An Intelligent Predictive Maintenance Framework with Autonomous Feature Selection based on Hybrid Fuzzy Set and Rough Set Theories for Multiclass Fault Classification

Albert Buabeng, Anthony Simons, Nana Kena Frempong, Yao Yevenyo Ziggah

Abstract


In this paper, an intelligent Predictive Maintenance (PdM) framework with an efficient and automated selection of relevant and most informative features has been proposed for fault classification. This was achieved by using the hybrid of Fuzzy Set and Rough Set Theories as a feature selection technique for pre-processing and the selection of features that contained only relevant fault characteristics. The selected features were then served as input for training the Support Vector Machine (SVM) classifier for the classification of the condition of four major hydraulic components (accumulator, cooler, pump and valve). To ascertain the performance of the proposed framework, a comparative study with five different and well-established machine learning classifiers was evaluated using nine different performance metrics. The result from the analysis proves the versatility of the proposed framework in classifying the various conditions of the hydraulic components whiles reducing the computational cost. When compared with prior works, a significant average improvement of over 26% in test accuracy was obtained for both accumulator and pump conditions whiles similar results were seen for cooler and valve conditions.

Keywords


Fuzzy Rough Feature Selection; Hydraulic System; Ordered Weighted Average; SVM

Full Text:

PDF

References


Abdulhafiz, W. A. and Khamis, A. (2013), “Handling Data Uncertainty and Inconsistency Using Multisensor Data Fusion”, Advances in Artificial Intelligence, Vol. 2013, pp. 1 - 11.

Bach, F. (2017), “Breaking the Curse of Dimensionality with Convex Neural Networks”, Journal of Machine Learning Research, Vol. 18, No. 19, pp. 1 - 53.

Bharti, K. K. and Singh, P. K. (2015), “Hybrid Dimension Reduction by Integrating Feature Selection with Feature Extraction Method for Text Clustering”, Expert Systems with Applications, Vol. 42, No. 6, pp. 3105 - 3114.

Binsaeid, S., Asfour, S., Cho, S. and Onar, A. (2009), “Machine Ensemble Approach for Simultaneous Detection of Transient and Gradual Abnormalities in End Milling using Multisensor Fusion”, Journal of Materials Processing Technology, Vol. 209, No. 10, pp. 4728 - 4738.

Bruzzone, L. and Persello, C. (2009), “A Novel Approach to the Selection of Spatially Invariant features for the Classification of Hyperspectral Images with Improved Generalization Capability”, IEEE Transactions on Geoscience and Remote Sensing, Vol. 47, No. 9, pp. 3180 - 3191.

Chawathe, S. S. (2019), “Condition Monitoring of Hydraulic Systems by Classifying Sensor Data Streams”, Proceedings of the IEEE 9th Annual Computing and Communication Workshop and Conference (CCWC), Las Vegas, NV, USA, pp. 898 - 904.

Cornelis, C., Verbiest, N. and Jensen, R. (2010), “Ordered Weighted Average Based Fuzzy Rough Sets”, In Rough Set and Knowledge Technology (RSKT), Yu J., Greco S., Lingras P., Wang G., Skowron A. (eds), Springer, Berlin, Heidelberg, pp. 78 - 85.

Di, Z., Kang, Q., Peng, D. and Zhou, M. (2019), “Density Peak-Based Pre-Clustering Support Vector Machine for Multi-Class Imbalanced Classification”, Proceedings of the IEEE International Conference on Systems, Man and Cybernetics (SMC), Bari, Italy, pp. 27 - 32.

Du, D., Jia, X. and Hao, C. (2016), “A New Least Squares Support Vector Machines Ensemble Model for Aero Engine Performance Parameter Chaotic Prediction”, Mathematical Problems in Engineering, Vol. 2016, pp. 1 - 8.

Gao, X., Wei, H., Li, T. and Yang, G. (2020), “A Rolling Bearing Fault Diagnosis Method based on LSSVM”, Advances in Mechanical Engineering, Vol. 12, No. 1, pp. 1 - 10.

Guha, R., Chatterjee, B., Hassan, S., Ahmed, S., Bhattacharyya, T. and Sarkar, R. (2022), “Py_FS: A Python Package for Feature Selection Using Meta-Heuristic Optimization Algorithms”, In: Computational Intelligence in Pattern Recognitionpp, Das A. K., Nayak, J., Naik, B., Dutta, S., Pelusi, D. (eds), Springer, Singapore, Vol. 1349, pp. 495 - 504.

Helwig, N., Pignanelli, E. and Schütze, A. (2015a), “Condition Monitoring of a Complex Hydraulic System using Multivariate Statistics”, Proceedings of the Instrumentation and Measurement Technology Conference (I2MTC), Pisa, Italy, pp. 210 - 215.

Helwig, N., Pignanelli, E. and Schütze, A. (2015b), “Detecting and Compensating Sensor Faults in a Hydraulic Condition Monitoring System”, Proceedings of Sensor, Nürnberg, Germany, pp. 641 - 646.

Herrmann, F. J., Friedlander, M. P. and Yilmaz, O. (2012), “Fighting the Curse of Dimensionality: Compressive Sensing in Exploration Seismology”, IEEE Signal Process Mag., Vol. 29, No. 3, pp. 88 - 100.

Huang, S. Y. (1992), Intelligent Decision Support: Handbook of Applications and Advances of the Rough Sets Theory, Springer Science and Business Media, Germany, 2nd edition, 490 pp.

Jensen, R. and Shen, Q. (2009), “New Approaches to Fuzzy-Rough Feature Selection”, IEEE Transactions on Fuzzy Systems, Vol. 17, No. 4, pp. 824 - 838.

König, C. and Helmi, A. M. (2020), “Sensitivity Analysis of Sensors in a Hydraulic Condition Monitoring System using CNN Models”, Sensors, Vol. 20, No. 11, pp. 1 - 19.

Mahmud, M. N., Ibrahim, M. N., Osman, M. K. and Hussain, Z. (2017), “Support Vector Machine (SVM) for Fault Classification in Radial Distribution Network”, Advanced Science Letters, Vol. 23, No. 5, pp. 4124 - 4128.

Mohapatra, P. and Chakravarty, S. (2015), “Modified PSO Based Feature Selection for Microarray Data Classification”, Proceedings of the 2015 IEEE Power, Communication and Information Technology Conference (PCITC), Bhubaneswar, India, pp. 703–709.

Pawlak, Z. (2012), Rough Sets: Theoretical Aspects of Reasoning about Data, Springer Science and Business Media, Berlin, Germany, Vol. 9, 252 pp.

Radzikowska, A. M. and Kerre, E. E. (2002), “A Comparative Study of Fuzzy Rough Sets”, Fuzzy Sets and Systems, Vol. 126, No. 2, pp. 137 - 155.

Riza, L. S., Janusz, A., Bergmeir, C., Cornelis, C., Herrera, F., Śle¸zak, D. and Benítez, J. M. (2014), “Implementing Algorithms of Rough Set Theory and Fuzzy Rough Set Theory in the R Package ‘RoughSets’”, Information Sciences, Vol. 287, pp. 68 - 89.

Schneider, T., Helwig, N. and Schütze, A. (2017), “Automatic Feature Extraction and Selection for Classification of Cyclical Time Series Data”, Tm-Technisches Messen, Vol. 84, No. 3, pp. 198 - 206.

Schneider, T., Helwig, N. and Schütze, A. (2018), “Automatic Feature Extraction and Selection for Condition Monitoring and Related Datasets”, Proceedings of the 2018 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), Houston, TX, USA, pp. 1 - 6.

Sheng, C., Li, Z., Qin, L., Guo, Z. and Zhang, Y. (2011), “Recent Progress on Mechanical Condition Monitoring and Fault Diagnosis”, Procedia Engineering, Vol. 15, pp. 142 - 146.

Wang, K., Wen, X., Hou, D., Tu, D., Zhu, N., Huang, P., Zhang, G. and Zhang, H. (2018), “Application of Least-Squares Support Vector Machines for Quantitative Evaluation of Known Contaminant in Water Distribution System using Online Water Quality Parameters”, Sensors, Vol. 18, No. 4, pp. 1 - 19.

Zadeh, L. A. (1965), “Information and Control”, Fuzzy Sets, Vol. 8, No. 3, pp. 338 - 353.

Zadeh, L. A. (1978), “Fuzzy Sets as a Basis for a Theory of Possibility”, Fuzzy Sets and Systems, Vol. 1, No. 1, pp. 3 - 28.


Refbacks

  • There are currently no refbacks.