A neural network model with a special structure, which is divided into linearand nonlinear parts, was proposed for identification of a nonlinear system. In this model, thenonlinear part of the object is treated as a m...A neural network model with a special structure, which is divided into linearand nonlinear parts, was proposed for identification of a nonlinear system. In this model, thenonlinear part of the object is treated as a measured disturbance, and is compensated by a feedforward method; an adaptive pole placement algorithm is used to control the linear part of theobject. The simulation results show that the identification efficiency and accuracy are improvedwhen the new controller is applied to sintering finish point control.展开更多
A shallow water tomography scheme based on the modal wave number inversion technique is considered in this paper. The scheme is based on the assumption that modal wave number for trapped modes can be measured in a sui...A shallow water tomography scheme based on the modal wave number inversion technique is considered in this paper. The scheme is based on the assumption that modal wave number for trapped modes can be measured in a suitable way. The tomographic inversion is accomplished in two steps: firstly, the bottom parameters are inverted by using the bottom reflection phase shift with the known sound speed profile; secondly, the variation of sound speed profile at different time is inverted provided the bottom parameters are known. A numerical simulation shows that the proposed scheme works well, and the sensitivity analysis of sound speed profile inversion is performed for shallow water environmental parameters: sound speed, density and attenuation coefficient of the bottom.展开更多
An approach of adaptive predictive control with a new structure and a fast algorithm of neural network (NN) is proposed. NN modeling and optimal predictive control are combined to achieve both accuracy and good contro...An approach of adaptive predictive control with a new structure and a fast algorithm of neural network (NN) is proposed. NN modeling and optimal predictive control are combined to achieve both accuracy and good control performance. The output of nonlinear network model is adopted as a measured disturbance that is therefore weakened in predictive feed-forward control. Simulation and practical application show the effectiveness of control by the proposed approach.展开更多
文摘A neural network model with a special structure, which is divided into linearand nonlinear parts, was proposed for identification of a nonlinear system. In this model, thenonlinear part of the object is treated as a measured disturbance, and is compensated by a feedforward method; an adaptive pole placement algorithm is used to control the linear part of theobject. The simulation results show that the identification efficiency and accuracy are improvedwhen the new controller is applied to sintering finish point control.
文摘A shallow water tomography scheme based on the modal wave number inversion technique is considered in this paper. The scheme is based on the assumption that modal wave number for trapped modes can be measured in a suitable way. The tomographic inversion is accomplished in two steps: firstly, the bottom parameters are inverted by using the bottom reflection phase shift with the known sound speed profile; secondly, the variation of sound speed profile at different time is inverted provided the bottom parameters are known. A numerical simulation shows that the proposed scheme works well, and the sensitivity analysis of sound speed profile inversion is performed for shallow water environmental parameters: sound speed, density and attenuation coefficient of the bottom.
基金the National Natural Science Foundation of China (No. 60075012).
文摘An approach of adaptive predictive control with a new structure and a fast algorithm of neural network (NN) is proposed. NN modeling and optimal predictive control are combined to achieve both accuracy and good control performance. The output of nonlinear network model is adopted as a measured disturbance that is therefore weakened in predictive feed-forward control. Simulation and practical application show the effectiveness of control by the proposed approach.
