking mutual information and PCA based condition monitoring. In: Proceedings of ASME 2010 international design engineering technical conferences. Montreal, Canada, 777--782.Google ScholarCross Ref
- Wu, B., Abbott, T., Fishman, D., Mcmurray, W., Mor, G., & Stone, K., et al. (2003). Comparison of statistical methods for classification of ovarian cancer using mass spectrometry data. Bioinformatics, 19 (13), 1636--1643.Google ScholarCross Ref
- Freeman, C., Dana Kulić, & Basir, O.. (2015). An evaluation of classifier-specific filter measure performance for feature selection. Pattern Recognition. 48(5), 1812--1826.Google ScholarDigital Library
- García-Torres, M., Gómez-Vela, F., Melián-Batista, B. and Moreno-Vega, J. M. (2016). High-dimensional feature selection via feature grouping: A Variable Neighborhood Search approach. Information Sciences, 326, 102--118.Google ScholarDigital Library
- Yu, L., Liu, H. (2004). Efficient feature selection via analysis of relevance and redundancy, The Journal of Machine Learning Research, 5 (12): 1205--1224.Google ScholarDigital Library
- Hall, M. (2000) Correlation-based feature selection for discrete and numeric class machine learning, in: Proceedings of the 17th International Conference on Machine Learning, Morgan Kaufmann, San Francisco, CA, 359--366.Google Scholar
- Duval, M., & Depabla, A.. (2002). Interpretation of gas-in-oil analysis using new iec publication 60599 and iec tc 10 databases. Electrical Insulation Magazine IEEE, 17(2), 31--41.Google ScholarCross Ref
Index Terms
- Data-driven Key Features Selection for Fault Detection in a Complex System
Recommendations
Feature selection for fault detection systems: application to the Tennessee Eastman process
In fault detection systems, a massive amount of data gathered from the life-cycle of equipment is often used to learn models or classifiers that aims at diagnosing different kinds of errors or failures. Among this huge quantity of information, some ...
Effect of Feature Selection in Software Fault Detection
Multi-disciplinary Trends in Artificial IntelligenceAbstractThe quality of software is enormously affected by the faults associated with it. Detection of faults at a proper stage in software development is a challenging task and plays a vital role in the quality of the software. Machine learning is, now a ...
Feature Selection for Aero-Engine Fault Detection
Database and Expert Systems ApplicationsAbstractTimely and accurate detection of aero-engine faults is crucial to preventing loss of lives and equipment. In recent times, there has been a focus on data-driven approaches to fault detection in aero-engines owing to the availability of numerous ...
Comments