Metaheuristics and Support Vector Data Description for Fault Detection in Industrial Processes
Source abstract
Abstract
In this study, a system for faults detection using a combination of Support Vector Data Description (SVDD) with metaheuristic algorithms is presented. The presented approach is applied to a real industrial process where the set of measured faults is scarce. The original contribution in this work is the industrial context of application and the comparison of swarm intelligence algorithms to optimize the SVDD hyper-parameters. Four recent metaheuristics are compared hereby to solve the corresponding optimization problem in an efficient manner. These optimization techniques are then implemented for fault detection in a multivariate industrial process with non-balanced data. The obtained numerical results seem to be promising when the considered optimization techniques are combined with SVDD. In particular, the Spotted Hyena algorithm outperforms other metaheuristics reaching values of F1 score near 100% in fault detection.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Fault Detection and Control Systems · Anomaly Detection Techniques and Applications · Spectroscopy and Chemometric Analyses
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Research Center on Applied Mathematics, Autonomous University of Coahuila, Prolongación David Berlanga, Edificio S, Primer Piso, Camporredondo, Saltillo 25115, Mexico
Division of Postgraduate Studies and Research, Tecnológico Nacional de México/IT de Saltillo. Blvd. Venustiano Carranza 2400, Colonia Tecnológico, Saltillo 25280, Mexico
Funding
Universidad Autónoma de Coahuila
References (51)
Show source-provided references
1. The Applications of Genetic Algorithms in Medicine10.5001/omj.2015.82 ↗
2. Vats, S., Dubey, S.K., and Pandey, N.K. (2013, January 1–3). Genetic algorithms for credit card fraud detection. Proceedings of the International Conference on Education and Educational Technologies, Barcelona, Spain.
3. Brabazon, A., O’Neill, M., and Maringer, D. (2012). A Comparison between Nature-Inspired and Machine Learning Approaches to Detecting Trend Reversals in Financial Time Series. Natural Computing in Computational Finance: Volume 4, Springer.
4. Arai, K., and Kapoor, S. (2020). Nature Inspired Meta-heuristic Algorithms for Deep Learning: Recent Progress and Novel Perspective. Advances in Computer Vision, Springer.10.1007/978-3-030-17798-0 ↗
5. A Novel Dynamic Weight Principal Component Analysis Method and Hierarchical Monitoring Strategy for Process Fault Detection and Diagnosis10.1109/TIE.2019.2942560 ↗
6. Principal Polynomial Analysis for Fault Detection and Diagnosis of Industrial Processes10.1109/ACCESS.2018.2870140 ↗
7. Process system fault detection and diagnosis using a hybrid technique10.1016/j.ces.2018.05.045 ↗
8. Deep convolutional neural network model based chemical process fault diagnosis10.1016/j.compchemeng.2018.04.009 ↗
9. Dynamic process fault detection and diagnosis based on a combined approach of hidden Markov and Bayesian network model10.1016/j.ces.2019.01.060 ↗
10. Support Vector Data Description10.1023/B:MACH.0000008084.60811.49 ↗
11. Paturi, U., and Cheruku, S. (2020). Application and performance of machine learning techniques in manufacturing sector from the past two decades: A review. Mater. Today Proc.10.1016/j.matpr.2020.07.209 ↗
12. Review of data mining applications for quality assessment in manufacturing industry: Support vector machines10.1051/ijmqe/2015023 ↗
13. Orru, P., Zoccheddu, A., Sassu, L., Mattia, C., Cozza, R., and Arena, S. (2020). Machine learning approach using MLP and SVM algorithms for the fault prediction of a centrifugal pump in the oil and gas industry. Sustainability, 12.10.3390/su12114776 ↗
14. A diagnostics tool for aero-engines health monitoring using machine learning technique10.1016/j.egypro.2018.08.109 ↗
15. Jiang, Z., Hu, M., Feng, K., and Wang, H. (2018). A SVDD and-Means Based Early Warning Method for Dual-Rotor Equipment under Time-Varying Operating Conditions. Shock Vib., 2018.10.1155/2018/5382398 ↗
16. Automatic inspection of TFT-LCD glass substrates using optimized support vector machines10.3182/20120710-4-SG-2026.00054 ↗
17. Zhuang, L., and Dai, H. (2006). Parameter optimization of kernel-based one-class classifier on imbalance text learning. Pacific Rim International Conference on Artificial Intelligence, Springer.10.1007/978-3-540-36668-3_47 ↗
18. Cao, Q., Yu, L., and Cheng, M. (2016). A Brief Overview on Parameter Optimization of Support Vector Machine. DEStech Trans. Mater. Sci. Eng.10.12783/dtmse/smne2016/10603 ↗
19. Intelligent fault diagnosis of rotating machinery using support vector machine with ant colony algorithm for synchronous feature selection and parameter optimization10.1016/j.neucom.2015.04.069 ↗
20. Lessmann, S., Stahlbock, R., and Crone, S.F. (2006, January 16–21). Genetic algorithms for support vector machine model selection. Proceedings of the 2006 IEEE International Joint Conference on Neural Network, Vancouver, BC, Canada.10.1109/IJCNN.2006.247266 ↗
21. Autonomously Determining the Parameters for SVDD with RBF Kernel from a One-Class Training Set
22. Xiao, T., Ren, D., Lei, S., Zhang, J., and Liu, X. (July, January 29). Based on grid-search and PSO parameter optimization for Support Vector Machine. Proceedings of the 11th World Congress on Intelligent Control and Automation, Shenyang, China.
23. Panda, N.E.A. (2020). Oppositional Spotted Hyena Optimizer with Mutation Operator for Global Optimization and Application in Training Wavelet Neural Network. J. Intell. Fuzzy Syst.10.3233/JIFS-179746 ↗
24. Moayedi, H., Bui, D.T., Dounis, A., and Kalantar, B. (2019). Spotted Hyena Optimizer and Ant Lion Optimization in Predicting the Shear Strength of Soil. Appl. Sci., 9.10.3390/app9224738 ↗
25. Dhiman, G., and Chahar, V. (2019). Spotted Hyena Optimizer for Solving Complex and Nonlinear Constrained Engineering Problems: Theory and Applications. Harmony Search and Nature Inspired Optimization Algorithms, Springer.10.1007/978-981-13-0761-4_81 ↗
26. Dhiman, G., and Kaur, A. (2018). Optimizing the Design of Airfoil and Optical Buffer Problems Using Spotted Hyena Optimizer. Designs, 2.10.3390/designs2030028 ↗
27. Binary Spotted Hyena Optimizer and its Application to Feature Selection
28. Bansal, J.C., Das, K.N., Nagar, A., Deep, K., and Ojha, A.K. (2019). A Hybrid Algorithm Based on Particle Swarm and Spotted Hyena Optimizer for Global Optimization. Soft Computing for Problem Solving, Springer.
29. Divya, S., El, K., Rao, M., and Vemulapati, P. (2020). Prediction of Gene Selection Features Using Improved Multi-objective Spotted Hyena Optimization Algorithm. Data Communication and Networks, Springer.10.1007/978-981-15-0132-6_5 ↗
30. Krill herd: A new bio-inspired optimization algorithm10.1016/j.cnsns.2012.05.010 ↗
31. A comprehensive review: Krill Herd algorithm (KH) and its applications10.1016/j.asoc.2016.08.041 ↗
32. Abualigah, L.M., Khader, A.T., Al-Betar, M.A., and Awadallah, M.A. (2016, January 30–31). A krill herd algorithm for efficient text documents clustering. Proceedings of the 2016 IEEE Symposium on Computer Applications & Industrial Electronics (ISCAIE), Batu Feringghi, Malaysia.10.1109/ISCAIE.2016.7575039 ↗
33. A novel hybridization strategy for krill herd algorithm applied to clustering techniques10.1016/j.asoc.2017.06.059 ↗
34. A combination of objective functions and hybrid krill herd algorithm for text document clustering analysis10.1016/j.engappai.2018.05.003 ↗
35. Hybrid clustering analysis using improved krill herd algorithm10.1007/s10489-018-1190-6 ↗
36. Optimized cluster head selection using krill herd algorithm for wireless sensor network10.1080/00051144.2019.1637174 ↗
37. Wang, Z., Zheng, L., Wang, J., and Du, W. (2019). Research on novel bearing fault diagnosis method based on improved krill herd algorithm and kernel extreme learning machine. Complexity, 2019.10.1155/2019/4031795 ↗
38. A fault diagnosis model of power transformers based on dissolved gas analysis features selection and improved krill herd algorithm optimized support vector machine10.1109/ACCESS.2019.2927018 ↗
39. A novel nature-inspired algorithm for optimization: Squirrel search algorithm10.1016/j.swevo.2018.02.013 ↗
40. Zheng, T., and Luo, W. (2019). An improved squirrel search algorithm for optimization. Complexity, 2019.10.1155/2019/6291968 ↗
41. Intelligent design in continuous galvanizing process for advanced ultra-high-strength dual-phase steels using back-propagation artificial neural networks and MOAMP-Squirrels search algorithm10.1007/s00170-020-06002-5 ↗
42. Squirrel search algorithm for multi-region combined heat and power economic dispatch incorporating renewable energy sources10.1016/j.energy.2019.06.087 ↗
43. A hybrid algorithm based on squirrel search algorithm and invasive weed optimization for optimization10.1109/ACCESS.2019.2932198 ↗
44. Nature inspired chaotic squirrel search algorithm (CSSA) for multi objective task scheduling in an IAAS cloud computing atmosphere
45. Shen, F., Song, Z., and Zhou, L. (2013, January 25–27). Improved PCA-SVDD based monitoring method for nonlinear process. Proceedings of the 2013 25th Chinese Control and Decision Conference (CCDC), Guiyang, China.10.1109/CCDC.2013.6561713 ↗
46. Online fault diagnosis method based on Incremental Support Vector Data Description and Extreme Learning Machine with incremental output structure10.1016/j.neucom.2013.01.061 ↗
47. A semi-supervised Support Vector Data Description-based fault detection method for rolling element bearings based on cyclic spectral analysis10.1016/j.ymssp.2020.106682 ↗
48. Dhiman, G., and Chahar, V. (2017). Spotted Hyena Optimizer: A Novel Bio-inspired based Metaheuristic Technique for Engineering Applications. Adv. Eng. Softw.10.1016/j.advengsoft.2017.05.014 ↗
49. Particle Swarm Optimization
50. A new feature selection method to improve the document clustering using particle swarm optimization algorithm10.1016/j.jocs.2017.07.018 ↗
51. Abdi, L.J.W.H. (2010). Encyclopedia of Research Design, SAGE Publications.