Search

The large-scale integration into electrical systems of intermittent power-generation sources, such as wind power plants, requires greater efforts and knowledge from operators to keep these systems operating efficiently. These sources require reliable output power forecasts to set up the optimal operating point of the electrical system. In previous research, the authors developed an evolutionary approach algorithm called RCDESIGN to optimize the hyperparameters and topology of Echo State Networks (ESN), and applied the model in different time series forecasting, including wind speed. In this paper, RCDESIGN was modified in some aspects of the genetic algorithm, and now it optimizes an ESN with augmented states (ESN-AS) and has been called RCDESIGN-AS. The evolutionary algorithm allows the search for the best parameters and topology of the recurrent neural network to be performed simultaneously. In addition, RCDESIGN-AS has the important characteristic of requiring little computational effort and processing time since it is not necessary for the eigenvalues of the reservoir weight matrix to be reduced and also due to the fact that the augmented states make it possible to reduce the number of neurons in the reservoir. The method was applied for wind speed forecasting with a 24-h ahead horizon using real data of wind speed from five cities in the Northeast Region of Brazil. All results obtained with the proposed method overcame forecasting performed by the persistence method, obtaining prediction gains ranging from 60% to 80% in relation to this reference method. In some datasets, the proposed method also yielded better results than the traditional ESN, showing that RCDESIGN-AS can be a powerful tool for wind-speed forecasting and possibly for other types of time series. [ABSTRACT FROM AUTHOR]

Purpose There has been a growing concern about air quality because in recent years, industrial and vehicle emissions have resulted in unsatisfactory human health conditions. There is an urgent need for the measurements and estimations of particulate pollutants levels, especially in urban areas. As a contribution to this issue, the purpose of this paper is to use data from measured concentrations of particulate matter and meteorological conditions for the predictions of PM10.Design/methodology/approach The procedure included daily data collection of current PM10 concentrations for the city of São Carlos-SP, Brazil. These data series enabled to use an estimator based on artificial neural networks. Data sets were collected using the high-volume sampler equipment (VFA-MP10) in the period ranging from 1997 to 2006 and from 2014 to 2015. The predictive models were created using statistics from meteorological data. The models were developed using two neural network architectures, namely, perceptron multilayer (MLP) and non-linear autoregressive exogenous (NARX) inputs network.Findings It was observed that, over time, there was a decrease in the PM10 concentration rates. This is due to the implementation of more strict environmental laws and the development of less polluting technologies. The model NARX that used as input layer the climatic variables and the PM10 of the previous day presented the highest average absolute error. However, the NARX model presented the fastest convergence compared with the MLP network.Originality/value The presentation of a given PM10 concentration of the previous day improved the performance of the predictive models. This paper brings contributions with the NARX model applications. [ABSTRACT FROM AUTHOR]

Sugar is an important commodity that is used beyond the food industry. It can be produced from sugarcane and sugar beet, depending on the region. Prices worldwide differ due to high volatility, making it difficult to estimate their forecast. Thus, the present work aims to predict the prices of kilograms of sugar from four databases: the European Union, the United States, Brazil, and the world. To achieve this, linear methods from the Box and Jenkins family were employed, together with classic and new approaches of artificial neural networks: the feedforward Multilayer Perceptron and extreme learning machines, and the recurrent proposals Elman Network, Jordan Network, and Echo State Networks considering two reservoir designs. As performance metrics, the MAE and MSE were addressed. The results indicated that the neural models were more accurate than linear ones. In addition, the MLP and the Elman networks stood out as the winners. [ABSTRACT FROM AUTHOR]

This study assesses the deterministic and probabilistic forecasting skill of a 1-month-lead ensemble of Artificial Neural Networks (EANN) based on low-frequency climate oscillation indices. The predictand is the February-April (FMA) rainfall in the Brazilian state of Ceará, which is a prominent subject in climate forecasting studies due to its high seasonal predictability. Additionally, the study proposes combining the EANN with dynamical models into a hybrid multi-model ensemble (MME). The forecast verification is carried out through a leave-one-out cross-validation based on 40 years of data. The EANN forecasting skill is compared with traditional statistical models and the dynamical models that compose Ceará's operational seasonal forecasting system. A spatial comparison showed that the EANN was among the models with the smallest Root Mean Squared Error (RMSE) and Ranked Probability Score (RPS) in most regions. Moreover, the analysis of the area-aggregated reliability showed that the EANN is better calibrated than the individual dynamical models and has better resolution than Multinomial Logistic Regression for above-normal (AN) and below-normal (BN) categories. It is also shown that combining the EANN and dynamical models into a hybrid MME reduces the overconfidence of the extreme categories observed in a dynamically-based MME, improving the reliability of the forecasting system. [ABSTRACT FROM AUTHOR]

Copyright of Revista Ingeniería Industrial is the property of Departamento de Ingenieria Industrial, Universidad del Bio-Bio 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.)

Dengue is a serious public health concern in Brazil and globally. In the absence of a universal vaccine or specific treatments, prevention relies on vector control and disease surveillance. Accurate and early forecasts can help reduce the spread of the disease. In this study, we developed a model for predicting monthly dengue cases in Brazilian cities 1 month ahead, using data from 2007–2019. We compared different machine learning algorithms and feature selection methods using epidemiologic and meteorological variables. We found that different models worked best in different cities, and a random forests model trained on monthly dengue cases performed best overall. It produced lower errors than a seasonal naive baseline model, gradient boosting regression, a feed-forward neural network, or support vector regression. For each city, we computed the mean absolute error between predictions and true monthly numbers of dengue cases on the test data set. The median error across all cities was 12.2 cases. This error was reduced to 11.9 when selecting the optimal combination of algorithm and input features for each city individually. Machine learning and especially decision tree ensemble models may contribute to dengue surveillance in Brazil, as they produce low out-of-sample prediction errors for a geographically diverse set of cities. [ABSTRACT FROM AUTHOR]

In recent years, renewable and sustainable energy sources have attracted the attention of various investors and stakeholders, such as energy sector agents and even consumers. It is perplexing to observe and anticipate the required levels of photovoltaic generation, which are inherent tasks for such rapid insertion into the electric grid. This distributed/renewable generation must be integrated in a coordinated way such that there is no negative impact on the electric performance of the grid, increasing in the complexity of energy management. In this article, a methodology for photovoltaic generation forecasting is addressed for a horizon of one week ahead, using a new approach based on an artificial neural network (ANN) ensemble. Two main questions will be explored with this approach: how to select the ANNs, and how to combine them in the ensemble. The design of experiments (DOE) approach is applied to the photovoltaic time series factors and ANN factors. Then, a cluster analysis is performed to select the best networks. From this point on, a mixture (MDE) is employed to determine the ideal weights for the ensemble formation. The methodology is detailed throughout the paper and, based on the combination of forecasts, the photovoltaic generation was estimated for a specific panel set located in the state of Minas Gerais, Brazil, reaching the value of 4.7% for the weekly mean absolute percentage error. The versatility of the proposed method allowed the change of the number of factors to be used in the experimental arrangement, the forecast model, and the desired forecast horizon, and consequently enhancing the forecasting determination. • An ANN ensemble is created for medium-term photovoltaic generation forecasting. • ANNs are selected by using a new design of experiments approach. • The ANN ensemble is built by using a new mixture design of experiments approach. • We predicted the photovoltaic generation for a panel set located in Brazil. [ABSTRACT FROM AUTHOR]

A bottleneck of laboratory analysis in process industries including steelmaking plants is the low sampling rate. Inference models using only variables measured online have then been used to made such information available in advance. This study develops predictive models for key mechanical properties of seamless steel tubes, by strength, ultimate tensile strength and hardness. A plant in Brazil was used as the case study. The sample sizes of some steel tube families given namely, yield a particular property are discrepant and sometimes very small. To overcome this sample imbalance and lack of representativeness, committees of predictive neural network models based on bagging predictors, a type of ensemble method, were adopted. As a result, all steel families for all properties have been satisfactorily described showing the correlations between targets and model estimates close to 99%. These results were compared to multiple linear regression, support vector machine and a simpler neural network. Such information available in advance favors corrective actions before complete tube production mitigating rework costs in general. [ABSTRACT FROM AUTHOR]

This work presents a novel investigation on the nowcasting prediction of wind speed for three sites in Bahia, Brazil. For this, it was applied the computational intelligence by supervised machine learning using different artificial neural network technique, which was trained, validated, and tested using time series are derived from measurements that are acquired in towers equipped with anemometers at heights of 100.0, 120.0 and 150.0 m. To define the most efficient ANN, different topologies were tested using MLP and RNN, applying Wavelet packet decomposition (bior, coif, db, dmey, rbior, sym). The best statistical analysis was RNN + discrete Meyer wavelet. A new methodology for improving forecast accuracy of wind speed using artificial neural network (ANN) and Wavelet packet decomposition. Using machine learning and Wavelet packet decomposition to nowcast wind speed (m/s). To predict the wind speed at 100.0 m, 120.0 m and 150.0 m height in tropical region. Performance evaluation of Wavelet packet decomposition applying 48 different mother Wavelet functions. ANN approach for the estimation of nine types of wind speed time series. The proposed hybrid model (ANN + Wavelet packet decomposition) is capable of wind speed forecasting efficiently. [ABSTRACT FROM AUTHOR]

Food production to meet human demand has been a challenge to society. Nowadays, one of the main sources of feeding is soybean. Considering agriculture food crops, soybean is sixth by production volume and the fourth by both production area and economic value. The grain can be used directly to human consumption, but it is highly used as a source of protein for animal production that corresponds 75% of the total, or as oil and derived food products. Brazil and the US are the most important players responsible for more than 70% of world production. Therefore, a reliable forecasting is essential for decision-makers to plan adequate policies to this important commodity and to establish the necessary logistical resources. In this sense, this study aims to predict soybean harvest area, yield, and production using Artificial Neural Networks (ANN) and compare with classical methods of Time Series Analysis. To this end, we collected data from a time series (1961–2016) regarding soybean production in Brazil. The results reveal that ANN is the best approach to predict soybean harvest area and production while classical linear function remains more effective to predict soybean yield. Moreover, ANN presents as a reliable model to predict time series and can help the stakeholders to anticipate the world soybean offer. [ABSTRACT FROM AUTHOR]