In the present work attempts have been made to determine the process parameters that could affect an injection moulding process based on governing equations of the mould-filling process. Focus is then directed to para...
详细信息
In the present work attempts have been made to determine the process parameters that could affect an injection moulding process based on governing equations of the mould-filling process. Focus is then directed to parameters that require the use of trial and error methods or other complex software to determine the process parameters. The two parameters that are predicted from the developed network are injection time and injection pressure. In this work, the training data are generated by simulation using C-MOLD flow simulation software. A total of 114 data points under different process conditions were collected out of which 94 data points were used to train the network using MATLAB and the remaining information was used for testing the network. Two algorithms are used during the training phase, namely the error back-propagation algorithm and the Levenberg-Marquardt approximation algorithm. Results showed that the latter algorithm is more suitable for this application since the Levenberg algorithm converged rapidly with fewer training cycles when compared with the error back-propagation algorithm. The accuracy of the developed network has been tested by predicting the injection pressure and injection time for few engineering components.
Feedforward artificial neural networks (ANNs) that are trained with the back-propagation algorithm are a useful tool for modelling environmental systems. They have already been successfully used to model salinity, nut...
详细信息
Feedforward artificial neural networks (ANNs) that are trained with the back-propagation algorithm are a useful tool for modelling environmental systems. They have already been successfully used to model salinity, nutrient concentrations, air pollution, and algal growth. These successes, coupled with their suitability for modelling complex systems, have resulted in an increase in their popularity and their application in an ever increasing number of areas. They are generally treated as black box models that are able to capture underlying relationships when presented with input and output data. In many instances, little consideration is given to potential input data and the internal workings of ANNs. This can result in inferior model performance and an inability to accurately compare the performance of different ANN models. back-propagation networks employ a modelling philosophy that is similar to that of statistical methods in the sense that unknown model parameters (i.e., connection weights) are adjusted in order to obtain the best match between a historical set of model inputs and corresponding outputs. Consequently, the principles that are considered good practice in the development of statistical models should be considered. In this paper, a systematic approach to the development of ANN based forecasting models is presented, which is intended to act as a guide for potential and current users of feedforward ANNs that are trained with the back-propagation algorithm. Issues that need to be considered in the model development phase are discussed and ways of addressing them presented. The major areas covered include data transformation, the determination of appropriate model inputs, the determination of an appropriate network geometry, the optimisation of connection weights, and validation of model performance. (C) 2001 Elsevier Science Ltd. All rights reserved.
This paper presents two different regimes to automatically hyphenate Norwegian text. One method is based on a back-propagation neural network while the other uses the TEX algorithm. The two approaches are described an...
详细信息
ISBN:
(纸本)0780370449
This paper presents two different regimes to automatically hyphenate Norwegian text. One method is based on a back-propagation neural network while the other uses the TEX algorithm. The two approaches are described and compared. The database consists of about 40,000 Norwegian words.
As the nonlinear adaptive filter: the neural filter is utilized to process the nonlinear signal and/or system. However, the neural filter requires large number of iterations for convergence. This letter presents a new...
详细信息
As the nonlinear adaptive filter: the neural filter is utilized to process the nonlinear signal and/or system. However, the neural filter requires large number of iterations for convergence. This letter presents a new structure of the multilayer neural filter where the orthonormal transform is introduced into all inter-layers to accelerate the convergence speed. The proposed structure is called the transform domain neural filter (TDNF) for convenience. The weights are basically updated by the back-propagation (BP) algorithm but it must be modified since the error back-propagates through the orthogonal transform. Moreover, the variable step size which is normalized by the transformed signal power is introduced into the BP algorithm to realize the orthonormal transform. Through the computer simulation, it is confirmed that the introduction of the orthonormal transform is effective for speedup of convergence in the neural filter.
The conventional back-propagation algorithm cannot be applied to networks of units having hard-limiting output functions, because these functions cannot be differentiated. In this paper, a gradient descent algorithm s...
详细信息
The conventional back-propagation algorithm cannot be applied to networks of units having hard-limiting output functions, because these functions cannot be differentiated. In this paper, a gradient descent algorithm suitable for training multilayer feedforward networks of units having hard-limiting output functions, is presented. In order to get a differentiable output function for a hard-limiting unit, we utilized that if the bias of a unit in such a network is a random variable with smooth distribution function, the probability of the unit's output being in a particular state is a continuously differentiable function of the unit's inputs. Three simulation results are given, which show that the performance of this algorithm is similar to that of the conventional hack-propagation.
This paper presents a mapping scheme for the proposed implementation of neural network models on systolic arrays. The mapping technique is illustrated on the multilayer perceptron with back-propagation learning. Depen...
详细信息
This paper presents a mapping scheme for the proposed implementation of neural network models on systolic arrays. The mapping technique is illustrated on the multilayer perceptron with back-propagation learning. Dependency graphs have been given that represent the operations in the execution phases of the neural network model and later suitable algorithms are presented to realize the operations in a linear bidirectional systolic array. The speedup metric has been used to evaluate the performance of the proposed implementation. (C) 2000 Academic Press.
In this paper, the general class of morphological/rank/linear (MRL) multilayer feed-forward neural networks (NNs) is presented as a unifying signal processing tool that incorporates the properties of multilayer percep...
详细信息
In this paper, the general class of morphological/rank/linear (MRL) multilayer feed-forward neural networks (NNs) is presented as a unifying signal processing tool that incorporates the properties of multilayer perceptrons (MLPs) and morphological/rank neural networks (MRNNs). The fundamental processing unit of MRL-NNs is the MRL-filter, where the combination of inputs in every node is formed by hybrid linear and nonlinear (of the morphological/rank type) operations. For its design we formulate a methodology using ideas from the back-propagation algorithm and robust techniques to circumvent the non-differentiability of rank functions. Extensive experimental results are presented from the problem of handwritten character recognition, which suggest that MRL-NNs not only provide better or similar performance when compared to MLPs but also can be trained faster. The MRL-NNs are a broad interesting class of nonlinear systems with many promising applications in pattern recognition and signal/image processing. (C) 2000 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.
We constructed a learning optical neural network with variable learning coefficient by fuzzy controlling. The system performs learning with two-dimensional optical means for handling images without scanning and pixeli...
详细信息
ISBN:
(纸本)0819437328
We constructed a learning optical neural network with variable learning coefficient by fuzzy controlling. The system performs learning with two-dimensional optical means for handling images without scanning and pixeling. By the fuzzy controlling;theory, the learning coefficient in back-propagation algorithm is adjusted based on the training error and training time. The effectiveness of the system confirmed by the learning experiments of the recognition of three human faces.
This paper presents an on-line PID tuning control method, based on the parameters of a first-order plus dead-time (FOPDT) model, which are obtained by using Neural Networks (NN). The outputs of the neural networks are...
详细信息
This paper presents an on-line PID tuning control method, based on the parameters of a first-order plus dead-time (FOPDT) model, which are obtained by using Neural Networks (NN). The outputs of the neural networks are the three parameters of the FOPDT model. By combining this algorithm with a conventional PID controller, an adaptive controller is obtained which requires very little a priori knowledge about the plant under control. The simplicity and feasibility of the scheme for real-time control provide a new approach for implementing neural network applications for a variety of on-line industrial control problems. Simulation results demonstrate the feasibility and adaptive property of the proposed scheme.
As the training process of back-propagation neural networks converges slowly and immerses in local vibration frequently, an algorithm named parallel training algorithm is proposed, which is based on the Master/Slave m...
详细信息
ISBN:
(纸本)7312012035
As the training process of back-propagation neural networks converges slowly and immerses in local vibration frequently, an algorithm named parallel training algorithm is proposed, which is based on the Master/Slave model and training learning samples in each search subspace at the same time. The experiment results show that this algorithm converges at high rate and reaches global minimum soon.
暂无评论