||Turbofan Engine Physical Characteristic and Machine Learning Based Modeling for Real-Time Fault Detection and Diagnosis
||Institute of Civil Aviation
turbofan engine modeling
Engine is the heart of an aircraft, driving the generator, pumping the hydraulic system and providing compressed air for all the systems on the aircraft. The health of the engine plays an essential role in flight safety. In the past, the standard operation procedure to evaluate healthy status of the engines usually depends on some specific parameters, like inter-stage turbine temperature, low-pressure spool rotating speed or high-pressure spool rotating speed. Once part of the parameters pass over certain safety boundaries that were previously set by the manufacturers or the operators, the engine will be regarded as unhealthy. Nevertheless, in practical applications, such the threshold-style mechanism cannot reflect engine fault immediately and therefore could lead to potential flight risk. To solve this issue, a precise forecast model of the engine has to be established. Consequently, this research dedicates to develop algorithms for engine modeling as well as optimal parameters identification. For the TFE731 engine, there are three section models considered, including low pressure compressor (LPC) model, high pressure compressor (HPC) model and overall turbofan dynamics model. Those models are derived with the consideration of physical isentropic compression equation as well as a regression technique. Experiments show that a precise modeling fitting can be achieved by using regression analysis and nonlinear optimal parameter estimation. To compare the prediction stability and accuracy, associated training models by using neural network (NN) are also presented. Finally, applying real TFE731 two-spool geared turbofan engine data as the verification proves that the proposed method is able to predict the engine output precisely and fulfill the real-time diagnosis demand successfully.
ABSTRACT IN CHINESE 1
LIST OF TABLES 8
LIST OF FIGURES 9
CHAPTER 1 INTRODUCTION 14
CHAPTER 2 DATA PREPROCESSING 19
2.1 Parameter Arrangement 19
2.2 Data Validation Check 20
CHAPTER 3 PARAMETER IDENTIFICATION 23
3.1 Linear Optimal Parameter Identification 23
3.2 Nonlinear Optimal Parameter Identification 24
CHAPTER 4 TURBOFAN ENGINE MODELING 25
4.1 Engine Overall Model 25
4.2 LPC Modeling 29
4.2.1 Theoretical Outlet Temperature Model and Improvement 29
4.2.2 Cascade Temperature Model 30
4.2.3 Hammerstein Temperature Model 32
4.2.4 LPC Outlet Pressure Model 33
4.3 HPC Modeling 36
4.3.1 Theoretical Model and Improvement 36
4.3.2 Cascade Model 38
4.3.3 Hammerstein Model 39
4.3.4 HPC Outlet Pressure Model 41
4.4 Model summary 44
4.4.1 Low pressure compressor 44
4.4.2 High pressure compressor 45
4.4.3 Engine overall model 46
CHAPTER 5 MODEL COMPARISON AND FEASIBILITY TEST 46
5.1 LPC temperature model 47
5.2 LPC pressure model 53
5.3 HPC outlet temperature model 55
5.4 HPC outlet pressure model 58
5.5 Overall model 61
CHAPTER 6 BOUNDARY DESIGN 64
CHAPTER 7 RESIDUAL ANALYSIS 65
7.1 Feature Extraction 65
7.2 Classifier Design 65
7.2.1 Linear Discriminant Analysis 66
7.2.2 Gaussian Classifier 68
CHAPTER 8 FEASIBILITY TEST 69
8.1 Modeling and Parameter Setting 69
8.2 Residual Analysis 71
8.3 Result 72
CHAPTER 9 ON-LINE MONITORING APPLICATION 73
9.1 Real-time monitoring system 73
9.2 Virtual monitoring system 77
CHAPTER 10 CONCLUSIONS 82
APPENDIX A 86
APPENDIX B 88
APPENDIX C 91
 R. Seemann, S. Langhans, T. Schilling, and V. Gollnick, Modeling the Life Cycle Cost of Jet Engine Maintenance. 2011.
 D. J. Smith, "Power-by-the-hour: the role of technology in reshaping business strategy at Rolls-Royce," Technology Analysis & Strategic Management, vol. 25, no. 8, pp. 987-1007, 2013/09/01 2013.
 蔡春文, "發動機維修管理," 2018.
 H. Saravanamuttoo, H. Cohen, and G. Rogers, "The turbofan engine," in GAS TURBINE THEORY 5 ed. India: PEARSON, 2001, pp. 121-136.
 A. R. Bhat. (2017). What's the difference between jet engine and turbofan engine? Available: https://www.quora.com/Whats-the-difference-between-jet-engine-and-turbofan-engine
 R. Kurz and K. Brun, "Degradation in Gas Turbine Systems," Journal of Engineering for Gas Turbines and Power, vol. 123, no. 1, pp. 70-77, 2000.
 L. Gao, Y. Zhang, Z. Xu, and X. Gao, "Research on turbofan engine performance seeking control based on the airborne composite model," in 2015 4th International Conference on Computer Science and Network Technology (ICCSNT), 2015, vol. 01, pp. 1524-1528.
 R. Luis Fajardo and R. M. Botez, "Civil turbofan engines thrust generic model," in IECON 2012 - 38th Annual Conference on IEEE Industrial Electronics Society, 2012, pp. 5444-5450.
 X. Zhang, "Optimization on turbofan engine cycle parameter based on improved differential evolution algorithm," in 2017 17th International Conference on Control, Automation and Systems (ICCAS), 2017, pp. 556-561.
 M. Yuan, Y. Wu, and L. Lin, "Fault diagnosis and remaining useful life estimation of aero engine using LSTM neural network," in 2016 IEEE International Conference on Aircraft Utility Systems (AUS), 2016, pp. 135-140.
 X. Chang, J. Huang, and F. Lu, "Robust In-Flight Sensor Fault Diagnostics for Aircraft Engine Based on Sliding Mode Observers," Sensors, vol. 17, no. 4, 2017.
 H. Yau and M. H. Wang, "Chaotic eye-based fault forecasting method for wind power systems," IET Renewable Power Generation, vol. 9, no. 6, pp. 593-599, 2015.
 B. Jian, C. Wang, J. Chang, X. Su, and H. Yau, "Machine Tool Chatter Identification Based on Dynamic Errors of Different Self-Synchronized Chaotic Systems of Various Fractional Orders," IEEE Access, vol. 7, pp. 67278-67286, 2019.
 H. Yau, C. Wang, J. Chang, and X. Su, "A Study on the Application of Synchronized Chaotic Systems of Different Fractional Orders for Cutting Tool Wear Diagnosis and Identification," IEEE Access, vol. 7, pp. 15903-15911, 2019.
 W. Gilbert, D. Henrion, J. Bernussou, and D. Boyer, "Polynomial LPV synthesis applied to turbofan engines," Control Engineering Practice, vol. 18, no. 9, pp. 1077-1083, 2010/09/01/ 2010.
 L. Reberga, D. Henrion, J. Bernussou, and F. Vary, "Lpv Modeling of a Turbofan Engine," IFAC Proceedings Volumes, vol. 38, no. 1, pp. 526-531, 2005.
 P. Dewallef and K. Mathioudakis, On-Line Aircraft Engine Diagnostic Using a Soft-Constrained Kalman Filter. 2004.
 Q. Kun, P. Xiangping, L. Bangyuan, and X. Shousheng, "Kalman Filtering with Inequality Constraints for Certain Turbofan Engine Sensors Fault Diagnosis," in 2006 6th World Congress on Intelligent Control and Automation, 2006, vol. 2, pp. 5428-5432.
 X. Liu and N. Xue, "An improved hybrid Kalman filter design for aircraft engine based on a velocity-based LPV framework," in 2016 Chinese Control and Decision Conference (CCDC), 2016, pp. 1873-1878.
 M. A. Boyacioglu and D. Avci, "An Adaptive Network-Based Fuzzy Inference System (ANFIS) for the prediction of stock market return: The case of the Istanbul Stock Exchange," Expert Systems with Applications, vol. 37, no. 12, pp. 7908-7912, 2010.
 H.-W. Chiu and C.-H. Lee, "Prediction of machining accuracy and surface quality for CNC machine tools using data driven approach," Advances in Engineering Software, vol. 114, pp. 246-257, 2017.
 C. Kailong, X. Shousheng, and Z. Kai, "Neural Network Model Research of Some Turbofan Engine Based on Recorded Flight Data," in 2006 6th World Congress on Intelligent Control and Automation, 2006, vol. 1, pp. 1857-1860.
 X. Chang, J. Huang, and F. Lu, "Health Parameter Estimation with Second-Order Sliding Mode Observer for a Turbofan Engine," Energies, vol. 10, no. 7, 2017.
 D. W. Marquardt, "An Algorithm for Least-Squares Estimation of Nonlinear Parameters," Journal of the Society for Industrial and Applied Mathematics, vol. 11, no. 2, pp. 431-441, 1963.
 J. Lu, F. Lu, and J. Huang, "Performance Estimation and Fault Diagnosis Based on Levenberg–Marquardt Algorithm for a Turbofan Engine," Energies, vol. 11, no. 1, 2018.
 Y. Diao and K. M. Passino, "Fault diagnosis for a turbine engine," Control Engineering Practice, vol. 12, no. 9, pp. 1151-1165, 2004.
 F. Chang and R. Luus, "A noniterative method for identification using Hammerstein model," IEEE Transactions on Automatic Control, vol. 16, no. 5, pp. 464-468, 1971.
 X.-S. Luo and Y.-D. Song, "Data-driven predictive control of Hammerstein–Wiener systems based on subspace identification," Information Sciences, vol. 422, pp. 447-461, 2018.
 J. Frère and F. Hug, Between-subject variability of muscle synergies during a complex motor skill. 2012.
 A. Widodo and B.-S. Yang, "Support vector machine in machine condition monitoring and fault diagnosis," Mechanical Systems and Signal Processing, vol. 21, no. 6, pp. 2560-2574, 2007/08/01/ 2007.
 Y. Yang, D. Yu, and J. Cheng, "A fault diagnosis approach for roller bearing based on IMF envelope spectrum and SVM," Measurement, vol. 40, no. 9, pp. 943-950, 2007/11/01/ 2007.
 C. Zhang, J. H. Sun, and K. C. Tan, "Deep Belief Networks Ensemble with Multi-objective Optimization for Failure Diagnosis," in 2015 IEEE International Conference on Systems, Man, and Cybernetics, 2015, pp. 32-37.
 P. A. Lachenbruch and M. Goldstein, "Discriminant Analysis," Biometrics, vol. 35, no. 1, pp. 69-85, 1979.
 C. Peng and Y. Lin, "Dynamics Modeling and Parameter Identification of a Cooling Fan System," in 2018 IEEE International Conference on Advanced Manufacturing (ICAM), 2018, pp. 257-260.
 L. Auria and R. A. Moro, Support Vector Machines (SVM) as a Technique for Solvency Analysis. 2008.
 G. C. Cawley and N. L. C. Talbot, "On Over-fitting in Model Selection and Subsequent Selection Bias in Performance Evaluation," J. Mach. Learn. Res., vol. 11, pp. 2079-2107, 2010.