In the injection of pulverized coal into a blast furnace, there are some factors which affect the readout of electronic weighing system. Through analyzing the measuring errors, it is found that the main reasons are p...
详细信息
In the injection of pulverized coal into a blast furnace, there are some factors which affect the readout of electronic weighing system. Through analyzing the measuring errors, it is found that the main reasons are pressure fluctuations of storage tank and puffing tank. According to the interaction of pressures, a neural network based method combined with fuzzy logic is adopted to enhance the precision. Experimental results show this method is satisfactory.
An algorithm for quickly training the bp neural network system identifier (bpNNSI) of the chaotic optical systems is presented in this paper. The ability of this algorithm, termed as the chaos speedup bp algorithm (CS...
详细信息
ISBN:
(纸本)0819420697
An algorithm for quickly training the bp neural network system identifier (bpNNSI) of the chaotic optical systems is presented in this paper. The ability of this algorithm, termed as the chaos speedup bp algorithm (CSbpA), has been demonstrated with the computer simulation of identifying the Bragg diffraction acousto-optic system (BDAOS) in which a 1:4:1 bp network was employed in identification. Taking the normalized output time series of the BDAOS as the training series, the bpNNSI was trained with the CSbpA as follows: (1) trained the bpNNSI to learn a chaotic state of the BDAOS with the bp algorithm where the initial weight distribution was set randomly; (2) took the final weight distribution obtained in (1) as the initial weight distribution for the other states of the BDAOS to be identified; (3) trained the bpNNSI to learn the other states still with the bp algorithm but with the initial weight distribution obtained in (2).
The reliability of telecommunication networks is one of the most important quality *** this paper,based on the analysis of indicator system of telecommunication network reliability,a model is provided to evaluate the ...
详细信息
ISBN:
(纸本)7800908275
The reliability of telecommunication networks is one of the most important quality *** this paper,based on the analysis of indicator system of telecommunication network reliability,a model is provided to evaluate the growth of telecommunication network reliability. In the evaluating model,how to determine the weight of every reliability indicator is a key *** combine the principal component analysis method with neural network method to determine the weight of every ***,an example of application of the evaluation model in a local network is given.
The neural network method applied for the color image segmentation of the human's head image in the simple background is studied in this paper. The adopted network model is bp network, The image segmented by the r...
详细信息
ISBN:
(纸本)0819430064
The neural network method applied for the color image segmentation of the human's head image in the simple background is studied in this paper. The adopted network model is bp network, The image segmented by the region growing method is used as the training Bet and the bp algorithm is adopted to train the target and background image. Then segmenting testing image can be processed. Experimenting results show that the segmenting effect of this method is as good as the region growing method.
In spite of its relatively slow learning speed, backpropagation (bp) is one of the most popular neural network training algorithms. Here, a method based on nonlinear stretching is presented that modifies the activatio...
详细信息
The typical error back-propagation learning algorithm (bp) of neural networks with layered structure is shown to be useful in a wide range of practical applications. The “slowdown” of the change in the evaluation er...
详细信息
Neural networks have been used for modeling the nonlinear characteristics of memoryless nonlinear channels using backpropagation (bp) learning with experimental training data. In order to better understand this neural...
详细信息
Neural networks have been used for modeling the nonlinear characteristics of memoryless nonlinear channels using backpropagation (bp) learning with experimental training data. In order to better understand this neural network application, this paper studies the transient and convergence properties of a simplified two-layer neural network that uses the bp algorithm and is trained with zero mean Gaussian data. The paper studies the effects of the neural net structure, weights, initial conditions, and algorithm step size on the mean square error (MSE) of the neural net approximation. The performance analysis is based on the derivation of recursions for the mean weight update that can be used to predict the weights and the MSE over time. Monte Carte simulations display good to excellent agreement between the actual behavior and the predictions of the theoretical model.
In spite of its relatively slow learning speed, backpropagation (bp) is one of the most popular neutral network training algorithms. Here, a method based on nonlinear stretching is presented that modifies the activati...
详细信息
In spite of its relatively slow learning speed, backpropagation (bp) is one of the most popular neutral network training algorithms. Here, a method based on nonlinear stretching is presented that modifies the activation function in a bp algorithm to speed up the convergence in training. A target recognition system that incorporates the approach and moment invariants is formulated and tested. The test results indicate that the speed of convergence can be effectively increased through appropriate selection of a stretch factor. (C) 1997 John Wiley & Sons, Inc.
The activation function for the node of Backpropagation (bp) network is the Sigmoid function. The gain of the Sigmoid is usually set equal to 1. Author considers that the fixative gain of the Sigmoid is disadvantageou...
详细信息
ISBN:
(纸本)7800033910
The activation function for the node of Backpropagation (bp) network is the Sigmoid function. The gain of the Sigmoid is usually set equal to 1. Author considers that the fixative gain of the Sigmoid is disadvantageous to the bp network to simulate the function of brain cells, and in some range it limits the convergent rate of bp network while training. Therefore, the paper presents a new improved bp network which the gain of the Sigmoid is variable while training. The improved bp network not only simulates brain cells better, but also converges faster while training.
In this paper, the possibility of utilizing artificial neural network (ANN) to estimate the real time operation parameters of power systems has been studied. The ANN which is used for estimation is a three-layer feedf...
详细信息
In this paper, the possibility of utilizing artificial neural network (ANN) to estimate the real time operation parameters of power systems has been studied. The ANN which is used for estimation is a three-layer feedforward neural network. The inputs of the ANN are some locally measurable operation parameters of one system bus. The output of the ANN can be some synchronous parameters of some other remote buses. Simulation results show that a well trained ANN not only can estimate the real time operation parameters of remote buses with satisfying accuracy but also has great generalization abilities.
暂无评论