Hybrid accident simulation methodology using artificial neural networks for nuclear power plants

A hybrid accident simulation methodology for nuclear power plants is proposed to enhance the capabilities of compact simulator by introducing artificial neural networks. Two neural networks are trained with the target values obtained from the analyses of detailed computer codes and trained results are combined with the compact simulator to perform the following roles: (i) compensation for inaccuracies of a compact simulator occurring from simplified governing equation and reduced number of physical control volumes, and (ii) prediction of the critical parameter usually calculated from the sophisticated computer code: the autoassociative neural network improves the computational results of the compact simulator up to the accuracy level of detailed best estimate computer code, while the backpropagation neural network predicts the minimum departure from nucleate boiling ratio (DNBR). Simulations are carried out to verify the applicability of the proposed methodology for the loss of flow accidents and the results show that the neural networks can be used as a complementary tool to improve the results of a compact simulator.     

Estimating the energy production of the wind turbine using artificial neural network

Due to fluctuating weather conditions, estimating wind energy potential is still a significant problem. Artificial neural networks (ANNs) have been commonly used in short-term and just-in-time modeling of wind power generation systems based on main weather parameters such as wind speed, temperature, and humidity. Two different datasets called hourly main weather data (MWD) and daily sub-data (DSD) are used to estimate a wind turbine power generation in this study. MWD are based on historically observed wind speed, wind direction, air temperature, and pressure parameters. Besides, DSD created with statistical terms of MWD consist of maximum, minimum, mean, standard deviation, skewness, and kurtosis values. The main purpose of this study in particular was to develop a multilinear model representing the relationship between the DSD with the calculated minimum (P _min) and maximum (P _max) power generation values as well as the total power generation (P _sum) produced in a day by a wind turbine based on the MWD. While simulation values of the turbine, P _min, P _max, and P _sum, were used as the separately dependent parameters, DSD were determined as independent parameters in the estimation models. Stepwise regression was used to determine efficient independent parameters on the dependent parameters and to remove the inefficient parameters in the exploratory phase of study. These efficient parameters and simulated power generation values were used for training and testing the developed ANN models. Accuracy test results show that interoperability framework models based on stepwise regression and the neural network models are more accurate and more reliable than a linear approach.     

Globally optimal bounding ellipsoid algorithm for parameter estimation using artificial neural networks

This paper develops a real-time implementation of a globally optimal bounding ellipsoid (GOBE) algorithm for parameter estimation of linear-in-parameter models with unknown but bounded (UBB)errors. A recently proposed recursively optimal bounding ellipsoid (ROBE) algorithm is introduced, and a GOBE algorithm is derived through repeating this ROBE algorithm. An analogue artificial neural network (ANN) is provided to implement the GOBE algorithm in real time. Convergence analyses on the ROBE, the GOBE algorithms, and the analogue ANN implementation of the GOBE algorithm are presented. No persistent excitation condition is required to ensure the convergence. Simulation results show the good performances of these algorithms and the ANN implementation.     

Modeling layered artificial neural networks using a visual programming paradigm

The understanding of soft computing methodology often requires grasping abstract concepts or imagining complex interactions of large models over long computing cycles. However, this can be difficult for students with a weak background in mathematics, especially in the early stages of soft computing education. This article introduces the idea of applying a visual programming paradigm as a tool for an educational introduction to soft computing methods. IntelligentPad, proposed by Y. Tanaka, was used as the visual programming paradigm. IntelligentPad gives a visual appearance to objects or classes, and allows users to operate and link different objects together using a mouse. This article reports on using IntelligentPad to teach the basic mechanisms of artificial neural networks. The proposed method was applied to 3rd-year college students to verify its validity as a teaching method.     

An artificial neural network for nonlinear estimation of the turbine flow-meter coefficient

Turbine flow meters find various applications in the process industries, such as batch control, measuring fuel oil and gas consumption, controlling blending processes, etc. The turbine meter is a rotor driven by the fluid being metered, at a speed proportional to the flow rate.The actual behavior of a turbine flow meter is a complex function of many variables; among these are the temperature, pressure, and viscosity of the fluid; the lubricating qualities of the fluid; bearing wear; and environmental factors. The turbine meter coefficient is referred to as the ‘K factor’, and is defined as the number of pulses per unit volume. At present, there is no single mathematical equation to predict the actual K factor. More accurate estimations and trending of the K factor will not only facilitate preventive maintenance, replacement analysis, etc., but will also ensure that material flow accounting is accurate.This research explores the use of neural-network models to aid in the estimation of the actual K factor that reflects the effect of the actual operating conditions of the turbine meter. This research analyzed data from three different turbine flow meters measuring the rate of pumping oil from the North Sea, for a company that operates off-shore oil platforms. The use of neural networks presents a new approach to the capturing of the underlying nonlinear relationships among the various input variables and the K factor. The results from this study report significant percentage reductions in mean absolute errors for the neural-network predictions over the company’s present estimation practices for the turbine flow-meter coefficient.     

Modeling nonlinear elastic behavior of reinforced soil using artificial neural networks

This paper presents the application using a multilayer neural network to model nonlinear elastic behavior of composite soil reinforced with fiber and stabilized with lime. First, shear modulus of the reinforced soil was assumed to be a nonlinear function of multiple variables such as contents of short fiber and lime powder, confining pressure, sample-aging period as well as shear strain. Secondly, a multilayer neural network was designed to map the highly nonlinear relationship between shear stress and strain. Thirdly, conventional triaxial shearing tests have been conducted for 34 sets of soil samples to provide experimental data for training and validating the neural network model. Finally, the neural network-based parameter sensitivities have been analyzed. The results of sensitivity analysis indicate that the lime content and the sample curing time play more significant roles than the fiber content in improving soil mechanical properties. It is the first attempt to apply the neural network to modeling of elastic behavior of composite soils, and has been found that modeling of reinforced soil using a multilayer neural network can provide more quality information on the performance of reinforced soil for better decision-making and continuous improvement of construction material designs.     

Modeling plasma surface modification of textile fabrics using artificial neural networks

In this paper, a neural network approach is used to understand the effects of fabric features and plasma processing parameters on fabric surface wetting properties. In this approach, fourteen features characterizing woven structures and two plasma parameters are taken as input variables, and the water contact angle cosine and the capillarity height of woven fabrics as output variables. In order to reduce the complexity of the model and effectively learn the network structure from a small number of data, a fuzzy logic based method is used for selecting the most relevant parameters which are taken as input variables of the reduced neural network models. With these relevant parameters, we can effectively control the plasma treatment by selecting the most appropriate fabric materials. Two techniques are used for improving the generalization capability of neural networks: (i) early stopping and (ii) Bayesian regularization. A methodology for optimizing such models is described. The learning abilities and prediction capabilities of the neural net models are compared in terms of different statistical performance criteria. Moreover, a connection weight method is used to determine the relative importance of each input variable in the networks. The obtained results show that neural network models could predict the process performance with reasonable accuracy. However, the neural model trained using Bayesian regularization provides the best results. Thus, it can be concluded that Bayesian network promises to be a valuable quantitative tool to evaluate, understand, and predict woven fabric surface modification by atmospheric air-plasma treatment.     

Dynamic brake switching strategies for stabilization of power systems using artificial neural networks

When a large disturbance appears on a power system, it may render the system unstable. One way to stabilize the post-disturbance system is to connect resistors or brakes at the generator terminals, and switch them dynamically. In this study, artificial neural networks have been trained to predict the switching times of these dynamic braking resistors for stability improvement. Training data for the nets were generated from a minimum time stabilizing strategy. Comparison of the back-propagation and radial-basis-function networks demonstrate that while both are suitable in estimating the switch times, the radial-basis-function networks are superior in terms of convergence characteristics as well as accuracy of prediction. The nets were also trained with different input features from the various generators.     

Modeling and simulation of static loads for wind power applications

This study aims to model and simulate static nonlinear loads with wind power generation to evaluate the impact of load models on wind power systems. Nonlinear loads are modeled as exponential load model, ZIP load model and combination of exponential/ZIP with an induction motor. The wind power generator is represented with a reduced-order doubly fed induction generator (DFIG) model. Developed models have been implemented in a grid-integrated wind power plant and simulated in MATLAB/SIMULINK. The effects of nonlinear loads into wind power plant are investigated in terms of bus voltages, angular speed, electrical torque, and d–q stator axes currents. Additional analyses are conducted to compare the behaviors of full- and reduced-order DFIG models under a selected loading condition. The results of this study indicate that the response of a system with DFIG is dependent of the load modeling and reduced-order DFIG model shows more stable trend than full-order DFIG model.     

Modeling and simulation of injection control system on a four-stroke type diesel engine development platform using artificial neural networks

Efficiency, reliability and emission demands on fuel consumptions have directed us to develop a microcontroller-based electromechanical educational platform that emulates the basic injection process of common four-stroke type diesel engines. Modeling of a system provides rapid programming and implementation capabilities. This study focuses on modeling and simulation of the platform in order to observe the results of novel methods and development strategies. The model determines the injection time (IT) and injection order (IO) of the related pistons. Determination of the IO has standard steps, where of IT which directly affects the fuel consumption lets novel optimization methods. In traditional applications, IT is assigned by a lookup table, whose inputs are crankshaft speed (CS) and manifold absolute pressure (MAP) values. In this study, an alternative relation surface created by feedforward artificial neural networks (ANNs) is suggested to determine the IT. The novel method could interpolate precise intermediate values of IT which bring about optimization in fuel consumption. Performances of the traditional method and the ANNs method are compared.     

Revisiting tests for neglected nonlinearity using artificial neural networks

Tests for regression neglected nonlinearity based on artificial neural networks (ANNs) have so far been studied by separately analyzing the two ways in which the null of regression linearity can hold. This implies that the asymptotic behavior of general ANN-based tests for neglected nonlinearity is still an open question. Here we analyze a convenient ANN-based quasi-likelihood ratio statistic for testing neglected nonlinearity, paying careful attention to both components of the null. We derive the asymptotic null distribution under each component separately and analyze their interaction. Somewhat remarkably, it turns out that the previously known asymptotic null distribution for the type 1 case still applies, but under somewhat stronger conditions than previously recognized. We present Monte Carlo experiments corroborating our theoretical results and showing that standard methods can yield misleading inference when our new, stronger regularity conditions are violated.     

Contingency evaluation and monitorization using artificial neural networks

In this paper, different neural network-based solutions to the contingency analysis problem are presented. Contingency analysis is examined from two perspectives: as a functional approximation problem obtaining a numerical evaluation and ranking contingencies; and as a graphical monitoring problem, obtaining an easy visualization system of the relative severity of the contingencies. For the functional evaluation problem, we analyze the use of different supervised feed-forward artificial neural networks (multilayer perceptron and radial basis function networks). The proposed systems produce a very accurate evaluation and ranking, and so present a high applicability. For the graphical monitoring problem, unsupervised artificial neural networks such as self-organizing maps by Kohonen have been used. This solution allows both a rapid, easy and simultaneous visualization of the severity level of the complete contingency set. The proposed solutions avoid the main drawbacks of previous neural network approaches to this problem, which are explicitly analyzed here.     

Modeling durations of syllables using neural networks

In this paper, we propose a neural network model for predicting the durations of syllables. A four layer feedforward neural network trained with backpropagation algorithm is used for modeling the duration knowledge of syllables. Broadcast news data in three Indian languages Hindi, Telugu and Tamil is used for this study. The input to the neural network consists of a set of features extracted from the text. These features correspond to phonological, positional and contextual information. The relative importance of the positional and contextual features is examined separately. For improving the accuracy of prediction, further processing is done on the predicted values of the durations. We also propose a two-stage duration model for improving the accuracy of prediction. From the studies we find that 85% of the syllable durations could be predicted from the models within 25% of the actual duration. The performance of the duration models is evaluated using objective measures such as average prediction error (μ), standard deviation (σ) and correlation coefficient (γ).     

Predicting power production from a photovoltaic panel through artificial neural networks using atmospheric indicators

Neural Computing and Applications - In this study, an artificial neural network was modeled in order to predict the power generated by a monocrystalline silicon photovoltaic panel. This...     

Performance analysis of modeling framework for prediction in wind farms employing artificial neural networks

This paper introduces the concept and practice of Neural Network architectures for wind speed prediction in wind farms. The wind speed prediction method has been analyzed by using back propagation network and radial basis function network. Artificial neural network is used to develop suitable architecture for predicting wind speed in wind farms. The key of wind speed prediction is rational selection of forecasting model and effective optimization of model performance. To verify the effectiveness of neural network architecture, simulations were conducted on real time wind data with different heights of wind mill. Due to fluctuation and nonlinearity of wind speed, accurate wind speed prediction plays a major role in the operational control of wind farms. The key advantages of Radial Basis Function Network include higher accuracy, reduction of training time and minimal error. The experimental results show that compared to existing approaches, proposed radial basis function network performs better in terms of minimization of errors.     

Locally recurrent neural networks for wind speed prediction using spatial correlation

This paper deals with the wind speed prediction in wind farms, using spatial information from remote measurement stations. Owing to the temporal complexity of the problem, we employ local recurrent neural networks with internal dynamics, as advanced forecast models. To improve the prediction performance, the training task is accomplished using on-line learning algorithms based on the recursive prediction error (RPE) approach. A global RPE (GRPE) learning scheme is first developed where all adjustable weights are simultaneously updated. In the following, through weight grouping we devise a simplified method, the decoupled RPE (DRPE), with reduced computational demands. The partial derivatives required by the learning algorithms are derived using the adjoint model approach, adapted to the architecture of the networks being used. The efficiency of the proposed approach is tested on a real-world wind farm problem, where multi-step ahead wind speed estimates from 15 min to 3 h are sought. Extensive simulation results demonstrate that our models exhibit superior performance compared to other network types suggested in the literature. Furthermore, it is shown that the suggested learning algorithms outperform three gradient descent algorithms, in training of the recurrent forecast models.     

Wavelet-based multi-resolution analysis and artificial neural networks for forecasting temperature and thermal power consumption

As part of the OptiEnR research project, the present paper deals with outdoor temperature and thermal power consumption forecasting. This project focuses on optimizing the functioning of a multi-energy district boiler (La Rochelle, west coast of France), adding to the plant a thermal storage unit and implementing a model-based predictive controller. The proposed short-term forecast method is based on the concept of time series and uses both a wavelet-based multi-resolution analysis and multi-layer artificial neural networks. One could speak of “MRA-ANN” methodology. The discrete wavelet transform allows decomposing sequences of past data in subsequences (named coefficients) according to different frequency domains, while preserving their temporal characteristics. From these coefficients, multi-layer Perceptrons are used to estimate future subsequences of 4 h and 30 min. Future values of outdoor temperature and thermal power consumption are then obtained by simply summing up the estimated coefficients. Substituting the prediction task of an original time series of high variability with the estimation of its wavelet coefficients on different levels of lower variability is the main idea of the present work. In addition, the sequences of past data are completed, for each of their components, by both the minute of the day and the day of the year to place the developed model in time. The present paper mainly focuses on the impact on forecast accuracy of various parameters, related with the discrete wavelet transform, such as both the wavelet order and the decomposition level, and the topology of the neural networks used. The number of past sequences to take into account and the chosen time step were also major concerns. The optimal configuration for the tools used leads to very good forecasting results and validates the proposed MRA-ANN methodology.     

Prediction of urban stormwater quality using artificial neural networks

There are a vast number of complex, interrelated processes influencing urban stormwater quality. However, the lack of measured fundamental variables prevents the construction of process-based models. Furthermore, hybrid models such as the buildup-washoff models are generally crude simplifications of reality. This has created the need for statistical models, capable of making use of the readily accessible data. In this paper, artificial neural networks (ANN) were used to predict stormwater quality at urbanized catchments located throughout the United States. Five constituents were analysed: chemical oxygen demand (COD), lead (Pb), suspended solids (SS), total Kjeldhal nitrogen (TKN) and total phosphorus (TP). Multiple linear regression equations were initially constructed upon logarithmically transformed data. Input variables were primarily selected using a stepwise regression approach, combined with process knowledge. Variables found significant in the regression models were then used to construct ANN models. Other important network parameters such as learning rate, momentum and the number of hidden nodes were optimized using a trial and error approach. The final ANN models were then compared with the multiple linear regression models. In summary, ANN models were generally less accurate than the regression models and more time consuming to construct. This infers that ANN models are not more applicable than regression models when predicting urban stormwater quality.     

Evolutionary ensemble of diverse artificial neural networks using speciation

Recently, many researchers have designed neural network architectures with evolutionary algorithms but most of them have used only the fittest solution of the last generation. To better exploit information, an ensemble of individuals is a more promising choice because information that is derived from combining a set of classifiers might produce higher accuracy than merely using the information from the best classifier among them. One of the major factors for optimum accuracy is the diversity of the classifier set. In this paper, we present a method of generating diverse evolutionary neural networks through fitness sharing and then combining these networks by the behavior knowledge space method. Fitness sharing that shares resources if the distance between the individuals is smaller than the sharing radius is a representative speciation method, which produces diverse results than standard evolutionary algorithms that converge to only one solution. Especially, the proposed method calculates the distance between the individuals using average output, Pearson correlation and modified Kullback–Leibler entropy to enhance fitness sharing performance. In experiments with Australian credit card assessment, breast cancer, and diabetes in the UCI database, the proposed method performed better than not only the non-speciation method but also better than previously published methods.     

Evaluating of traumatic brain injuries using artificial neural networks

The purpose of this study is to develop a diagnostic system to detect the severity of traumatic brain injuries using artificial neural networks. Three layered back propagation neural network with an input layer of 10 nodes whose output providing the inputs to a hidden layer was used. Thirty-two patients with traumatic brain injuries in different age and gender were taken in the study. Electroencephalography, Trauma and Glasgow coma scores were used for evaluating the data. The results obtained from the system were compared with the findings of neurologists. We found a significant relationship between the findings of neurologists and systems output for normal, mild, moderate and severe electroencephalography tracing data. Getting this system in routine use will lead to make a rapid decision for the degree of trauma with electroencephalography and revised trauma score.