Nonlinear Dynamic Probabilistic Analysis for Turbine Casing Radial Deformation Using Extremum Response Surface Method Based on Support Vector Machine

2013 ◽  
Vol 8 (4) ◽  
Author(s):  
Chengwei Fei ◽  
Guangchen Bai
Keyword(s):  
Support Vector Machine ◽  
Response Surface ◽  
Response Surface Method ◽  
Probabilistic Analysis ◽  
Nonlinear Dynamic ◽  
Nonlinear Material ◽  
Support Vector ◽  
Radial Deformation ◽  
Surface Method ◽  
Turbine Casing

To improve the computational efficiency of nonlinear dynamic probabilistic analysis for aeroengine typical components, an extremum response surface method based on the support vector machine (SVM ERSM) was proposed in this paper. The basic principle was introduced and the mathematical model was established for the SVM ERSM. The probabilistic analysis of turbine casing radial deformation was taken as an example to validate the SVM ERSM considering the influences of nonlinear material property and dynamic heat loads. The results of probabilistic analysis imply that the distribution features of random parameters and the major factors are gained for more accurate the design of casing radial deformation. The SVM ERSM offers a feasible and valid method, which possesses high efficiency and high precision in the nonlinear dynamic probabilistic analysis. Moreover, the SVM ERSM is promising to provide an useful insight for casing dynamic optimal design and the blade-tip clearance control of aeroengine high pressure turbine.

scholarly journals Optimum Control for Nonlinear Dynamic Radial Deformation of Turbine Casing with Time-Varying LSSVM

2015 ◽  
Vol 2015 ◽  
pp. 1-9 ◽  
Author(s):  
Cheng-Wei Fei ◽  
Guang-Chen Bai ◽  
Wen-Zhong Tang ◽  
Yatsze Choy
Keyword(s):  
Nonlinear Dynamic ◽  
High Performance ◽  
High Reliability ◽  
Nonlinear Material ◽  
Support Vector ◽  
Radial Deformation ◽  
Time Varying ◽  
Optimum Control ◽  
Probabilistic Optimization ◽  
Turbine Casing

With the development of the high performance and high reliability of aeroengine, the blade-tip radial running clearance (BTRRC) of high pressure turbine seriously influences the reliability and performance of aeroengine, wherein the radial deformation control of turbine casing has to be concerned in BTRRC design. To improve BTRRC design, the optimum control-based probabilistic optimization of turbine casing radial deformation was implemented using time-varying least square support vector machine (T-LSSVM) by considering nonlinear material properties and dynamic thermal load. First the T-LSSVM method was proposed and its mathematical model was established. And then the nonlinear dynamic optimal control model of casing radial deformation was constructed with T-LSSVM. Thirdly, through the numerical experiments, the T-LSSVM method is demonstrated to be a promising approach in reducing additional design samples and improving computational efficiency with acceptable computational precision. Through the optimum control-based probabilistic optimization for nonlinear dynamic radial turbine casing deformation, the optimum radial deformation is 7.865 × 10−4 m with acceptable reliability degree 0.995 6, which is reduced by 7.86 × 10−5 m relative to that before optimization. These results validate the effectiveness and feasibility of the proposed T-LSSVM method, which provides a useful insight into casing radial deformation, BTRRC control, and the development of gas turbine with high performance and high reliability.

A dynamic probabilistic design method for blade-tip radial running clearance of aeroengine high-pressure turbine

2014 ◽  
Vol 229 (10) ◽  
pp. 1861-1872 ◽  
Author(s):  
Cheng-Wei Fei ◽  
Wen-Zhong Tang ◽  
Guang-chen Bai ◽  
Zhi-Ying Chen
Keyword(s):  
High Pressure ◽  
Response Surface ◽  
Response Surface Method ◽  
Probabilistic Analysis ◽  
High Reliability ◽  
Probabilistic Design ◽  
High Pressure Turbine ◽  
Analysis And Design ◽  
Surface Method ◽  
Blade Tip

Around the engineering background of the probabilistic design of high-pressure turbine (HPT) blade-tip radial running clearance (BTRRC) which conduces to the high-performance and high-reliability of aeroengine, a distributed collaborative extremum response surface method (DCERSM) was proposed for the dynamic probabilistic analysis of turbomachinery. On the basis of investigating extremum response surface method (ERSM), the mathematical model of DCERSM was established. The DCERSM was applied to the dynamic probabilistic analysis of BTRRC. The results show that the blade-tip radial static clearance δ = 1.82 mm is advisable synthetically considering the reliability and efficiency of gas turbine. As revealed by the comparison of three methods (DCERSM, ERSM, and Monte Carlo method), the DCERSM reshapes the possibility of the probabilistic analysis for turbomachinery and improves the computational efficiency while preserving computational accuracy. The DCERSM offers a useful insight for BTRRC dynamic probabilistic analysis and optimization. The present study enrichs mechanical reliability analysis and design theory.

Sign in / Sign up

Export Citation Format

Share Document