The genetic algorithm is a new random search algorithm based on natural selection and the principle of gene genetics. As the back propagation algorithm has some shortages, such as low efficiency of le
The genetic algorithm is a new random search algorithm based on natural selection and the principle of gene genetics. As the back propagation algorithm has some shortages, such as low efficiency of le
Artificial neural networks (ANN) constitute a recently emerged intriguing data processing technique. Over the last decade chemistry became a field of their wide application. Nevertheless, few has been known of the app...
详细信息
Artificial neural networks (ANN) constitute a recently emerged intriguing data processing technique. Over the last decade chemistry became a field of their wide application. Nevertheless, few has been known of the application of ANN modeling technique in inorganic ceramic materials. Based on the homogeneous experimental design the experimental results of 21 samples were analyzed by a three-layer bp (back propagation) network. Influence of the additives on the properties of the materials were illustrated by the registered ANN model. The basic reasons for the relationships between the additives and the electrical properties of the materials produced by the ANN model were also explained by the doping theory for piezoelectric ceramics. The optimized formulation was calculated and examined. The precise prediction results indicate that the three-layer bp network based modeling is a practically very useful tool in both property analysis and formulation design of the multicomponent oxide ceramic material. (c) 2005 Elsevier B.V. All rights reserved.
An isothermal compressive experiment using Gleeble 1500 thermal simulator was studied to acquire flow stress at different deformation temperatures, strains and strain rates. The artificial neural networks with the err...
详细信息
An isothermal compressive experiment using Gleeble 1500 thermal simulator was studied to acquire flow stress at different deformation temperatures, strains and strain rates. The artificial neural networks with the error back propagation(bp) algorithm was used to establish constitutive model of 2519 aluminum alloy based on the experiment data. The model results show that the systematical error is small(δ=3.3%) when the value of objective function is 0.2, the number of nodes in the hidden layer is 5 and the learning rate is 0.1. Flow stresses of the material under various thermodynamic conditions are predicted by the neural network model, and the predicted results correspond with the experimental results. A knowledge-based constitutive relation model is developed.
This paper proposes a new approach for training FNN by, hybrid DE and bp. It combines the advantages of the global search performed by DE over the FNN parameter space and the local search of bp. Using a function appro...
详细信息
ISBN:
(纸本)0387283188
This paper proposes a new approach for training FNN by, hybrid DE and bp. It combines the advantages of the global search performed by DE over the FNN parameter space and the local search of bp. Using a function approximation as an illustration, we compare the HDEbp and bp for effectiveness and efficiency for training FNN. It shows that the use of new method can provide better results than bp.
Binarization of gray scale document images is one of the most important steps in automatic document image processing. In this paper, we present a two-stage document image binarization approach, which includes a top-do...
详细信息
Binarization of gray scale document images is one of the most important steps in automatic document image processing. In this paper, we present a two-stage document image binarization approach, which includes a top-down region-based binarization at the first stage and a neural network based binarization technique for the problematic blocks at the second stage after a feedback checking. Our two-stage approach is particularly effective for binarizing text images of highlighted or marked text. The region-based binarization method is fast and suitable for processing large document images. However, the block effect and regional edge noise are two unavoidable problems resulting in poor character segmentation and recognition. The neural network based classifier can achieve good performance in two-class classification problem such as the binarization of gray level document images. However, it is computationally costly. In our two-stage binarization approach, the feedback criteria are employed to keep the well binarized blocks from the first stage binarization and to re-binarize the problematic blocks at the second stage using the neural network binarizer to improve the character segmentation quality. Experimental results on a number of document images show that our two-stage binarization approach performs better than the single-stage binarization techniques tested in terms of character segmentation quality and computational cost.
Hot strip coiling temperature is one important parameter of performance index in hot rolled strip, and its control system is highly nonlinear. The coiling temperature of hot rolled strip is exactly predicted based on ...
详细信息
ISBN:
(纸本)7506274027
Hot strip coiling temperature is one important parameter of performance index in hot rolled strip, and its control system is highly nonlinear. The coiling temperature of hot rolled strip is exactly predicted based on neural network (NN) by means of its approximation to any non-linear system and its ability of approximation to any nonlinear system and its ability of prediction. Additional momentum method, which is an improved bp algorithm, is used in the NN. A new coiling temperature control system based on NN combined with mathematical model is presented. Its feed-forward control is based on the NN, and its feed-backward control is based on mathematic model. Finally, the prediction by the NN shows that the control performance is satisfactory, and it can make mathematical model of coiling temperature identified.
The Paper is the study of Gabor wavelet neural network algorithm and its application in gray image target recognition. The mostly thought t are real time recognizing gray image target with Gabor wavelet neural network...
详细信息
ISBN:
(纸本)081945592X
The Paper is the study of Gabor wavelet neural network algorithm and its application in gray image target recognition. The mostly thought t are real time recognizing gray image target with Gabor wavelet neural networks algorithm. The main thoughts are through combing the forward neural networks (bp net) with Gabor wavelet based on they were applied in target feature extraction and recognition. A model of Gabor wavelet neural network is constructed with automatic target recognition, the good impact is gained when it is applied target recognition. The principle of Gabor filter is expounded. The multi-channel Gabor filter is designed based on theory and practicality, the neural network recognizing algorithm based on multi-channel Gabor filter feature is presented. Training algorithm of Gabor wavelet neural networks model was given out. Principally analyzed Gabor wavelet neural networks from theory, in the mean time training algorithm of Gabor wavelet network suited to target recognition was designed by bp algorithm. Theory and simulate experiment indicated the astringency and robustness of this algorithm excelled bp net. Target was recognized by this algorithm not only increased recognition precision but also overcame the bug of bp algorithm get in minimum.
A new neural network PID (NNPID) controller, which is based on PID by means of neural network's ability of self-learning and adaptive, is presented. The NNPID controller is designed by combining neural network wit...
详细信息
ISBN:
(纸本)7506274027
A new neural network PID (NNPID) controller, which is based on PID by means of neural network's ability of self-learning and adaptive, is presented. The NNPID controller is designed by combining neural network with PID control strategy. Additional momentum method, that is an improved bp algorithm, is used in the neural network is analyzed. This paper presents the control for the highly nonlinear, time-varying hydraulic AGC of rolling mills based on the NNPID controller. The simulation shows that the dynamic quality of the system is improved, and NNPID has good adaptability.
This paper proposes a new approach for training FNN by hybrid DE and *** combines the advantages of the global search performed by DE over the FNN parameter space and the local search of *** a function approximation a...
详细信息
This paper proposes a new approach for training FNN by hybrid DE and *** combines the advantages of the global search performed by DE over the FNN parameter space and the local search of *** a function approximation as an illustration,we compare the HDEbp and bp for effectiveness and efficiency for training *** shows that the use of new method can provide better results than bp.
By analyzing bp training model, a solution named division and assembly by deducing the size of bp neural network to overcome entering the local best points is introduced. The dividing process is realized by dividing a...
详细信息
By analyzing bp training model, a solution named division and assembly by deducing the size of bp neural network to overcome entering the local best points is introduced. The dividing process is realized by dividing a big bp neural network into several small ones, each of which can carry out study alone. Thereafter, they can be assembled to become the quondam big bp neural work. This approach is analyzed in detail with an example.
暂无评论