			Home About us Contact

Feedforward Neural Networks (feedforward + neural_network)

Distribution by Scientific Domains

Engineering	63%
Chemistry	21%

Selected Abstracts

Feedforward neural network-based transient stability analysis of electric power systems

EUROPEAN TRANSACTIONS ON ELECTRICAL POWER, Issue 6 2006
H. Hadj Abdallah
Abstract This paper presents a neural approach for the transient stability analysis of electric power systems (EPS). The transient stability of an EPS expresses the ability of the system to preserve synchronism after sudden severe disturbances. Its analysis needs the computation of the critical clearing time (CCT), which determines the security degree of the system. The classical methods for the determination of the CCT are computation time consuming and may be not treatable in real time. A feedforward neural network trained off-line using an historical database can approximate the simulation studies to give in real time an accurate estimate of the CCT. The identified neural network can be updated using new significant data to learn more disturbance cases. Numerical simulations are presented to illustrate the proposed method. Copyright © 2006 John Wiley & Sons, Ltd. [source]

Near-Term Travel Speed Prediction Utilizing Hilbert,Huang Transform

COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING, Issue 8 2009
Khaled Hamad
In this study, we propose an innovative methodology for such prediction. Because of the inherently direct derivation of travel time from speed data, the study was limited to the use of speed only as a single predictor. The proposed method is a hybrid one that combines the use of the empirical mode decomposition (EMD) and a multilayer feedforward neural network with backpropagation. The EMD is the key part of the Hilbert,Huang transform, which is a newly developed method at NASA for the analysis of nonstationary, nonlinear time series. The rationale for using the EMD is that because of the highly nonlinear and nonstationary nature of link speed series, by decomposing the time series into its basic components, more accurate forecasts would be obtained. We demonstrated the effectiveness of the proposed method by applying it to real-life loop detector data obtained from I-66 in Fairfax, Virginia. The prediction performance of the proposed method was found to be superior to previous forecasting techniques. Rigorous testing of the distribution of prediction errors revealed that the model produced unbiased predictions of speeds. The superiority of the proposed model was also verified during peak periods, midday, and night. In general, the method was accurate, computationally efficient, easy to implement in a field environment, and applicable to forecasting other traffic parameters. [source]

Feedforward neural network-based transient stability analysis of electric power systems

Artificial neural networks for parameter estimation in geophysics

GEOPHYSICAL PROSPECTING, Issue 1 2000
Carlos Calderón-Macías
Artificial neural systems have been used in a variety of problems in the fields of science and engineering. Here we describe a study of the applicability of neural networks to solving some geophysical inverse problems. In particular, we study the problem of obtaining formation resistivities and layer thicknesses from vertical electrical sounding (VES) data and that of obtaining 1D velocity models from seismic waveform data. We use a two-layer feedforward neural network (FNN) that is trained to predict earth models from measured data. Part of the interest in using FNNs for geophysical inversion is that they are adaptive systems that perform a non-linear mapping between two sets of data from a given domain. In both of our applications, we train FNNs using synthetic data as input to the networks and a layer parametrization of the models as the network output. The earth models used for network training are drawn from an ensemble of random models within some prespecified parameter limits. For network training we use the back-propagation algorithm and a hybrid back-propagation,simulated-annealing method for the VES and seismic inverse problems, respectively. Other fundamental issues for obtaining accurate model parameter estimates using trained FNNs are the size of the training data, the network configuration, the description of the data and the model parametrization. Our simulations indicate that FNNs, if adequately trained, produce reasonably accurate earth models when observed data are input to the FNNs. [source]

Using feedforward neural networks and forward selection of input variables for an ergonomics data classification problem

HUMAN FACTORS AND ERGONOMICS IN MANUFACTURING & SERVICE INDUSTRIES, Issue 1 2004
Chuen-Lung Chen
A method was developed to accurately predict the risk of injuries in industrial jobs based on datasets not meeting the assumptions of parametric statistical tools, or being incomplete. Previous research used a backward-elimination process for feedforward neural network (FNN) input variable selection. Simulated annealing (SA) was used as a local search method in conjunction with a conjugate-gradient algorithm to develop an FNN. This article presents an incremental step in the use of FNNs for ergonomics analyses, specifically the use of forward selection of input variables. Advantages to this approach include enhancing the effectiveness of the use of neural networks when observations are missing from ergonomics datasets, and preventing overspecification or overfitting of an FNN to training data. Classification performance across two methods involving the use of SA combined with either forward selection or backward elimination of input variables was comparable for complete datasets, and the forward-selection approach produced results superior to previously used methods of FNN development, including the error back-propagation algorithm, when dealing with incomplete data. © 2004 Wiley Periodicals, Inc. Hum Factors Man 14: 31,49, 2004. [source]

Adaptive predistortion of COFDM signals for a mobile satellite channel

INTERNATIONAL JOURNAL OF COMMUNICATION SYSTEMS, Issue 2 2003
Nibaldo Rodriguez
Abstract In this paper, we consider the optimization of the performance of QPSK and 16-QAM coded orthogonal frequency division multiplexing (COFDM) signals over the non-linear and mobile satellite channel. A high power amplifier and Rician flat fading channel produces non-linear and linear distortions; an adaptive predistortion technique combined with turbo codes will reduce both types of distortion. The predistorter is based on a feedforward neural network, with the coefficients being derived using an extended Kalman filter (EKF). The conventional turbo code is used to mitigate Rician flat fading distortion and Gaussian noise. The performance over a non-linear satellite channel indicates that QPSK COFDM followed by a predistorter provides a gain of about 1.7 dB at a BER of 3×10,3 when compared to QPSK COFDM without the predistortion scheme and 16-QAM COFDM provides a gain of 0.5 dB output back-off and 1.2 dB signal to noise ratio at a BER of 3×10,5 when compared with an adaptive predistorter based on the Harmmerstein model. We also investigate the influence of the guard time interval and Doppler frequency effect on the BER performance. When the guard interval increases from 0 to 0.125T samples and the normalized Doppler frequency is 0.001, there is a gain of 0.7 and 1 dB signal to noise ratio at a BER of 6×10,4 for QPSK and 16-QAM COFDM, respectively. Copyright © 2003 John Wiley & Sons, Ltd. [source]

High-sensitive neural network ammonia sensor based on shear horizontal surface acoustic wave devices

JOURNAL OF CHEMOMETRICS, Issue 10 2008
Chi-Yen Shen
Abstract In this paper, a shear horizontal surface acoustic wave devices coated with L-glutamic acid hydrochloride were applied as ammonia sensors. This sensor has shown high sensitivity and fast responses to ppb-level ammonia. The frequency shift linearly increased as the ammonia concentration increased from 40 to 400,ppb in dry environment. In the humid environment, the frequency shift gradually decreased with ammonia concentration increasing. In order to precisely estimate the ammonia in humid environment, two different neural models, the conventional feedforward neural network and quantum neural network, were used as the identifier and their performances were reported and compared. Copyright © 2008 John Wiley & Sons, Ltd. [source]

Recurrent neural networks with multi-branch structure

ELECTRONICS & COMMUNICATIONS IN JAPAN, Issue 9 2008
Takashi Yamashita
Abstract Universal Learning Networks (ULNs) provide a generalized framework for many kinds of structures in neural networks with supervised learning. Multi-Branch Neural Networks (MBNNs) which use the framework of ULNs have already been shown to have better representation ability in feedforward neural networks (FNNs). The multi-branch structure of MBNNs can be easily extended to recurrent neural networks (RNNs) because the characteristics of ULNs include the connection of multiple branches with arbitrary time delays. In this paper, therefore, RNNs with multi-branch structure are proposed and are shown to have better representation ability than conventional RNNs. RNNs can represent dynamical systems and are useful for time series prediction. The performance evaluation of RNNs with multi-branch structure was carried out using a benchmark of time series prediction. Simulation results showed that RNNs with multi-branch structure could obtain better performance than conventional RNNs, and also showed that they could improve the representation ability even if they are smaller-sized networks. © 2009 Wiley Periodicals, Inc. Electron Comm Jpn, 91(9): 37,44, 2008; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/ecj.10157 [source]

Evolving modular networks with genetic algorithms: application to nonlinear time series

EXPERT SYSTEMS, Issue 4 2004
A.S. Cofiño
Abstract: A key problem of modular neural networks is finding the optimal aggregation of the different subtasks (or modules) of the problem at hand. Functional networks provide a partial solution to this problem, since the inter-module topology is obtained from domain knowledge (functional relationships and symmetries). However, the learning process may be too restrictive in some situations, since the resulting modules (functional units) are assumed to be linear combinations of selected families of functions. In this paper, we present a non-parametric learning approach for functional networks using feedforward neural networks for approximating the functional modules of the resulting architecture; we also introduce a genetic algorithm for finding the optimal intra-module topology (the appropriate balance of neurons for the different modules according to the complexity of their respective tasks). Some benchmark examples from nonlinear time-series prediction are used to illustrate the performance of the algorithm for finding optimal modular network architectures for specific problems. [source]

Short-term electric power load forecasting using feedforward neural networks

EXPERT SYSTEMS, Issue 3 2004
Heidar A. Malki
Abstract: This paper presents the results of a study on short-term electric power load forecasting based on feedforward neural networks. The study investigates the design components that are critical in power load forecasting, which include the selection of the inputs and outputs from the data, the formation of the training and the testing sets, and the performance of the neural network models trained to forecast power load for the next hour and the next day. The experiments are used to identify the combination of the most significant parameters that can be used to form the inputs of the neural networks in order to reduce the prediction error. The prediction error is also reduced by predicting the difference between the power load of the next hour (day) and that of the present hour (day). This is a promising alternative to the commonly used approach of predicting the actual power load. The potential of the proposed method is revealed by its comparison with two existing approaches that utilize neural networks for electric power load forecasting. [source]

Using feedforward neural networks and forward selection of input variables for an ergonomics data classification problem

Sliding,window neural state estimation in a power plant heater line

INTERNATIONAL JOURNAL OF ADAPTIVE CONTROL AND SIGNAL PROCESSING, Issue 8 2001
A. Alessandri
Abstract The state estimation problem for a section of a real power plant is addressed by means of a recently proposed sliding-window neural state estimator. The complexity and the nonlinearity of the considered application prevent us from successfully using standard techniques as Kalman filtering. The statistics of the distribution of the initial state and of noises are assumed to be unknown and the estimator is designed by minimizing a given generalized least-squares cost function. The following approximations are enforced: (i) the state estimator is a finite-memory one, (ii) the estimation functions are given fixed structures in which a certain number of parameters have to be optimized (multilayer feedforward neural networks are chosen from among various possible nonlinear approximators), (iii) the algorithms for optimizing the parameters (i.e., the network weights) rely on a stochastic approximation. Extensive simulation results on a complex model of a part of a real power plant are reported to compare the behaviour of the proposed estimator with the extended Kalman filter. Copyright © 2001 John Wiley & Sons, Ltd. [source]

Reconstruction of chaotic signals with application to channel equalization in chaos-based communication systems

INTERNATIONAL JOURNAL OF COMMUNICATION SYSTEMS, Issue 3 2004
Jiuchao Feng
Abstract A number of schemes have been proposed for communication using chaos over the past years. Regardless of the exact modulation method used, the transmitted signal must go through a physical channel which undesirably introduces distortion to the signal and adds noise to it. The problem is particularly serious when coherent-based demodulation is used because the necessary process of chaos synchronization is difficult to implement in practice. This paper addresses the channel distortion problem and proposes a technique for channel equalization in chaos-based communication systems. The proposed equalization is realized by a modified recurrent neural network (RNN) incorporating a specific training (equalizing) algorithm. Computer simulations are used to demonstrate the performance of the proposed equalizer in chaos-based communication systems. The Hénon map and Chua's circuit are used to generate chaotic signals. It is shown that the proposed RNN-based equalizer outperforms conventional equalizers as well as those based on feedforward neural networks for noisy, distorted linear and non-linear channels. Copyright © 2004 John Wiley & Sons, Ltd. [source]

Complexity versus integrity solution in adaptive fuzzy-neural inference models

INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS, Issue 5 2008
Georgi M. Dimirovski
This paper explores aspects of computational complexity versus rule reduction and of integrity preservation versus optimality index, which have become an issue of considerable concern in learning techniques for adaptive fuzzy inference models. In control-oriented applications of adaptive fuzzy inference systems, implemented as fuzzy-neural networks, a balanced observation of these conflicting requirements appeared rather important for a good yet feasible application design. The focus is confined to a family of adaptive fuzzy inference systems that can be interpreted as a partially connected multilayer feedforward neural networks employing Gaussian activation function. The knowledge base rules are designed implying the connections are a priori fixed, and then the respective strengths adapted on the grounds of input and output data sets. Information granulation plays a significant role too. These as well as membership-function parameters ought to be adapted in a learning-training process via the minimization of an appropriate error function. © 2008 Wiley Periodicals, Inc. [source]

Reformulated radial basis function neural networks with adjustable weighted norms

INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS, Issue 10 2003
Mary M. Randolph-Gips
This article presents a new family of reformulated radial basis function (RBF) neural networks that employ adjustable weighted norms to measure the distance between the training vectors and the centers of the radial basis functions. The reformulated RBF model introduced in this article incorporates norm weights that can be updated during learning to facilitate the implementation of the desired input-output mapping. Experiments involving classification and function approximation tasks verify that the proposed RBF neural networks outperform conventional RBF neural networks and reformulated RBF neural networks employing fixed Euclidean norms. Reformulated RBF neural networks with adjustable weighted norms are also strong competitors to conventional feedforward neural networks in terms of performance, implementation simplicity, and training speed. © 2003 Wiley Periodicals, Inc. [source]

Nonlinear experimental design using Bayesian regularized neural networks

AICHE JOURNAL, Issue 6 2007
Matthew C Coleman
Abstract Novel criteria for designing experiments for nonlinear processes are presented. These criteria improve on a previous methodology in that they can be used to suggest a batch of new experiments to perform (as opposed to a single new experiment) and are also optimized for discovering improved optima of the system response. This is accomplished by using information theoretic criterion, which also heuristically penalize experiments that are likely to result in low (nonoptimal) results. While the methods may be applied to any type of nonlinear-nonparametric model (radial basis functions and generalized linear regression), they are here exclusively considered in conjunction with Bayesian regularized feedforward neural networks. A focus on the application of rapid process development, and how to use repeated experiments to optimize the training procedures of Bayesian regularized neural networks is shown. The presented methods are applied to three case studies. The first two case studies involve simulations of one and two-dimensional (2-D) nonlinear regression problems. The third case study involves real historical data from bench-scale fermentations generated in our laboratory. It is shown that using the presented criteria to design new experiments can greatly increase a feedforward neural network's ability to predict global optima. © 2007 American Institute of Chemical Engineers AIChE J, 2007 [source]

Dynamic Process Modelling using a PCA-based Output Integrated Recurrent Neural Network

THE CANADIAN JOURNAL OF CHEMICAL ENGINEERING, Issue 4 2002
Yu Qian
Abstract A new methodology for modelling of dynamic process systems, the output integrated recurrent neural network (OIRNN), is presented in this paper. OIRNN can be regarded as a modified Jordan recurrent neural network, in which the past values for certain steps of the output variables are integrated with the input variables, and the original input variables are pre-processed using principal component analysis (PCA) for the purpose of dimension reduction. The main advantage of the PCA-based OIRNN is that the input dimension is reduced, so that the network can be used to model the dynamic behavior of multiple input multiple output (MIMO) systems effectively. The new method is illustrated with reference to the Tennessee-Eastman process and compared with principal component regression and feedforward neural networks. On présente dans cet article une nouvelle méthodologie pour la modélisation de systèmes de procédés dynamiques, soit le réseau neuronal récurrent avec intégration de la réponse (OIRNN). Ce dernier peut être vu comme un réseau neuronal récurrent de Jordan modifié, dans lequel les valeurs passées pour certaines étapes des valeurs de sortie sont intégrées aux variables d'entrée et les variables d'entrée originales pré-traitée par l'analyse des composants principaux (PCA) dans un but de réduction des dimensions. Le principal avantage de l'OIRNN basé sur la PCA est que la dimension d'entée est réduite de sorte que le réseau peut servir à modéliser le comportement dynamique de systèmes à entrée et sorties multiples (MIMO) de façon efficace. La nouvell méthod est illustrée dans le cas du procédé Tennessee-Eastman et est comparée aux réseaux neuronaux anticipés et à régression des composants principaux. [source]

Identification and control of a riser-type FCC unit

THE CANADIAN JOURNAL OF CHEMICAL ENGINEERING, Issue 6 2001
Abdul-Alghasim Alaradi
Abstract This paper addresses the use of feedforward neural networks for the steady-state and dynamic identification and control of a riser type fluid catalytic cracking unit (FCCU). The results are compared with a conventional PI controller and a model predictive control (MPC) using a state space subspace identification algorithm. A back propagation algorithm with momentum term and adaptive learning rate is used for training the identification networks. The back propagation algorithm is also used for the neuro-control of the process. It is shown that for a noise-free system the adaptive neuro-controller and the MPC are capable of maintaining the riser temperature, the pressure difference between the reactor vessel and the regenerator, and the catalyst bed level in the reactor vessel, in the presence of set-point and disturbance changes. The MPC performs better than the neuro controller that in turn is superior to the conventional multi-loop diagonal PI controller. On examine dans cet article l'utilisation de réseaux neuronaux à anticipation pour la détermination et la régulation en régimes dynamique et permanent d'une unité de craquage catalytique de fluide de type colonne montante (FCCU). Un algorithme de rétro-propagation avec un terme de quantité de mouvement et une vitesse d'apprentissage adaptative est utilisé pour l'entraînement des réseaux d'identification. L'algorithme de rétro-propagation est également utilisé pour le controle neuronal du procédé. On montre que pour un système non bruité le contôleur neuronal adaptatif est capable de maintenir la température de colonne, la différence de pression entre le réacteur et le régénerateur ainsi que le niveau de lit de catalyseur dans le réacteur, en présence de changements dans les point de consigne et les perturbations. [source]