作者机构：
[王旭红] School of Electrical and Information Engineering, Changsha University of Science and Technology, Changsha 410076, China;[何怡刚; 王旭红] School of Electrical and Information Engineering, Hunan University, Changsha 410082, China
通讯机构：
[Wang, X.-H.] S;School of Electrical and Information Engineering, Changsha University of Science and Technology, China
作者机构：
[王旭红] College of Electrical and Information Engineering, Changsha University of Science and Technology, Changsha 410076, China;[何怡刚; 王旭红] College of Electrical and Information Engineering, Hunan University, Changsha 410082, China
通讯机构：
[Wang, X.] C;College of Electrical and Information Engineering, Changsha University of Science and Technology, China
作者机构：
[何怡刚; 王旭红] College of Electrical and Information Engineering, Hunan Univ., Changsha, Hunan 410082, China;[王旭红] School of Electrical and Information Engineering, Changsha Univ. of Science and Technology, Changsha, Hunan 410076, China
通讯机构：
College of Electrical and Information Engineering, Hunan Univ., China
期刊：
The Journal of Information and Computational Science,2009年6(3):1689-1695 ISSN：1548-7741
通讯作者：
Wang, X.
作者机构：
[Wang, Xuhong] School of Electrical and Information Engineering, Changsha University of Science and Technology, Changsha 410076, China;[He, Yigang; Wang, Xuhong] School of Electrical and Information Engineering, Hunan University, Changsha 410082, China
通讯机构：
School of Electrical and Information Engineering, Changsha University of Science and Technology, China
关键词：
BP Algorithm;Fault Detection;Induction Motor;Modified Elman Neural Network;Stator Windings
关键词：
frequency-response masking;FIR digital filter;neural network;optimal design
摘要：
This paper presents a new optimization method for the design of various frequency-response-masking (FRM)-based linear-phase finite-impulse response (FIR) digital filters. The method is based on a batch back-propagation neural network algorithm (NNA), which is taken as a variable learning rate mode. In order to reduce the complexity, the following two-step optimization technique is proposed. At the first step, an initial FRM filter is designed by alternately optimizing the sub-filters. This solution is then used as a start-up solution for further optimization. At the second step, the coefficients of overall sub-filters are optimized simultaneously by the NNA. Algorithm details for the design of basic and multistage FRM filters are presented to show that the proposed approach offers a unified design framework for a variety of FRM filters. Some examples taken from the literatures are included and the results show that the proposed algorithm can design better FRM filters than several existing methods.
会议名称：
2nd IEEE Conference on Industrial Electronics and Applications(ICIEA 2007)(第二届IEEE工业电子与应用国际会议)
会议时间：
2007-05-23
会议地点：
哈尔滨
摘要：
A support vector machine (SVM) based predictive control strategy for active power filter is presented in this paper. In the strategy, SVM is employed to model and predict future harmonic compensating current, it has the advantages of nonexistence of local minima solutions, automatic choice of model complexity and good generalization performance. Based on the model output, branch-and-bound optimization method is adopted to produce proper value of control vector, this value is adequately modulated by means of a space vector PWM modulator which generate proper gating patterns of the inverter switches to maintain tracking of reference current. The SVM based predictive algorithm is used in internal model control scheme to compensate for process disturbances, measurement noise and modeling errors. The proposed control is applied to compensate the harmonic produced by the variable non-linear load, simulation results show SVM based predictive controller is effective.
会议名称：
2nd IEEE Conference on Industrial Electronics and Applications(ICIEA 2007)(第二届IEEE工业电子与应用国际会议)
会议时间：
2007-05-23
会议地点：
哈尔滨
摘要：
A fuzzy neural network based on-line turn fault detection approach for induction motors is proposed in this paper. B-spline membership fuzzy neural network is employed to detect turn fault, since the selection of the weighting factors, the knot positions and the control points of the B-spline membership fuzzy-neural networks is crucial to obtaining good approximation for complex nonlinear systems, a genetic algorithm with an efficient search strategy is developed to optimize network parameters. Based on it, Experiments are carried out on a special rewound laboratory induction motor, the results show fuzzy neural network based diagnosis model determines the shorted turns exactly, and is more effective than the parameters estimation method under the condition of detecting a slowly developing turn fault.
摘要：
A fuzzy model based on-line turn fault detection approach for induction motors is presented in this paper. Two T-S fuzzy models are employed to detect turn fault, one is used to estimate the fault severity, the other is used to determine the exact number of fault turns. During fuzzy modeling, a fuzzy clustering algorithm based on similarity assessing is proposed to determine the optimal structure of the model and real-coded genetic algorithm (GA) is adopted to online optimize model parameters. All these techniques make the fuzzy model compact and accurate. Based on it, Experiments are carried out on a special rewound laboratory induction motor, the results show T-S fuzzy model based diagnosis model determines the shorted turns exactly, and is more effective than the forward neural network based diagnosis model under the condition of detecting a slowly developing turn fault.
关键词：
2-D linear-phase digital filters;back-propagation neural network;convergence theorem;stability
摘要：
This paper provides a new approach for the design of 2-D FIR linear-phase digital filters based on a parallel back-propagation neural-networks algorithm (PBPNNA). According to the frequency response characteristic of a 2-D linear-phase FIR filter, a compact expression for the transfer function is derived, and a new PBPNNA is established for designing 2-D FIR linear-phase filters. The convergence theorem is presented and proved to illustrate the stability of the PBPNNA. Design examples are also given to illustrate the effectiveness of the proposed design approach.
关键词：
linear phase FIR notch filters;magnitude response;neural networks;convergence theorem;stability
摘要：
A novel optimal design approach for linear phase finite impulse response (FIR) notch filters is proposed based on a new parallel neural networks algorithm (PNNA), the main idea is to minimize the squared-error function in the frequency-domain. By using the PNNA, the coefficients of the designed notch filter can be obtained directly from the specified magnitude response. The convergence theorem is presented and proved to illustrate the stability of the PNNA. Finally, some examples are given to illustrate the effectiveness of the proposed linear phase FIR notch filters design method.
会议名称：
Electronic imaging and multimedia technology IV :
会议时间：
2004-11-08
会议论文集名称：
Electronic imaging and multimedia technology IV :
关键词：
linear-phase 2-D FTR digital filters;image processing;neural network;convergence theorem;magnitude response
摘要：
Two-dimensional (2-D) digital filters are widely useful in image processing and other 2-D digital signal processing fields,but designing 2-D filters is much more difficult than designing one-dimensional (1-D) ones.In this paper, a new design approach for designing linear-phase 2-D digital filters is described,which is based on a new neural networks algorithm (NNA).By using the symmetry of the given 2-D magnitude specification,a compact express for the magnitude response of a linear-phase 2-D finite impulse response (FIR) filter is derived.Consequently,the optimal problem of designing linear-phase 2-D FIR digital filters is turned to approximate the desired 2-D magnitude response by using the compact express.To solve the problem,a new NNA is presented based on minimizing the mean-squared error,and the convergence theorem is presented and proved to ensure the designed 2-D filter stable.Three design examples are also given to illustrate the effectiveness of the NNA-based design approach.
摘要：
The main limitation of feed-forward neural network based modeling methods for stator winding turn fault detection is its poor dynamical processing capability. To solve this problem, a diagonal recurrent neural network based on-line turn fault detection approach for induction motors is presented in this paper. Two diagonal recurrent neural networks are employed to detect turn fault. One is used to estimate the fault severity, the other is used to determine the exact number of fault turns. In order to make the diagonal recurrent neural network model more simple and accurate, an adaptive dynamic back propagation algorithm is proposed to determine the optimum number of the hidden layer neurons. Experiments are carried out on a special rewound laboratory induction motor, the results show that the diagonal recurrent neural network based diagnosis model determines the shorted turns exactly, and is more effective than the forward neural network based diagnosis model under the condition of detecting a slowly developing turn fault.
摘要：
A neural network based predictive control strategy for active power filter is presented in this paper. In the strategy, RBF neural network is employed to predict future harmonic compensating current. In order to make the predictive model much simpler and tighter, an adaptive learning algorithm for RBF network is proposed. Based on the model output, Genetic algorithm is introduced to optimize objective function, which generates proper value of control vector. The neural network based predictive algorithm is used in internal model control scheme to compensate for process disturbances, measurement noise and modeling errors. Simulation test under various conditions is implemented. The results show the neural network based predictive control is more effective and feasible than PI control or digit adaptive control.
