Avaliação da aplicabilidade de correlações matemáticas e redes neurais na predição de parâmetros de especificação do diesel

Diesel fuel is one of leading petroleum products marketed in Brazil, and has its quality monitored by specialized laboratories linked to the National Agency of Petroleum, Natural Gas and Biofuels - ANP. The main trial evaluating physicochemical properties of diesel are listed in the resolutions ANP Nº 65 of December 9th, 2011 and Nº 45 of December 20th, 2012 that determine the specification limits for each parameter and methodologies of analysis that should be adopted. However the methods used although quite consolidated, require dedicated equipment with high cost of acquisition and maintenance, as well as technical expertise for completion of these trials. Studies for development of more rapid alternative methods and lower cost have been the focus of many researchers. In this same perspective, this work conducted an assessment of the applicability of existing specialized literature on mathematical equations and artificial neural networks (ANN) for the determination of parameters of specification diesel fuel. 162 samples of diesel with a maximum sulfur content of 50, 500 and 1800 ppm, which were analyzed in a specialized laboratory using ASTM methods recommended by the ANP, with a total of 810 trials were used for this study. Experimental results atmospheric distillation (ASTM D86), and density (ASTM D4052) of diesel samples were used as basic input variables to the equations evaluated. The RNAs were applied to predict the flash point, cetane number and sulfur content (S50, S500, S1800), in which were tested network architectures feed-forward backpropagation and generalized regression varying the parameters of the matrix input in order to determine the set of variables and the best type of network for the prediction of variables of interest. The results obtained by the equations and RNAs were compared with experimental results using the nonparametric Wilcoxon test and Student's t test, at a significance level of 5%, as well as the coefficient of determination and percentage error, an error which was obtained 27, 61% for the flash point using a specific equation. The cetane number was obtained by three equations, and both showed good correlation coefficients, especially equation based on aniline point, with the lowest error of 0,816%. ANNs for predicting the flash point and the index cetane showed quite superior results to those observed with the mathematical equations, respectively, with errors of 2,55% and 0,23%. Among the samples with different sulfur contents, the RNAs were better able to predict the S1800 with error of 1,557%. Generally, networks of the type feedforward proved superior to generalized regression.

Implementação de uma matriz de neurônios dinamicamente reconfigurável para descrição de topologias de redes neurais artificiais multilayer perceptrons

The Artificial Neural Networks (ANN), which is one of the branches of Artificial Intelligence (AI), are being employed as a solution to many complex problems existing in several areas. To solve these problems, it is essential that its implementation is done in hardware. Among the strategies to be adopted and met during the design phase and implementation of RNAs in hardware, connections between neurons are the ones that need more attention. Recently, are RNAs implemented both in application specific integrated circuits's (Application Specific Integrated Circuits - ASIC) and in integrated circuits configured by the user, like the Field Programmable Gate Array (FPGA), which have the ability to be partially rewritten, at runtime, forming thus a system Partially Reconfigurable (SPR), the use of which provides several advantages, such as flexibility in implementation and cost reduction. It has been noted a considerable increase in the use of FPGAs for implementing ANNs. Given the above, it is proposed to implement an array of reconfigurable neurons for topologies Description of artificial neural network multilayer perceptrons (MLPs) in FPGA, in order to encourage feedback and reuse of neural processors (perceptrons) used in the same area of the circuit. It is further proposed, a communication network capable of performing the reuse of artificial neurons. The architecture of the proposed system will configure various topologies MLPs networks through partial reconfiguration of the FPGA. To allow this flexibility RNAs settings, a set of digital components (datapath), and a controller were developed to execute instructions that define each topology for MLP neural network.

Implementação de uma matriz de neurônios dinamicamente reconfigurável para descrição de topologias de redes neurais artificiais multilayer perceptrons

The Artificial Neural Networks (ANN), which is one of the branches of Artificial Intelligence (AI), are being employed as a solution to many complex problems existing in several areas. To solve these problems, it is essential that its implementation is done in hardware. Among the strategies to be adopted and met during the design phase and implementation of RNAs in hardware, connections between neurons are the ones that need more attention. Recently, are RNAs implemented both in application specific integrated circuits's (Application Specific Integrated Circuits - ASIC) and in integrated circuits configured by the user, like the Field Programmable Gate Array (FPGA), which have the ability to be partially rewritten, at runtime, forming thus a system Partially Reconfigurable (SPR), the use of which provides several advantages, such as flexibility in implementation and cost reduction. It has been noted a considerable increase in the use of FPGAs for implementing ANNs. Given the above, it is proposed to implement an array of reconfigurable neurons for topologies Description of artificial neural network multilayer perceptrons (MLPs) in FPGA, in order to encourage feedback and reuse of neural processors (perceptrons) used in the same area of the circuit. It is further proposed, a communication network capable of performing the reuse of artificial neurons. The architecture of the proposed system will configure various topologies MLPs networks through partial reconfiguration of the FPGA. To allow this flexibility RNAs settings, a set of digital components (datapath), and a controller were developed to execute instructions that define each topology for MLP neural network.

Reconstrução e reconhecimento de imagens binárias utilizando o algoritmo Máquina de Boltzmann

The objective of this work is to use algorithms known as Boltzmann Machine to rebuild and classify patterns as images. This algorithm has a similar structure to that of an Artificial Neural Network but network nodes have stochastic and probabilistic decisions. This work presents the theoretical framework of the main Artificial Neural Networks, General Boltzmann Machine algorithm and a variation of this algorithm known as Restricted Boltzmann Machine. Computer simulations are performed comparing algorithms Artificial Neural Network Backpropagation with these algorithms Boltzmann General Machine and Machine Restricted Boltzmann. Through computer simulations are analyzed executions times of the different described algorithms and bit hit percentage of trained patterns that are later reconstructed. Finally, they used binary images with and without noise in training Restricted Boltzmann Machine algorithm, these images are reconstructed and classified according to the bit hit percentage in the reconstruction of the images. The Boltzmann machine algorithms were able to classify patterns trained and showed excellent results in the reconstruction of the standards code faster runtime and thus can be used in applications such as image recognition.

Prognóstico de falhas baseado em redes neurais com estados de eco

Tese (mestrado)—Universidade de Brasília, Faculdade de Tecnologia, Departamento de Engenharia Mecânica, 2015.

Machine Learning algorithm on seat comfort level measurement, mapping pressure values with body regions

The comfort level of the seat has a major effect on the usage of a vehicle; thus, car manufacturers have been working on elevating car seat comfort as much as possible. However, still, the testing and evaluation of comfort are done using exhaustive trial and error testing and evaluation of data. In this thesis, we resort to machine learning and Artificial Neural Networks (ANN) to develop a fully automated approach. Even though this approach has its advantages in minimizing time and using a large set of data, it takes away the degree of freedom of the engineer on making decisions. The focus of this study is on filling the gap in a two-step comfort level evaluation which used pressure mapping with body regions to evaluate the average pressure supported by specific body parts and the Self-Assessment Exam (SAE) questions on evaluation of the person’s interest. This study has created a machine learning algorithm that works on giving a degree of freedom to the engineer in making a decision when mapping pressure values with body regions using ANN. The mapping is done with 92% accuracy and with the help of a Graphical User Interface (GUI) that facilitates the process during the testing time of comfort level evaluation of the car seat, which decreases the duration of the test analysis from days to hours.

Modelagem da composição química do leite através de indicadores metabólicos em vacas leiteiras de alta produção

A lactação é um processo fisiológico complexo que ainda não foi compreendido na sua totalidade. Inúmeros fatores intervêm na síntese e secreção do leite, sendo os mais importantes a nutrição e o metabolismo endógeno dos nutrientes. A qualidade do leite é valorizada tanto pela sua composição química, como pelo conteúdo de células somáticas. No entanto, visando a comercialização do leite, as maiores mudanças e melhoras na qualidade podem ser atingidas através da manipulação da dieta dos animais, em especial em vacas leiteiras de alta produção. Avaliar os processos de absorção de alimentos, bem como o metabolismo catabólico e anabólico direcionado para a síntese do leite, têm sido uma grande preocupação na pesquisa de nutrição e bioquímica da produção animal. O principal objetivo da presente pesquisa foi gerar modelos matemáticos que pudessem explicar a participação de diferentes metabólitos sobre a composição química do leite. Neste intuito foram coletadas amostras de fluído ruminal, sangue, urina e leite de 140 vacas da raça Holandesa nas primeiras semanas de lactação e mantidas sob sistema semi-intensivo de produção e dieta controlada. Os animais foram selecionados de sistemas de produção no ecossistema do Planalto Médio de Rio Grande do Sul e foram amostrados em dois períodos climáticos críticos. No fluido ruminal foram avaliados o pH e o tempo de redução do azul de metileno. No sangue foram determinados os metabólitos: glicose, colesterol, β-hidroxibutirato (BHB), triglicerídeos, fructosamina, ácidos graxos não esterificados (NEFA), proteínas totais, albumina, globulina, uréia, creatinina, cálcio, fósforo e magnésio. As enzimas: aspartato amino transferase (AST), gama glutamil transferase (GGT) e creatina kinase (CK). Os hormônios: cortisol, insulina, triiodotironina (T3), tiroxina (T4), e leptina. Foi efetuado hemograma, para conhecer: hematócrito, hemoglobina, e contagem total e diferencial de células brancas. Na urina foram dosados: corpos cetônicos, pH e densidade. No leite foi determinada: proteína, gordura, lactose, sólidos totais, sólidos não gordurosos, contagem de células somáticas e uréia. Para a determinação de cada um dos metabólitos ou compostos foram usadas técnicas específicas validadas internacionalmente. Os diferentes valores obtidos constituíram os parâmetros básicos de entrada para a construção dos diversos modelos matemáticos executados para predizer a composição do leite. Mediante procedimentos de regressão linear múltipla algoritmo Stepwise, procedimentos de correlação linear simples de Pearson e procedimentos de análise computacional através de redes neurais, foram gerados diferentes modelos para identificar os parâmetros endógenos de maior relevância na predição dos diferentes componentes do leite. A parametrização das principais rotas bioquímicas, do controle endócrino, do estado de funcionamento hepático, da dinâmica ruminal e da excreção de corpos cetônicos aportou informação suficiente para predizer com diferente grau de precisão o conteúdo dos diferentes sólidos no leite. O presente trabalho é apresentado na forma de quatro artigos correspondentes aos parâmetros energéticos, de controle endócrino, modelagem matemática linear múltipla e predição através de Artificial Neural Networks (ANN).

International evidence on the predictability of returns to securitized real estate assets: econometric models versus neural networks

The performance of various statistical models and commonly used financial indicators for forecasting securitised real estate returns are examined for five European countries: the UK, Belgium, the Netherlands, France and Italy. Within a VAR framework, it is demonstrated that the gilt-equity yield ratio is in most cases a better predictor of securitized returns than the term structure or the dividend yield. In particular, investors should consider in their real estate return models the predictability of the gilt-equity yield ratio in Belgium, the Netherlands and France, and the term structure of interest rates in France. Predictions obtained from the VAR and univariate time-series models are compared with the predictions of an artificial neural network model. It is found that, whilst no single model is universally superior across all series, accuracy measures and horizons considered, the neural network model is generally able to offer the most accurate predictions for 1-month horizons. For quarterly and half-yearly forecasts, the random walk with a drift is the most successful for the UK, Belgian and Dutch returns and the neural network for French and Italian returns. Although this study underscores market context and forecast horizon as parameters relevant to the choice of the forecast model, it strongly indicates that analysts should exploit the potential of neural networks and assess more fully their forecast performance against more traditional models.

Neural networks and statistical analysis for classification of corneal videokeratography maps based on Zernike coefficients: a quantitative comparison

PURPOSE: The main goal of this study was to develop and compare two different techniques for classification of specific types of corneal shapes when Zernike coefficients are used as inputs. A feed-forward artificial Neural Network (NN) and discriminant analysis (DA) techniques were used. METHODS: The inputs both for the NN and DA were the first 15 standard Zernike coefficients for 80 previously classified corneal elevation data files from an Eyesys System 2000 Videokeratograph (VK), installed at the Departamento de Oftalmologia of the Escola Paulista de Medicina, São Paulo. The NN had 5 output neurons which were associated with 5 typical corneal shapes: keratoconus, with-the-rule astigmatism, against-the-rule astigmatism, "regular" or "normal" shape and post-PRK. RESULTS: The NN and DA responses were statistically analyzed in terms of precision ([true positive+true negative]/total number of cases). Mean overall results for all cases for the NN and DA techniques were, respectively, 94% and 84.8%. CONCLUSION: Although we used a relatively small database, results obtained in the present study indicate that Zernike polynomials as descriptors of corneal shape may be a reliable parameter as input data for diagnostic automation of VK maps, using either NN or DA.

Forecasting tourism demand to Catalonia: neural networks vs. time series models

The increasing interest aroused by more advanced forecasting techniques, together with the requirement for more accurate forecasts of tourismdemand at the destination level due to the constant growth of world tourism, has lead us to evaluate the forecasting performance of neural modelling relative to that of time seriesmethods at a regional level. Seasonality and volatility are important features of tourism data, which makes it a particularly favourable context in which to compare the forecasting performance of linear models to that of nonlinear alternative approaches. Pre-processed official statistical data of overnight stays and tourist arrivals fromall the different countries of origin to Catalonia from 2001 to 2009 is used in the study. When comparing the forecasting accuracy of the different techniques for different time horizons, autoregressive integrated moving average models outperform self-exciting threshold autoregressions and artificial neural network models, especially for shorter horizons. These results suggest that the there is a trade-off between the degree of pre-processing and the accuracy of the forecasts obtained with neural networks, which are more suitable in the presence of nonlinearity in the data. In spite of the significant differences between countries, which can be explained by different patterns of consumer behaviour,we also find that forecasts of tourist arrivals aremore accurate than forecasts of overnight stays.

Development and evaluation of neural network freeway incident detection models using field data

This paper discusses a multi-layer feedforward (MLF) neural network incident detection model that was developed and evaluated using field data. In contrast to published neural network incident detection models which relied on simulated or limited field data for model development and testing, the model described in this paper was trained and tested on a real-world data set of 100 incidents. The model uses speed, flow and occupancy data measured at dual stations, averaged across all lanes and only from time interval t. The off-line performance of the model is reported under both incident and non-incident conditions. The incident detection performance of the model is reported based on a validation-test data set of 40 incidents that were independent of the 60 incidents used for training. The false alarm rates of the model are evaluated based on non-incident data that were collected from a freeway section which was video-taped for a period of 33 days. A comparative evaluation between the neural network model and the incident detection model in operation on Melbourne's freeways is also presented. The results of the comparative performance evaluation clearly demonstrate the substantial improvement in incident detection performance obtained by the neural network model. The paper also presents additional results that demonstrate how improvements in model performance can be achieved using variable decision thresholds. Finally, the model's fault-tolerance under conditions of corrupt or missing data is investigated and the impact of loop detector failure/malfunction on the performance of the trained model is evaluated and discussed. The results presented in this paper provide a comprehensive evaluation of the developed model and confirm that neural network models can provide fast and reliable incident detection on freeways. (C) 1997 Elsevier Science Ltd. All rights reserved.

Active Learning with Statistical Models

For many types of learners one can compute the statistically 'optimal' way to select data. We review how these techniques have been used with feedforward neural networks. We then show how the same principles may be used to select data for two alternative, statistically-based learning architectures: mixtures of Gaussians and locally weighted regression. While the techniques for neural networks are expensive and approximate, the techniques for mixtures of Gaussians and locally weighted regression are both efficient and accurate.

Application of ARX neural networks to model the rate of penetration of petroleum wells drilling

Bit performance prediction has been a challenging problem for the petroleum industry. It is essential in cost reduction associated with well planning and drilling performance prediction, especially when rigs leasing rates tend to follow the projects-demand and barrel-price rises. A methodology to model and predict one of the drilling bit performance evaluator, the Rate of Penetration (ROP), is presented herein. As the parameters affecting the ROP are complex and their relationship not easily modeled, the application of a Neural Network is suggested. In the present work, a dynamic neural network, based on the Auto-Regressive with Extra Input Signals model, or ARX model, is used to approach the ROP modeling problem. The network was applied to a real oil offshore field data set, consisted of information from seven wells drilled with an equal-diameter bit.

Neural networks models for wear patterns recognition of single-point dresser

Grinding is a workpiece finishing process for advanced products and surfaces. However, the constant friction between workpiece and grinding wheel causes the latter to lose its sharpness, thereby impairing the result of the grinding process. When this occurs, the dressing process is essential to sharpen the worn grains of the grinding wheel. The dressing conditions strongly influence the performance of the grinding operation; hence, monitoring them throughout the process can increase its efficiency. The purpose of this study was to classify the wear condition of a single-point dresser using intelligent systems whose inputs were obtained by digitally processing acoustic emission signals. Two multilayer perceptron (MLP) neural networks were compared for their classification ability, one using the root mean square (RMS) statistics and another the ratio of power (ROP) statistics as input. In this study, it was found that the harmonic content of the acoustic emission signal is influenced by the condition of the dresser, and that the condition of the tool under study can be classified by using the aforementioned statistics to feed a neural network. © IFAC.

Tool Condition Monitoring of Single-Point Dresser Using Acoustic Emission and Neural Networks Models

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)