Soft Computing Application for Gas Path Fault Isolation
Volume 2: Turbo Expo 2004, 2004
A fuzzy system that automatically develops its rule base from a linearized performance model of t... more A fuzzy system that automatically develops its rule base from a linearized performance model of the engine by selecting the membership functions and number of fuzzy sets is developed in this study to perform gas turbine fault isolation. 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’. A genetic algorithm is used to tune the fuzzy sets to maximize fault isolation success rate. A novel scheme is developed which optimizes the fuzzy system using very few design variables and therefore is computationally efficient. Results with simulated data show that genetic fuzzy system isolates faults with accuracy greater than that of a manually developed fuzzy system developed by the authors. Furthermore, the genetic fuzzy system allows rapid develo...
A finite element based approach is used to simulate the evolution of low cycle fatigue damage in ... more A finite element based approach is used to simulate the evolution of low cycle fatigue damage in a turbine blade. The turbine blade is modelled as a rotating Timoshenko beam with taper and twist. A damage growth model for low cycle fatigue damage developed using a continuum mechanics approach is integrated with the finite element model. Numerical results are obtained to study the effect of damage growth on the rotating frequencies. It is found that low cycle fatigue causes sufficient degradation in blade stiffness for changes in rotating frequency to be used as an indicator to track damage growth. Continuum damage mechanics models in conjunction with finite element analysis are used to develop thresholds for damage indicators. By placing suitable threshold on the frequency change, it is possible to detect the onset of the final stage of damage in the structure before failure occurs.
Structural damage in materials evolves over time due to growth of fatigue cracks in homogenous ma... more Structural damage in materials evolves over time due to growth of fatigue cracks in homogenous materials and a complicated process of matrix cracking, delamination, fiber breakage and fiber matrix debonding in composite materials. In this study, a finite element model of the helicopter rotor blade is used to analyze the effect of damage growth on the modal frequencies in a qualitative manner. Phenomenological models of material degradation for homogenous and composite materials are used. Results show that damage can be detected by monitoring changes in lower as well as higher mode flap (outof-plane bending), lag (in-plane bending) and torsion rotating frequencies, especially for composite materials where the onset of the last stage of damage of fiber breakage is most critical. Curve fits are also proposed for mathematical modeling of the relationship between rotating frequencies and cycles. Finally, since operational data are noisy and also contaminated with outliers, denoising algorithms based on recursive median filters and radial basis function neural networks and wavelets are studied and compared with a moving average filter using simulated data for improved health-monitoring application. A novel recursive median filter is designed using integer programming through genetic algorithm and is found to have comparable performance to neural networks with much less complexity and is better than wavelet denoising for outlier removal. This filter is proposed as a tool for denoising time series of damage indicators.
The problem of denoising damage indicator signals for improved operational health monitoring of s... more The problem of denoising damage indicator signals for improved operational health monitoring of systems is addressed by applying soft computing methods to design filters. Since measured data in operational settings is contaminated with noise and outliers, pattern recognition algorithms for fault detection and isolation can give false alarms. A direct approach to improving the fault detection and isolation is to remove noise and outliers from time series of measured data or damage indicators before performing fault detection and isolation. Many popular signal-processing approaches do not work well with damage indicator signals, which can contain sudden changes due to abrupt faults and non-Gaussian outliers. Signal-processing algorithms based on radial basis function (RBF) neural network and weighted recursive median (WRM) filters are explored for denoising simulated time series. The RBF neural network filter is developed using a K-means clustering algorithm and is much less computationally expensive to develop than feedforward neural networks trained using backpropagation. The nonlinear multimodal integer-programming problem of selecting optimal integer weights of the WRM filter is solved using genetic algorithm. Numerical results are obtained for helicopter rotor structural damage indicators based on simulated frequencies. Test signals consider low order polynomial growth of damage indicators with time to simulate gradual or incipient faults and step changes in the signal to simulate abrupt faults. Noise and outliers are added to the test signals. The WRM and RBF filters result in a noise reduction of 54-71 and 59-73% for the test signals considered in this study, respectively. Their performance is much better than the moving average FIR filter, which causes significant feature distortion and has poor outlier removal capabilities and shows the potential of soft computing methods for specific signal-processing applications.
A fuzzy system is developed using a linearized performance model of the gas turbine engine for pe... more 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 Ôgood engineÕ. 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)
A fuzzy system that automatically develops its rule base from a linearized performance model of t... more A fuzzy system that automatically develops its rule base from a linearized performance model of the engine by selecting the membership functions and number of fuzzy sets is developed in this study to perform gas turbine fault isolation. 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'. A genetic algorithm is used to tune the fuzzy sets to maximize fault isolation success rate. A novel scheme is developed which optimizes the fuzzy system using very few design variables and therefore is computationally efficient. Results with simulated data show that genetic fuzzy system isolates faults with accuracy greater than that of a manually developed fuzzy system. Furthermore, the genetic fuzzy system allows rapid development of the rule base if the fault signatures and measurement uncertainties change. In addition, the genetic fuzzy system reduces the human effort needed in the trial and error process used to design the fuzzy system. A radial basis neural network is also used to preprocess the measurements before fault isolation. The radial basis network shows significant noise reduction and when combined with the genetic fuzzy system leads to a diagnostic system that is highly robust to the presence of noise in data.
Uploads
Papers by Niranjan Roy