Search

One of the major research topics in electrical engineering in recent years is load prediction. Short-term load forecasting is necessary for the design, operation, and management of the power system. It is used, among others, by utilities, system operators, electricity producers, and suppliers. Artificial Neural Networks (ANN) have been used for short-term load prediction. The work has been completed to ensure day-to-day operations. Here, the proposed neural networks were trained and tested using newly available data from Hubli Electricity Supply Company Limited (HESCOM). This paper presents a method for predicting the load of a power system based on a Neural Network (NN). Matrix Laboratory (MATLAB) software is used to create training and test simulations. The error was defined as Mean Absolute Percentage Error (MAPE). [ABSTRACT FROM AUTHOR]

With the vast popularity of the deep learning models in the engineering and mathematical fields, Artificial Neural Networks (ANN) have recently attracted significant research applications in agriculture, economics, informatics and finance. In this paper, we use a deep learning method to capture and predict the unknown complex nonlinear characteristics of agricultural output based on autoregressive artificial neural network, using Nigeria as a case study. Using the proposed model, shocks in agricultural output is analyzed and modeled using data obtained for a period of forty years (1980-2019), and compared with analyses obtained from the autoregressive integrated moving average model (ARIMA). This result is significant because it justifies the superiority of the hybrid ANN model over the traditional Box-Jenkins methodology for forecasting non-stationary time series. The empirical results show that the proposed autoregressive ANN model achieves an improved forecasting accuracy over the traditional Box-Jenkins ARIMA method. It is further proposed that various types of artificial neural networks would be useful in forecasting and solving relevant tasks and problems widely defined in global agricultural production. [ABSTRACT FROM AUTHOR]

Pore pressure prediction is a critical parameter in petroleum engineering and is essential for safe drilling operations and wellbore stability. However, traditional methods for pore pressure prediction, such as empirical correlations, require selecting appropriate input parameters and may not capture the complex relationships between these parameters and the pore pressure. In contrast, artificial neural networks (ANNs) can learn complex relationships between inputs and outputs from data. This paper presents a new empirical correlation for predicting pore pressure using ANNs. The proposed method uses 42 datasets of well log data, including temperature, porosity, and water saturation, to train ANNs for pore pressure prediction. The trained model, with the Bayesian regularization backpropagation function, predicts the pore pressure with an average absolute percentage error (AAPE) and correlation coefficient (R) of 4.22% and 0.875, respectively. The trained ANN is then used to develop a new empirical correlation that relates pore pressure to the input parameters considering the weights and biases of the optimized ANN model. To validate the proposed correlation, it is applied to a blind dataset, where the model successfully predicts the pore pressure with an AAPE of 5.44% and R of 0.957. The results show that the proposed correlation provides accurate and reliable predictions of pore pressure. The proposed method provides a robust and accurate approach for predicting pore pressure in petroleum engineering applications, which can be used to improve drilling safety and wellbore stability. [ABSTRACT FROM AUTHOR]

The paper addresses the problem of forecasting in manufacturing systems. The main aim of the research is to propose new hybrid forecasting models combining artificial intelligencebased methods with traditional techniques based on time series – namely: Hybrid econometric model, Hybrid artificial neural network model, Hybrid support vector machine model and Hybrid extreme learning machine model. The study focuses on solving the problem of limited access to independent variables. Empirical verification of the proposed models is built upon real data from the three manufacturing system areas – production planning, maintenance and quality control. Moreover, in the paper, an algorithm for the forecasting accuracy assessment and optimal method selection for industrial companies is introduced. It can serve not only as an efficient and costless tool for advanced manufacturing companies willing to select the right forecasting method for their particular needs but also as an approach supporting the initial steps of transformation towards smart factory and Industry 4.0 implementation. [ABSTRACT FROM AUTHOR]

The purpose of this paper is to predict the maximum pressure of journal bearing using ANN. The maximum pressure values are analysed using FEM and predicted using ANN. The FEM analysis is performed for micropolar lubricated hybrid journal bearing, and the results are used for training and testing the ANN model. Feedforward backpropagation algorithm is used for ANN model development. The externally applied load and rotational speed of the journal are considered as input parameters for performance predictions. ANN predictions are made within and outside the prescribed range of input parameters. This approach shows better predictions for journal bearing performance. Results obtained from FEM and ANN are in close agreement with each other. The percentage error less than 0.5 is observed for training and testing of the ANN model. The prediction error is in the range of −0.6% to 0.48%. In this paper, a mathematical model is established using FEM. The performance predictions obtained using ANN are very useful because much time can be saved which would be otherwise consumed in the experimental or theoretical bearing analysis. [ABSTRACT FROM AUTHOR]

Despite advancements in smart grid (SG) technology, effective load forecasting utilizing big data or large-scale datasets remains a complex task for energy management, planning, and control. The Saudi SGs, in alignment with the Saudi Vision 2030, have been envisioned as future electrical grids with a bidirectional flow of power and data. To that end, data analysis and predictive models can enhance Saudi SG planning and control via artificial intelligence (AI). Recently, many AI methods including deep learning (DL) algorithms for SG applications have been published in the literature and have shown superior time series predictions compared with conventional prediction models. Current load-prediction research for the Saudi grid focuses on identifying anticipated loads and consumptions, on utilizing limited historical data and the behavior of the load's consumption, and on conducting shallow forecasting models. However, little scientific proof on complex DL models or real-life application has been conducted by researchers; few articles have studied sophisticated large-scale prediction models for Saudi grids. This paper proposes hybrid DL methods to enhance the outcomes in Saudi SG load forecasting, to improve problem-relevant features, and to accurately predict complicated power consumption, with the goal of developing reliable forecasting models and of obtaining knowledge of the relationships between the various features and attributes in the Saudi SGs. The model in this paper utilizes a real dataset from the Jeddah and Medinah grids in Saudi Arabia for a full year, 2021, with a one-hour time resolution. A benchmark strategy using different conventional DL methods including artificial neural network, recurrent neural network (RNN), conventional neural networks (CNN), long short-term memory (LSTM), gated recurrent unit (GRU), and different real datasets is used to verify the proposed models. The prediction results demonstrate the effectiveness of the proposed hybrid DL models, with CNN–GRU and CNN–RNN with NRMSE obtaining 1.4673% and 1.222% improvements, respectively, in load forecasting accuracy. [ABSTRACT FROM AUTHOR]

Purpose: Solid waste (SW) is the result of rapid urbanization and industrialization, and is increasing day by day by the increasing number of population. This thesis paper emphasizes on the prediction of SW generation in the city of Dhaka and finding sustainable pathways for minimizing the gaps in the existing system. Design/methodology/approach: In this paper, the survey of different questionnaires of the Dhaka South City Corporation (DSCC) was conducted. The data of SW generation, for few years of each month, in the city of Dhaka were collected to develop a model named Artificial Neural Network (ANN). The ANN model was used for the accurate prediction of SW generation. Findings: At first, by using the ANN model with the one hidden layer and changing the number of neurons of the layer different models were created and tested. Finally, according to R values (training, test, all) the structure with six neurons in the hidden layer was selected as the suitable model. Finally, six gaps were found in the existing system of solid waste management (SWM) in the DSCC. These gaps are the main barrier for the better SWM. Originality/value: The authors propose that the best model for prediction is 12-6-3, and its training and testing results are given as 0.9972 and 0.80380, respectively. So the resulting prediction is so much close in comparison with actual data. In this paper, the opportunities of those gaps are provided for working properly and the DSCC will find the better result in the aspect of SW problem. [ABSTRACT FROM AUTHOR]

Load forecasting (LF) is an essential factor in power system management. LF helps the utility maximize the utilization of power-generating plants and schedule them both reliably and economically. In this paper, a novel and hybrid forecasting method is proposed, combining a long short-term memory network (LSTM) and neural prophet (NP) through an artificial neural network. The paper aims to predict electric load for different time horizons with improved accuracy as well as consistency. The proposed model uses historical load data, weather data, and statistical features obtained from the historical data. Multiple case studies have been conducted with two different real-time data sets on three different types of load forecasting. The hybrid model is later compared with a few established methods of load forecasting found in the literature with different performance metrics: mean average percentage error (MAPE), root mean square error (RMSE), sum of square error (SSE), and regression coefficient (R). Moreover, a guideline with various attributes is provided for different types of load forecasting considering the applications of the proposed model. The results and comparisons from our test cases showed that the proposed hybrid model improved the forecasting accuracy for three different types of load forecasting over other forecasting techniques. [ABSTRACT FROM AUTHOR]

The Gravity Recovery and Climate Experiment (GRACE) satellite has proven adept at monitoring, characterizing, and predicting hydrological variables. This paper attempted to investigate the applicability of using nonlinear autoregressive with exogenous input (NARX) neural network to forecast GRACE terrestrial water storage anomalies over 11 basins. By using six hydrological indicators as external inputs and forming all possible combinations of these variables, we have found the appropriate external inputs of the optimal NARX model for each basin. In addition, the number of acceptable time delays and the number of hidden neurons are adjusted to train out the optimal NARX model. The results reveal that the NARX models with one time delay perform better than the models with higher than one delay, and the structures of the optimal NARX models vary with basins. The performance of the optimal NARX models of the 11 basins falls into "very good" category whether during training, validating, or testing period. In comparison with GRACE Follow On (GRACE-FO) results, the predictions from the optimal NARX models are satisfactory, with the highest correlation coefficient of 0.97 in the Amazon basin and the lowest correlation coefficient of 0.62 over the Yangtze basin. The results shown here not only bridge the data gap between GRACE and GRACE-FO but also facilitate the applications of using the NARX neural network to predict climate extremes like droughts and flooding. [ABSTRACT FROM AUTHOR]

Gray theory is a truly multidisciplinary and generic theory that deals with systems that are characterized by poor information and/or for which information is lacking, so it was very important to expand the current gray theory and find out an appropriate model building method. In this paper, an improved gray GM (1, 1) model, using a technique that combines gray residual modification with artificial neural network. The fluctuation of data sequence is weakened by the gray theory and the neural network is capable of processing nonlinear adaptable information, and the GMNN is a combination of those advantages. Therefore, the paper constructs a model base of burn-through point and the simulation proves that the model base has a good performance and can improve the prediction accuracy. [ABSTRACT FROM AUTHOR]

Application of artificial neural network (ANN) models has been reported to solve variety of water resources and environmental related problems including prediction, forecasting and classification, over the last two decades. Though numerous research studies have witnessed the improved estimate of ANN models, the practical applications are sometimes limited. The black box nature of ANN models and their parameters hardly convey the physical meaning of catchment characteristics, which result in lack of transparency. In addition, it is perceived that the point prediction provided by ANN models does not explain any information about the prediction uncertainty, which reduce the reliability. Thus, there is an increasing consensus among researchers for developing methods to quantify the uncertainty of ANN models, and a comprehensive evaluation of uncertainty methods applied in ANN models is an emerging field that calls for further improvements. In this paper, methods used for quantifying the prediction uncertainty of ANN based hydrologic models are reviewed based on the research articles published from the year 2002 to 2015, which focused on modeling streamflow forecast/prediction. While the flood forecasting along with uncertainty quantification has been frequently reported in applications other than ANN in the literature, the uncertainty quantification in ANN model is a recent progress in the field, emerged from the year 2002. Based on the review, it is found that methods for best way of incorporating various aspects of uncertainty in ANN modeling require further investigation. Though model inputs, parameters and structure uncertainty are mainly considered as the source of uncertainty, information of their mutual interaction is still lacking while estimating the total prediction uncertainty. The network topology including number of layers, nodes, activation function and training algorithm has often been optimized for the model accuracy, however not in terms of model uncertainty. Finally, the effective use of various uncertainty evaluation indices should be encouraged for the meaningful quantification of uncertainty. This review article also discusses the effectiveness and drawbacks of each method and suggests recommendations for further improvement. [ABSTRACT FROM AUTHOR]

This paper proposes a new model for optimal similar days selection and its use in short-term load forecasting based on artificial neural network. Proposed day similarity metric model is based on the multi-filtering process and introduces a few novelties: (1) introduction of pre-history of similar days in a selection process; (2) extension of forecasting factors: load inertia, daylight duration and load profiles; (3) open model with possibility to add additional contribution factors; (4) particle swarm optimization is applied for calculation of the impact of different contributing factors. This approach results in optimal similar days selection even in a case where it is not obvious in advance which factors are the most relevant. Finally, the artificial neural network is used as a basic procedure for the short-term load forecast. The proposed model has been tested in the transmission system utility in Serbia, and the results are presented. [ABSTRACT FROM AUTHOR]

Solar power generation forecasting plays a vital role in optimizing grid management and stability, particularly in renewable energy-integrated power systems. This research paper presents a comprehensive study on solar power generation forecasting, evaluating traditional and advanced machine learning methods, including ARIMA, Exponential Smoothing, Support Vector Regression, Random Forest, Gradient Boosting, and Physics-based Models. Moreover, we propose an innovative Enhanced Artificial Neural Network (ANN) model, which incorporates Weather Modulation and Leveraging Prior Forecasts to enhance prediction accuracy. The proposed model is evaluated using real-world solar power generation data, and the results demonstrate its superior performance compared to traditional methods and other machine learning approaches. The Enhanced ANN model achieves an impressive Root Mean Square Error (RMSE) of 0.116 and a Mean Absolute Percentage Error (MAPE) of 36.26%. The integration of Weather Modulation allows the model to adapt to changing weather conditions, ensuring reliable forecasts even during adverse scenarios. Leveraging Prior Forecasts enables the model to capture short-term trends, reducing forecasting errors arising from abrupt weather changes. The proposed Enhanced ANN model showcases its potential as a promising tool for precise and reliable solar power generation forecasting, contributing to the efficient integration of solar energy into the power grid and advancing sustainable energy practices. [ABSTRACT FROM AUTHOR]

Daily electricity peak load forecasting is important for electricity generation capacity planning. Accurate forecasting leads to saving on excessive electricity generating capacity, while maintaining the stability of the power system. The main challenging tasks in this research field include improving forecasting accuracy and reducing computational time. This paper proposes a hybrid model involving variational mode decomposition (VMD), empirical mode decomposition (EMD), fast Fourier transform (FFT), stepwise regression, similar days selection (SD) method, and artificial neural network (ANN) for daily electricity peak load forecasting. Stepwise regression and similar days selection method are used for input variable selection. VMD and FFT are applied for data decomposition and seasonality capturing, while EMD is employed for determining an appropriate decomposition level for VMD. The hybrid model is constructed to effectively forecast special holidays, which have different patterns from other normal weekdays and weekends. The performance of the hybrid model is tested with real electricity peak load data provided by the Electricity Generating Authority of Thailand, the leading power utility state enterprise under the Ministry of Energy. Experimental results show that the hybrid model gives the best performance while saving computation time by solving the problems in input variable selection, data decomposition, and imbalance data of normal and special days in the training process. [ABSTRACT FROM AUTHOR]

In this paper, we present a new hybrid forecasting model using a decomposition method with SARIMAX model and Artificial Neural Network (ANN). The proposed model has combined linear and non- linear models such as a decomposition method with SARIMAX model and ANN. The new hybrid model is compared to SARIMA, SARIMAX, decomposition methods with SARIMA/SARIMAX models and ANN. We applied the new hybrid forecasting model to real monthly data sets such that the electricity consumption in the provincial area of Thailand and the SET index. The result shows that the new hybrid forecasting using a decomposition method with SARIMAX model and ANN performs well. The best hybrid model has reduced average error rate for 3 months and 12 months lead time forecasting of 47.3659% and 33.1853%, respectively. In addition, the new hybrid forecasting model between decomposition method with SARIMAX models and ANN has the lowest average MAPE of 1.9003% for 3 months and 2.2113% for 12 months lead time forecasting, respectively. The best forecasting model has been checked by using residual analysis. We conclude that the combined model is an effective way to improve more accurate forecasting than a single forecasting method. [ABSTRACT FROM AUTHOR]

SUMMARY: In this paper, a hybrid model of fuzzy clustering and ANN (Artificial Neural Network) is proposed for electricity price forecasting. Due to the complicated behavior of electricity price in power markets, market players are interested in maximizing profits while minimizing risks. As a result, more accurate models are required to deal with electricity price forecasting. This paper proposes a new method that makes use of fuzzy clustering preconditioned GRBFN (Generalized Radial Basis Function Network) to provide more accurate predicted prices. Fuzzy clustering plays a key role to prevent the number of learning data from decreasing at each cluster. GRBFN is one of efficient ANNs to approximate nonlinear systems. Furthermore, a modified GRBFN model is developed to improve the performance of GRBFN with the use of DA (Deterministic Annealing) clustering for the parameters initialization and EPSO (Evolutionary Particle Swarm Optimization) for optimizing the parameters of GRBFN. The proposed method is successfully applied to real data of ISO New England, USA. [ABSTRACT FROM AUTHOR]

Tarbela is the largest earth-filled dam in Pakistan, used for both irrigation and power production. Tarbela has already lost around 41.2% of its water storage capacity through 2019, and WAPDA predicts that it will continue to lose storage capacity. If this issue is ignored for an extended period of time, which is not far away, a huge disaster will occur. Sedimentation is one of the significant elements that impact the Tarbela reservoir's storage capacity. Therefore, it is crucial to accurately predict the sedimentation inside the Tarbela reservoir. In this paper, an Artificial Neural Network (ANN) architecture and multivariate regression technique are proposed to validate and predict the amount of sediment deposition inside the Tarbela reservoir. Four input parameters on yearly basis including rainfall (Ra), water inflow (Iw), minimum water reservoir level (Lr), and storage capacity of the reservoir (Cr) are used to evaluate the proposed machine learning models. Multivariate regression analysis is performed to undertake a parametric study for various combinations of influencing parameters. It was concluded that the proposed neural network model estimated the amount of sediment deposited inside the Tarbela reservoir more accurately as compared to the multivariate regression model because the maximum error in the case of the proposed neural network model was observed to be 4.01% whereas in the case of the multivariate regression model was observed to be 60.7%. Then, the validated neural network model was used for the prediction of the amount of sediment deposition inside the Tarbela reservoir for the next 20 years based on the time series univariate forecasting model ETS forecasted values of Ra, Iw, Lr, and Cr. It was also observed that the storage capacity of the Tarbela reservoir is the most influencing parameter in predicting the amount of sediment. [ABSTRACT FROM AUTHOR]

The analysis of influential machine parameters can be useful to plan and design a plastic injection molding process. However, current research in parameter analysis is mostly based on computer-aided engineering (CAE) or simulation which have been demonstrated to be inadequate for analyzing complex behavioral changes in the real injection molding process. More advanced approaches using machine learning technology specifically with artificial neural networks (ANNs) brought promising results in terms of prediction accuracy. Nevertheless, the black box and distributed representation of ANN prevent humans from gaining an insight into which process parameters give a significant influence on the final prediction output. Therefore, in this paper, we develop a simpler ANN model by using structural learning with forgetting (SLF) as the algorithm for the training process. Instead of typical backpropagation which generated a fully connected layer of the ANN model, SLF only reveals the important neurons and connections. Hence, the training process of SLF leaves only influential connections and neurons. Since each of the neurons specifically on the input layer represent each of the injection molding parameters, the ANN-SLF model can be further investigated to determine the influential process parameters. By applying SLF to the ANN training process, this experiment has successfully extracted a set of significant injection molding process parameters. [ABSTRACT FROM AUTHOR]

Southwest Asia has different climate types including arid, semiarid, Mediterranean, and temperate regions. Due to the complex interactions among components of the Earth system, forecasting precipitation is a difficult task in such large regions. The aim of this paper is to propose a learning approach, based on artificial neural network (ANN) and random forest (RF) algorithms for post-processing the output of forecasting models, in order to provide a multi-model ensemble forecasting of monthly precipitation in southwest Asia. For this purpose, four forecasting models, including GEM-NEMO, NASA-GEOSS2S, CanCM4i, and COLA-RSMAS-CCSM4, included in the North American multi-model ensemble (NMME) project, are considered for the ensemble algorithms. Since each model has nine different lead times, a total of 108 different ANN and RF models are trained for each month of the year. To train the proposed ANN an RF models, the ERA5 reanalysis dataset is employed. To compare the performance of the proposed algorithms, four performance evaluation criteria are calculated for each model. The results indicate that the performance of the ANN and RF post-processing is better than that of the individual NMME models. Moreover, RF outperformed ANN for all lead times and months of the year. [ABSTRACT FROM AUTHOR]

Conventional methods of spatial prediction, such as Kriging, require assumptions such as stationarity and isotropy, which are not easy to evaluate, and often do not hold for spatial data. For these methods, the spatial dependency structure between data should be accurately modeled, which requires expert knowledge in spatial statistics. On the other hand, spatial prediction using artificial neural network (ANN) has attracted considerable interest due to ANN's ability in learning from data without the need for complex and specialized assumptions. However, ANN models require suitable input variables for better and efficient spatial prediction. This paper aims to improve the accuracy of ANNs spatial prediction using neighboring information. Given the general principle that "closer spatial data are more dependent", we tried to somehow enter data dependency into the network by using the neighboring observations. We proposed a hybrid model of ANN and inverse distance weighting, based on nearby observations. We also proposed an ANN-based model for spatial prediction based on weighted values of nearby observations. The accuracy of the models was compared through a simulation study. The results showed that using neighboring information to train ANN, dramatically increases the prediction accuracy. [ABSTRACT FROM AUTHOR]

Wind energy is a type of renewable energy that has received much attention in the electricity market. This study focuses on forecasting wind speed at Malacca state's Station. This paper proposes using a Group Method of Data Handling (GMDH) model with a hyperbolic tangent transfer function in forecasting wind speed data in Malacca state. The performance of this model is compared with three other models: Artificial neural network (ANN) hyperbolic tangent, ANN log sigmoid and GMDH model. In addition, this study investigates the impact of using different transfer functions in data-driven models for forecasting wind speed. Usually, the application of the GMDH model only implements the second-order polynomial as a partial description. However, in this study, we implement the hyperbolic tangent transfer function in the GMDH model. The forecasting model's accuracy is evaluated using mean absolute percentage error (MAPE), root mean square error (RMSE) and mean absolute error (MAE). The results show that the GMDH model with hyperbolic tangent is highly accurate with more negligible computational power than other models. The GMDH-hyperbolic tangent model managed to improve the forecasting performance of the conventional GMDH model by 11.21% in mean absolute percentage error and outperforms other ANN models. [ABSTRACT FROM AUTHOR]

This paper proposes a novel short-term wind power forecasting approach by mining the bad data of numerical weather prediction (NWP). Today's short-term wind power forecast (WPF) highly depends on the NWP, which contributes the most in the WPF error. This paper first introduces a bad data analyzer to fully study the relationship between the WPF error with several new extracted features from the raw NWP. Second, a hierarchical structure is proposed, which is composed of a K-means clustering-based bad data detection module and a neural network (NN)-based forecasting module. In the NN module, the WPF is fully adjusted based on the output of the bad data analyzer. Simulations are performed comparing with two other different methods. It proves that the proposed approach can improve the short-term wind power forecasting by effectively identifying and adjusting the errors from NWP. [ABSTRACT FROM PUBLISHER]

We thank Zhang et al. (Nat Resour Res, 2019. 10.1007/s11053-019-09512-6) for investigating the accuracy of artificial intelligence techniques in the prediction of drought in China. In the paper by Zhang et al. (2019), two data-driven models, namely artificial neural network and support vector machine, and autoregressive integrated moving average (ARIMA) model were established to estimate standardized precipitation evapotranspiration index (SPEI) values. In that paper, temperature and precipitation values were used as independent variables to predict SPEI. They stated that ARIMA models give higher accuracy in the prediction of SPEI values. Here, not only some of the missing points and deficiencies in the original publication, but also improvements that can be made in future studies, were mentioned. In addition, several points are introduced in order to make these points more clarified for potential readers. [ABSTRACT FROM AUTHOR]

To find the optimal design for an engineering object, thousands of (or even more) simulations should be implemented to obtain the outcome data for the variously designed objects. However, repeating simulations this many times is impossible because a typical simulation is a computationally expensive task. Instead of conducting all the required simulations, a more efficient way is predicting the outcome from the approximation model, called the surrogate model. The response surface method (RSM) with polynomials and artificial neural network (ANN) are the most prominent methods in constructing a surrogate model in the engineering fields. In this study, the prediction accuracy of the surrogate models computed by using an RSM and ANN is compared with several datasets showing different complexities. This comparison is investigated by constructing the surrogate models in predicting aerodynamic performance of a wind turbine airfoil. In the current paper, it is verified that the prediction accuracy of the ANN-computed surrogate model is higher than the RSM-computed one when the datasets have a high level of complexity, but the opposite phenomenon is observed if the datasets have a low level of complexity. When the surrogate models with different accuracies are used to enhance the performance of a wind turbine airfoil, the surrogate model with a high level of accuracy produces the optimal design, showing a high performance improvement. The current study is expected to give guidance on how to properly choose between an RSM and ANN to construct a highly accurate surrogate model that can help in finding a design with a high performance improvement during the optimization process. [ABSTRACT FROM AUTHOR]

This paper presents the development of artificial neural network (ANN) model for predicting the dynamic across-wind response of tall building as per the provisions given in Indian Wind Code (IWC), IS 875 (Part-3):2015. IWC has given the procedure for estimating across-wind load response for limited aspect ratios of the building. For calculating the across-wind response not conforming to the ratios specified in the code, additional time-consuming and expensive studies are required. In order to minimise such tedious studies, an efficient computational technique is essential to determine wind response. ANN proves to be a promising alternative technique for analysing complex engineering problems. Thus, in this paper, using the best-fit model of ANN, predictions are made for the building configurations that are not included in IWC. The results are plotted as a series of charts in terms of base shear and the base bending moment. It is found that the predictions made using the trained and developed ANN models are in good agreement with the desired output. [ABSTRACT FROM AUTHOR]

The calorific value of coal is the basic technical basis for calculating parameters such as boiler heat balance, thermal efficiency, and boiler output. The calorific value of coal has different meanings, such as the calorific value of the cartridge, the high calorific value of coal, and the low calorific value of coal to generate heat at a high level of constant humidity and no ash. This paper focuses on the analysis of the structure and algorithm characteristics of artificial neural network and RBF neural network. On this basis, the predictive modelling of the received low-level calorific value is carried out. Through the test summary, the predictiveness of the neural network is better than the empirical formula. For the prediction problem with small sample size, the RBF network has better prediction performance. In addition, the quality of the sample, including its quantity and comprehensiveness, has an important impact on the predictive performance and generalization ability of the model. [ABSTRACT FROM AUTHOR]

Solar radiation represents the most important parameter for sizing and planning solar power systems. However, solar radiation depends significantly on meteorological conditions which are variable and uncontrollable. Therefore, forecasting global solar radiation can play a key role to integrate solar energy resources into the electric grid. This paper presents a new hybrid approach based on seasonal clustering technique and artificial neural network (ANN) for forecasting 1 h-ahead of global solar radiation. For this purpose, the fuzzy c-means algorithm (FCM) was used to cluster 3 years of monthly average experimental data into different seasons according to solar and meteorological parameters of Évora city. Subsequently, based on the seasonal clustering results, the meteorological dataset was divided into dfferent training subsets. Furthermore, for each subset, an ANN model has been designed to forecast hourly global solar radiation. In this study, hourly meteorological data from January 2012 to December 2016 have been used for forecasting. The hourly data were collected from Évora-city's meteorological station in Portugal (38°34 N, 07°54 W). The results show the superiority of the hybrid approach compared to the individual ANN model according to statistical indicators. [ABSTRACT FROM AUTHOR]

During wire electrical discharge machining (WEDM), wire rupture may deteriorate workpieces' machined surfaces and increase the processing time. However, only a few referenced papers focused on wire rupture during past decades because of its complexity. In this research, machine learning (ML) technique was applied to analyze the relationship between manufacturing parameters and the chance of wire rupture. Three parameters, including gap voltage (GV), feed rate (FR), and water resistance (WR), were considered as training features, and a total of 298 sets were used to train an artificial neural network (ANN). The results show that the prediction accuracy of wire rupture for 10 s in advance is above 85%. This research developed a new method to apply the real-time predict wire rupture and is faster, more accurate than prior research. Besides, this method is extendable for future measured data when the usable sensor data are increasing. [ABSTRACT FROM AUTHOR]

This paper brings together two important developments in forecasting literature; the artificial neural networks and factor models. The paper introduces the factor augmented artificial neural network (FAANN) hybrid model in order to produce a more accurate forecasting. Theoretical and empirical findings have indicated that integration of various models can be an effective way of improving on their predictive performance, especially when the models in the ensemble are quite different. The proposed model is used to forecast three time series variables using large South African monthly panel, namely, deposit rate, gold mining share prices and Long term interest rate, using monthly data over the in-sample period (training set) 1992:1-2006:12. The variables are used to compute out-of-sample (testing set) results for 3, 6 and 12 month-ahead forecasts for the period of 2007:1-2011:12. The out-of-sample root mean square error findings show that the FAANN model yields substantial improvements over the autoregressive AR benchmark model and standard dynamic factor model (DFM). The Diebold-Mariano test results also further confirm the superiority of the FAANN model forecast performance over the AR benchmark model and the DFM model forecasts. The superiority of the FAANN model is due to the ANN flexibility to account for potentially complex nonlinear relationships that are not easily captured by linear models. [ABSTRACT FROM AUTHOR]

These days load forecasting is much more required in order to reduce the wastage of energy. This paper is to implement & develop the idea of short term load forecasting by using Artificial Neural Network, the design of the neural network model, input data selection and Training & Testing by using short term load forecasting will be described in paper. For the EV load forecasting only 2 variables are being used as temperature and humidity to forecast the output as load. This type of designed ANN model will be mapped by using historical data of temperature and humidity (taken from meteorological sites), whereas it is being Trained & Tested by using historical data of loading of EV charging stations (Chetan maini, Bangalore) of a particular area as Coimbatore to give the desired result. Training & Testing done by using large amount of historical data of weather conditions and loading data (kV). By the help of this model they can predict their daily loads (next day's load) by putting historical data in the acquired algorithm. [ABSTRACT FROM AUTHOR]

Automotive aftermarket industry is possessed of a wide product portfolio range which is in the 4th rank by its worldwide trade volume. The demand characteristic of automotive aftermarket parts is volatile and uncertain. Nevertheless, the cause-and-effect relationship of automotive aftermarket industry has not been defined obviously heretofore. These conditions bring automotive aftermarket sales forecasting into a challenging process. This paper is composed to determine the relevant external factors for automotive aftermarket sales based on expert reviews and to propose a sales forecasting model for automotive aftermarket industry. Since computational intelligence techniques yield a framework to focus on predictive analytics and prescriptive analytics, an artificial neural network model constructed for Turkey automotive aftermarket industry. Artificial intelligence is a subset of computational intelligence that focused on problems which have complex and nonlinear relationships. The data which have complex and nonlinear relationships could be modelled successfully even though incomplete data in case of implementation of appropriate model. The proposed ANN model for sales forecast is compared with multiple linear regression and revealed a higher prediction performance. [ABSTRACT FROM AUTHOR]

Purpose: Inadequate balancing of resources often results in resource conflict in the multiproject management process. Past research has focused on how to allocate a small amount of resources optimally but has scarcely explored how to foresee multiproject resource conflict risk in advance. The purpose of this study is to address this knowledge gap by developing a model to predict multiproject resource conflict risk. Design/methodology/approach: A fuzzy comprehensive evaluation method is used to transform subjective judgments into quantitative information, based on which an evaluation index system for multiproject resource conflict risk that focuses on the interdependence of multiple project resources is proposed. An artificial neural network (ANN) model combined with this system is proposed to predict the comprehensive risk score that can describe the severity of risk. Findings: Accurately predicting multiproject resource conflict risks in advance can reduce the risk to the organization and increase the probability of achieving the project objectives. The ANN model developed in this paper by the authors can capture the essential components of the underlying nonlinear relevance and is capable of predicting risk appropriately. Originality/value: The authors explored the prediction of the risks associated with multiproject resource conflicts, which is important for improving the success rate of projects but has received limited attention in the past. The authors established an evaluation index system for these risks considering the interdependence among project resources to describe the underlying factors that contribute to resource conflict risks. The authors proposed an effective model to forecast the risk of multiproject resource conflicts using an ANN. The model can effectively predict complex phenomena with complicated and highly nonlinear performance functions and solve problems with many random variables. [ABSTRACT FROM AUTHOR]

Shot peening is an important process for the forming in aerospace industries. However, it is difficult to design the process parameters because of the complex nonlinear relationship between shot peening parameters and the deformation response of shot peened components which is affected by various nonlinear factors such as geometric nonlinearity, material nonlinearity, and coupling effects between process parameters. In this paper, a back propagation artificial neural network (BP-ANN) optimized by genetic algorithm (GA) method, called GA-ANN, is presented for the prediction of shot peen forming parameters. GA is applied to optimize the initial parameters of the BP-ANN to avoid falling into local minimum error. The initially optimized BP-ANN is then directly used to simulate the complex nonlinear relationships between the shot peening parameters (e.g. air pressure, shot mass flow, workpiece feeding speed, etc.) and the mechanical responses of the workpiece (e.g. the bending radius of target workpiece). The experimental results show that the shot peen forming process parameters can be effectively predicted by BP-ANN and that the prediction accuracy can be significantly improved when the ANN model is optimized first using a GA algorithm. [ABSTRACT FROM AUTHOR]

According to the significance of power load demand forecasting, this paper suggests a new hybrid method to reach more accurate model with fast response. The proposed model consists of two algorithms: Self Adaptive Modified Bat Algorithm (SAMBA) and Artificial Neural Network (ANN). In recent years, SAMBA has been used as a powerful tool in the optimization problems. On the other hand among the most popular methods, ANN has shown powerful performance in load prediction as the result of its ability to detect nonlinear mappings among different variables. In addition, the special ability of SAMBA in fast convergence, its low dependency to setting parameters and simple implementation make this algorithm more premiere than the other optimization algorithms. Therefore, in this paper for the first time we use SAMBA to regulate the weight matrix of ANN and optimize the degree of uncertainty which exist in load demand prediction. [ABSTRACT FROM AUTHOR]

Accurately and efficiently predicting the LHV of MSW is vital for designing and operating a waste-to-energy plant. However, previous prediction models possess limited geographical applicability. In this paper, we employ multiple linear regression and artificial neural network (ANN) techniques to predict LHV. These data-driven models utilize 151 globally distributed datasets identified during a systematic literature review, describing the wet physical composition of MSW and measured LHV. The results show that models built via both methods exhibited acceptable and compatible levels of performance in predicting LHV, based on the multiple statistical indicators. However, the ANN model proved to be more robust in handling of datasets of diverse quality. Models developed from both methods demonstrate clearly that the wet proportion of food waste has a negative impact on LHV. Supported by the strong and significant correlation between food waste and moisture content, we concluded that the negative impact of high moisture content in food waste on LHV outweighed its calorific value. Separating food waste or any other waste with high moisture content from the MSW for incineration can significantly improve energy recovery efficiency. Contrary to expectation, the models also reveal a higher contribution of paper waste to the LHV of MSW than plastic waste. • Models estimating LHV based on worldwide MSW composition were generated. • Models using multiple linear regression analysis and ANN techniques were compared.. • Models were found to yield acceptable accuracy and were broadly compatible. • ANN models prove to be more robust than regression models.. • Results indicate that high moisture content waste should be separated at source. [ABSTRACT FROM AUTHOR]

The Baltic Dry Index (BDI) is a robust indicator in the shipping sector in terms of global economic activities, future world trade, transport capacity, freight rates, ship demand, ship orders, etc. It is hard to forecast the BDI because of its high volatility and complexity. This paper proposes an artificial neural network (ANN) approach for BDI forecasting. Data from January 2010 to December 2016 are used to forecast the BDI. Three different ANN models are developed: (i) the past weekly observation of the BDI, (ii) the past two weekly observations of the BDI, and (iii) the past weekly observation of the BDI with crude oil price. While the performance parameters of these three models are close to each other, the most consistent model is found to be the second one. Results show that the ANN approach is a significant method for modeling and forecasting the BDI and proving its applicability. [ABSTRACT FROM AUTHOR]

The power generated by wind generators is usually associated with uncertainties, due to the intermittency of wind speed and other weather variables. This creates a big challenge for transmission system operators (TSOs) and distribution system operators (DSOs) in terms of connecting, controlling and managing power networks with high-penetration wind energy. Hence, in these power networks, accurate wind power forecasts are essential for their reliable and efficient operation. They support TSOs and DSOs in enhancing the control and management of the power network. In this paper, a novel two-stage hybrid approach based on the combination of the Hilbert-Huang transform (HHT), genetic algorithm (GA) and artificial neural network (ANN) is proposed for day-ahead wind power forecasting. The approach is composed of two stages. The first stage utilizes numerical weather prediction (NWP) meteorological information to predict wind speed at the exact site of the wind farm. The second stage maps actual wind speed vs. power characteristics recorded by SCADA. Then, the wind speed forecast in the first stage for the future day is fed to the second stage to predict the future day's wind power. Comparative selection of input-data parameter sets for the forecasting model and impact analysis of input-data dependency on forecasting accuracy have also been studied. The proposed approach achieves significant forecasting accuracy improvement compared with three other artificial intelligence-based forecasting approaches and a benchmark model using the smart persistence method. [ABSTRACT FROM AUTHOR]

It is of a high importance to introduce intelligent systems for estimation and optimization of blasting-induced ground vibration because it is one the most unwanted phenomena of blasting and it can damage surrounding structures. Hence, in this paper, estimation and minimization of blast-induced peak particle velocity (PPV) were conducted in two separate phases, namely prediction and optimization. In the prediction phase, an artificial neural network (ANN) model was developed to forecast PPV using as model inputs burden, spacing, distance from blast face, and charge per delay. The results of prediction phase showed that the ANN model, with coefficient of determinations of 0.938 and 0.977 for training and testing stages, respectively, can provide a high level of accuracy. In the optimization phase, the developed ANN model was used as an objective function of firefly algorithm (FA) in order to minimize the PPV. Many FA models were constructed to see the effects of FA parameters on the optimization results. Eventually, it was found that the FA-based optimization was able to decrease PPV to 17 mm/s (or 60% reduction). In addition, burden of 3.1 m, spacing of 3.9 m, and charge per delay of 247 kg were obtained as the values optimized by FA. The results confirmed that both developed techniques of ANN and FA are powerful, accurate, and applicable in estimating and minimizing blasting-induced ground vibration and they can be used with caution in similar fields. [ABSTRACT FROM AUTHOR]

One of the ongoing tasks in space structure testing is the vibration test, in which a given structure is mounted onto a shaker and excited by a certain input load on a given frequency range, in order to reproduce the rigor of launch. These vibration tests need to be conducted in order to ensure that the devised structure meets the expected loads of its future application. However, the structure must not be overtested to avoid any risk of damage. For this, the system's response to the testing loads, i.e., stresses and forces in the structure, must be monitored and predicted live during the test. In order to solve the issues associated with existing methods of live monitoring of the structure's response, this paper investigated the use of artificial neural networks (ANNs) to predict the system's responses during the test. Hence, a framework was developed with different use cases to compare various kinds of artificial neural networks and eventually identify the most promising one. Thus, the conducted research accounts for a novel method for live prediction of stresses, allowing failure to be evaluated for different types of material via yield criteria. [ABSTRACT FROM AUTHOR]

There are different process parameters of bonding joints in the literature. The main objective of the paper was to investigate the effects of bonding angle, composite lay-up sequences and adherend thickness on failure load of adhesively bonded joints under tensile load. For this aim, the joint has four types of the bonding angles 30°, 45°, 60° and 75°. Composite materials have three different lay-up sequences and various thicknesses. The bonding angle, adherend thickness and composite lay-up sequences lead to an increase of the failure load. Moreover, artificial neural network that utilized Levenberg-Marquardt algorithm model was used to predict failure load of bonding joints. Mean square error was put into account to evaluate productivity of ANN estimation model. Experimental results have been consistent with the predicted results obtained with ANN for training, validation and testing data set at a rate of 0.998, 0.997 and 0.998 respectively. [ABSTRACT FROM AUTHOR]

Pedestrian behavior tends to depend on the type of facility. The flow at bottlenecks, for instance, can exceed the maximal rates observed in straight corridors. Consequently, accurate predictions of pedestrians movements in complex buildings including corridors, corners, bottlenecks, or intersections are difficult tasks for minimal models with a single setting of the parameters. Artificial neural networks are robust algorithms able to identify various types of patterns. In this paper, we will investigate their suitability for forecasting of pedestrian dynamics in complex architectures. Therefore, we develop, train, and test several artificial neural networks for predictions of pedestrian speeds in corridor and bottleneck experiments. The estimations are compared with those of a classical speed-based model. The results show that the neural networks can distinguish the two facilities and significantly improve the prediction of pedestrian speeds. [ABSTRACT FROM AUTHOR]

Featured Application: This paper presents solutions for smart devices with embedded artificial intelligence dedicated to vehicular applications. Virtual sensors based on neural networks or regressors provide real-time predictions on diesel engine power loss caused by increased exhaust back pressure. The actual trade-off among engine emissions and performance requires detailed investigations into exhaust system configurations. Correlations among engine data acquired by sensors are susceptible to artificial intelligence (AI)-driven performance assessment. The influence of exhaust back pressure (EBP) on engine performance, mainly on effective power, was investigated on a turbocharged diesel engine tested on an instrumented dynamometric test-bench. The EBP was externally applied at steady state operation modes defined by speed and load. A complete dataset was collected to supply the statistical analysis and machine learning phases—the training and testing of all the AI solutions developed in order to predict the effective power. By extending the cloud-/edge-computing model with the cloud AI/edge AI paradigm, comprehensive research was conducted on the algorithms and software frameworks most suited to vehicular smart devices. A selection of artificial neural networks (ANNs) and regressors was implemented and evaluated. Two proof-of concept smart devices were built using state-of-the-art technology—one with hardware acceleration for "complete cycle" AI and the other with a compact code and size ("AI in a nut-shell") with ANN coefficients embedded in the code and occasionally offline "statistical re-calibration". [ABSTRACT FROM AUTHOR]

Analytical models based on physical metallurgy are of limited ability to predict the strength of steel due to the complexities of steelmaking. This paper presents the results obtained using Machine Learning procedures to predict the tensile strength of steel rods manufactured in an electric arc furnace. The available dataset includes 5540 observations (tensile tests) and 97 features (fabrication parameters) monitored during the different stages of the process (electric arc furnace, ladle furnace, continuous casting and hot rolling). The following regression algorithms have been implemented: Multiple Linear Regression, K-Nearest Neighbors, Classification and Regression Tree, three Ensemble Methods (Random Forest, Gradient Boosting and Adaboost) and Artificial Neural Networks. The fine-tuned Random Forest, provided an R2 of 0.775 and a mean absolute percentage error of 0.76% in the test dataset. After optimization, the Feature Importance and the Permutation Importance algorithms showed that chemical variables have the greater influence on the material strength. The quantitative influence of these variables was represented through Partial Dependence Plots. In short, this research has enabled validating a series of Machine Learning models that provide the necessary information for a correct decision-making to optimize the strength of the steel rods. [ABSTRACT FROM AUTHOR]

Field permeability of Hot Mix Asphalt (HMA) needs to be controlled to prevent excessive ingress of water into asphalt pavements, which leads to premature failure. Existing literature shows scatter in the prediction of field permeability values and relationships between factors affecting permeability are complex and are not known precisely. The objective of this paper is to present the analysis and modelling of field permeability of HMA with artificial neural networks (ANN). Permeability data from field testing at five sites, along with materials and mix data are presented. Preliminary statistical analysis to identify correlations and significant factors were conducted. A three-layer ANN was built and trained with part of the data and it was validated and also tested on two separate sets of data. The performance results indicated excellent prediction ability of the neural network. Experiments were conducted to improve the model, and the relative importance of the different factors was evaluated. Gradation and air voids were identified as two of the primary factors affecting field permeability. It is recommended that ANNs be considered to be used on a regular basis for predicting field permeability, particularly because field permeability tests are processes that require a considerable amount of time and resources. [ABSTRACT FROM AUTHOR]

During the past century, energy consumption and associated greenhouse gas emissions have increased drastically due to a wide variety of factors including both technological and population-based. Therefore, increasing our energy efficiency is of great importance in order to achieve overall sustainability. Forecasting the building energy consumption is important for a wide variety of applications including planning, management, optimization, and conservation. Data-driven models for energy forecasting have grown significantly within the past few decades due to their increased performance, robustness and ease of deployment. Amongst the many different types of models, artificial neural networks rank among the most popular data-driven approaches applied to date. This paper offers a review of the studies published since the year 2000 which have applied artificial neural networks for forecasting building energy use and demand, with a particular focus on reviewing the applications, data, forecasting models, and performance metrics used in model evaluations. Based on this review, existing research gaps are identified and presented. Finally, future research directions in the area of artificial neural networks for building energy forecasting are highlighted. [ABSTRACT FROM AUTHOR]

One of the momentous transformation performed by an artificial neural network (ANN), Support Vector Machine (SVM), Radial basis Function (RBF) and many other machine learning method is the application of activation function. MyAct the proposed activation method is used here with various ANN architectures for link prediction, classification and general prediction. Statistical properties of data used here to prove the effectiveness of proposed activation function MyAct over other popular activation methods. A data dependent transfer method is developed, which is pioneer in its own way. This proves to be an unified formulation for the robust and generalised learning for the classification, link prediction and regression problem types. Classification is done with Iris dataset using ANN with different activation method and results are compared. Improved results are achieved when MyAct used with Tailored Deep Feed Forward Artificial Neural Network (TDFFANN), simple Artificial Neural Network and Deep Artificial Neural Network. Aim here is to develop a novel activation method which work with positive data, negative data, small size data, big size data, skewed data or corrupt data. An attempt is made to cover complete versatile behaviour of data. Currently not a single activation method can work well on all above mentioned data. Results obtained using MyAct on the datasets used here proves it to be a good choice in comparison to logsig, tansig and other popular activation methods for classification and link prediction. Satisfactory improvement is achieved by using data length as well as negative range values in the prediction done by proposed method. MyAct had 22% better standard deviation than ReLU (Rectified Linear unit) and 36. 28% better standard deviation than ELU (Exponential linear unit). MyAct has 2. 6% better accuracy in regression error than Swiss method and 2. 5% better accuracy in regression error than ELU. Other results are discussed in the paper. [ABSTRACT FROM AUTHOR]

This paper evaluates the potential of five modeling approaches, namely M5 model tree, random forest, artificial neural networks, support vector machines and Gaussian processes, for the prediction of unconfined compressive strength of stabilized pond ashes with lime and lime sludge. The study not only presents five models for the same set of data but also compares the overall performance of them. Dataset used consists of 255 samples acquired from laboratory experiments. Out of the total, 170 randomly chosen samples were used for training and remaining 85 were used for testing the models. Input dataset consists of eight parameters (uniformity coefficient, coefficient of curvature, maximum dry density, optimum moisture content, lime, lime sludge, curing period and 7-day soaked California bearing ratio), while the output is UCS value at 7, 28, 45, 90 and 180 days of curing. Comparisons of results propose that Gaussian processes modeling strategy works well and the overall performance was substantially nearer to the exact agreement line. As a result of GP model, higher value of CC = 0.997 and lower values of RMSE = 23.016 kPa and MAE = 16.455 were obtained for testing the dataset. Sensitivity analysis suggests that lime, lime sludge, curing period and California bearing ratio are the significant parameters for predicting the unconfined compressive strength of stabilized pond ashes. The results confirmed that GP models are in a position to predict the unconfined compressive strength of stabilized pond ashes with an excessive degree of accuracy; however, GP modeling approach proves that this approach is more economical and less difficult in comparison with tedious laboratory work. [ABSTRACT FROM AUTHOR]

Wireless sensor networks employed in field monitoring have severe energy and memory constraints. Energy harvested from the natural resources such as solar energy is highly intermittent. However, its future values can be predicted with reasonable accuracy. Forecasting future values of solar irradiance prolongs the wireless sensor networks lifetime by enabling efficient task scheduling. In this paper, we propose a model for forecasting solar energy for wireless sensor networks using feed forward neural networks and compare it with other models both in terms of accuracy and memory occupancy. Intensity of solar radiations is predicted 24 h ahead based on temperature, pressure, relative humidity, dew point, wind speed, zenith angle, hour of the day and historical values of solar intensity. The dataset of 4 months is used from National Renewable Energy Laboratory. The results indicate that the proposed model is quite efficient with coefficient of correlation (R2) and RMSE values 98.052 and 56.61 respectively. [ABSTRACT FROM AUTHOR]

Axial bearing capacity of piles is the most important parameter in pile foundation design. In this paper, artificial neural network (ANN) and random forest (RF) algorithms were utilized to predict the ultimate axial bearing capacity of driven piles. An unprecedented database containing 2314 driven pile static load test reports were gathered, including the pile diameter, length of pile segments, natural ground elevation, pile top elevation, guide pile segment stop driving elevation, pile tip elevation, average standard penetration test (SPT) value along the embedded length of pile, and average SPT blow counts at the tip of pile as input variables, whereas the ultimate load on pile top was considered as output variable. The dataset was divided into the training (70%) and testing (30%) parts for the construction and validation phases, respectively. Various error criteria, namely mean absolute error (MAE), root mean squared error (RMSE), and the coefficient of determination (R2) were used to evaluate the performance of RF and ANN algorithms. In addition, the predicted results of pile load tests were compared with five empirical equations derived from the literature and with classical multi-variable regression. The results showed that RF outperformed ANN and other methods. Sensitivity analysis was conducted to reveal that the average SPT value and pile tip elevation were the most important factors in predicting the axial bearing capacity of piles. [ABSTRACT FROM AUTHOR]

The mean age of air (MAA) is one of the most useful parameters in evaluating indoor air quality in natural ventilated buildings. Its evaluation is generally based on the CO2 monitoring within the environment; however, other methods can be found in the literature, but they have not always led to satisfactory results. In this context, the present paper is focused on two main topics: the effect of the windows airtightness and of the environmental conditions on MAA and the application of artificial neural network (ANN) for the CO2 prediction within the room. Two case studies (case study 1 located in Terni and case study 2 located in Perugia) were investigated, which differ in geometric dimensions (useful area, volume, window area) and in airtightness of windows. The indoor and outdoor environmental conditions (air temperature, pressure, relative humidity, air velocity, and indoor CO2 concentration) were monitored in 33 experimental campaigns, in four room configurations: open door-open window (OD-OW); closed door-open window (CD-OW); open door-closed window (OD-CW); closed door-closed window (CD-CW). Tracer decay methodology, according to ISO 16000-8:2007 standard, was compiled during all the experimental campaigns. A feedforward ANN, able to simulate the indoor CO2 concentration within the rooms, was then implemented; the monitored environmental conditions (air temperature, pressure, relative humidity, and air velocity), the geometric dimensions (useful area, volume, window area), and the airtightness of windows were provided as input data, while the CO2 concentration was used as target. In particular, data of 19 experimental campaigns were provided for the training process of the network, while 14 were only used for testing the reliability of ANN. The CO2 concentration predicted by ANN was then used for the MAA calculation in the four room configurations. Experimental results show that MAA of case study 2 is always higher, in all the examined configurations, due to the higher airtightness characteristics of the window and to the higher volume of the room. When the difference between indoor and outdoor temperature increases, the MAA increases too, in almost all the investigated configurations. Finally, the CO2 concentration predicted by ANN was compared with experimental data; results show a good accuracy of the network both in CO2 prediction and in the MAA calculation. The predicted CO2 concentration at the beginning of experimental campaigns (time step 0) always differs less than 2% from experimental data, while a mean percentage difference of −18.8% was found considering the maximum CO2 concentration. The MAA calculated using the predicted CO2 of ANN was greater than the one obtained from experimental data, with a difference in the 0.5–1.3 min range, depending on the configuration. According to the results, the developed ANN can be considered an alternative and valuable tool for a preliminary evaluation of MAA. [ABSTRACT FROM AUTHOR]