A thrust estimator with high precision and excellent real-time performance is needed to mitigate perfor- mance deterioration for future aero-engines. A weight least squares support vector regression is proposed using ...A thrust estimator with high precision and excellent real-time performance is needed to mitigate perfor- mance deterioration for future aero-engines. A weight least squares support vector regression is proposed using a novel weighting strategy. Then a thrust estimator based on the proposed regression is designed for the perfor- mance deterioration. Compared with the existing weighting strategy, the novel one not only satisfies the require- ment of precision but also enhances the real-time performance. Finally, numerical experiments demonstrate the effectiveness and feasibility of the proposed weighted least squares support vector regression for thrust estimator. Key words : intelligent engine control; least squares ; support vector machine ; performance deterioration展开更多
A new particle deposition model, namely partial deposition model, is developed in order to improve the accuracy of prediction to particle deposition. Concepts of critical velocity and critical angle are proposed and u...A new particle deposition model, namely partial deposition model, is developed in order to improve the accuracy of prediction to particle deposition. Concepts of critical velocity and critical angle are proposed and used to determine whether particles are deposited or not. The comparison of numerical results calculated by partial deposition model and existing deposition model shows that the deposition distribution obtained by partial deposition model is more reasonable. Based on the predicted deposition results, the change of total pressure loss coefficient with operating time and the distribution of pressure coefficients on blade surface after 500 hours are predicted by using partial deposition model.展开更多
Surface roughness is a critical health parameter of a turbine blade due to its implications on blade surface heat transfer and structural integrity.This paper proposes a physics-based online framework for Gas Turbine ...Surface roughness is a critical health parameter of a turbine blade due to its implications on blade surface heat transfer and structural integrity.This paper proposes a physics-based online framework for Gas Turbine Engines(GTE),in order to assess the blade surface roughness in a highpressure turbine without engine shutdown.The framework consolidates Gas Path Analysis(GPA)based performance monitoring models and meanline turbomachinery analysis,using a novel GPAmeanline matching process.This extracts meaningful performance deviation trends from GPA,while addressing the uncertainties associated with the measurements and modelling.To relate efficiency loss to surface roughness severity,a meanline-based system-identification process has been developed to establish the meanline representation of the turbine stage,and to incorporate the empirical surface roughness loss correlations.The roughness loss correlations have been evaluated against recent transonic test data in the literature.A modification to the compressibility correction factor has been made according to the evaluation outcome,which improved loss predictions compared to the experimental measurements.The framework was tested on the three-year operational data of a cogeneration GTE,and the results verified the framework’s potential for online surface roughness monitoring.The predicted surface roughness showed agreement in both trend and the magnitude-level with the measurements reported in the literature.展开更多
基金Supported by the National Natural Science Foundation of China(51006052)the Nanjing University of Science and Technology Outstanding Scholar Supporting Program~~
文摘A thrust estimator with high precision and excellent real-time performance is needed to mitigate perfor- mance deterioration for future aero-engines. A weight least squares support vector regression is proposed using a novel weighting strategy. Then a thrust estimator based on the proposed regression is designed for the perfor- mance deterioration. Compared with the existing weighting strategy, the novel one not only satisfies the require- ment of precision but also enhances the real-time performance. Finally, numerical experiments demonstrate the effectiveness and feasibility of the proposed weighted least squares support vector regression for thrust estimator. Key words : intelligent engine control; least squares ; support vector machine ; performance deterioration
文摘A new particle deposition model, namely partial deposition model, is developed in order to improve the accuracy of prediction to particle deposition. Concepts of critical velocity and critical angle are proposed and used to determine whether particles are deposited or not. The comparison of numerical results calculated by partial deposition model and existing deposition model shows that the deposition distribution obtained by partial deposition model is more reasonable. Based on the predicted deposition results, the change of total pressure loss coefficient with operating time and the distribution of pressure coefficients on blade surface after 500 hours are predicted by using partial deposition model.
基金This project was supported by the Life Prediction Technologies Inc.(LPTi)and Natural Sciences and Engineering Research Council of Canada.
文摘Surface roughness is a critical health parameter of a turbine blade due to its implications on blade surface heat transfer and structural integrity.This paper proposes a physics-based online framework for Gas Turbine Engines(GTE),in order to assess the blade surface roughness in a highpressure turbine without engine shutdown.The framework consolidates Gas Path Analysis(GPA)based performance monitoring models and meanline turbomachinery analysis,using a novel GPAmeanline matching process.This extracts meaningful performance deviation trends from GPA,while addressing the uncertainties associated with the measurements and modelling.To relate efficiency loss to surface roughness severity,a meanline-based system-identification process has been developed to establish the meanline representation of the turbine stage,and to incorporate the empirical surface roughness loss correlations.The roughness loss correlations have been evaluated against recent transonic test data in the literature.A modification to the compressibility correction factor has been made according to the evaluation outcome,which improved loss predictions compared to the experimental measurements.The framework was tested on the three-year operational data of a cogeneration GTE,and the results verified the framework’s potential for online surface roughness monitoring.The predicted surface roughness showed agreement in both trend and the magnitude-level with the measurements reported in the literature.