Identificação não linear usando uma rede fuzzy wavelet neural network modificada

In last decades, neural networks have been established as a major tool for the identification of nonlinear systems. Among the various types of networks used in identification, one that can be highlighted is the wavelet neural network (WNN). This network combines the characteristics of wavelet multiresolution theory with learning ability and generalization of neural networks usually, providing more accurate models than those ones obtained by traditional networks. An extension of WNN networks is to combine the neuro-fuzzy ANFIS (Adaptive Network Based Fuzzy Inference System) structure with wavelets, leading to generate the Fuzzy Wavelet Neural Network - FWNN structure. This network is very similar to ANFIS networks, with the difference that traditional polynomials present in consequent of this network are replaced by WNN networks. This paper proposes the identification of nonlinear dynamical systems from a network FWNN modified. In the proposed structure, functions only wavelets are used in the consequent. Thus, it is possible to obtain a simplification of the structure, reducing the number of adjustable parameters of the network. To evaluate the performance of network FWNN with this modification, an analysis of network performance is made, verifying advantages, disadvantages and cost effectiveness when compared to other existing FWNN structures in literature. The evaluations are carried out via the identification of two simulated systems traditionally found in the literature and a real nonlinear system, consisting of a nonlinear multi section tank. Finally, the network is used to infer values of temperature and humidity inside of a neonatal incubator. The execution of such analyzes is based on various criteria, like: mean squared error, number of training epochs, number of adjustable parameters, the variation of the mean square error, among others. The results found show the generalization ability of the modified structure, despite the simplification performed

Sistemas de automação e supervisão do laboratório de avaliação dos processos de medição de vazão e BSW

During a petroleum well production process, It is common the slmultaneous oil and water production, in proportion that can vary from 0% up to values close to 100% of water. Moreover, the production flows can vary a lot, depending on the charaeteristies of eaeh reservoir. Thus being, the meters used in field for the flow and BSW (water in the oil) measurement must work well in wide bands of operation. For the evaluation of the operation of these meters, in the different operation conditions, a Laboratory will be built in UFRN, that has for objective to evaluate in an automatic way the processes of flow and BSW petroleum measurement, considering different operation conditions. The good acting of these meters is fundamental for the accuracy of the measures of the volumes of production liquid and rude of petroleum. For the measurement of this production, the petroleum companies use meters that should indicate the values with tha largast possible accuracy and to respect a series of conditions and minimum requirements, estabelished by the united Entrance ANP/INMETRO 19106/2000. The laboratory of Evafuation of the Processes of Measurement of Flow and BSW to be built will possess an oil tank basically, a tank of water, besides a mixer, a tank auditor, a tank for separation and a tank of residues for discard of fluids, fundamental for the evaluation of the flow metars and BSW. The whole process will be automated through the use of a Programmable Logicat Controller (CLP) and of a supervisory system.This laboratory besides allowing the evaluation of flow meters and BSW used by petroleum companies, it will make possible the development of researches related to the automation. Besides, it will be a collaborating element to the development of the Computer Engineering and Automation Department, that it will propitiate the evolution of the faculty and discente, qualifying them for a job market in continuous growth. The present work describes the project of automation of the laboratory that will be built at of UFRN. The system will be automated using a Programmable Logical Controller and a supervisory system. The programming of PLC and the screens of the supervisory system were developed in this work

Lógica Fuzzy para Controle de pH em um Processo Petrolífero

This work proposes the design, the performance evaluation and a methodology for tuning the initial MFs parameters of output of a function based Takagi-Sugeno-Kang Fuzzy-PI controller to neutralize the pH in a stirred-tank reactor. The controller is designed to perform pH neutralization of industrial plants, mainly in units found in oil refineries where it is strongly required to mitigate uncertainties and nonlinearities. In addition, it adjusts the changes in pH regulating process, avoiding or reducing the need for retuning to maintain the desired performance. Based on the Hammerstein model, the system emulates a real plant that fits the changes in pH neutralization process of avoiding or reducing the need to retune. The controller performance is evaluated by overshoots, stabilization times, indices Integral of the Absolute Error (IAE) and Integral of the Absolute Value of the Error-weighted Time (ITAE), and using a metric developed by that takes into account both the error information and the control signal. The Fuzzy-PI controller is compared with PI and gain schedule PI controllers previously used in the testing plant, whose results can be found in the literature.

Estudo e implementação em plantas físicas de um controlador preditivo generalizado com restrições

This work shows a study about the Generalized Predictive Controllers with Restrictions and their implementation in physical plants. Three types of restrictions will be discussed: restrictions in the variation rate of the signal control, restrictions in the amplitude of the signal control and restrictions in the amplitude of the Out signal (plant response). At the predictive control, the control law is obtained by the minimization of an objective function. To consider the restrictions, this minimization of the objective function is done by the use of a method to solve optimizing problems with restrictions. The chosen method was the Rosen Algorithm (based on the Gradient-projection). The physical plants in this study are two didactical systems of water level control. The first order one (a simple tank) and another of second order, which is formed by two tanks connected in cascade. The codes are implemented in C++ language and the communication with the system to be done through using a data acquisition panel offered by the system producer

Estudo da estimativa da incerteza de medição para determinação do BS&W e da vazão aplicado no laboratório de avaliação de medição do petróleo

The considered work presents the procedure for evaluation of the uncertainty related to the calibration of flow measurers and to BS&W. It is about a new method of measurement purposed by the conceptual project of the laboratory LAMP, at Universidade Federal do Rio Grande do Norte, that intends to determine the conventional true value of the BS&W from the total height of the liquid column in the auditor tank, hydrostatic pressure exerted by the liquid column, local gravity, specific mass of the water and the specific mass of the oil, and, to determine the flow, from total height of liquid column and transfer time. The calibration uses a automatized system of monitoration and data acquisition of some necessary largnesses to determine of flow and BS&W, allowing a better trustworthiness of through measurements

Desempenho de um veículo flex em bancada dinamométrica de chassi

Flex-fuel vehicles are equipped with Otto Cycle internal combustion engines and have the capability of functioning with more than one type of fuel, mixed at the same tank and burned in the combustion chamber simultaneously. This sort of motorization is a world pattern due to the scarcity of petroleum, the trade of several types of fuels, technology advances and the restriction imposed to gas emissions to the atmosphere. In Brazil, the Flexfuel vehicles are a reality, specially the ones using fuel with 20 to 25% anhydrous alcohol mixed with gasoline and those that use natural gas or original liquid fuel (gasoline or hydrated ethanol). The Brazilian model Fiat Siena, the object of this present scientific investigation, is equipped with a unique electronic central capable of managing the liquid or gaseous fuels. The purpose of this research was to perform a comparative analysis in terms of performance (in terms of both potency and consumption) of a tetra-fuel vehicle - using a chassis dynamometer, operating with different fuels: common gasoline, premium gasoline, Podium gasoline, ethanol or natural gas. It became necessary to develop a bench of tests and trials procedures, as well as to know the functioning of the electronic management of the vehicle under analysis. The experiments were performed at the automotive laboratory in CTGAS-ER (Center of Gas Technologies and Renewable energies) at the light of Brazilian standard ABNT, NBR 7024: Light on-road vehicles - measurement of fuel consumption. The essay results on specific fuel consumption using common gasoline, premium gasoline and Podium gasoline have shown similar results, both for urban and road driving cycles

Efeito de variáveis de processo no tempo de fermentação e na concentração das dicetonas vicinais totais

Among the main challenges in the beer industrial production is the market supply at the lowest cost and high quality, in order to ensure the expectations of customers and. consumers The beer fermentation stage represents approximately 70% of the whole time necessary to its production, having a obligatoriness of strict process controls to avoid becoming bottleneck in beer production. This stage is responsible for the formation of a series of subproducts, which are responsible for the composition of aroma/bouquet existing in beer and some of these subproducts, if produced in larger quantities, they will confer unpleasant taste and odor to the final product. Among the subproducts formed during the fermentation stage, total vicinal diketones is the main component, since it is limiting for product transfusion to the subsequent steps, besides having a low perception threshold by the consumer and giving undesirable taste and odor. Due to the instability of main raw materials quality and also process controls during fermentation, the development of alternative forms of beer production without impacting on total fermentation time and final product quality is a great challenge to breweries. In this work, a prior acidification of the pasty yeast was carried out, utilizing for that phosphoric acid, food grade, reducing yeast pH of about 5.30 to 2.20 and altering its characteristic from flocculent to pulverulent during beer fermentation. An increase of six times was observed in amount of yeast cells in suspension in the second fermentation stage regarding to fermentations by yeast with no prior acidification. With alteration on two input variables, temperature curve and cell multiplication, which goal was to minimize the maximum values for diketones detected in the fermenter tank, a reduction was obtained from peak of formed diacetyl and consequently contributed to reduction in fermentation time and total process time. Several experiments were performed with those process changes in order to verify the influence on the total fermentation time and total vicinal diketones concentration at the end of fermentation. This experiment reached as the best production result a total fermentation time of 151 hours and total vicinal diketone concentration of 0.08 ppm. The mass of yeast in suspension in the second phase of fermentation increased from 2.45 x 106 to 16.38 x 106 cells/mL of yeast, which fact is key to a greater efficiency in reducing total vicinal diketones existing in the medium, confirming that the prior yeast acidification, as well as the control of temperature and yeast cell multiplication in fermentative process enhances the performance of diketones reduction and consequently reduce the total fermentation time with diketones concentration below the expected value (Max: 0.10 ppm)

Influência da intensidade de aeração na formação do floco de lodo ativado e na eficiência de remoção de matéria orgânica

In wastewater treatment, activated sludge systems have been a technology widely applied as secondary treatment. During this step, which has a strong biological aspect, it is necessary to introduce oxygen supply for the maintenance of metabolic activity of the bacteria through the aerators. Aeration devices are responsible for most of the energy consumption in this stage. In this background, the influence of three aeration intensities (atmospheric air flow 3.5, 7.0 and 10.5 L.min-1) and the concentration of dissolved oxygen (DO) on the dimension of activated sludge flocs as well as on the efficiency of organic matter removal were assessed using a traditional activated sludge system which was fed with synthetic domestic wastewater. Samples were taken weekly from the three units that make up the system feed, aeration and storage tank in order to verify the Chemical Oxygen Demand (COD). It was established the process efficiency through a comparison between the initial and final COD. Besides the parameters already mentioned, this monitoring work on activated sludge batch system was also observed by Mixed Liquor Suspend Solids (MLSS), Volatile Suspend Solids (VSS), pH and temperature measures. The results have showed a maximum removal efficiency around 75% in the first aeration sequence and approximately 85% for the second and third one. For the first aeration, the DO concentration remained higher than 3.0 mg.L-1 and a diameter range from 10 to 60 μm was observed. In the second e third sequence, the DO concentration remained higher than 4.0 mg.L-1 with a diameter range of 10 until 200 μm. Although the sequence 1 and 2 have presented similar performances for organic matter removal, the sequence 2 promoted a regular floc size distribution and with lower values of Sludge Volumetric Index (SVI) meaning a better flocculating ability. In addition, the results reaffirmed what the literature has reported: higher DO concentrations produce flocs with greater dimensions

Fatores de influência na produção de leite bovino sobre os níveis da contagem bacteriana total

The objective of this study was to evaluate the influence of milking procedures on the levels of total bacterial count (TBC) in bovine milk. In the first study the influences of procedures for hygienic milking, cleaning of milking equipment and milk cooling tanks on the TBC levels were evaluated. Four bulk samples of milk were collected from each tank in eight properties for TBC analysis, employing the flow cytometry method. A questionnaire was applied in each property to assess the current situation of milking procedures on each production system that took part on this research, followed by training of employees in good agricultural practices in the production of milk and monitoring of the TBC measurements. The methodology for analysis of longitudinal data was considered, focusing on random effects models. The results showed that the handling procedures for milking and the cleanliness of the cooling tank contributed to a further reduction in the levels of TBC raw milk cooling tanks. The second study aimed to describe the percentage of the properties that comply with the Normative Instruction Nº 51 (Brazil s IN 51) with regard to total bacterial count (TBC) in bovine milk. The study was conducted from January 2010 to July 2011. Milk samples were collected from the eight properties selected for TBC analysis by the flow cytometry method. Again, on each property a questionnaire was applied to assess the current situation of milking procedures on each production system that took part on this research, followed by training of employees in good agricultural practices in the production of milk and monitoring of the TBC measurements. The methodology of marginal models based on Generalized Estimate Equations (GEEs) was followed in the statistical analysis. The results showed that the handling procedures of the milking and the cleanliness of the cooling tanks contributed to a considerable percentage of the properties that reached the limits of TBC established by IN 51

Aplicação de tecnologias eletroquímicas (oxidação via radicais hidroxila, oxidação mediada via cloro ativo e eletrocoagulação) para o tratamento de efluentes reais ou sintéticos

In this work the degradation of real and synthetic wastewater was studied using electrochemical processes such as oxidation via hydroxyl radicals, mediated oxidation via active chlorine and electrocoagulation. The real effluent used was collected in the decanter tank of the Federal University of Rio Grande do Norte (ETE-UFRN) of Effluent Treatment Plant and the other a textile effluent dye Ácido Blue 113 (AB 113) was synthesized in the laboratory. In the electrochemical process, the effects of anode material, current density, the presence and concentration of chloride as well as the active chlorine species on site generated were evaluated. Electrodes of different compositions, Ti/Pt, Ti/Ru0,3Ti0,7O2, BDD, Pb/PbO2 and Ti/TiO2-nanotubes/PbO2 were used as anodes. These electrodes were subjected to electroanalytical analysis with the goal of checking how happen the anodic and cathodic processes across the concentrations of NaCl and supporting electrolyte used. The potential of oxygen evolution reaction were also checked. The effect of active chlorine species formed under the process efficiency was evaluated by removing the organic matter in the effluent-ETE UFRN. The wastewater treatment ETE-UFRN using Ti/Pt, DDB and Ti/Ru0,3Ti0,7O2 electrodes was evaluated, obtaining good performances. The electrochemical degradation of effluent-UFRN was able to promote the reduction of the concentration of TOC and COD in all tested anodes. However, Ti/Ru0,3Ti0,7O2 showed a considerable degradation due to active chlorine species generated on site. The results obtained from the electrochemical process in the presence of chloride were more satisfactory than those obtained in the absence. The addition of 0.021 M NaCl resulted in a faster removal of organic matter. Secondly, was prepared and characterized the electrode Ti/TiO2-nanotubes/PbO2 according to what the literature reports, however their preparation was to disk (10 cm diameter) with surface area and higher than that described by the same authors, aiming at application to textile effluent AB 113 dye. SEM images were taken to observe the growth of TiO2 nanotubes and confirm the electrodeposition of PbO2. Atomic Force Microscope was also used to confirm the formation of these nanotubes. Furthermore, was tested and found a high electrochemical stability of the electrode Ti/TiO2-nanotubes/PbO2 for applications such as long-term indicating a good electrocatalytic material. The electrochemical oxidation of AB 113 using Ti/Pt, Pb/PbO2 and Ti/TiO2-nanotubes/PbO2 and Al/Al (electrocoagulation) was also studied. However, the best color removal and COD decay were obtained when Ti/TiO2-nanotubes/PbO2 was used as the anode, removing up to 98% of color and 92,5% of COD decay. Analysis of GC/MS were performed in order to identify possible intermediates formed in the degradation of AB 113.

Estimativas, variabilidade e análise de tendência da evapotranspiração de referência em perímetros irrigados, no semiárido do nordeste brasileiro

The variability / climate change has generated great concern worldwide, is one of the major issues as global warming, which can is affecting the availability of water resources in irrigated perimeters. In the semiarid region of Northeastern Brazil it is known that there is a predominance of drought, but it is not enough known about trends in climate series of joint water loss by evaporation and transpiration (evapotranspiration). Therefore, this study aimed to analyze whether there is increase and / or decrease evidence in the regime of reference evapotranspiration (ETo), for the monthly, annual and interdecadal scales in irrigated polo towns of Juazeiro, BA (9 ° 24'S, 40 ° 26'W and 375,5m) and Petrolina, PE (09 ° 09'S, 40 ° 22'W and 376m), which is the main analysis objective. The daily meteorological data were provided by EMBRAPA Semiárido for the period from 01.01.1976 to 31.12.2014, estimated the daily ETo using the standard method of Penman-Monteith (EToPM) parameterized by Smith (1991). Other methods of more simplified estimatives were calculated and compared to EToPM, as the ones following: Solar Radiation (EToRS), Linacre (EToL), Hargreaves and Samani (EToHS) and the method of Class A pan (EToTCA). The main statistical analysis were non-parametric tests of homogeneity (Run), trend (Mann-kendall), magnitude of the trend (Sen) and early trend detection (Mann-Whitney). The statistical significance adopted was 5 and / or 1%. The Analysis of Variance - ANOVA was used to detect if there is a significant difference in mean interdecadal mean. For comparison between the methods of ETo, it were used the correlation test (r), the Student t test and Tukey levels of 5% significance. Finally, statistics Willmott et al. (1985) statistics was used to evaluate the concordance index and performance of simplified methods compared to the standard method. It obtained as main results that there was a decrease in the time series of EToPM in irrigated areas of Juazeiro, BA and Petrolina, PE, significant respectively at 1 and 5%, with an annual magnitude of -14.5 mm (Juazeiro) and -7.7 mm (Petrolina) and early trend in 1996. The methods which had better for better agreement with EToPM were EToRS with very good performance, in both locations, followed by the method of EToL with good performance (Juazeiro) and median (Petrolina). EToHS had the worst performance (bad) for both locations. It is suggested that this decrease of EToPM can be associated with the increase in irrigated agricultural areas and the construction of Sobradinho lake upstream of the perimeters.

Critério de correntropia no treinamento de redes fuzzy wavelet neural networks para identificação de sistemas dinâmicos não lineares

The great interest in nonlinear system identification is mainly due to the fact that a large amount of real systems are complex and need to have their nonlinearities considered so that their models can be successfully used in applications of control, prediction, inference, among others. This work evaluates the application of Fuzzy Wavelet Neural Networks (FWNN) to identify nonlinear dynamical systems subjected to noise and outliers. Generally, these elements cause negative effects on the identification procedure, resulting in erroneous interpretations regarding the dynamical behavior of the system. The FWNN combines in a single structure the ability to deal with uncertainties of fuzzy logic, the multiresolution characteristics of wavelet theory and learning and generalization abilities of the artificial neural networks. Usually, the learning procedure of these neural networks is realized by a gradient based method, which uses the mean squared error as its cost function. This work proposes the replacement of this traditional function by an Information Theoretic Learning similarity measure, called correntropy. With the use of this similarity measure, higher order statistics can be considered during the FWNN training process. For this reason, this measure is more suitable for non-Gaussian error distributions and makes the training less sensitive to the presence of outliers. In order to evaluate this replacement, FWNN models are obtained in two identification case studies: a real nonlinear system, consisting of a multisection tank, and a simulated system based on a model of the human knee joint. The results demonstrate that the application of correntropy as the error backpropagation algorithm cost function makes the identification procedure using FWNN models more robust to outliers. However, this is only achieved if the gaussian kernel width of correntropy is properly adjusted.

Qualidade do leite de búfala (Bubalus bubalis) suplementada com selênio

This study aimed to evaluate the effect of diet with selenium on the physico-chemical composition and somatic cell count of buffalo milk, and check the selenium waste in milk and minas kind fresh cheese. For the analysis of physical-chemical composition and SCC were used 2264 buffalo milk data from the Murrah, belonging to Tapuio Ltda, located in the agreste region of the state of Rio Grande do Norte, in the period 2010 to 2014. To check the amount of selenium residue in buffalo milk and fresh cheese mines were used 100 Murrah buffaloes divided into 5 lots. The batches were formed according to the production levels of animals, wherein the amount of concentrate fed varied within each lot, which received 0.08 ppm / Se / kg of concentrate. Was collected from 300 ml of tank milk from and each lot, as well as 300 gr minas cheese, from August to November 2014, with the collection of lots held only in the month of November. The samples were sent to the Pernambuco Tecnology Institute for selenium residue analysis. The effect of the seasons was contrasted in two ways, namely: Spring, Summer, Autumn and Winter season or drought and rainy season. The analyzes statistics were performed using the procedures available in the software SAS® (SAS, 2002). Selenium level provided to the animals in this study was not significant to the point of detection of their residue in milk and the cheeses. However, it influences the reduction of the CCS. The milk characteristics were not affected by selenium use only the seasons.

Qualidade do leite de búfala (Bubalus bubalis) suplementada com selênio

This study aimed to evaluate the effect of diet with selenium on the physico-chemical composition and somatic cell count of buffalo milk, and check the selenium waste in milk and minas kind fresh cheese. For the analysis of physical-chemical composition and SCC were used 2264 buffalo milk data from the Murrah, belonging to Tapuio Ltda, located in the agreste region of the state of Rio Grande do Norte, in the period 2010 to 2014. To check the amount of selenium residue in buffalo milk and fresh cheese mines were used 100 Murrah buffaloes divided into 5 lots. The batches were formed according to the production levels of animals, wherein the amount of concentrate fed varied within each lot, which received 0.08 ppm / Se / kg of concentrate. Was collected from 300 ml of tank milk from and each lot, as well as 300 gr minas cheese, from August to November 2014, with the collection of lots held only in the month of November. The samples were sent to the Pernambuco Tecnology Institute for selenium residue analysis. The effect of the seasons was contrasted in two ways, namely: Spring, Summer, Autumn and Winter season or drought and rainy season. The analyzes statistics were performed using the procedures available in the software SAS® (SAS, 2002). Selenium level provided to the animals in this study was not significant to the point of detection of their residue in milk and the cheeses. However, it influences the reduction of the CCS. The milk characteristics were not affected by selenium use only the seasons.

Análise experimental do consumo de um veículo flex operando com diferentes misturas de gasolina/etanol em tráfego urbano

This study is an analysis, on a trial basis, the fuel consumption of a Flex vehicle, operating with different mixtures of gasoline and ethanol in urban traffic, allowing more consistent results with the reality of the driver. Considering that most owners unaware of the possibility of mixing the fuel at the time of supply, thus enabling the choice of the most economically viable mixing gasoline / ethanol, resulting in lower costs and possibly a decrease in pollutant emission rates. Currently, there is a myth created by the people that supply ethanol only becomes viable if the value of not more than 70% of regular gasoline. However vehicles with this technology make it possible to operate with any percentage of mixture in the fuel tank, but today many of the owners of these vehicles do not use this feature effectively, because they ignore the possibility of mixing or the reason there is a deeper study regarding the optimal percentage of the mixture to provide a higher yield with a lower cost than proposed by the manufacturers.