This paper describes a new method of the optimal design of electrical capacitance sensor, which is based on genetic algorithm, and a modified bp algorithm of image reconstruction for electrical capacitance tomography ...
详细信息
ISBN:
(纸本)0819447145
This paper describes a new method of the optimal design of electrical capacitance sensor, which is based on genetic algorithm, and a modified bp algorithm of image reconstruction for electrical capacitance tomography system. In the optimal design of sensor, the evenness of sensitivity distribution, the ratio of maximum capacitance to minimum capacitance and the ratio of full-pipe capacitance to empty-pipe capacitance are considered. In image reconstruction we use the curve of components ratio and threshold valve of pixel gray to improve the performance of bp algorithm. Better quality and accuracy is obtained in experiment.
For the first time, artificial neural network (ANN) technique was used to investigate the properties of PZT based piezoelectric ceramic system in this article. Selecting several rare earth oxide dopants, the experimen...
详细信息
For the first time, artificial neural network (ANN) technique was used to investigate the properties of PZT based piezoelectric ceramic system in this article. Selecting several rare earth oxide dopants, the experimental results of 21 samples were analyzed by a three-layer bp network based on the homogenous experimental design. Through comparison it is found that the ANN model are much more accurate than conventional multiple nonlinear regression analysis (MNLR) model for the same set of data. The results of ANN model were also expressed and analyzed by intuitive graphics. The ANN prediction of the formulations not included in the train set also agree well with the testing values. It is indicated that the three-layer bp network based modeling is a very useful tool in dealing with problems with serious non-linearity encountered in the formulation design of piezoelectric ceramics.
In this paper, we develop GA-bp algorithm by combining genetic algorithm (GA) with back propagation (bp) algorithm and establish genetic bp neural network. We also applied bp neural network based on bp algorithm and g...
详细信息
In this paper, we develop GA-bp algorithm by combining genetic algorithm (GA) with back propagation (bp) algorithm and establish genetic bp neural network. We also applied bp neural network based on bp algorithm and genetic bp neural network based on GA-bp algorithm to discriminate earthquakes and explosions. The obtained result shows that the discriminating performance of genetic bp network is slightly better than that of bp network.
It is one of the most important tasks to improve the training time in the back-propagation (bp) neural networks. In the paper two methods based on error back propagation by adopting dynamic adjusting weights for reduc...
详细信息
The micropositioning system using flexural bearing (e.g., for wafer steppers and coarse-fine positioning systems) is a system of infinite degrees of freedom. It is difficult to design a controller for the partial diff...
详细信息
The micropositioning system using flexural bearing (e.g., for wafer steppers and coarse-fine positioning systems) is a system of infinite degrees of freedom. It is difficult to design a controller for the partial differential equation of the system directly. In this paper, a closed-form dynamics model is first developed using the assumed modes method and the least squares method. Then, a hierarchical neuro-fuzzy controller using backpropagation (bp) training algorithm is proposed for the precision control and active damping of the micropositioning system. Simulation results show that the suggested strategy can actively suppress the flexible vibration and have high positioning performance.
In this paper, an artificial neural network method that can predict the chemical composition of deposited weld metal by CO 2 Shielded Flux Cored Wire Surfacing was studied. It is found that artificial neural networ...
详细信息
In this paper, an artificial neural network method that can predict the chemical composition of deposited weld metal by CO 2 Shielded Flux Cored Wire Surfacing was studied. It is found that artificial neural network is a good approach on studying welding metallurgy processes that cannot be described by conventional mathematical methods. In the same time we explored a new way to study the no equilibrium welding metallurgy processes.
The standard back-propagation (bp) algorithm for multilayer feedforward neural networks is basically a gradient-descent method, it has the problems of local minima and slow convergence. In this paper, a simple method ...
详细信息
It is one of the most important tasks to improve the training time in the back-propagation(bp) neural *** this paper two new methods based on error back propagation by adopting dynamic adjusting weights for reduction ...
详细信息
It is one of the most important tasks to improve the training time in the back-propagation(bp) neural *** this paper two new methods based on error back propagation by adopting dynamic adjusting weights for reduction the training time are *** approaches are based on an adequate modification of the traditional and classical *** interesting results of computer experiments with the modified bp algorithm are *** results prove that these new methods are effective to solve some problems and faster than the traditional methods in training multi-layer feed-forward neural networks.
A new improved genetic bp algorithm was put forward in the paper. To determine whether the network falls into local minimum point, a discriminant of local minimum was put forth in the training process of a neural netw...
详细信息
A new improved genetic bp algorithm was put forward in the paper. To determine whether the network falls into local minimum point, a discriminant of local minimum was put forth in the training process of a neural network. A genetic algorithm was used to revise the weights of the neural network if the bp algorithm fell into minimums. The mechanical faults were diagnosed using the algorithm put forward in the paper, which verified the validity of this improved genetic bp algorithm.
暂无评论