Search

Applying artificial neural network techniques to forecast the electricity production of photovoltaic (PV) power plants is a novel concept. A reliable analytical model for calculating the energy output of a grid-connected solar plant is very difficult to establish because of hourly, daily, and seasonal variations in climate. The current study estimated and predicted the energy production of a connected PV system that was installed in Cairo, Egypt (30.13° N and 31.40 ° E) using an artificial neural network. Four seasons' worth of data (summer, autumn, winter, and spring) were methodically assessed using information from the climate database. The parameters that had an impact on the electrical data of PV modules included meteorological and irradiation variables, energy output, and the user's needs used to verify the NARX feedback neural networks. Prediction performance metrics were obtained, such as the correlation coefficient (R) and root mean square error (RMSE). The observed correlation coefficient ranged from 99% to 100%, indicating that the expected results are verified, while the mean error fluctuates very little. [ABSTRACT FROM AUTHOR]

The paper involved conducting preliminary research to explore the identification and control of a multi-dimensional, non-linear, and non-stationary cement grinding process using artificial neural networks and various other non-linear models. The primary objective was to establish a precise model that accurately characterizes the functioning of the grinding system. Several model structures were employed, including NARX models based on feed-forward network, Elman, Jordan, and Layer-Recurrent Network (LRN) recurrent networks, as well as MTL (Multi-Task Learning) and traditional NARX non-linear models. It was observed that, in contrast to the linear models, the non-linear models exhibited significantly superior performance in the modeling of the system. Another notable outcome of this research is the proposal of a neurocontroller, functioning as an expert system, which can provide control signals to operators. The development and implementation of such a neurocontroller have the potential to enhance the quality, simplicity, and efficiency of cement grinding process control.

Copyright of Revista CienciaUAT is the property of Universidad Autonoma de Tamaulipas and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Nowadays, most of the world's population lives in urban centres, where air quality levels are not strictly checked; citizens are exposed to air quality levels over the limits of the World Health Organization. The interaction between the issuing and atmospheric sources influences the air quality or level. The local climate conditions (temperature, humidity, winds, rainfall) determine a greater or less dispersion of the pollutants present in the atmosphere. In this sense, this work aimed to build a math modelling prediction to control the air quality around the campus of IPBeja, which is in the vicinity of a car traffic zone. The researchers have been analysing the data from the last months, particle matter (PM10 and PM2.5), and meteorological parameters for prediction using NARX. The results show a considerable increase in particles in occasional periods, reaching average values of 135 μg/m3 for PM10 and 52 μg/m3 for PM2.5. Thus, the monitoring and prediction serve as a warning to perceive these changes and be able to relate them to natural phenomena or issuing sources in specific cases. [ABSTRACT FROM AUTHOR]

Precise wind speed prediction is a key factor in many energy applications, especially when wind energy is integrated with power grids. However, because of the intermittent and nonstationary nature of wind speed, modeling and predicting it is a challenge. In addition, using uncorrelated multivariate variables as exogenous input variables often adversely impacts the performance of prediction models. In this paper, we present a multistep short-term wind speed prediction using multivariate exogenous input variables. We implement different variable selection methods to select the best set of variables that significantly improve the performance of prediction models. We evaluate the performance of eight transfer learning methods, four shallow neural networks (NNs), and the persistence method on predicting the future values of wind speed using ultrashort-term, short-term, and multistep time horizons. We performed the evaluation over two-year high-sampled wind speed data averaged at 10-minute intervals. Results show that Nonlinear Auto-Regressive Exogenous (NARX) model outperformed all other methods, achieving an average mean absolute error (MAE) and root mean square error (RMSE) of 0.2205 and 0.3405 for multistep predictions, respectively. Despite the lower performance of the transfer learning methods (i.e., 0.43 and 0.58 for MAE and RMSE, respectively), it is believed that results could be further improved with a better enhancement of the feature selection and model parameters.

Groundwater resources (GWR) are vital to agricultural crop production, everyday life, and economic development. As a result, accurate groundwater level (GWL) prediction would aid in the long-term management of GWR. A comparative analysis was performed to test the predictive capabilities of models based on non-linear autoregressive with exogenous inputs (NARX) and extreme learning machine (ELM). Long-term predictions were performed using GWL and rainfall time series measured in two sites, Bogra and Dinajpur, in Bangladesh's northwest region from 1981 to 2017. The delay between precipitation and GWL was assessed through the cross-correlation function, computing an input delay equal to 2 months for both sites. Furthermore, the auto-correlation of the GWL was also performed to evaluate the optimal feedback delay, showing the seasonality of GWL fluctuations with a peak at 12 months for both sites. However, the sensitivity to changes in the feedback delay was also assessed, comparing the predictions produced for a feedback delay equivalent to 12 months with those computed for delays ranging from 1 to 11 months. Outputs of the two proposed models were evaluated using different metrics: the root mean square error (RMSE), mean absolute error (MAE), relative absolute error (RAE), and correlation coefficient (CC). The results revealed that NARX models outperformed ELM models. NARX models were able to provide accurate long-term predictions, with R2 equal to 0.918 and 0.947 for Bogra and Dinajpur sites, respectively, with a forecasting horizon τ = 12 months. ELM models also provided good forecasts for Dinajpur, but less accurate for Bogra, with R2 respectively equal to 0.825 and 0.675 with τ = 12 months. This research would provide a practical and efficient approach to GWL prediction that could aid policymakers in implementing long-term GWR management. [ABSTRACT FROM AUTHOR]

Precise wind speed prediction is a key factor in many energy applications, especially when wind energy is integrated with power grids. However, because of the intermittent and nonstationary nature of wind speed, modeling and predicting it is a challenge. In addition, using uncorrelated multivariate variables as exogenous input variables often adversely impacts the performance of prediction models. In this paper, we present a multistep short-term wind speed prediction using multivariate exogenous input variables. We implement different variable selection methods to select the best set of variables that significantly improve the performance of prediction models. We evaluate the performance of eight transfer learning methods, four shallow neural networks (NNs), and the persistence method on predicting the future values of wind speed using ultrashort-term, short-term, and multistep time horizons. We performed the evaluation over two-year high-sampled wind speed data averaged at 10-minute intervals. Results show that Nonlinear Auto-Regressive Exogenous (NARX) model outperformed all other methods, achieving an average mean absolute error (MAE) and root mean square error (RMSE) of 0.2205 and 0.3405 for multistep predictions, respectively. Despite the lower performance of the transfer learning methods (i.e., 0.43 and 0.58 for MAE and RMSE, respectively), it is believed that results could be further improved with a better enhancement of the feature selection and model parameters. [ABSTRACT FROM AUTHOR]

Highlights • NARX were applied to obtain groundwater level forecasts with lead times up to half a year. • Porous, fractured and karst aquifers with and without external influences on groundwater levels. • The developed approach is easily transferable on other wells. • Input- and feedback delays were determined by applying STL time series decomposition. • The results indicate an outstanding suitability of NARX for groundwater level predictions. Abstract While the application of neural networks for groundwater level forecasting in general has been investigated by many authors, the use of nonlinear autoregressive networks with exogenous inputs (NARX) is relatively new. For this work NARX were applied to obtain groundwater level forecasts for several wells in southwest Germany. Wells in porous, fractured and karst aquifers were investigated and forecasts of lead times up to half a year were conducted for both influenced (e.g. nearby pumping) and uninfluenced wells. Precipitation and temperature were chosen as predictors, which makes the selected approach easily transferable, since both parameters are widely available and simple to measure. Input and feedback delays were determined by applying STL time series decomposition on the data and using auto- and cross-correlation functions on the remainders to determine significant time lags. Coefficient of determination, (relative) root mean squared error and Nash-Sutcliffe efficiency were used to evaluate forecasts, the model selection was based on an out-of-sample validation on rolling basis. The results are promising and indicate an outstanding suitability of NARX for groundwater level predictions with such a small set of inputs in all three aquifer types. [ABSTRACT FROM AUTHOR]

Economic activity nowcasting (i. e., making current-period estimates) is convenient because most traditional measures of economic activity come with substantial lags. We aim at nowcasting ise, a short-term economic activity indicator in Colombia. Inputs are the ise's lags and a dataset of payments made with electronic transfers and cheques among individuals, firms, and the central government. Under a predictive modeling approach, we employ a non-linear autoregressive exogenous neural network model. Results suggest that our choice of inputs and predictive method enable us to nowcast economic activity with fair accuracy. Also, we validate that electronic payments data significantly reduce the nowcast error of a benchmark non-linear autoregressive neural network model. Nowcasting economic activity from electronic payment instruments data not only contributes to agents' decision making and economic modeling, but also supports new research paths on how to use retail payments data for appending current models. [ABSTRACT FROM AUTHOR]

Current cybersecurity approaches are response-driven and ineffective, as they do not account for dynamic adversarial movement. Using empirical evidence from observations of two Red Team-Blue Team cybersecurity training exercises held at Idaho National Laboratory and the Michigan Cyber Range, we used four different models to make temporal predictions of how adversaries progress through cyberattacks: nonlinear autoregressive (NAR) neural network, NAR neural network with exogenous input (NARX), NAR neural network for multi-steps-ahead prediction, and autoregressive integrated moving average (ARIMA). The obtained results demonstrate that the trained models can capture different variations in adversarial movement across the two datasets with reliable accuracy. [ABSTRACT FROM AUTHOR]

This paper addresses the nonlinear identification of liquid saturated steam heat exchanger (LSSHE) using artificial neural network model. Heat exchanger is a highly nonlinear and non-minimum phase process and often its working conditions are variable. Experimental data obtained from fluid outlet temperature measurement in laboratory environment is used as the output variable and the rate of change of fluid flow into the system as input too. The results of identification using neural network and conventional nonlinear models are compared together. The simulation results show that neural network model is more accurate and faster in comparison with conventional nonlinear models for a time series data because of the independence of the model assignment. [ABSTRACT FROM AUTHOR]

• Application of NN models for exhaust gas aftertreatment reactors is presented. • Different NN architectures are used for predicting the state and outlet variables. • Training data is generated by virtually driving a physics-based system level model. • Variety of real-world driving conditions are considered for producing quality data. • Model accuracy and generalizability is evaluated by comprehensive comparisons. A comprehensive evaluation of neural network (NN) methods to model exhaust gas aftertreatment reactors is presented in this study. A combination of non-linear autoregressive model with exogenous inputs (NARX) network and static NN is utilized to capture the dynamic behavior of the state and outlet variables, such as coverage fractions, temperatures, and conversions, of monolith reactors used in the abatement of automobile emissions. The efficacy of this methodology is illustrated by modeling the diesel oxidation catalyst (DOC) and selective catalytic reduction (SCR) reactors of a diesel engine exhaust gas aftertreatment system. The final NN topology is designed by carefully comparing the model performances in the training and testing datasets. Model parsimony quantified by Akaike's Information Criterion is employed for choosing the number of input and feedback delays in the NARX network. The novelty of this work lies in generating quality training and validation data using a physics-based system level model comprising of the engine and aftertreatment reactor components. The accuracy and generalizability of the NN models are demonstrated by comparing the model predictions with physical model simulation results in five disparate test datasets used in vehicle certification protocols. Overall, the NN models are found to reproduce all the qualitative trends in the various state and output variables while needing minimum computing resources resulting in better than real-time performance. Therefore, with appropriate training, these models can be embedded in the electronic control unit (ECU) and utilized for model-based predictive control systems. [ABSTRACT FROM AUTHOR]

Abstract: This paper describes the modelling of dry friction using a NARX (Nonlinear AutoRegressive with eXogeneous inputs) type shunting neural network model. An ensemble model is then constructed by combining the shunting neural network model with the physics based DNLR (dynamic nonlinear regression) Maxwell slip model. [Copyright &y& Elsevier]

To overcome the data limitations of wave and environmental characteristics for estimating the significant wave height (Hs), this study investigates the use of an available dataset for wave characteristics to predict a long-term period of Hs for the Red Sea. A novel soft-computing approach is designed for the time-series prediction of Hs using the time delay of average wave period and Hs measurements. Buoy station of Jeddah, Saudi Arabia, datasets for 2009 and 2010 are used for designing and validating the proposed model. The time-series identification system of nonlinear autoregressive networks with exogenous inputs (NARX) and recurrent neural network (RNN) with cascade input variables based on neural network solutions were integrated through a sequential system to develop the new approach RNNARX. The RNNARX was compared with the conventional RNN, NARX neural network (NNARX), and previous studies' results to verify its robustness. The proposed model was evaluated to predict hourly and daily Hs. The results showed that the proposed model achieves good performance for long-term prediction of Hs. The sequential system improved the performance of RNN and NNARX models for the time-series prediction of Hs. The comparison results showed that RNNARX performance is suitable for the Hs prediction of the study region. The model performances in terms of coefficient determination and root mean square error were 0.90 and 0.149 m, respectively, with a prediction error of 2.95% for four days lead times. • A newRNNARX model is proposed for short- and long-terms time series predictions of Hs. • RNNARX model is designed based on current wave characteristics for predicting Hs. • RNNARX is suitable for the time-series prediction of Hs at hourly and daily lead times. [ABSTRACT FROM AUTHOR]

Power consumption in electronic systems is an essential feature for the management of energy autonomy, performance analysis, and the aging monitoring of components. Thus, several research studies have been devoted to the development of power models and profilers for embedded systems. Each of these models is designed to fit a specific usage context. This paper is a part of a series of works dedicated to modeling and monitoring embedded systems in airborne equipment. The objective of this paper is twofold. Firstly, it presents an overview of the most used models in the literature. Then, it offers a comparative analysis of these models according to a set of criteria, such as the modeling assumptions, the necessary instrumentation necessary, the accuracy, and the complexity of implementation. Secondly, we introduce a new power estimator for ARM-Based embedded systems, with component-level granularity. The estimator is based on NARX neural networks and used to monitor power for diagnosis purposes. The obtained experimental results highlight the advantages and limitations of the models presented in the literature and demonstrate the effectiveness of the proposed NARX, having obtained the best results in its class for a smartphone (An online Mean Absolute Percentage Error = 2.2%). [ABSTRACT FROM AUTHOR]