The paper presents a scheme of optimization of the cooling process of the gas turbine blade. As an optimization criterion has been taken into account on the outer surface temperature of the blade. Inverse problem is s...The paper presents a scheme of optimization of the cooling process of the gas turbine blade. As an optimization criterion has been taken into account on the outer surface temperature of the blade. Inverse problem is solved for stationary heat conduction in which beside the optimization criterion of the heat transfer coefficient on the outer surface of the blade the temperature distribution is known, and the values sought are the heat transfer coefficients and surface temperature of the cooling channels. This problem was solved by the boundary element method using SVD algorithm and Tikhonov regularization. The temperature and heat transfer coefficient of cooling channels obtained from the inverse problem was oscillating in nature. This solution is nonphysical, so the heat transfer coefficients on the surface of cooling channels were averaged. Then the problem was solved simply with averaged coefficients of heat transfer on the surface of the cooling channels and the known distribution on the outer surface of blade. The temperature distribution obtained from the solution of direct problem with averaged values of heat transfer coefficient was compared with the criterion of optimization.The calculation results obtained using the SVD algorithm gave the temperature distribution on the external wall of the blade closer to the criterion of optimization.展开更多
A local discriminant regularized soft k-means （LDRSKM） method with Bayesian inference is proposed for multimode process monitoring. LDRSKM extends the regularized soft k-means algorithm by exploiting the local and n...A local discriminant regularized soft k-means （LDRSKM） method with Bayesian inference is proposed for multimode process monitoring. LDRSKM extends the regularized soft k-means algorithm by exploiting the local and non-local geometric information of the data and generalized linear discriminant analysis to provide a better and more meaningful data partition. LDRSKM can perform clustering and subspace selection simultaneously, enhancing the separability of data residing in different clusters. With the data partition obtained, kernel support vector data description （KSVDD） is used to establish the monitoring statistics and control limits. Two Bayesian inference based global fault detection indicators are then developed using the local monitoring results associated with principal and residual subspaces. Based on clustering analysis, Bayesian inference and manifold learning methods, the within and cross-mode correlations, and local geometric information can be exploited to enhance monitoring performances for nonlinear and non-Gaussian processes. The effectiveness and efficiency of the proposed method are evaluated using the Tennessee Eastman benchmark process.展开更多
文摘The paper presents a scheme of optimization of the cooling process of the gas turbine blade. As an optimization criterion has been taken into account on the outer surface temperature of the blade. Inverse problem is solved for stationary heat conduction in which beside the optimization criterion of the heat transfer coefficient on the outer surface of the blade the temperature distribution is known, and the values sought are the heat transfer coefficients and surface temperature of the cooling channels. This problem was solved by the boundary element method using SVD algorithm and Tikhonov regularization. The temperature and heat transfer coefficient of cooling channels obtained from the inverse problem was oscillating in nature. This solution is nonphysical, so the heat transfer coefficients on the surface of cooling channels were averaged. Then the problem was solved simply with averaged coefficients of heat transfer on the surface of the cooling channels and the known distribution on the outer surface of blade. The temperature distribution obtained from the solution of direct problem with averaged values of heat transfer coefficient was compared with the criterion of optimization.The calculation results obtained using the SVD algorithm gave the temperature distribution on the external wall of the blade closer to the criterion of optimization.
基金supported by the National Natural Science Foundation of China(No.61272297)
文摘A local discriminant regularized soft k-means （LDRSKM） method with Bayesian inference is proposed for multimode process monitoring. LDRSKM extends the regularized soft k-means algorithm by exploiting the local and non-local geometric information of the data and generalized linear discriminant analysis to provide a better and more meaningful data partition. LDRSKM can perform clustering and subspace selection simultaneously, enhancing the separability of data residing in different clusters. With the data partition obtained, kernel support vector data description （KSVDD） is used to establish the monitoring statistics and control limits. Two Bayesian inference based global fault detection indicators are then developed using the local monitoring results associated with principal and residual subspaces. Based on clustering analysis, Bayesian inference and manifold learning methods, the within and cross-mode correlations, and local geometric information can be exploited to enhance monitoring performances for nonlinear and non-Gaussian processes. The effectiveness and efficiency of the proposed method are evaluated using the Tennessee Eastman benchmark process.
