Aspectos matemáticos do problema de aprendizagem em inteligência artificial

O objetivo deste trabalho é apresentar a base teórica para o problema de aprendizagem através de exemplos conforme as ref. [14], [15] e [16]. Aprender através de exemplos pode ser examinado como o problema de regressão da aproximação de uma função multivaluada sobre um conjunto de dados esparsos. Tal problema não é bem posto e a maneira clássica de resolvê-lo é através da teoria de regularização. A teoria de regularização clássica, como será considerada aqui, formula este problema de regressão como o problema variacional de achar a função f que minimiza o funcional Q[f] = 1 n n Xi=1 (yi ¡ f(xi))2 + ¸kfk2 K; onde kfk2 K é a norma em um espa»co de Hilbert especial que chamaremos de Núcleo Reprodutivo (Reproducing Kernel Hilbert Spaces), ou somente RKHS, IH definido pela função positiva K, o número de pontos do exemplo n e o parâmetro de regularização ¸. Sob condições gerais a solução da equação é dada por f(x) = n Xi=1 ciK(x; xi): A teoria apresentada neste trabalho é na verdade a fundamentação para uma teoria mais geral que justfica os funcionais regularizados para a aprendizagem através de um conjunto infinito de dados e pode ser usada para estender consideravelmente a estrutura clássica a regularização, combinando efetivamente uma perspectiva de análise funcional com modernos avanços em Teoria de Probabilidade e Estatística.

Application of multivariable control using artificial neural networks in a debutanizer distillation column

LOPES, Jose Soares Batista et al. Application of multivariable control using artificial neural networks in a debutanizer distillation column.In: INTERNATIONAL CONGRESS OF MECHANICAL ENGINEERING - COBEM, 19, 5-9 nov. 2007, Brasilia. Anais... Brasilia, 2007

SISAL - Um sistema supervisório para elevação artificial de petróleo

MEDEIROS, Adelardo A. D. et al. SISAL - Um Sistema Supervisório para Elevação Artificial de Petróleo. In: Rio Oil and Gas Expo Conference, 2006, Rio de Janeiro, RJ. Anais... Rio de Janeiro, 2006.

Efeitos da tilápia do Nilo (Oreochromis niloticus) e do enriquecimento por nutrientes sobre a comunidade planctônica em um lago artificial no semi-árido brasileiro

The major aim of this study was to test the hypothesis that the introduction of the Nile tilapia (Oreochromis niloticus) and the enrichment with nutrients (N and P) interact synergistically to change the structure of plankton communities, increase phytoplankton biomass and decrease water transparency of a semi-arid tropical reservoir. One field experiment was performed during five weeks in twenty enclosures (8m3) to where four treatments were randomly allocated: with tilapia addition (T), with nutrients addition (NP), with tilapia and nutrients addition (T+NP) and a control treatment with no tilapia or nutrients addition (C). A two-way repeated measures ANOVA was done to test for time (t), tilapia (T) and nutrient (NP) effects and their interaction on water transparency, total phosphorus, total nitrogen, phytoplankton and zooplankton. The results show that there was no effect of nutrient addition on these variables but significant fish effects on the biomass of total zooplankton, nauplii, rotifers, cladocerans and calanoid copepods, on the biovolume of Bacillariophyta, Zygnemaphyceae and large algae (GALD ≥ 50 μm) and on Secchi depth. In addition, we found significant interaction effects between tilapia and nutrients on Secchi depth and rotifers. Overall, tilapia decreased the biomass of most zooplankton taxa and large algae (diatoms) and decreased the water transparency while nutrient enrichment increased the biomass of zooplankton (rotifers) but only in the absence of tilapia. In conclusion, the influence of fish on the reservoir plankton community and water transparency was greater than that of nutrient loading. This finding suggests that biomanipulation should be a greater priority in the restoration of eutrophic reservoirs in tropical semi-arid regions

Sistema supervisório para poços de petróleo baseados no método de elevação artificial Plunger Lift

The several existing methods for oil artificial lifting and the variety of automation equipment for these methods many times lead the supervisory systems to be dedicated to a unique method and/or to a unique manufacturer. To avoid this problem, it has been developed the supervisory system named SISAL, conceived to supervise wells with different lifting methods and different automation equipments. The SISAL system is working in several Brazilian states but, nowadays, it is only supervising rod pump-based wells. The objective of this work is the development of a supervision module to the plunger lift artificial lift method. The module will have the same characteristics of working with automation hardware of many manufacturers. The module will be integrated to the SISAL system, incorporating the capacity to supervise the plunger lift artificial lift method.

Ambiente para avaliação de controladores fuzzy aplicados ao método de elevação artificial por bombeio centrífugo submerso

From their early days, Electrical Submergible Pumping (ESP) units have excelled in lifting much greater liquid rates than most of the other types of artificial lift and developed by good performance in wells with high BSW, in onshore and offshore environments. For all artificial lift system, the lifetime and frequency of interventions are of paramount importance, given the high costs of rigs and equipment, plus the losses coming from a halt in production. In search of a better life of the system comes the need to work with the same efficiency and security within the limits of their equipment, this implies the need for periodic adjustments, monitoring and control. How is increasing the prospect of minimizing direct human actions, these adjustments should be made increasingly via automation. The automated system not only provides a longer life, but also greater control over the production of the well. The controller is the brain of most automation systems, it is inserted the logic and strategies in the work process in order to get you to work efficiently. So great is the importance of controlling for any automation system is expected that, with better understanding of ESP system and the development of research, many controllers will be proposed for this method of artificial lift. Once a controller is proposed, it must be tested and validated before they take it as efficient and functional. The use of a producing well or a test well could favor the completion of testing, but with the serious risk that flaws in the design of the controller were to cause damage to oil well equipment, many of them expensive. Given this reality, the main objective of the present work is to present an environment for evaluation of fuzzy controllers for wells equipped with ESP system, using a computer simulator representing a virtual oil well, a software design fuzzy controllers and a PLC. The use of the proposed environment will enable a reduction in time required for testing and adjustments to the controller and evaluated a rapid diagnosis of their efficiency and effectiveness. The control algorithms are implemented in both high-level language, through the controller design software, such as specific language for programming PLCs, Ladder Diagram language.

Sistema de sensoriamento eletromagnético utilizado para detecção da contaminação do óleo isolante do motor no método de elevação artificial do tipo bombeio centrífugo submerso

In the artificial lift method by Electrical Submersible Pump (ESP), the energy is transmitted for the well´s deep through a flat electric handle, where it is converted into mechanical energy through an engine of sub-surface, which is connected to a centrifugal pump. This transmits energy to the fluid under the pressure form, bringing it to the surface In this method the subsurface equipment is basically divided into: pump, seal and motor. The main function of the seal is the protect the motor, avoiding the motor´s oil be contaminated by oil production and the consequent burning of it. Over time, the seal will be wearing and initiates a contamination of motor oil, causing it to lose its insulating characteristics. This work presents a design of a magnetic sensor capable of detecting contamination of insulating oil used in the artificial lift method of oil-type Electrical Submersible Pump (ESP). The objective of this sensor is to generate alarm signal just the moment when the contamination in the isolated oil is present, enabling the implementation of a predictive maintenance. The prototype was designed to work in harsh conditions to reach a depth of 2000m and temperatures up to 150°C. It was used a simulator software to defined the mechanical and electromagnetic variables. Results of field experiments were performed to validate the prototype. The final results performed in an ESP system with a 62HP motor showed a good reliability and fast response of the prototype.

Dose inseminante para fertilização artificial de ovócitos de dourado

Objetivou-se determinar a dose inseminante adequada para uso na fertilização artificial de ovócitos de dourado (Salminus brasiliensis). Os ovócitos foram distribuídos em delineamento inteiramente casualizado, e fertilizados com uma das relações espermatozoides/ovócito 6,0×10³; 6,0×10(4); 6,0×10(5); 6,0×10(6) ou 3,0×10(7), cada uma com quatro repetições. Considerou-se unidade experimental uma incubadora de volume útil de 2,5 L, contendo 2,0 mL de ovócitos não-hidratados. As taxas de fertilização foram mensuradas 8 horas após o início da fertilização. Com intuito de verificar possíveis efeitos da diluição seminal na movimentação dos espermatozoides, realizou-se a mensuração do tempo de duração da motilidade espermática dos espermatozoides de dourado, ativados por meio de diferentes relações de diluição: 6,8×10-5; 6,8×10-4; 6,8×10-3; 6,8×10-2; 3,4×10-1 e 1,0 mL de sêmen por mL de água. O tempo de duração da motilidade foi avaliado em delineamento inteiramente casualizado composto de seis tratamentos e três repetições. As taxas de fertilização apresentaram relação quadrática com o número de espermatozoides por ovócito. As relações de diluição do sêmen tiveram efeito inversamente proporcional sobre a duração da motilidade espermática. A relação que proporcionou melhores taxas de fertilização artificial de ovócitos de dourado (Salminus brasiliensis) foi de 30.722 espermatozoides por ovócio.

Artificial fertilization of oocytes and sperm activation in pacu: effects of the spermatozoa:oocyte ratio, water volume, and in natura semen preservation

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Effects of the spermatozoa: oocyte ratio, water volume and water temperature on artificial fertilization and sperm activation of cascudo-preto

The objective of this study was to evaluate the effects of water volume and water temperature on the sperm motility duration and the number of spermatozoa, and the water volume on the fertilization rates of oocytes of Rhinelepis aspera. Experiments were carried out to evaluate the effect of semen dilutions (1.74×10-5, 1.74×10-4, 1.74×10-3, 1.74×10-2, 1.74×10-1 and 1.00 mL of sperm.mL-1 of water) and water temperature (5, 10, 15, 20, 25, 30, 35, 40, 45, and 50 ºC) on spermatozoa motility duration. In addition, the effects of insemination dose (7×10³, 7×10(4), 7×10(5), 7×10(6) and 7×10(7) spermatozoa.oocyte-1) and water volume (1.0, 30.0, 60.0, 90.0 and 120.0 mL water.2.0 mL-1 oocytes) on the artificial fertilization rates of oocytes were evaluated. The longest sperm motility duration were observed for the semen dilution of 1.74×10-5 mL semen.mL-1 water and in water at 5 ºC. The highest fertilization rates were obtained for insemination doses between 7.00×10³ and 1.23×10(7) spermatozoa. oocyte-1 and water volume of 28.11 mL water.2.0 mL-1 oocytes.

Florescimento e frutificação do maracujazeiro-amarelo submetido à iluminação artificial, irrigação e sombreamento

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