BP feed-forward network is the most widely applied neural network. There are a number of algorithms *** respective strengths and weaknesses of 8 kinds of BP algorithm provided by the neural network toolbox in MATLA...
详细信息
BP feed-forward network is the most widely applied neural network. There are a number of algorithms *** respective strengths and weaknesses of 8 kinds of BP algorithm provided by the neural network toolbox in MATLAB are studied in the paper in order to choose a more appropriate and faster algorithms under different conditions .Based on this, the measurement of vacuum level with the method of magnetron-discharge is taken as an example to carry on the simulation, the convergence steps of a variety of BP algorithm are compared in different situations, the fast convergence property of trainlm is confirmed, the conclusion is obtained that BP algorithm can forecast the vacuum level.
In this paper,the theory of artificial neural network with back-propagation algorithm (BPN) is presented,and the BPN model is used to predict the accumulated temperature for Northeast China,North China,and the Huang-H...
详细信息
In this paper,the theory of artificial neural network with back-propagation algorithm (BPN) is presented,and the BPN model is used to predict the accumulated temperature for Northeast China,North China,and the Huang-Huai-Hai Plain.A total of 235 records collected from 235 meteorology stations were fed into the BPN model for training and *** latitude,longitude and elevation of each station were used as input variables of BPN,and the accumulated temperature as output *** key network parameters, such as learning rate,momentum,the number of hidden nodes,and the learning iterations, were optimized using a trial and error *** optimized BPN model was compared with the multiple linear regression(MLR) *** summary,BPN model was generally more accurate than MLR *** infers that artificial neural network models are more applicable than regression models when predicting accumulated temperature.
In general, seismic waveform inversion adopts an objective function based on the l(2)-norm. However, waveform inversion using the l(2)-norm produces distorted results because the l(2)-norm is sensitive to statisticall...
详细信息
In general, seismic waveform inversion adopts an objective function based on the l(2)-norm. However, waveform inversion using the l(2)-norm produces distorted results because the l(2)-norm is sensitive to statistically invalid data such as outliers. As an alternative, there have been several studies applying l(1)-norm-based objective functions to waveform inversion. Although waveform inversion based on the l(1)-norm is known to produce robust inversion results against specific outliers in the time domain, its effectiveness and characteristics are yet to be studied in the frequency domain. The present study proposes an algorithm for l(1)-norm-based waveform inversion in the frequency domain. The proposed algorithm employs a structure identical to those used in conventional frequency-domain waveform inversion algorithms that exploit the back-propagation technique, but displays robustness against outliers, which has been confirmed based on inversion of the synthetic Marmousi model. The characteristics and advantages of the l(1)-norm were analysed by comparing it with the l(2)-norm. In addition, inversion was performed on data containing outliers to examine the robustness against outliers. The effectiveness of removing outliers was verified by using the l(1)-norm to calculate the residual wave field and its spectrum for the data containing outliers.
The continuous chip generated during turning operation deteriorates the workpiece precision and causes safety hazards for the operator. Appropriate control of the chip shape becomes a very important task for maintaini...
详细信息
The continuous chip generated during turning operation deteriorates the workpiece precision and causes safety hazards for the operator. Appropriate control of the chip shape becomes a very important task for maintaining reliable machining process. In particular, effective chip control is necessary for a CNC machine or automatic production system because any failure in chip control can cause the lowering in productivity and the worsening in operation due to frequent stop. Therefore, a grooved chip breaker has been widely used for obtaining reliable discontinuous chips. in general, in order to develop a new cutting insert with a chip breaker, extensive time, research, and expense are required because several processes such as forming, sintering, grinding, and coating of products as well as different evaluation tests are necessary. In this study, the performance of commercial chip breakers was evaluated using a neural network that was trained through a backpropagationalgorithm. Important form elements (depth of cut, land, breadth, and radius) that directly influenced the chip formation were chosen among commercial chip breakers, and were used as input values of the neural network. As a result, the performance evaluation method has been developed and applied to commercial tools, which resulted in excellent performance. if the training data in the neural network is collected with greater consideration given to the effect of cutting conditions and the performance of chip breakers, it can be used for the design of chip breakers in the future. (c) 2008 Elsevier B.V. All rights reserved.
This paper presents experimental data and modeling for membrane-based treatment of leather plant effluent. The effluent coming out from the various upstream steps of leather plant are combined and pressure driven memb...
详细信息
This paper presents experimental data and modeling for membrane-based treatment of leather plant effluent. The effluent coming out from the various upstream steps of leather plant are combined and pressure driven membrane processes like nanofiltration (NF) and reverse osmosis (RO) are undertaken after a pretreatment consisting of gravity settling and coagulation followed by cloth filtration. Performances of two NF membranes (200 and 400 molecular weight cut offs (MWCO)) are evaluated. Experiments are conducted using an unstirred batch cell. It is observed that a combined operation of NF using 400 MWCO membrane followed by RO operation is better option compared to a single operation of NF with 200 MWCO (membrane). After selection of proper NF membrane from batch experimental data, the entire membrane separation scheme is validated by conducting experiments using a cross flow cell. A detailed parametric study for cross flow experiment is investigated and the suitable operating trans-membrane pressure and the cross flow rates are found out (experimentally) in both NF and RO. The experimental flux data are correlated and analyzed using artificial neural network (ANN). A multi-layered feed-forward network with back-propagation algorithm is used for training of ANN models. Two artificial neural network models with input, output and hidden layer(s) are used to predict the flux data for both the batch and cross flow run. A good agreement has been observed using the ANN model with the experimental flux data with a deviation not more than 1% for most of the cases considered. The BOD and COD values of the finally treated effluent are well within the permissible limits. (C) 2009 Elsevier B.V. All rights reserved.
Engineered fabric manufacturing needs a thorough understanding of the functional properties and their key control construction parameters. When the relationship between a set of interrelated properties goes out of the...
详细信息
Engineered fabric manufacturing needs a thorough understanding of the functional properties and their key control construction parameters. When the relationship between a set of interrelated properties goes out of the complete comprehension of human brain, neural networks could be used to find the unknown function. This article describes the method of applying the artificial neural network for the prediction performance parameters for airbag fabrics. The results of the ANN performance prediction had low prediction error i.e., 12% with all the samples and the artificial neural network based on Error back-propagation were found promising for a new domain of design prediction technique. The prediction performance of the neural network was based on the amount of training given to it, i.e., the diversity of the data and the amount of data;resulting in better the mapping of the network, and better predictions. Airbag fabrics could be successfully engineered using artificial neural network.
The agricultural sector in India is up against a series of problems when it comes to increasing crop productivity. A number of successful researches have been carried out to discover productive agricultural practices ...
详细信息
ISBN:
(纸本)9781424445189
The agricultural sector in India is up against a series of problems when it comes to increasing crop productivity. A number of successful researches have been carried out to discover productive agricultural practices to improve crop cultivation but despite their efforts, productivity achieved by most of the farmers has not been in upper-bound level. The prime reason stated globally for crop loss is Insect pests. An efficient pest management technique can be devised if we could predict in advance the occurrences of peak activities of a given pest. Researchers are undertaken to understand the pest population dynamics by employing analytical and other techniques on pest surveillance data sets. In this paper, we present an intelligent system for pest prediction in cotton crop with the aid of the data obtained from College of Agriculture, Raichur, India. We make an effort to understand population dynamics of Thrips tabaci Linde (Thrips) pest on cotton (Gossypium Arboreum) crop using neural networks by analyzing pest surveillance data. The Multi-layer perceptron neural network with back-propagation training algorithm is utilized in the design of the presented intelligent system. The results show that neural network system can be able to give results with a very high degree of accuracy and is best suited to build a prediction system. With the aid of this pest prediction system, the farming communities get more beneficiaries in crop productivity.
Information fusion is an important research field, one major theory and technology is neural networks especially back-propagation (BP) neural network. Meanwhile BP neural network has been applied in many fields. But t...
详细信息
ISBN:
(纸本)9780769535609
Information fusion is an important research field, one major theory and technology is neural networks especially back-propagation (BP) neural network. Meanwhile BP neural network has been applied in many fields. But traditional BP neural network has some faults, such as bad convergence rate and low learning rate aiming at huge date sets, poor generalization, poor ability of error weight update and batch learning. Aiming at these faults, some improved methods are proposed to solve these problems, one of methods is BP neural network based on Kalman Filter which can solve before-mentioned faults partly. But present methods of BP neural network based on Kalman Filter can not do batch processing and study multi-sample conditions. Improved BP neural network based on Kalman Filter is proposed depending on present BP neural network based on Kalman Filter. The idea of new method includes two steps, firstly we obtain the update of estimation weight, secondly we use the obtained results to mend the Kalman Gain for new update of time and measurement, at the some time the new algorithm can adopt batch processing to learning neural network. Experiments show the new algorithm can solve high-dimensional, large computation problem, keeping robustness and improving the learning efficiency.
In the present study, input-output relationships of metal inert gas welding process have modeled using radial basis function neural networks. As the performance of a neural network depends on its structure and paramet...
详细信息
ISBN:
(纸本)9781424450534
In the present study, input-output relationships of metal inert gas welding process have modeled using radial basis function neural networks. As the performance of a neural network depends on its structure and parameters, some approaches have been developed to optimize them simultaneously. The performances of the developed approaches have been compared among them on some test cases. It has been observed that clustering plays an important role in deciding a suitable structure of the network. Moreover, it has been felt that a combined optimization scheme involving one global optimizer (a genetic algorithm) and one local optimizer (back-propagation algorithm) could be efficient to optimize both the structure and parameters of a network simultaneously.
暂无评论