Single Artificial Neural Network Research Articles

A transferable artificial neural network model for atomic forces in nanoparticles.

We have designed a new method to fit the energy and atomic forces using a single artificial neural network (SANN) for any number of chemical species present in a molecular system. The traditional approach for fitting the potential energy surface for a multicomponent system using artificial neural network (ANN) is to consider n number of networks for n number of chemical species in the system. This shoots the computational cost and makes it difficult to apply to a system containing more number of species. We present a new strategy of using a SANN to compute energy and forces of a chemical system. Since atomic forces are significant for geometry optimizations and molecular dynamics simulations for any chemical system, their accurate prediction is of utmost importance. So, to predict the atomic forces, we have modified the traditional way of fitting forces from underlying energy expression. We have applied our strategy to study geometry optimizations and dynamics in gold-silver nanoalloys and thiol protected gold nanoclusters. Also, force fitting has made it possible to train smaller sized systems and extrapolate the parameters to make accurate predictions for larger systems. This proposed strategy has definitely made the mapping and fitting of atomic forces easier and can be applied to a wide variety of molecular systems.

Gas turbine gas-path fault identification using nested artificial neural networks

Purpose The purpose of this paper is to present a quantitative fault diagnostic technique for a two-shaft gas turbine engine applications. Design/methodology/approach Nested artificial neural networks (NANNs) were used to estimate the progressive deterioration of single and multiple gas-path components in terms of mass flow rate and isentropic efficiency indices. The data required to train and test this method are attained from a thermodynamic model of the engine under steady-state conditions. To evaluate the tolerance of the method against measurement uncertainties, Gaussian noise values were considered. Findings The test results revealed that this proposed method is capable of quantifying single, double and triple component faults with a sufficiently high degree of accuracy. Moreover, the authors confirmed that NANNs have derivable advantages over the single structure-based methods available in the public domain, particularly over those designed to perform single and multiple faults together. Practical implications This method can be used to assess engine’s health status to schedule its maintenance. Originality/value For complicated gas turbine diagnostic problems, the conventional single artificial neural network (ANN) structure-based fault diagnostic technique may not be enough to get robust and accurate results. The diagnostic task can rather be better done if it is divided and shared with multiple neural network structures. The authors thus used seven decentralized ANN structures to assess seven different component fault scenarios, which enhances the fault identification accuracy significantly.

Modelling reference evapotranspiration using a new wavelet conjunction heuristic method: Wavelet extreme learning machine vs wavelet neural networks

Evapotranspiration is an important parameter in linking ecosystem functioning, climate and carbon feedbacks, agricultural management, and water resources. This study investigates the applicability of wavelet extreme learning machine (WELM) model which uses discrete wavelet transform and ELM methods in estimating daily reference evapotranspiration (ET0). Various combination of climatic data of temperature, solar radiation, relative humidity and wind speed from two stations, Ankara and Kirikkale, located in central Anatolia region of Turkey were used as inputs to the WELM models. The WELM estimates were compared with wavelet artificial neural networks (WANN) and single artificial neural network (ANN), ELM and online sequential ELM (OS-ELM) models. The results indicate that the models comprising four input variables as inputs provide better accuracy than the models with less inputs. Solar radiation was found to be the most effective variable on ET0. Wavelet conjunction models (e.g. WELM and WANN) generally show better accuracy compared to the single models and WELM model is found to be the best model in estimating ET0. The root mean square error and mean relative error accuracies of the ELM, ANN and WANN models were improved by 28–25%, 32–32% and 27–26% for the Ankara Station and by 14–14%, 58–58% and 32–36% for the Kirikkale Station.

A Single Layer Functional Link Artificial Neural Network based on Chebyshev Polynomials for Neural Evaluations of Nonlinear Nth Order Fuzzy Differential Equations

Abstract Bearing in mind the considerable importance of fuzzy differential equations (FDEs) in different fields of science and engineering, in this paper, nonlinear nth order FDEs are approximated, heuristically. The analysis is carried out on using Chebyshev neural network (ChNN), which is a type of single layer functional link artificial neural network (FLANN). Besides, explication of generalized Hukuhara differentiability (gH-differentiability) is also added for the nth order differentiability of fuzzy-valued functions. Moreover, general formulation of the structure of ChNN for the governing problem is described and assessed on some examples of nonlinear FDEs. In addition, comparison analysis of the proposed method with Runge-Kutta method is added and also portrayed the error bars that clarify the feasibility of attained solutions and validity of the method.

Organic memristive devices for perceptron applications

One of the most challenging tasks in neuromorphic applications, in the field of artificial intelligence, is the hardware realization of artificial neural networks (ANNs) which are able to learn during information processing (pattern recognition and classification, approximation, prediction, etc).In this scenario, thanks to their ability to keep the memory of their previous conductive state, memristors are widely considered as promising elements for the efficient implementation of ANNs. In this paper we present a short review of the design and the hardware realization of single and double layer ANNs, which are able to perform linearly separable and non-separable logic classification, using organic memristive devices as elements, ensuring the network weight adjustment.

Machine learning closures for model order reduction of thermal fluids

• A machine learning closure approach is proposed for reduced order modeling of thermal fluids. • A single hidden layer feed forward neural network architecture is developed for Boussinesq equations. • An extreme learning machine strategy is implemented for fast training. • The robustness of the model has been tested by considering the differentially heated cavity flow problem. • It is shown that the proposed model significantly improves the performance of reduced order models. We put forth a data-driven closure modeling approach for stabilizing projection based reduced order models for the Bousinessq equations. The effect of discarded modes is taken into account using a machine learning architecture consisting of a single hidden layer feed-forward artificial neural network to achieve robust stabilization with respect to parameter changes. For training our network architecture, we implement an extreme learning machine strategy to utilize fast learning speeds and excellent generalized predictive capabilities for underlying statistical trends. The architecture is then deployed to recover reduced order model dynamics of flow phenomena which are not used in our training data set. A two-dimensional differentially heated cavity flow is used to demonstrate the advantage of the proposed framework considering a large set of modeling parameters. It is observed that the proposed closure strategy performs remarkably well in stabilizing the temporal mode evolution and represents a promising direction for closure development of predictive reduced order models for thermal fluids.

A novel modular ANN architecture for efficient monitoring of gases/odours in real-time

Data pre-processing is tremendously used for enhanced classification of gases. However, it suppresses the concentration variances of different gas samples. A classical solution of using single artificial neural network (ANN) architecture is also inefficient and renders degraded quantification. In this paper, a novel modular ANN design has been proposed to provide an efficient and scalable solution in real–time. Here, two separate ANN blocks viz. classifier block and quantifier block have been used to provide efficient and scalable gas monitoring in real—time. The classifier ANN consists of two stages. In the first stage, the Net1-NDSRT has been trained to transform raw sensor responses into corresponding virtual multi-sensor responses using normalized difference sensor response transformation (NDSRT). These responses have been fed to the second stage (i.e., Net2-classifier). The Net2-classifier has been trained to classify various gas samples to their respective class. Further, the quantifier block has parallel ANN modules, multiplexed to quantify each gas. Therefore, the classifier ANN decides class and quantifier ANN decides the exact quantity of the gas/odor present in the respective sample of that class.

Comparison of single and modular ANN based fault detector and classifier for double circuit transmission lines

Comparison of single and modular artificial neural network based techniques for shunt faults detection and classification in double end fed double circuit transmission line is presented in this paper. The proposed method uses the voltages and currents signals available at the local end of line. The model of the power system is developed using MATLAB® software. Effects of variations in pre-fault power flow angle, fault inception angle, source strength, fault resistance, fault type, fault distance and CT saturation have been investigated extensively on the performance of the ANN based protection scheme. Additionally, the effects of network changes: double circuit and single circuit operation with other line switched out and grounded (/ungrounded), intercircuit and cross-country faults have also been investigated. Thus, the present work encompasses practically the entire range of possible operating conditions, which has not been reported earlier. The simulation results are presented to validate the effectiveness of the proposed approach. The main advantage of the proposed technique is that the variation in power system parameters under a variety of operating conditions and single/double circuit operations does not affect its performance. And this technique correctly detects and classifies the intercircuit and cross-country faults which have not been reported so-far.Keywords: Artificial neural network, cross country fault; transmission line protection; intercircuit faults and single circuit operation.

Estimation of Leakage Ratio Using Principal Component Analysis and Artificial Neural Network in Water Distribution Systems

Leaks in a water distribution network (WDS) constitute losses of water supply caused by pipeline failure, operational loss, and physical factors. This has raised the need for studies on the factors affecting the leakage ratio and estimation of leakage volume in a water supply system. In this study, principal component analysis (PCA) and artificial neural network (ANN) were used to estimate the volume of water leakage in a WDS. For the study, six main effective parameters were selected and standardized data obtained through the Z-score method. The PCA-ANN model was devised and the leakage ratio was estimated. An accuracy assessment was performed to compare the measured leakage ratio to that of the simulated model. The results showed that the PCA-ANN method was more accurate for estimating the leakage ratio than a single ANN simulation. In addition, the estimation results differed according to the number of neurons in the ANN model’s hidden layers. In this study, an ANN with multiple hidden layers was found to be the best method for estimating the leakage ratio with 12–12 neurons. This suggested approaches to improve the accuracy of leakage ratio estimation, as well as a scientific approach toward the sustainable management of water distribution systems.

A comparison between single layer and multilayer artificial neural networks in predicting diesel fuel properties using near infrared spectrum

ABSTRACTThe implementation of near infrared spectroscopy in monitoring diesel fuel properties is highly dependent on the capability of its predictive model. This study investigates the feasibility of a single layer artificial neural networks among various predictive models in predicting the diesel fuel properties using near infrared spectrum. Results were compared and discussed with that reported in previous studies that used the same data in predicting the diesel fuel properties. Findings show that the proposed single layer outperforms popular models, and is comparable with a recent advanced models in predicting the diesel fuel properties using near Infrared spectrum without data reduction.

Neural prediction of concrete compressive strength

In the past, a few researchers predicted the compressive strength of concrete from its ingredients by employing artificial neural network (ANN). Evaluation of the models with different performance metrics, such as correlation coefficient and errors of estimation, indicated that there was scope for improvement in the prediction performance of ANN. In this paper development of prediction models has been carried out for superior performance with two concepts: single ANN and modular ANN. Experimental data from literature have been utilised for the study. Better overall performance of the developed ANN models than reported in the literature was ascertained by higher correlation, less root mean square error and mean absolute error. The performance of the modular ANN concept was superior to that of single ANN concept for the present application.

Neural prediction of concrete compressive strength

In the past, a few researchers predicted the compressive strength of concrete from its ingredients by employing artificial neural network (ANN). Evaluation of the models with different performance metrics, such as correlation coefficient and errors of estimation, indicated that there was scope for improvement in the prediction performance of ANN. In this paper development of prediction models has been carried out for superior performance with two concepts: single ANN and modular ANN. Experimental data from literature have been utilised for the study. Better overall performance of the developed ANN models than reported in the literature was ascertained by higher correlation, less root mean square error and mean absolute error. The performance of the modular ANN concept was superior to that of single ANN concept for the present application.

Two-Stage Artificial Neural Network Model for Short-Term Load Forecasting

Abstract Short-term load forecast (STLF) is important to ensure stable, reliable and efficient power system operations. In this paper, we propose a two-stage artificial neural network (ANN) model for load forecasting application. The proposed system is currently being tested in the Taiwan Power Company (TPC) with potential for future adoption in their decision support systems. The accuracy of the proposed forecast model is tested using the historical data obtained from TPC; the results show that the proposed two-stage ANN model can outperform a previously proposed single stage ANN load forecast model.

A multiobjective approach in constructing a predictive model for Fischer‐Tropsch synthesis

AbstractFischer‐Tropsch synthesis (FTS) is an important chemical process that produces a wide range of hydrocarbons. The exact mechanism of FTS is not yet fully understood, so prediction of the FTS products distribution is a not a trivial task. So far, artificial neural network (ANN) has been successfully applied for modeling varieties of chemical processes whenever sufficient and well‐distributed training patterns are available. However, for most chemical processes such as FTS, acquiring such amount of data is very time‐consuming and expensive. In such cases, neural network ensemble (NNE) has shown a significant generalization ability. An NNE is a set of diverse and accurate ANNs trained for the same task, and its output is a combination of outputs of these ANNs. This paper proposes a new NNE approach called NNE‐NSGA‐II that tries to prune this set by a modified nondominated sorting genetic algorithm to achieve an optimum subset according to 2 conflicting objectives, which are minimizing root‐mean‐square error in training and unseen data sets. Finally, a comparative study is performed on a single best ANN, a regular NNE, NNE‐NSGA, and 3 popular ensemble of decision trees called random forest, stochastic gradient boosting, and AdaBoost.R2. The results show that in training data set, stochastic gradient boosting and AdaBoost.R2 have better fitted the samples; however, for the predicted FTS products in unseen data set, NNEs methods specially NNE‐NSGA‐II have considerably improved the generalization ability in comparison with the other competing approaches.

Prediction of overall glucose yield in hydrolysis of pretreated sugarcane bagasse using a single artificial neural network: good insight for process development

AbstractBACKGROUNDIn this work a single artificial neural network (ANN) was used to model the overall yield of glucose (YGLC) as a function of a wide range of operating conditions of both pretreatment and enzymatic hydrolysis.RESULTSThe model was validated experimentally and presented good predictions of YGLC. Sensitivity analysis using the ANN model indicated that most of the operating parameters, except for pretreatment time, were statistically significant (P‐value <0.05). Experiments showed that the processing of sugarcane bagasse (in natura) results in a satisfactory glucose yield of 69.34% when pretreated for 60 min with low initial biomass concentration and acid concentration (10% and 1.0% w/v), and followed by enzymatic hydrolysis for 72 h with 3.0% w/v substrate loading and 60 FPU per gWIS enzyme concentration.CONCLUSIONThis study demonstrated how pretreatment and enzymatic hydrolysis data can be used to parameterize a single ANN model. Acceptable predictions of YGLC are achieved in terms of RSD, MSE and R2. Supported by the model, this study provided a good insight for process development. © 2017 Society of Chemical Industry

Prediction of the concentration of dye and nanosilver particle on silk fabric using artificial neural network

PurposeThis study aimed to Simultaneous matching of color and antimicrobial properties of silk fabric treated with silver nanoparticle. The antimicrobial finishing using silver nanoparticles (AgNPs) is one of the most important finishing processes in the textile industry. Color matching is widely applied in the textile industry, but there has been a need for the prediction of AgNPs concentration for the matching of dyed silver-treated samples.Design/methodology/approachIn this research, the silk fabrics were dyed with various concentrations of C.I. Acid Red 359 dye at 0.5, 1, 1.5 and 2 per cent (w/w). The dyed fabrics were then coated with AgNPs in several concentrations at 0.015, 0.030, 0.050, 0.100 and 0.250 ml/l. The prediction of dye and AgNPs concentrations were evaluated using single constant color matching and artificial neural network techniques.FindingsThe obtained results indicate that the accuracy of dye concentration prediction, as well as AgNPs concentration prediction, was improved by using a neural network method. Also, the correlation between actual and predicted dye and AgNPs concentrations in the best neural networks is more than the single constant color matching method.Originality/valueSimultaneous antibacterial and color matching of nanosilver-treated fabric is novel. This method achieved acceptable accuracy for antibacterial and color matching.

Variable complexity online sequential extreme learning machine, with applications to streamflow prediction

In situations where new data arrive continually, online learning algorithms are computationally much less costly than batch learning ones in maintaining the model up-to-date. The extreme learning machine (ELM), a single hidden layer artificial neural network with random weights in the hidden layer, is solved by linear least squares, and has an online learning version, the online sequential ELM (OSELM). As more data become available during online learning, information on the longer time scale becomes available, so ideally the model complexity should be allowed to change, but the number of hidden nodes (HN) remains fixed in OSELM. A variable complexity VC-OSELM algorithm is proposed to dynamically add or remove HN in the OSELM, allowing the model complexity to vary automatically as online learning proceeds. The performance of VC-OSELM was compared with OSELM in daily streamflow predictions at two hydrological stations in British Columbia, Canada, with VC-OSELM significantly outperforming OSELM in mean absolute error, root mean squared error and Nash-Sutcliffe efficiency at both stations.

American Sign Language Alphabet Recognition Using a Neuromorphic Sensor and an Artificial Neural Network.

This paper reports the design and analysis of an American Sign Language (ASL) alphabet translation system implemented in hardware using a Field-Programmable Gate Array. The system process consists of three stages, the first being the communication with the neuromorphic camera (also called Dynamic Vision Sensor, DVS) sensor using the Universal Serial Bus protocol. The feature extraction of the events generated by the DVS is the second part of the process, consisting of a presentation of the digital image processing algorithms developed in software, which aim to reduce redundant information and prepare the data for the third stage. The last stage of the system process is the classification of the ASL alphabet, achieved with a single artificial neural network implemented in digital hardware for higher speed. The overall result is the development of a classification system using the ASL signs contour, fully implemented in a reconfigurable device. The experimental results consist of a comparative analysis of the recognition rate among the alphabet signs using the neuromorphic camera in order to prove the proper operation of the digital image processing algorithms. In the experiments performed with 720 samples of 24 signs, a recognition accuracy of 79.58% was obtained.

Fault detection and diagnosis in asymmetric multilevel inverter using artificial neural network

ABSTRACTThe increased component requirement to realise multilevel inverter (MLI) fallout in a higher fault prospect due to power semiconductors. In this scenario, efficient fault detection and diagnosis (FDD) strategies to detect and locate the power semiconductor faults have to be incorporated in addition to the conventional protection systems. Even though a number of FDD methods have been introduced in the symmetrical cascaded H-bridge (CHB) MLIs, very few methods address the FDD in asymmetric CHB-MLIs. In this paper, the gate-open circuit FDD strategy in asymmetric CHB-MLI is presented. Here, a single artificial neural network (ANN) is used to detect and diagnose the fault in both binary and trinary configurations of the asymmetric CHB-MLIs. In this method, features of the output voltage of the MLIs are used as to train the ANN for FDD method. The results prove the validity of the proposed method in detecting and locating the fault in both asymmetric MLI configurations. Finally, the ANN response to the input parameter variation is also analysed to access the performance of the proposed ANN-based FDD strategy.

Bi-modal derivative adaptive activation function sigmoidal feedforward artificial neural networks

In this work an adaptive mechanism for choosing the activation function is proposed and described. Four bi-modal derivative sigmoidal adaptive activation function is used as the activation function at the hidden layer of a single hidden layer sigmoidal feedforward artificial neural networks. These four bi-modal derivative activation functions are grouped as asymmetric and anti-symmetric activation functions (in groups of two each). For the purpose of comparison, the logistic function (an asymmetric function) and the function obtained by subtracting 0.5 from it (an anti-symmetric) function is also used as activation function for the hidden layer nodes’. The resilient backpropagation algorithm with improved weight-tracking (iRprop+) is used to adapt the parameter of the activation functions and also the weights and/or biases of the sigmoidal feedforward artificial neural networks. The learning tasks used to demonstrate the efficacy and efficiency of the proposed mechanism are 10 function approximation tasks and four real benchmark problems taken from the UCI machine learning repository. The obtained results demonstrate that both for asymmetric as well as anti-symmetric activation usage, the proposed/used adaptive activation functions are demonstratively as good as if not better than the sigmoidal function without any adaptive parameter when used as activation function of the hidden layer nodes.