DOI QR코드

DOI QR Code

Faults detection and identification for gas turbine using DNN and LLM

  • Received : 2018.07.21
  • Accepted : 2019.03.09
  • Published : 2019.04.25

Abstract

Applying more features gives us better accuracy in modeling; however, increasing the inputs causes the curse of dimensions. In this paper, a new structure has been proposed for fault detecting and identifying (FDI) of high-dimensional systems. This structure consist of two structure. The first part includes Auto-Encoders (AE) as Deep Neural Networks (DNNs) to produce feature engineering process and summarize the features. The second part consists of the Local Model Networks (LMNs) with LOcally LInear MOdel Tree (LOLIMOT) algorithm to model outputs (multiple models). The fault detection is based on these multiple models. Hence the residuals generated by comparing the system output and multiple models have been used to alarm the faults. To show the effectiveness of the proposed structure, it is tested on single-shaft industrial gas turbine prototype model. Finally, a brief comparison between the simulated results and several related works is presented and the well performance of the proposed structure has been illustrated.

Keywords

References

  1. Adeniran, A.A. and El Ferik, S. (2017). "Modeling and identification of nonlinear systems: A review of the multimodel approach-Part 1", IEEE T. Syst, Man, Cy. : Syst., 47(7), 1149-1159. https://doi.org/10.1109/TSMC.2016.2560147
  2. Ahmadi, S. and Karrari, M. (2012), "An iterative approach to determine the complexity of local models for robust identification of nonlinear systems", Int. J. Control, Autom. Syst., 10(1), 1-10. https://doi.org/10.1007/s12555-012-0101-6
  3. Alizadeh, S., Kalhor, A., Jamalabadi, H., Araabi, B.N. and Ahmadabadi, M.N. (2016), "Online local input selection through evolving heterogeneous fuzzy inference system", IEEE T. Fuzzy Syst., 24(6), 1364-1377. https://doi.org/10.1109/TFUZZ.2016.2516580
  4. Aydin, K. and Kisi, O. (2015), "Damage detection in structural beam elements using hybrid neuro fuzzy systems", Smart Struct. Syst., 16(6), 1107-1132. https://doi.org/10.12989/sss.2015.16.6.1107
  5. Baghernezhad, F. and Khorasani, K. (2016), "Computationally intelligent strategies for robust fault detection, isolation, and identification of mobile robots", Neurocomput., 171, 335-346. https://doi.org/10.1016/j.neucom.2015.06.050
  6. Banfer, O. and Nelles, O. (2009), "Polynomial model tree (POLYMOT)-A new training algorithm for local model networks with higher degree polynomials", Proceedings of the 2009 IEEE International Conference on Control and Automation.
  7. Bengio, Y., Courville, A. and Vincent, P. (2013), "Representation earning: A review and new perspectives", IEEE T. Pattern Anal. Machine Intel., 35(8), 1798-1828. https://doi.org/10.1109/TPAMI.2013.50
  8. Bengio, Y., Lamblin, P., Popovici, D. and Larochelle, H. (2007), "Greedy layer-wise training of deep networks", Adv. Neural Inform. Process. Syst., 153-160
  9. Breiman, L. (1993), "Hinging hyperplanes for regression, classification, and function approximation", IEEE T. Inform. Theory 39(3), 999-1013. https://doi.org/10.1109/18.256506
  10. Chang, C.M., Chou, J.Y., Tan, P. and Wang, L. (2017), "A sensor fault detection strategy for structural health monitoring systems", Smart Struct. Syts., 20(1), 43-52.
  11. Erhan, D., Manzagol, P.A., Bengio, Y., Bengio, S. and Vincent, P. (2009), "The difficulty of training deep architectures and the effect of unsupervised pre-training", Artif. Intell. Stat., 153-160
  12. Ernst, S. (1998), "Hinging hyperplane trees for approximation and identification", Decision and Control, 1998. Proceedings of the 37th IEEE Conference on, 2, 1266-1271.
  13. Fischer, T., Hartmann, B. and Nelles, O. (2012), "Increasing the Performance of a Training Algorithm for Local Model Networks", Proceedings of the World Congress of Engineering and Computer Science (WCECS), San Francisco, USA.
  14. Goroshin, R. and LeCun, Y. (2013), "Saturating auto-encoders", arXiv preprint arXiv, 1301.3577.
  15. Han, T., Jiang, D., Zhao, Q., Wang, L. and Yin, K. (2018), "Comparison of random forest, artificial neural networks and support vector machine for intelligent diagnosis of rotating machinery", T. Inst. Measurement Control 40(8), 2681-2693. https://doi.org/10.1177/0142331217708242
  16. Hartmann, B., Ebert, T., Fischer, T., Belz, J., Kampmann, G. and Nelles, O. (2014), "LMNTOOL-Toolbox zum automatischen Trainieren lokaler Modellnetze", Proceedings of the 22. Workshop Computational Intelligence (Hoffmann, F.; Hullermeier, E., Hg.),
  17. Hartmann, B. and Nelles, O. (2009), "Advantages of hierarchical versus flat model structures for high-dimensional mappings", Workshop Computational Intelligence. Bommerholz.
  18. Hartmann, B. and Nelles, O. (2009), "On the smoothness in local model networks", Proceedings of the American Control Conference (ACC), St. Louis, USA (June 2009).
  19. Hartmann, B. and Nelles, O. (2012), "Structure trade-off strategy for local model networks", Proceedings of the Control Applications (CCA), 2012 IEEE International Conference on.
  20. Hartmann, B., Nelles, O., Skrjanc, I. and Sodja, A. (2009), "Supervised hierarchical clustering (SUHICLUST) for nonlinear system identification", Proceedings of the 2009 IEEE Symposium on Computational Intelligence in Control and Automation.
  21. Hinton, G.E. and Salakhutdinov, R.R. (2006), "Reducing the dimensionality of data with neural networks", Science, 313(5786), 504-507. https://doi.org/10.1126/science.1127647
  22. Huang, H.B., Yi, T.H. and Li, H.N. (2015), "Sensor fault diagnosis for structural health monitoring based on statistical hypothesis test and missing variable approach", J. Aerosp. Eng., 30(2), B4015003. https://doi.org/10.1061/(ASCE)AS.1943-5525.0000572
  23. Huang, H.B., Yi, T.H. and Li, H.N. (2016), "Canonical correlation analysis based fault diagnosis method for structural monitoring sensor networks", Smart Struct. Syst., 7(6), 1031-1053. https://doi.org/10.12989/sss.2016.17.6.1031
  24. Jakubek, S. and Keuth, N. (2006), "A local neuro-fuzzy network for high-dimensional models and optimization", Eng. Appl. Artif. Intel., 19(6), 705-717. https://doi.org/10.1016/j.engappai.2005.12.014
  25. Johansen, T.A. and Foss, B.A. (1995), "Identification of non-linear system structure and parameters using regime decomposition", Automatica, 31(2), 321-326. https://doi.org/10.1016/0005-1098(94)00096-2
  26. Jung, U. and Koh, B.H. (2014), "Bearing fault detection through multiscale wavelet scalogram-based SPC", Smart Struct. Syst., 14(3), 377-395. https://doi.org/10.12989/sss.2014.14.3.377
  27. Kavukcuoglu, K., Fergus, R. and LeCun, Y. (2009), "Learning invariant features through topographic filter maps", Proceedings of the Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on, 1605-1612.
  28. Kavukcuoglu, K., Ranzato, M.A. and LeCun, Y. (2010), "Fast inference in sparse coding algorithms with applications to object recognition", arXiv preprint arXiv,1010.3467.
  29. Konda, K., Memisevic, R. and Krueger, D. (2014). "Zero-bias autoencoders and the benefits of co-adapting features." arXiv preprint arXiv:1402.3337.
  30. Mehran, R., Fatehi, A., Lucas, C. and Araabi, B.N. (2006), "Particle swarm extension to LOLIMOT", Proceedings of the 6th International Conference on Intelligent Systems Design and Applications.
  31. Mohammadzadeh1a, S. and Kim, Y. (2015), "PCA-based neurofuzzy model for system identification of smart structures", Smart Struct. Syst., 15(4), 1139-1158. https://doi.org/10.12989/sss.2015.15.4.1139
  32. Mutlu, B., Sezer, E.A. and Nefeslioglu, H.A. (2016), "A defuzzification-free hierarchical fuzzy system (DF-HFS): Rock mass rating prediction", Fuzzy Set. Syst., 307, 50-66. https://doi.org/10.1016/j.fss.2016.01.001
  33. Nelles, O. (2006), "Axes-oblique partitioning strategies for local model networks", Proceedings of the 2006 IEEE Conference on Computer Aided Control System Design, 2006 IEEE International Conference on Control Applications, 2006 IEEE International Symposium on Intelligent Control.
  34. Nelles, O. (2013), "Nonlinear system identification: from classical approaches to neural networks and fuzzy models", Springer Science & Business Media.
  35. Nelles, O. and Hartmann, B. (2012), "Structure trade-off strategy for local model networks", Proceedings of the IEEE International Conference on Control Applications (CCA), Dubrovnik, Croatia, Part of 2012 IEEE Multi-Conference on Systems and Control.
  36. Nelles, O., Sinsel, S. and Isermann, R. (1996), "Local basis function networks for identification of a turbocharger", Proceedings of the Control'96, UKACC International Conference on (Conf. Publ. No. 427), IET 7-12.
  37. Ng, A. (2011), "Sparse Autoencoder", vol. 72 of. CS294A Lecture Notes.
  38. Nozari, H.A., Shoorehdeli, M.A., Simani, S. and Banadaki, H.D. (2012), "Model-based robust fault detection and isolation of an industrial gas turbine prototype using soft computing techniques", Neurocomput., 91, 29-47. https://doi.org/10.1016/j.neucom.2012.02.014
  39. Palade, V., Patton, R.J., Uppal, F.J., Quevedo, J. and Daley, S. (2002), "Fault diagnosis of an industrial gas turbine using neuro-fuzzy methods", IFAC Proceedings Volumes, 35(1), 471-476.
  40. Poultney, C., Chopra, S. and Cun, Y. L. (2007), "Efficient learning of sparse representations with an energy-based model", Adv. neural information processing syst., 1137-1144.
  41. Pourbabaee, B., Meskin, N. and Khorasani, K. (2013), "Multiplemodel based sensor fault diagnosis using hybrid kalman filter approach for nonlinear gas turbine engines", Proceedings of the 2013 American Control Conference, IEEE 4717-4723.
  42. Rezaie, J., Moshiri, B., Rafati, A. and Araabi, B.N. (2007), "Modified LOLIMOT algorithm for nonlinear centralized Kalman filtering fusion", Proceedings of the Information Fusion, 2007 10th International Conference on, IEEE 1-8.
  43. Rifai, S., Vincent, P., Muller, X., Glorot, X. and Bengio, Y. (2011), "Contractive auto-encoders: Explicit invariance during feature extraction", Proceedings of the 28th International Conference on International Conference on Machine Learning, Omnipress 833-840.
  44. Saleh, A.E., Moustafa, M.S., Abo-Al-Ez, K.M. and Abdullah, A. A. (2016), "A hybrid neuro-fuzzy power prediction system for wind energy generation", Int. J. Elec. Power Energy Syst., 74, 384-395. https://doi.org/10.1016/j.ijepes.2015.07.039
  45. Sarabi-Jamab, A. and Araabi, B.N. (2011), "PiLiMoT: A modified combination of LoLiMoT and PLN learning algorithms for local linear neurofuzzy modeling", J, Control Sci. Eng., 2011.
  46. Shen, C., Wang, D., Liu, Y., Kong, F. and Tse, P.W. (2014), "Recognition of rolling bearing fault patterns and sizes based on two-layer support vector regression machines", Smart Struct. Syst., 13(3), 453-471. https://doi.org/10.12989/sss.2014.13.3.453
  47. Simani, S. (2005), "Identification and fault diagnosis of a simulated model of an industrial gas turbine", IEEE T. Ind. Inform., 1(3), 202-216. https://doi.org/10.1109/TII.2005.844425
  48. Simani, S. and Fantuzzi, C. (2006), "Dynamic system identification and model-based fault diagnosis of an industrial gas turbine prototype", Mechatronics, 16(6), 341-363. https://doi.org/10.1016/j.mechatronics.2006.01.002
  49. Simani, S., Fantuzzi, C. and Patton, R.J. (2003), "Model-based fault diagnosis in dynamic systems using identification techniques", Springer, 19-60.
  50. Simani, S., Fantuzzi, C. and Spina, R. (1998), "Application of a neural network in gas turbine control sensor fault detection", Control Applications, 1998. Proceedings of the 1998 IEEE International Conference on, IEEE, 1, 182-186.
  51. Simani, S. and Patton, R.J. (2008), "Fault diagnosis of an industrial gas turbine prototype using a system identification approach", Control Eng. Pract., 16(7), 769-786. https://doi.org/10.1016/j.conengprac.2007.08.009
  52. Vincent, P., Larochelle, H., Bengio, Y. and Manzagol, P.A. (2008), "Extracting and composing robust features with denoising autoencoders", Proceedings of the 25th international conference on Machine learning, ACM 1096-1103.
  53. Yi, T.H., Huang, H.B. and Li, H.N. (2017), "Development of sensor validation methodologies for structural health monitoring: A comprehensive review", Measurement, 109, 200-214. https://doi.org/10.1016/j.measurement.2017.05.064
  54. Yi, T.H., Ye, X., Li, H.N. and Guo, Q. (2017), "Outlier detection of GPS monitoring data using relational analysis and negative selection algorithm", Smart Struct. Syst., 20(2), 219-229. https://doi.org/10.12989/SSS.2017.20.2.219
  55. Zhang, Q., Yang, L.T., Chen, Z. and Li, P. (2018), "A survey on deep learning for big data", Inform. Fusion, 42, 146-157. https://doi.org/10.1016/j.inffus.2017.10.006