In this paper, the author studies a class of mixed nonlinear variational-like inequalities in reflexive Banach space. By applying a minimax inequality obtained by the author, some existence uniqueness theorems of solu...In this paper, the author studies a class of mixed nonlinear variational-like inequalities in reflexive Banach space. By applying a minimax inequality obtained by the author, some existence uniqueness theorems of solutions for the mixed nonlinear variational-like inequalities are proved. Next, by applying the auxiliary problem technique, rite author suggests an innovative iterative algorithm to compute the approximate solutions of the mixed nonlinear variational-like inequalities. Finally, the convergence criteria is also discussed.展开更多
The purpose of this paper is to analyse theoretically and numerically the coupled vibration of an ideal fluid with a linear elastic structure, It is proved in the paper that the natural frequencies of the coupled vibr...The purpose of this paper is to analyse theoretically and numerically the coupled vibration of an ideal fluid with a linear elastic structure, It is proved in the paper that the natural frequencies of the coupled vibration do exist and are all real positive. The paper presents an efficient method to transform a coupled fluid-structure system to the structure with added mass and the vibrational analysis of the former is replaced by the latter in vacuum only. Numerical solution is outlined for the transformed problem and a compact jrequeney equation is derived in which fluid variables do not appear. This simplifies the analysis significantly. A convergent proof has been given to guarantee the reliability of the solution. The paper also offers a general algorithm combined with Ritz method, boundary element method, and finite element method to analyse the transformed problem. Based on this algorithm, one can apply a known structural analysing program, with a little modification, to solve many different kinds of fluid-structure coupling problems. Some numerical results are given to show the efficiency of the algorithm.展开更多
In this paper, an SQP type algorithm with a new nonmonotone line search technique for general constrained optimization problems is presented. The new algorithm does not have to solve the second order correction subpro...In this paper, an SQP type algorithm with a new nonmonotone line search technique for general constrained optimization problems is presented. The new algorithm does not have to solve the second order correction subproblems for each iterations, but still can circumvent the so-called Maratos effect. The algorithm's global convergence and superlinear convergent rate have been proved. In addition, we can prove that, after a few iterations, correction subproblems need not be solved, so computation amount of the algorithm will be decreased much more. Numerical experiments show that the new algorithm is effective.展开更多
A new algorithm based on a Supervised Self-Organizing neural network for the pas sive sonar target recognition was proposed. Because of the incompleteness of the passive sonar exemplar set, the algorithm introduced a ...A new algorithm based on a Supervised Self-Organizing neural network for the pas sive sonar target recognition was proposed. Because of the incompleteness of the passive sonar exemplar set, the algorithm introduced a Multi-Activation-function structure and Supervised Self-Organizing competitive learning algorithm into the classic feed-forward neural networks,and obviously improved the generalization ability in target recognition. Besides, it can effi ciently reduce the learning time and avoid the local optimum. The recognition experiments of realistic passive sonar signals show that this new algorithm has good generalization ability and high recognition rate展开更多
文摘In this paper, the author studies a class of mixed nonlinear variational-like inequalities in reflexive Banach space. By applying a minimax inequality obtained by the author, some existence uniqueness theorems of solutions for the mixed nonlinear variational-like inequalities are proved. Next, by applying the auxiliary problem technique, rite author suggests an innovative iterative algorithm to compute the approximate solutions of the mixed nonlinear variational-like inequalities. Finally, the convergence criteria is also discussed.
文摘The purpose of this paper is to analyse theoretically and numerically the coupled vibration of an ideal fluid with a linear elastic structure, It is proved in the paper that the natural frequencies of the coupled vibration do exist and are all real positive. The paper presents an efficient method to transform a coupled fluid-structure system to the structure with added mass and the vibrational analysis of the former is replaced by the latter in vacuum only. Numerical solution is outlined for the transformed problem and a compact jrequeney equation is derived in which fluid variables do not appear. This simplifies the analysis significantly. A convergent proof has been given to guarantee the reliability of the solution. The paper also offers a general algorithm combined with Ritz method, boundary element method, and finite element method to analyse the transformed problem. Based on this algorithm, one can apply a known structural analysing program, with a little modification, to solve many different kinds of fluid-structure coupling problems. Some numerical results are given to show the efficiency of the algorithm.
文摘In this paper, an SQP type algorithm with a new nonmonotone line search technique for general constrained optimization problems is presented. The new algorithm does not have to solve the second order correction subproblems for each iterations, but still can circumvent the so-called Maratos effect. The algorithm's global convergence and superlinear convergent rate have been proved. In addition, we can prove that, after a few iterations, correction subproblems need not be solved, so computation amount of the algorithm will be decreased much more. Numerical experiments show that the new algorithm is effective.
文摘A new algorithm based on a Supervised Self-Organizing neural network for the pas sive sonar target recognition was proposed. Because of the incompleteness of the passive sonar exemplar set, the algorithm introduced a Multi-Activation-function structure and Supervised Self-Organizing competitive learning algorithm into the classic feed-forward neural networks,and obviously improved the generalization ability in target recognition. Besides, it can effi ciently reduce the learning time and avoid the local optimum. The recognition experiments of realistic passive sonar signals show that this new algorithm has good generalization ability and high recognition rate
