Focused on various bp algorithms with variable learning rate based on network system error gradient, a modified learning strategy for training non-linear network models is developed with both the incremental and the d...
详细信息
Focused on various bp algorithms with variable learning rate based on network system error gradient, a modified learning strategy for training non-linear network models is developed with both the incremental and the decremental factors of network learning rate being adjusted adaptively and dynamically. The golden section law is put forward to build a relationship between the network training parameters, and a series of data from an existing model is used to train and test the network parameters. By means of the evaluation of network performance in respect to convergent speed and predicting precision, the effectiveness of the proposed learning strategy can be illustrated.
An artificial neural network (ANN) short term forecasting model of consumption per hour was built based on seasonality,trend and randomness of a city period of time water consumption *** hidden layer nodes,same inpu...
详细信息
An artificial neural network (ANN) short term forecasting model of consumption per hour was built based on seasonality,trend and randomness of a city period of time water consumption *** hidden layer nodes,same inputs and forecasting data were selected to train and forecast and then the relative errors were compared so as to confirm the NN structure.A model was set up and used to forecast concretely by *** is tested by examples and compared with the result of time series trigonometric function analytical *** result indicates that the prediction errors of NN are small and the velocity of forecasting is *** can completely meet the actual needs of the control and run of the water supply system.
This paper deals with the characteristics and design of visual quick nerval network. Numerous case studies are made on slopes to calculate the stability of slopes which have undergone potential arc failure and wedge f...
详细信息
This paper deals with the characteristics and design of visual quick nerval network. Numerous case studies are made on slopes to calculate the stability of slopes which have undergone potential arc failure and wedge failure. Calculation results indicate that reliable judge can be made with regard to the stability of slopes using nerval network.
The back-propagation algorithm(bp) is a wellknown method of training a multilayer Feed -Forward Artificial Neural Networks(FFANNS).Although the algorithm is successful,it has some disadvantages. Because of adopting th...
详细信息
The back-propagation algorithm(bp) is a wellknown method of training a multilayer Feed -Forward Artificial Neural Networks(FFANNS).Although the algorithm is successful,it has some disadvantages. Because of adopting the gradient method by bp neural network,the problems including slowly learning convergent velocity and easily converging to local minimum can not be *** addition,the selection of learning factor and inertial factor affects the convergence of bp neural network,which are usually determined by *** the effective application of bp neural network is limited. In this paper a new method in bp algorithm to avoid local minimum was proposed by means of adding gradually training data and hidden *** addition, the paper also proposed a new model of controllable feed-forward neural network.
The reliability growth prediction is a most important part of the reliability engineering. The artificial neural network is a new subject developed in recent years. This paper presents the reliability growth and bp al...
详细信息
ISBN:
(纸本)7312012035
The reliability growth prediction is a most important part of the reliability engineering. The artificial neural network is a new subject developed in recent years. This paper presents the reliability growth and bp algorithm, then considers emphatically bp algorithm application in the reliability growth prediction. Gompertz model is a better model of the reliability growth models, the paper examines the algorithm by some instances and compares with results of Gompertz model, and results are basically consistent. It shows the approach is feasible, effective, simple, and adaptive. The reliability storage in the weapon system is negative growth;this paper also discusses the prediction of the reliability storage in the weapon system using the bp algorithm.
Regarding heat forming process of 1Cr18Ni9Ti as typical forming process, this paper presents the study of the effect of various parameters on flow stress, grain size and hardness of formed specimen by means of Gleeble...
详细信息
Regarding heat forming process of 1Cr18Ni9Ti as typical forming process, this paper presents the study of the effect of various parameters on flow stress, grain size and hardness of formed specimen by means of Gleeble-1500 Thermo-simulation machine and metalloscope. On the basis of technical experi- ment this paper, data are proceeded by applying multilayer feedforward back-propagation neural network, a prediction model of technological parameters together with microstructure and property in the heat forming process is established, thus forging property prediction in the heat forming process is realized.
In this paper, based on the property of sintering process, a hybrid fuzzy neural networks (FNN) and genetic algorithm (GA) system is proposed to solve the difficult and challenging problem of constructing a system mod...
详细信息
In this paper, based on the property of sintering process, a hybrid fuzzy neural networks (FNN) and genetic algorithm (GA) system is proposed to solve the difficult and challenging problem of constructing a system model from the given input and output data to predict the quality of chemical components of the finished sinter mineral. A bidirectional fuzzy neural network (BFNN) is proposed to represent the fuzzy model and realize the fuzzy inference. The learning process of BFNN is divided into off-line and on-line learning. In off-line learning, the GA is used to train the BFNN and construct a system model based on the training data. During on-line operation, the algorithm inherited from the principle of backpropagation is used to adjust the network parameters and improve the system precision in each sampling period. The process of constructing a system model is introduced in details. The results obtained from the actual prediction demonstrate that the performance and capability of the proposed system are superior.
In this paper,Chaos are imported into bp algorithm:The synaptic strengths are assigned with chaotic values at the beginning,and with conventional bp algorithm to train the neural *** is shown that the ability of getti...
详细信息
In this paper,Chaos are imported into bp algorithm:The synaptic strengths are assigned with chaotic values at the beginning,and with conventional bp algorithm to train the neural *** is shown that the ability of getting rid of local minimum with the new method is better than that of conventional bp method.
By using alternating current plasma arc welding,the influences were studied of such parameters as welding curent,arc voltage,welding speed,wire feed rate,and magnitude of ion gas flow on front melting width,wdle rei...
详细信息
By using alternating current plasma arc welding,the influences were studied of such parameters as welding curent,arc voltage,welding speed,wire feed rate,and magnitude of ion gas flow on front melting width,wdle reinforcement,and back melting width of LF6 aluminum *** of the formation of welding seam in alternating current plasma arc welding of aluminum was set up with the method of artificial neural neural network - bp algorithm. Qyakuty of formation was consequently predicted and *** experimental result shows that,compared with other modeling methods,artificial network model can be used to more accurately predict formation of weld,and to guide the production practice.
This paper is about the application of ANN (artificial neural networks) theory in evaluation of mine design schemes and a quantified evaluation method based on a three\|layer neural network is given. It studies the st...
详细信息
This paper is about the application of ANN (artificial neural networks) theory in evaluation of mine design schemes and a quantified evaluation method based on a three\|layer neural network is given. It studies the structure of the three\|layer neural network, its learning process, its operating algorithm to realize the evaluation of mine design schemes in a computer and a practical example is also involved in it.
暂无评论