Gas turbine diagnostics using a soft computing approach

A fuzzy system is developed using a linearized performance model of the gas turbine engine for performing gas turbine fault isolation from noisy measurements. By using a priori information about measurement uncertainties and through design variable linking, the design of the fuzzy system is posed as an optimization problem with low number of design variables which can be solved using the genetic algorithm in considerably low amount of computer time. The faults modeled are module faults in five modules: fan, low pressure compressor, high pressure compressor, high pressure turbine and low pressure turbine. The measurements used are deviations in exhaust gas temperature, low rotor speed, high rotor speed and fuel flow from a base line 'good engine'. The genetic fuzzy system (GFS) allows rapid development of the rule base if the fault signatures and measurement uncertainties change which happens for different engines and airlines. In addition, the genetic fuzzy system reduces the human effort needed in the trial and error process used to design the fuzzy system and makes the development of such a system easier and faster. A radial basis function neural network (RBFNN) is also used to preprocess the measurements before fault isolation. The RBFNN shows significant noise reduction and when combined with the GFS leads to a diagnostic system that is highly robust to the presence of noise in data. Showing the advantage of using a soft computing approach for gas turbine diagnostics

[1]  Mo M. Jamshidi.  Autonomous control of complex systems: robotic applications , 2001, Appl. Math. Comput..

[2]  C. L. Philip Chen,et al.  The equivalence between fuzzy logic systems and feedforward neural networks , 2000, IEEE Trans. Neural Networks Learn. Syst..

[3]  David L. Doel,et al.  TEMPER - A gas-path analysis tool for commercial jet engines , 1992 .

[4]  Allan J. Volponi,et al.  Mathematical Methods of Relative Engine Performance Diagnostics , 1992 .

[5]  Mei Zhao,et al.  A niche hybrid genetic algorithm for global optimization of continuous multimodal functions , 2005, Appl. Math. Comput..

[6]  Anastassios G. Stamatis,et al.  Turbofan Performance Deterioration Tracking Using Nonlinear Models and Optimization Techniques , 2002 .

[7]  Ph. Kamboukos,et al.  Turbofan Performance Deterioration Tracking Using Non-Linear Models and Optimization Techniques , 2002 .

[8]  Yi-Guang Li,et al.  Performance-analysis-based gas turbine diagnostics: A review , 2002 .

[9]  Ranjan Ganguli,et al.  Jet Engine Gas-Path Measurement Filtering Using Center Weighted Idempotent Median Filters , 2003 .

[10]  Prabhat Hajela,et al.  Soft computing in multidisciplinary aerospace design—new directions for research , 2002 .

[11]  Ranjan Ganguli,et al.  Genetic fuzzy system for damage detection in beams and helicopter rotor blades , 2003 .

[12]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[13]  David L. Doel.  Interpretation of Weighted-Least-Squares Gas Path Analysis Results , 2003 .

[14]  Ranjan Ganguli,et al.  An automated hybrid genetic-conjugate gradient algorithm for multimodal optimization problems , 2005, Appl. Math. Comput..

[15]  Michele Pinelli,et al.  Gas Turbine Field Performance Determination: Sources of Uncertainties , 2000 .

[16]  D. E. Goldberg,et al.  Genetic Algorithms in Search , 1989 .

[17]  Zong-Yi Lee.  Applying the double side method of weighted residual to the solution of shell deformation problem , 2005, Appl. Math. Comput..

[18]  Riti Singh,et al.  Advanced engine diagnostics using artificial neural networks , 2003, Appl. Soft Comput..

[19]  Jinwu Gao,et al.  Fuzzy quadratic minimum spanning tree problem , 2005, Appl. Math. Comput..

[20]  Hans R. Depold,et al.  The Application of Expert Systems and Neural Networks to Gas Turbine Prognostics and Diagnostics , 1998 .

[21]  Lucien Duckstein,et al.  A fuzzy approach to the definition of standardized visibility in fog , 1994 .

[22]  Allan J. Volponi,et al.  The Use of Kalman Filter and Neural Network Methodologies in Gas Turbine Performance Diagnostics: A Comparative Study , 2000 .

[23]  Klaus Brun,et al.  Degradation in Gas Turbine Systems , 2001 .

[24]  Xin Li,et al.  On simultaneous approximations by radial basis function neural networks , 1998, Appl. Math. Comput..

[25]  Yoshiki Uchikawa,et al.  A Fuzzy Classifier System for evolutionary learning of robot behaviors , 1998 .

[26]  Fred J. Hickernell,et al.  Radial basis function approximations as smoothing splines , 1999, Appl. Math. Comput..

[27]  Ranjan Ganguli,et al.  Application of Fuzzy Logic for Fault Isolation of Jet Engines , 2001 .

[28]  Stephen Ogaji,et al.  Engine-fault diagnostics:an optimisation procedure , 2002 .

[29]  P. Hajela.  Nongradient Methods in Multidisciplinary Design Optimization-Status and Potential , 1999 .

[30]  Jin Zhang,et al.  An Evaluation of Engine Faults Diagnostics Using Artificial Neural Networks , 2001 .

[31]  Lotfi A. Zadeh,et al.  Fuzzy logic = computing with words , 1996, IEEE Trans. Fuzzy Syst..

[32]  Lyle H. Ungar,et al.  Using radial basis functions to approximate a function and its error bounds , 1992, IEEE Trans. Neural Networks.

[33]  Cheng-Shion Shieh,et al.  Genetic fuzzy control for time-varying delayed uncertain systems with a robust stability safeguard , 2002, Appl. Math. Comput..

[34]  K. Mathioudakis,et al.  Setting Up of a Probabilistic Neural Network for Sensor Fault Detection Including Operation With Component Faults , 2002 .

[35]  Ranjan Ganguli.  Application of Fuzzy Logic for Fault Isolation of Jet Engines , 2001 .

[36]  Salam Sawadogo,et al.  Long-term fuzzy management of water resource systems , 2003, Appl. Math. Comput..

[37]  K. Mathioudakis,et al.  Setting up of a probabilistic neural network for sensor fault detection including operation with component faults , 2003 .

[38]  Pong-Jeu Lu,et al.  Application of Autoassociative Neural Network on Gas-Path Sensor Data Validation , 2002 .

[39]  Clarence W de Silva.  The role of soft computing in intelligent machines , 2003, Philosophical Transactions of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[40]  Hans R. Depold,et al.  The Application of Expert Systems and Neural Networks to Gas Turbine Prognostics and Diagnostics , 1998 .