Estratégias baseadas em aprendizado para coordenação de uma frota de robôs em tarefas cooperativas

In multi-robot systems, both control architecture and work strategy represent a challenge for researchers. It is important to have a robust architecture that can be easily adapted to requirement changes. It is also important that work strategy allows robots to complete tasks efficiently, considering that robots interact directly in environments with humans. In this context, this work explores two approaches for robot soccer team coordination for cooperative tasks development. Both approaches are based on a combination of imitation learning and reinforcement learning. Thus, in the first approach was developed a control architecture, a fuzzy inference engine for recognizing situations in robot soccer games, a software for narration of robot soccer games based on the inference engine and the implementation of learning by imitation from observation and analysis of others robotic teams. Moreover, state abstraction was efficiently implemented in reinforcement learning applied to the robot soccer standard problem. Finally, reinforcement learning was implemented in a form where actions are explored only in some states (for example, states where an specialist robot system used them) differently to the traditional form, where actions have to be tested in all states. In the second approach reinforcement learning was implemented with function approximation, for which an algorithm called RBF-Sarsa($lambda$) was created. In both approaches batch reinforcement learning algorithms were implemented and imitation learning was used as a seed for reinforcement learning. Moreover, learning from robotic teams controlled by humans was explored. The proposal in this work had revealed efficient in the robot soccer standard problem and, when implemented in other robotics systems, they will allow that these robotics systems can efficiently and effectively develop assigned tasks. These approaches will give high adaptation capabilities to requirements and environment changes.

Desgaste corrosivo-cavitativo-erosivo de um aço-carbono em meio aquoso com frações de sal (NaCl), CO2 e particulados sólidos (SiO2)

A batch of eighty-four coupons of low carbon steel were investigated at laboratory conditions under a corrosive, cavitative-corrosive (CO2) and corrosive-erosive (SiO2 + CO2) in an aqueous salt solution and two levels of temperature. The following measurements were made on Vickers (HV0,05, HV0,10, HV0,20) Microhardness tests at three levels of subsurface layer. A turbulent flow collided on the cylindrical sample, with and without mechanical stirring and gas bubbling, with and without fluid contamination by solid particles of SiO2, at two temperatures. Surface Roughness and Waviness, under two conditions "as received, after machining" and "after worn out", as well as gravimetric and electrochemical parameter were measured on the two opposite generatrices of each cylindrical sample, on the flow upstream (0°) and downstream (180°) by Profilometry, Mass Variation and Linear Polarization Resistance (LPR). The results of the Microhardness and Surface Texture of all coupons were subjected to statistical comparison, using the software Statgraphics® Centurion XVI, 95% statistical certainty, and significant differences were observed in some arrays of measurements. The corrosive wear rate measured by LPR and mass variation shown to be sensitive to the presence of bubbles and hydrodynamic fluctuations inside the cell, considering the temperature and contamination of corrosive fluid by solid particles. The main results of visual inspection relative to some topologies of the surface damages involving different mechanisms that were seen to give explanation for some fluctuations in wear rates of the steel experimentally investigated

Desenvolvimento e teste de um protótipo de reator de plasma com gaiola catódica rotatória para nitretação em lote de pequenas peças

The technique of ion nitriding, despite being fully consolidated in the industry, has great limitations when applied to the treatment of small parts. This is because effects that occur due to non-uniformity of the electric field, generate localized heating in parts, damaging the uniformity of nitrided layer. In addition, because the samples are treated static parts thereof are untreated. To expand the use of plasma nitriding, this work presents the development, assembly and testing of a prototype plasma reactor with rotatory cathodic cage [patent pending], able to meet these needs, giving the material a uniform treatment and opening doors to industrial scale production. The samples tested with hexagonal nuts are 6.0 mm in diameter, made of stainless steel AISI 304 nitrided at a pressure of 1 mbar in an atmosphere of 20% H2 + 80% N2 for 1 h. After treatment, testing visual inspection, optical microscopy and microhardness were carried out to check the effectiveness of the process for uniformity and hardness of the parts. All samples exhibited uniform color, and matte brownish, unlike the untreated samples, silver color and gloss. The hardness of the surface (top and sides) was 65% and even higher than the original hardness. The nitrided layer showed great uniformity in microstructure and thickness. It is concluded, therefore, that the unit was effective constructed for the purposes for which it was designed

Extração do óleo e caracterização dos resíduos da borra de petróleo para fins de reuso

The petroleum industry, in consequence of an intense activity of exploration and production, is responsible by great part of the generation of residues, which are considered toxic and pollutants to the environment. Among these, the oil sludge is found produced during the production, transportation and refine phases. This work had the purpose to develop a process to recovery the oil present in oil sludge, in order to use the recovered oil as fuel or return it to the refining plant. From the preliminary tests, were identified the most important independent variables, like: temperature, contact time, solvents and acid volumes. Initially, a series of parameters to characterize the oil sludge was determined to characterize its. A special extractor was projected to work with oily waste. Two experimental designs were applied: fractional factorial and Doehlert. The tests were carried out in batch process to the conditions of the experimental designs applied. The efficiency obtained in the oil extraction process was 70%, in average. Oil sludge is composed of 36,2% of oil, 16,8% of ash, 40% of water and 7% of volatile constituents. However, the statistical analysis showed that the quadratic model was not well fitted to the process with a relative low determination coefficient (60,6%). This occurred due to the complexity of the oil sludge. To obtain a model able to represent the experiments, the mathematical model was used, the so called artificial neural networks (RNA), which was generated, initially, with 2, 4, 5, 6, 7 and 8 neurons in the hidden layer, 64 experimental results and 10000 presentations (interactions). Lesser dispersions were verified between the experimental and calculated values using 4 neurons, regarding the proportion of experimental points and estimated parameters. The analysis of the average deviations of the test divided by the respective training showed up that 2150 presentations resulted in the best value parameters. For the new model, the determination coefficient was 87,5%, which is quite satisfactory for the studied system

Desenvolvimento de um destilador solar para tratamento de águas de produção de petróleo com vistas a sua utilização na agricultura e geração de vapor

The production of petroleum is frequently accomplished with great volumes of water, that it is carried of the underground with the oil. It is a challenge of the present century the development of technologies that allow the use of waste water for purposes that consume great amounts of water and don't demand as rigid as the one of the drinking water requirements. The solar distillation has been configuring as an alternative of clean technology for desalination of brine and saline. Besides causing the minimum possible damage to the environment, it takes advantage of an abundant and free energy source: the solar energy. That study aims to develop a Solar Distillator for treatment of the produced water of the oil wells, to obtain an efluent to use in agriculture and vapor generation. The methodology for collection, conservation and analysis of the physical-chemical parameters obeyed the norms in APHA (1995). The sampling was of the composed type. Experiments were accomplished in the solar distillation pilot and simulation in thermostatic bathing. The operation was in batch system and for periods of 4, 6 and 12 h. The developed Distillator is of the type simple effect of two waters. It was still tested two inclination angles for covering; 20º and 45º. The Distillator presented minimum of 2,85 L/m2d revenues and maximum of 7,14 L/m2d. The removals of salts were great than 98%. The removal of TOC in the simulation was great than 90%. In agreement with the data of energy and mass balance, it was verified that the developed solar Distillator presented compatible revenues with those found in literature for similar types. It can be inferred that the obtained distilled water assists to the requirements CONAMA in almost all the points and could be used for irrigation of cultures such as cotton and mamona. As the distilled water has characteristics of fresh water it can be used in the generation of vapor

Purificação da glicerina bruta obtida a partir da transesterificação do óleo de algodão

The crude glycerine is a raw material that can be used in a wide variety of products. Even with all the impurities inherent in the process of being obtained, the crude glycerin is already in a marketable product. However, the market is much more favorable to the commercialization of purified glycerine. The glycerin is a byproduct gotten from the process of transesterification of waste oils and fats in the production of biodiesel. More recently, the deployment of the new Federal Law of Brazil, related to the implementation of energy resources, forces, from 2008, the increase of 2% biodiesel in diesel common with prospects for 5% (B5). Therefore, it is indispensable that new routes of purification as well as new markets are developed. The objective of this work was to purify, through ion exchange, the crude glycerin, obtained from the reaction of transesterification of cottonseed oil. The cottonseed oil was characterized as the fatty acid composition and physical-chemical properties. The process of ion exchange was conducted in batch. In this process were used strong cation, low anion resins and a mixed resin used to de-ionize water. The purified glycerin was characterized as the content of metals. Tests were performed with activated charcoal adsorption, and for this, it was made tests of time contact with coal as well as quantity of coal used. The time of activation, the amount of the activation solution, the contact time of the glycerol solution in resins, the amount and type of resin applied were evaluated. Considering the analysis made with activated charcoal, when the glycerin solution was treated using the resins individually it was observed that in the conditions for treatment with 10 g of resin, 5 hours of contact with each resin and 50 mL of glycerin solution, its conductivity decreased to a cationic resin, increased to the anionic resin and had a variable value with respect to resin mixed. In the treatment in series, there was a constant decrease in the conductivity of the solution of glycerin. Considering two types of treatment, in series and individually, the content of glycerol in glycerin pre-purified solution with the different resins varied from 12,46 to 29.51% (diluted solution). In analysis performed without the use of activated charcoal, the behavior of the conductivity of the solution of glycerin were similar to results for treatment with activated charcoal, both in series as individually. The solution of glycerin pre-purified had a glycerol content varying from 8.3 to 25.7% (diluted solution). In relation to pH, it had a behavior in accordance with the expected: acid for the glycerin solution treated with cationic resin, basic when the glycerin solution was treated with the anionic resin and neutral when treated with the mixed resin, independent of the kind of procedure used (with or without coal, resins individually or in series). In relation to the color of the glycerin pre-purified solution, the resin that showed the best result was the anionic (colorless), however this does not mean that the solution is more in pure glycerol. The chromatographic analysis of the solutions obtained after the passage through the resins indicated that the treatment was effective by the presence of only one component (glycerol), not considering the solvent of the analysis

Aplicação de microemulsões na solubilização de frações pesadas de petróleo

This work presents studies related to the use of microemulsions in the solubilization of heavy crude oil fractions responsible by the formation of deposits. The first stage of the work was addressed to the construction of phases diagrams, with the intention of determining the area within which the microemulsion is formed. The following systems were studied: UNITOL L 90 n-Butanol - Water - Kerosene (system 1); UNITOL L 90 - n-Butanol - Water - Xylene (system 2); UNITOL L 90 n-Butanol - Water - Kerosene/Xylene 10% (system 3); UNITOL L 90 - Sec-Butanol - Water - Xylene (system 4). In parallel experiments of physical adsorption were carried out by the static method, with the intention of simulating natural conditions of reservoirs. Crude oil of the Fazenda Belém field (Rio Grande do Norte), was used as solute, xylene as solvent and the Assu sandstone (Rio Grande do Norte, Brazil) and Botucatu sandstone (Paraná, Brazil) as rock reservoirs. The curves of adsorption presented the S format type, in agreement with the classification proposed by Giles, Smith and Huitson (1974). The solubilization process was accomplished in the batch method, by varying the time of agitation, the microemulsions and the solid/solution ratio. The experiments showed that the microemulsions presented high efficiency in the solubilization of the crude oil adsorbed on the sandstones. System 2 presented an efficiency of 99% for the Assu sandstone and 97% for the Botucatu sandstone

Avaliação do processo oxidativo avançado por permanganato de potássio no tratamento de solos contaminados com idrocarbonetos poliaromáticos

The soil contamination with petroleum is one of the major concern of industries operating in the field and also of environmental agencies. The petroleum consists mainly of alkanes and aromatic hydrocarbons. The most common examples of hydrocarbons polyaromatic are: naphthalene, anthracene, phenanthrene, benzopyrene and their various isomers. These substances cause adverse effects on human and the environment. Thus, the main objective of this work is to study the advanced oxidation process using the oxidant potassium permanganate (KMnO4) for remediation of soils contaminated with two polyaromatic hydrocarbons (PAHs): anthracene and phenanthrene. This study was conducted at bench scale, where the first stage was at batch experiment, using the variables: the time and oxidant dosage in the soil. The second stage was the remediation conducted in continous by a fix column, to this stage, the only variable was remediation time. The concentration of oxidant in this stage was based on the best result obtained in the tests at batch, 2,464 mg / L. The results of degradation these contaminants were satisfactory, at the following dosages and time: (a) 5g of oxidant per kg soil for 48 hours, it was obtained residual contaminants 28 mg phenanthrene and 1.25 mg anthracene per kg of soil and (b) for 7g of oxidant per kg soil in 48 hours remaining 24 mg phenanthrene and anthracene 0.77 mg per kg soil, and therefore below the intervention limit residential and industrial proposed by the State Company of Environmental Sao Paulo (CETESB)

Montagem e operação de um secador pneumático tipo flash

In this work, a pneumatic dryer has been designed and assembled in laboratory scale in order to study and evaluate configurations more efficient for application in drying of important materials of Northeast region in Brazil. The equipment was tested with drying of corn and rice grains, in conditions of temperature and air velocity at 80 oC and 35 m/s, respectively. For this type of dryer, it is recommended to work at temperatures above 200 °C and air velocity with higher dynamic pressure. However, even under operating conditions below what it is recommended, the results obtained with the pneumatic dryer were satisfactory. In addition, experiments of drying were performed by using a cabinet dryer (batch dryer) under the same conditions used in the pneumatic dryer. Flash one curves for the corn were fitted satisfactorily by applying of the Lewis model, while a better agreement was found for rice by using the Page model. The data obtained with both drying processes allowed to compare the performance between pneumatic and batch dryers. In respect to drying rate, the pneumatic dryer presented a similar performance to the batch dryer during processing with corn and a superior performance to the last one during processing with rice. Therefore, it was possible to verify that the pneumatic dryer assembled in this preliminar study can be applied for different materials and under different operating conditions

Avaliação da capacidade de adsorção do CO2 em zeólita 12X com gases sintéticos e originados da pirólise do lodo de esgoto

This work depicts a study of the adsorption of carbon dioxide on zeolite 13X. The activities were divided into four stages: study batch adsorption capacity of the adsorbent with synthetic CO2 (4%), fixed bed dynamic evaluation with the commercial mixture of gases (4% CO2, 1.11% CO, 1 2% H2, 0.233% CH4, 0.1% C3, 0.0233% C4 argon as inert closing balance), fixed bed dynamic modeling and evaluation of the breakthrough curve of CO2 originated from the pyrolysis of sewage sludge. The sewage sludge and the adsorbent were characterized by analysis TG / DTA, SEM, XRF and BET. Adsorption studies were carried out under the following operating conditions: temperature 40 °C (for the pyrolysis of the sludge T = 600 °C), pressures of 0.55 to 5.05 bar (batch process), flow rate of the gaseous mixture between 50 - 72 ml/min and the adsorbent masses of 10, 15 and 20 g (fixed bed process). The time for the adsorption batch was 7 h and on the fixed bed was around 180 min. The results of this study showed that in batch adsorption process step with zeolite 13X is efficient and the mass of adsorbed CO2 increases with the increases pressure, decreases with temperature increases and rises due the increase of activation temperature adsorbent. In the batch process were evaluated the breakthrough curves, which were compared with adsorption isotherms represented by the models of Langmuir, Freündlich and Toth. All models well adjusted to the experimental points, but the Langmuir model was chosen in view of its use in the dynamic model does not have implications for adsorption (indeterminacy and larger number of parameters such as occurred with others) in solving the equation. In the fixed bed dynamic study with the synthetic gas mixture, 20 g of mass adsorbent showed the maximum adsorption percentage 46.7% at 40 °C temperature and 50 mL/min of flow rate. The model was satisfactorily fitted to the three breakthrough curves and the parameters were: axial dispersion coefficient (0.0165 dm2/min), effective diffusivity inside the particle (dm2/min 0.0884) and external transfer coefficient mass (0.45 dm/min). The breakthrough curve for CO2 in the process of pyrolysis of the sludge showed a fast saturation with traces of aerosols presents in the gas phase into the fixed bed under the reaction process

Recuperação e purificação de quitosanases usando adsorção em leito expandido com streamline DEAE com modelagem e simulação usando redes neurais

Expanded Bed Adsorption (EBA) is an integrative process that combines concepts of chromatography and fluidization of solids. The many parameters involved and their synergistic effects complicate the optimization of the process. Fortunately, some mathematical tools have been developed in order to guide the investigation of the EBA system. In this work the application of experimental design, phenomenological modeling and artificial neural networks (ANN) in understanding chitosanases adsorption on ion exchange resin Streamline® DEAE have been investigated. The strain Paenibacillus ehimensis NRRL B-23118 was used for chitosanase production. EBA experiments were carried out using a column of 2.6 cm inner diameter with 30.0 cm in height that was coupled to a peristaltic pump. At the bottom of the column there was a distributor of glass beads having a height of 3.0 cm. Assays for residence time distribution (RTD) revelead a high degree of mixing, however, the Richardson-Zaki coefficients showed that the column was on the threshold of stability. Isotherm models fitted the adsorption equilibrium data in the presence of lyotropic salts. The results of experiment design indicated that the ionic strength and superficial velocity are important to the recovery and purity of chitosanases. The molecular mass of the two chitosanases were approximately 23 kDa and 52 kDa as estimated by SDS-PAGE. The phenomenological modeling was aimed to describe the operations in batch and column chromatography. The simulations were performed in Microsoft Visual Studio. The kinetic rate constant model set to kinetic curves efficiently under conditions of initial enzyme activity 0.232, 0.142 e 0.079 UA/mL. The simulated breakthrough curves showed some differences with experimental data, especially regarding the slope. Sensitivity tests of the model on the surface velocity, axial dispersion and initial concentration showed agreement with the literature. The neural network was constructed in MATLAB and Neural Network Toolbox. The cross-validation was used to improve the ability of generalization. The parameters of ANN were improved to obtain the settings 6-6 (enzyme activity) and 9-6 (total protein), as well as tansig transfer function and Levenberg-Marquardt training algorithm. The neural Carlos Eduardo de Araújo Padilha dezembro/2013 9 networks simulations, including all the steps of cycle, showed good agreement with experimental data, with a correlation coefficient of approximately 0.974. The effects of input variables on profiles of the stages of loading, washing and elution were consistent with the literature

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

Microemulsões aplicadas ao tratamento de Óleos isolantes

Naphthenic lubricating oils are used in transformers with the purpose of promoting electrical insulation and dissipating heat. The working temperature range of these oils typically lies between 60°C and 90°C and their useful life is 40 years in average. In that temperature range, the oils are decomposed during operation, whereby a small fraction of polar compounds are formed. The presence of these compounds may induce failure and loss of physical, chemical and electrical properties of the oil, thus impairing the transformer operation. By removing these contaminants, one allows the oxidized insulating oil to be reused without damaging the equipment. In view of this, an investigation on the use of surfactants and microemulsions as extracting agents, and modified diatomite as adsorbent, has been proprosed in this work aiming to remove polar substances detected in oxidized transformer oils. The extraction was carried out by a simple-contact technique at room temperature. The system under examination was stirred for about 10 minutes, after which it was allowed to settle at 25°C until complete phase separation. In another experimental approach, adsorption equilibrium data were obtained by using a batch system operating at temperatures of 60, 80 and 100°C. Analytical techniques involving determination of the Total Acidity Number (TAN) and infrared spectrophotometry have been employed when monitoring the decomposition and recovery processes of the oils. The acquired results indicated that the microemulsion extraction system comprising Triton® X114 as surfactant proved to be more effective in removing polar compounds, with a decrease in TAN index from 0.19 to 0.01 mg KOH/g, which is consistent with the limits established for new transformer oils (maximal TAN = 0.03 mg KOH/g). In the adsorption studies, the best adsorption capacity values were as high as 0.1606 meq.g/g during conventional adsoprtion procedures using natural bauxite, and as high as 0.016 meq.g/g for the system diatomite/Tensiofix® 8426. Comparatively in this case, a negative effect could be observed on the adsorption phenomenon due to microemulsion impregnation on the surface of the diatomite

Avaliação de catalisadores a base de carbeto e nitreto de molibdênio na obtenção de lactitol via hidrogenação da lactose

Seeking a greater appreciation of cheese whey was developed to process the hydrogenation of lactose for the production of lactitol, a polyol with high added value, using the catalyst Ni / activated carbon (15% and 20% nickel), the nitride Mo2N, the bimetallic carbide Ni-Mo/ activated carbon and carbide Mo2C. After synthesis, the prepared catalysts were analyzed by MEV, XRD, laser granulometry and B.E.T. The reactor used in catalytic hydrogenation of lactose was the type of bed mud with a pressure (68 atm), temperature (120 oC) and stirring speed (500 rpm) remained constant during the experiments. The system operated in batch mode for the solid and liquid and semi-continuous to gas. Besides the nature of the catalyst, we studied the influence of pH of reaction medium for Mo2C carbide as well as evaluating the character of the protein inhibitor and chloride ions on the activity of catalysts Ni (20%)/Activated Carbon and bimetallic carbide Ni-Mo/Activated Carbon. The decrease in protein levels was performed by coagulation with chitosan and adsorption of chloride ions was performed by ion exchange resins. In the process of protein adsorption and chloride ions, the maximum percentage extracted was about 74% and 79% respectively. The micrographs of the powders of Mo2C and Mo2N presented in the form of homogeneous clusters, whereas for the catalysts supported on activated carbon, microporous structure proved impregnated with small particles indicating the presence of metal. The results showed high conversion of lactose to lactitol 90% for the catalyst Ni (20%)/Activated Carbon at pH 6 and 46% for the carbide Mo2C pH 8 (after addition of NH4OH) using the commercial lactose. Monitoring the evolution of the constituents present in the reaction medium was made by liquid chromatography. A kinetic model of heterogeneous Langmuir Hinshelwood type was developed which showed that the estimated constants based catalysts promoted carbide and nitride with a certain speed the adsorption, desorption and production of lactitol

Produção de bioetanol a partir de pedúnculo de caju (Anacardium occidentale L.) por fermentação submersa

Recently, global demand for ethanol fuel has expanded very rapidly, and this should further increase in the near future, almost all ethanol fuel is produced by fermentation of sucrose or glucose in Brazil and produced by corn in the USA, but these raw materials will not be enough to satisfy international demand. The aim of this work was studied the ethanol production from cashew apple juice. A commercial strain of Saccharomyces cerevisiae was used for the production of ethanol by fermentation of cashew apple juice. Growth kinetics and ethanol productivity were calculated for batch fermentation with different initial sugar (glucose + fructose) concentration (from 24.4 to 103.1 g.L-1). Maximal ethanol, cell and glycerol concentrations (44.4 g.L-1, 17.17 g.L-1, 6.4 g.L-1, respectively) were obtained when 103.1 g.L-1 of initial sugar concentration were used, respectively. Ethanol yield (YP/S) was calculated as 0.49 g (g glucose + fructose)-1. Pretreatment of cashew apple bagasse (CAB) with dilute sulfuric acid was investigated and evaluated some factors such as sulfuric acid concentration, solid concentration and time of pretreatment at 121°C. The maximum glucose yield (162.9 mg/gCAB) was obtained by the hydrolysis with H2SO4 0.6 mol.L-1 at 121°C for 15 min. Hydrolysate, containing 16 ± 2.0 g.L-1 of glucose, was used as fermentation medium for ethanol production by S. cerevisiae and obtained a ethanol concentration of 10.0 g.L-1 after 4 with a yield and productivity of 0.48 g (g glucose)-1 and 1.43 g.L-1.h-1, respectively. The enzymatic hydrolysis of cashew apple bagasse treated with diluted acid (CAB-H) and alkali (CAB-OH) was studied and to evaluate its fermentation to ethanol using S. cerevisiae. Glucose conversion of 82 ± 2 mg per g CAB-H and 730 ± 20 mg per g CAB-OH was obtained when was used 2% (w/v) of solid and loading enzymatic of 30 FPU/g bagasse at 45 °C. Ethanol concentration and productivity was achieved of 20.0 ± 0.2 g.L-1 and 3.33 g.L-1.h-1, respectively when using CAB-OH hydrolyzate (initial glucose concentration of 52.4 g.L-1). For CAB-H hydrolyzate (initial glucose concentration of 17.4 g.L-1), ethanol concentration and productivity was 8.2 ± 0.1 g.L-1 and 2.7 g.L-1.h-1, respectively. Hydrolyzates fermentation resulted in an ethanol yield of 0.38 g/g glucose and 0.47 g/g glucose, with pretreated CABOH and CAB-H, respectively. The potential of cashew apple bagasse as a source of sugars for ethanol production by Kluyveromyces marxianus CE025 was evaluated too in this work. First, the yeast CE025 was preliminary cultivated in a synthetic medium containing glucose and xylose. Results showed that it was able to produce ethanol and xylitol at pH 4.5. Next, cashew apple bagasse hydrolysate (CABH) was prepared by a diluted sulfuric acid pre-treatment. The fermentation of CABH was conducted at pH 4.5 in a batch-reactor, and only ethanol was produced by K. marxianus CE025. The influence of the temperature in the kinetic parameters was evaluated and best results of ethanol production (12.36 ± 0.06 g.L-1) was achieved at 30 ºC, which is also the optimum temperature for the formation of biomass and the ethanol with a volumetric production rate of 0.25 ± 0.01 g.L-1.h-1 and an ethanol yield of 0.42 ± 0.01 g/g glucose. The results of this study point out the potential of the cashew apple bagasse hydrolysate as a new source of sugars to produce ethanol by S. cerevisiae and K. marxianus CE025. With these results, conclude that the use of cashew apple juice and cashew apple bagasse as substrate for ethanol production will bring economic benefits to the process, because it is a low cost substrate and also solve a disposal problem, adding value to the chain and cashew nut production