When an aircraft executes large amplitude maneuvers, it is characterized by nonlinear aerodynamics so that the linear model which is usually used at the trim condition is not adequate in this situation. To solve this ...
详细信息
ISBN:
(纸本)9789881563903
When an aircraft executes large amplitude maneuvers, it is characterized by nonlinear aerodynamics so that the linear model which is usually used at the trim condition is not adequate in this situation. To solve this problem, a method is proposed for the modeling of nonlinear aerodynamic coefficients using large amplitude maneuver flight data. orthogonalleastsquare (OLS) algorithm and the error reduction ratio (ERR) are combined to model nonlinear aerodynamic coefficients and estimate parameters. The OLS can provide accurate estimates of the parameters, while the ERR value that is a byproduct of OLS can be computed easily to select the terms that the model should include. The proposed method is tested in F-16 large amplitude maneuver using the tabular aerodynamic database. The aerodynamic models are constructed for the pitching moment coefficient, the vertical force coefficient and the axial force coefficient. The results show that the nonlinear model obtained by OLS and ERR matches the measured coefficient very well.
When an aircraft executes large amplitude maneuvers, it is characterized by nonlinear aerodynamics so that the linear model which is usually used at the trim condition is not adequate in this situation. To solve this ...
详细信息
When an aircraft executes large amplitude maneuvers, it is characterized by nonlinear aerodynamics so that the linear model which is usually used at the trim condition is not adequate in this situation. To solve this problem, a method is proposed for the modeling of nonlinear aerodynamic coefficients using large amplitude maneuver flight data. orthogonalleastsquare(OLS) algorithm and the error reduction ratio(ERR) are combined to model nonlinear aerodynamic coefficients and estimate parameters. The OLS can provide accurate estimates of the parameters, while the ERR value that is a byproduct of OLS can be computed easily to select the terms that the model should include. The proposed method is tested in F-16 large amplitude maneuver using the tabular aerodynamic database. The aerodynamic models are constructed for the pitching moment coefficient, the vertical force coefficient and the axial force coefficient. The results show that the nonlinear model obtained by OLS and ERR matches the measured coefficient very well.
The phenomenon of the hydraulic jump is so complex that despite considerable laboratory and prototype studies, estimation of its main characteristics in a generalized and accurate form is still difficult. The Artifici...
详细信息
The phenomenon of the hydraulic jump is so complex that despite considerable laboratory and prototype studies, estimation of its main characteristics in a generalized and accurate form is still difficult. The Artificial Neural Network (ANN) approach aims at limiting the needs for costly and timeconsuming experiments. In this study, two ANN models, multi-layer perceptron using back propagation algorithm (MLP/BP) and radial basis function using orthogonalleast-squares algorithm (RBF/OLS), were used to predict the roller length, sequent depth, and the relative energy loss of the 13-jump. Based on a pre-specified range of jump parameters, the input vectors include: upstream bed slope (tan theta), inflow depth h 1, approach velocity V, and elevation of jump toe from the datum plane z(1), generated from the experimental data of Hager (J. Hydraul. Res., IAHR, 26(5), 539-558, 1988) and Kawagoshi and Hager (J. Hydraul. Res., IAHR, 28(4), 461-480, 1990). Once the network is trained to an acceptable level of accuracy, it produces an outputofjump rollerlength, sequentdepth, and relative energy loss for any inputvector. The predicted values agreewell with measurements. Sensitivity analysis was performed to investigate the importance of each input neuron. Finally a matrix of weights was specified for use at any given location.
Fault section estimation is of great importance to the restoration of power systems. Many techniques have been used to solve this problem. In this paper, the application of radial basis function neural network (RBF NN...
详细信息
Fault section estimation is of great importance to the restoration of power systems. Many techniques have been used to solve this problem. In this paper, the application of radial basis function neural network (RBF NN) to fault section estimation is addressed. The orthogonalleastsquare (OLS) algorithm has been extended to optimize the number of neurons in hidden layer and the connection weights of RBF NN. A classical back-propagation neural network (BP NN) has been developed to solve the same problem for comparison. Computer test is conducted on a four-bus test system and the test results show that the RBF NN is quite effective and superior to BP NN in fault section estimation. (C) 2002 Elsevier Science Ltd. All rights reserved.
暂无评论