Towards Enhanced Performance of Neural-Network-Based Fault Detection Using an Sequential D-Optimum Experimental Design
Source abstract
Abstract
Increasing expectations of industrial system reliability require development of more effective and robust fault diagnosis methods. The paper presents a framework for quality improvement on the neural model applied for fault detection purposes. In particular, the proposed approach starts with an adaptation of the modified quasi-outer-bounding algorithm towards non-linear neural network models. Subsequently, its convergence is proven using quadratic boundedness paradigm. The obtained algorithm is then equipped with the sequential D-optimum experimental design mechanism allowing gradual reduction of the neural model uncertainty. Finally, an emerging robust fault detection framework on the basis of the neural network uncertainty description as the adaptive thresholds is proposed.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Fault Detection and Control Systems · Machine Fault Diagnosis Techniques · Structural Health Monitoring Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Faculty of Engineering Management, Poznan University of Technology, Strzelecka 11, 60-965 Poznan, Poland
Funding
Politechnika Poznańska
References (61)
Show source-provided references
1. Schalkoff, R. (2011). Artificial Neural Networks, McGraw-Hill Companies.
2. Haykin, S. (2009). Neural Networks and Learning Machines, Prentice Hall.
3. Nelles, O. (2001). Non-Linear Systems Identification. From Classical Approaches to Neural Networks and Fuzzy Models, Springer.
4. A Survey of Fault Diagnosis and Fault-Tolerant Techniques—Part I: Fault Diagnosis With Model-Based and Signal-Based Approaches10.1109/TIE.2015.2417501 ↗
5. A Survey of Fault Diagnosis and Fault-Tolerant Techniques—Part II: Fault Diagnosis With Knowledge-Based and Hybrid/Active Approaches10.1109/TIE.2015.2417501 ↗
6. Zolfaghari, S., Noor, S., Rezazadeh Mehrjou, M., Marhaban, M., and Mariun, N. (2018). Broken Rotor Bar Fault Detection and Classification Using Wavelet Packet Signature Analysis Based on Fourier Transform and Multi-Layer Perceptron Neural Network. Appl. Sci., 8.10.3390/app8010025 ↗
7. Farrar, C., and Worden, K. (2012). Structural Health Monitoring: A Machine Learning Perspective, John Wiley & Sons.10.1002/9781118443118 ↗
8. Blanke, M., and Schröder, J. (2006). Diagnosis and Fault-Tolerant Control, Springer.
9. Patton, R.J., Frank, P.M., and Clark, R.N. (2000). Issues of Fault Diagnosis for Dynamic Systems, Springer.10.1007/978-1-4471-3644-6 ↗
10. Qi, X., Theilliol, D., Qi, J., Zhang, Y., Han, J., Song, D., Wang, L., and Xia, Y. (2013, January 9–11). Fault diagnosis and fault tolerant control methods for manned and unmanned helicopters: A literature review. Proceedings of the 2013 Conference on Control and Fault-Tolerant Systems (SysTol), Nice, France.10.1109/SysTol.2013.6693906 ↗
11. Isermann, R. (2011). Fault Diagnosis Applications: Model Based Condition Monitoring, Actuators, Drives, Machinery, Plants, Sensors, and Fault-Tolerant Systems, Springer.10.1007/978-3-642-12767-0 ↗
12. Cao, M.S., Ding, Y.J., Ren, W.X., Wang, Q., Ragulskis, M., and Ding, Z.C. (2017). Hierarchical Wavelet-Aided Neural Intelligent Identification of Structural Damage in Noisy Conditions. Appl. Sci., 7.10.3390/app7040391 ↗
13. Sutton, R., and Barto, A. (2018). Reinforcement Learning, An Introduction, The MIT Press. [2nd ed.].
14. On the value of information in system identification? bounded noise case10.1016/0005-1098(82)90110-8 ↗
15. Milanese, M., Norton, J., Piet-Lahanier, H., and Walter, E. (1996). Bounding Approaches to System Identification, Plenum Press.10.1007/978-1-4757-9545-5 ↗
16. Bounded error identification of Hammerstein systems through sparse polynomial optimization10.1016/j.automatica.2012.06.078 ↗
17. Modified quasi-OBE Algorithm with Improved Numerical Properties10.1016/j.sigpro.2012.09.024 ↗
18. Automated finite element model updating of a scale bridge model using measured static and modal test data10.1016/j.engstruct.2015.07.029 ↗
19. Sohn, H., Farrar, C.R., Hemez, F.M., Shunk, D.D., Stinemates, D.W., Nadler, B.R., and Czarnecki, J.J. (2003). A Review of Structural Health Monitoring Literature: 1996–2001.10.1117/12.434158 ↗
20. On robust regression analysis as a means of exploring environmental and operational conditions for SHM data10.1016/j.jsv.2015.02.039 ↗
21. Damage detection in a girder bridge by artificial neural network technique10.1111/j.1467-8667.2006.00449.x ↗
22. Walter, E., and Pronzato, L. (1997). Identification of Parametric Models from Experimental Data, Springer.
23. Atkinson, A.C., and Donev, A.N. (1992). Optimum Experimental Designs, Oxford University Press.
24. Robust Fault Detection: Active Versus Passive Approaches10.1016/S1474-6670(17)37353-6 ↗
25. Passive robust fault detection using interval observers: Application to the DAMADICS benchmark problem10.1016/j.conengprac.2005.03.016 ↗
26. Active Robust Fault Detection in Closed-Loop Systems: Quadratic Optimization Approach10.1109/TAC.2012.2188430 ↗
27. A combined passive-active sensor fault detection and isolation approach for air handling units10.1016/j.enbuild.2015.04.035 ↗
28. Actuator fault detection and isolation: An optimised parity space approach10.1016/j.conengprac.2014.01.013 ↗
29. Real-Time Fault Detection Approach for Nonlinear Systems and its Asynchronous T-S Fuzzy Observer-Based Implementation
30. Actuator fault estimation based adaptive polytopic observer for a class of LPV descriptor systems10.1002/rnc.3236 ↗
31. Set-membership parity space approach for fault detection in linear uncertain dynamic systems10.1002/acs.2476 ↗
32. An Interval NLPV Parity Equations Approach for Fault Detection and Isolation of a Wind Farm
33. Effect of model uncertainty on failure detection: The threshold selector10.1109/9.14432 ↗
34. Observer-Based Phase-Shift Fault Detection Using Adaptive Threshold for Rotor Position Sensor of Permanent-Magnet Synchronous Machine Drives in Electromechanical Brake10.1109/TIE.2014.2350453 ↗
35. Speed and Current Sensor Fault Detection and Isolation Technique for Induction Motor Drive Using Axes Transformation10.1109/TIE.2014.2345337 ↗
36. Fault detection for nonlinear networked systems based on quantization and dropout compensation: An interval type-2 fuzzy-model method10.1016/j.neucom.2016.01.061 ↗
37. Robust fault detection in bond graph framework using interval analysis and Fourier-Motzkin elimination technique10.1016/j.ymssp.2017.02.022 ↗
38. Witczak, M. (2014). Fault Diagnosis and Fault-Tolerant Control Strategies for Non-Linear Systems. Lectures Notes in Electrical Engineering, Springer.10.1007/978-3-319-03014-2 ↗
39. Kamali, A.J., Longpré, L., and Koshelev, M. (2011, January 18–20). Estimating mean under interval uncertainty and variance constraint. Proceedings of the 2011 Annual Meeting of the North American Fuzzy Information Processing Society, El Paso, TX, USA.10.1109/NAFIPS.2011.5752029 ↗
40. Bolajraf, M., Rami, M.A., and Tadeo, F. (2010, January 23–25). Robust interval observer with uncertainties in the output. Proceedings of the 18th Mediterranean Conference on Control Automation (MED), Marrakech, Morocco.10.1109/MED.2010.5547617 ↗
41. An artificial NN based approach to fault diagnosis and classification of fluid power systems
42. Neural networks for fault diagnosis of a nuclear fuel processing plant at different operating points10.1016/S0967-0661(97)00003-8 ↗
43. Diagnosis of process valve actuator faults using a multilayer neural network10.1016/S0967-0661(02)00245-9 ↗
44. Gupta, M., Liang, J., and Homma, N. (2004). Static and Dynamic Neural Networks: From Fundamentals to Advanced Theory, Wiley-IEEE Press.10.1002/0471427950 ↗
45. The cascade-correlation learning architecture
46. A convergence theorem for sequential learning in two-layer perceptrons10.1209/0295-5075/11/6/001 ↗
47. Touretzky, D. (1989). Second order derivaties for network prunning: Optimal brain surgeon. Advances in Neural Information Processing Systems 1, Morgan Kaufmann.
48. Learning feedforward layered networks: The tiling algorithm
49. Multilayer Feed-Forward Artificial Neural Network Integrated with Sensitivity Based Connection Pruning Method10.1007/978-3-642-35615-5_10 ↗
50. Teodorescu, H., Mlynek, D., Kandel, A., and Zimmermann, H. (2000). Diagnosis strategies and systems. Principles, fuzzy and neural approaches. Intelligent Systems and Interfaces, Kluwer Academic Publishers.10.1007/978-1-4615-4401-2 ↗
51. Design of state estimators for uncertain linear systems using quadratic boundedness10.1016/j.automatica.2005.10.013 ↗
52. Principal minors, Part I: A method for computing all the principal minors of a matrix10.1016/j.laa.2006.04.008 ↗
53. Fedorov, V.V., and Hackl, P. (1997). Model-Oriented Design of Experiments, Springer.10.1007/978-1-4612-0703-0 ↗
54. Vuchkov, I.N., and Boyadjieva, L.N. (2002). Quality Improvement with Design of Experiments: A Response Surface Approach, Kluwer Academic Publishers.
55. Minimization by random search techniques10.1287/moor.6.1.19 ↗
56. Kleinmann, S., Fairusz Abdul Jalal, M., and Stetter, J. (2010, January 18–19). Modelling of positive displacement pumps for monitoring, planning, control and diagnosis. Proceedings of the 8th ACD 2010 European Workshop on Advanced Control and Diagnosis, Ferrara, Italy.
57. Gao, M., Tian, J., Cao, L., and Zhang, F. (2008, January 18–20). The Fault Diagnosis System with Self-Repair Function for Screw Oil Pump Based on Fuzzy Neural Network. Proceedings of the 2008 3rd International Conference on Innovative Computing Information and Control, Dalian, China.10.1109/ICICIC.2008.554 ↗
58. Karimaghaee, P., Hosseinzadeh, A., Amidi, A., and Roshandel, E. (2017, January 21–23). Adaptive control application on syringe pump pressure control systems in oil and gas industries. Proceedings of the 2017 5th International Conference on Control, Instrumentation, and Automation (ICCIA), Fars, Iran.10.1109/ICCIAutom.2017.8258689 ↗
59. Wi, J., Kim, H., Yoo, J., Son, H., Kim, H., and Kim, B. (2018, January 10–12). Energy consumption of parallel type hybrid electric vehicle with continuously variable transmission using electric oil pump. Proceedings of the 2018 13th International Conference on Ecological Vehicles and Renewable Energies (EVER), Monte-Carlo, Monaco.10.1109/EVER.2018.8362364 ↗
60. A model-based fault detection and prognostics scheme for Takagi–Sugeno fuzzy systems10.1109/TFUZZ.2013.2272584 ↗
61. Survey of robust residual generation and evaluation methods in observer-based fault detection systems10.1016/S0959-1524(97)00016-4 ↗