Multiclassificador inteligente de falhas no domínio do tempo em motores de indução trifásicos alimentados por inversores de frequência

Os motores de indução desempenham um importante papel na indústria, fato este que destaca a importância do correto diagnóstico e classificação de falhas ainda em fase inicial de sua evolução, possibilitando aumento na produtividade e, principalmente, eliminando graves danos aos processos e às máquinas. Assim, a proposta desta tese consiste em apresentar um multiclassificador inteligente para o diagnóstico de motor sem defeitos, falhas de curto-circuito nos enrolamentos do estator, falhas de rotor e falhas de rolamentos em motores de indução trifásicos acionados por diferentes modelos de inversores de frequência por meio da análise das amplitudes dos sinais de corrente de estator no domínio do tempo. Para avaliar a precisão de classificação frente aos diversos níveis de severidade das falhas, foram comparados os desempenhos de quatro técnicas distintas de aprendizado de máquina; a saber: (i) Rede Fuzzy Artmap, (ii) Rede Perceptron Multicamadas, (iii) Máquina de Vetores de Suporte e (iv) k-Vizinhos-Próximos. Resultados experimentais obtidos a partir de 13.574 ensaios experimentais são apresentados para validar o estudo considerando uma ampla faixa de frequências de operação, bem como regimes de conjugado de carga em 5 motores diferentes.

Desenvolvimento de um método para diagnose de falhas na operação de navios transportadores de gás natural liquefeito através de redes bayesianas.

O Gás Natural Liquefeito (GNL) tem, aos poucos, se tornado uma importante opção para a diversificação da matriz energética brasileira. Os navios metaneiros são os responsáveis pelo transporte do GNL desde as plantas de liquefação até as de regaseificação. Dada a importância, bem como a periculosidade, das operações de transporte e de carga e descarga de navios metaneiros, torna-se necessário não só um bom plano de manutenção como também um sistema de detecção de falhas que podem ocorrer durante estes processos. Este trabalho apresenta um método de diagnose de falhas para a operação de carga e descarga de navios transportadores de GNL através da utilização de Redes Bayesianas em conjunto com técnicas de análise de confiabilidade, como a Análise de Modos e Efeitos de Falhas (FMEA) e a Análise de Árvores de Falhas (FTA). O método proposto indica, através da leitura de sensores presentes no sistema de carga e descarga, quais os componentes que mais provavelmente estão em falha. O método fornece uma abordagem bem estruturada para a construção das Redes Bayesianas utilizadas na diagnose de falhas do sistema.

Mitigação de falhas críticas em sistemas produtivos.

O cenário competitivo e globalizado em que as empresas estão inseridas, sobretudo a partir do século XXI, associados a ciclos de vida cada vez menores dos produtos, rigorosos requisitos de qualidade, além de políticas de preservação do meio ambiente, com redução de consumo energético e de recursos hídricos, somadas às exigências legais de melhores condições de trabalho, resultaram em uma quebra de paradigma nos processos produtivos até então concebidos. Como solução a este novo cenário produtivo pode-se citar o extenso uso da automação industrial, fato que resultou em sistemas cada vez mais complexos, tanto do ponto de vista estrutural, em função do elevado número de componentes, quanto da complexidade dos sistemas de controle. A previsibilidade de todos os estados possíveis do sistema torna-se praticamente impossível. Dentre os estados possíveis pode-se citar os estados de falha que, dependendo da severidade do efeito associado à sua ocorrência, podem resultar em sérios danos para o homem, o meio ambiente e às próprias instalações, caso não sejam corretamente diagnosticados e tratados. Fatos recentes de catástrofes relacionadas à sistemas produtivos revelam a necessidade de se implementar medidas para prevenir e para mitigar os efeitos da ocorrência de falhas, com o objetivo de se evitar a ocorrência de catástrofes. De acordo com especialistas, os Sistemas Instrumentados de Segurança SIS, referenciados em normas como a IEC 61508 e IEC 61511, são uma solução para este tipo de problema. Trabalhos publicados tratam de métodos para a implementação de camadas SIS de prevenção, porém com escassez de trabalhos para camadas SIS de mitigação. Em função do desconhecimento da dinâmica do sistema em estado de falha, técnicas tradicionais de modelagem tornam-se inviáveis. Neste caso, o uso de inteligência artificial, como por exemplo a lógica fuzzy, pode se tornar uma solução para o desenvolvimento do algoritmo de controle, associadas a ferramentas de edição, modelagem e geração dos códigos de controle. A proposta deste trabalho é apresentar uma sistemática para a implementação de um sistema de controle para a mitigação de falhas críticas em sistemas produtivos, com referência às normas IEC 61508/61511, com ação antecipativa à ocorrência de catástrofes.

Método híbrido para detecção e diagnóstico de falhas baseado em resíduos

The detection and diagnosis of faults, ie., find out how , where and why failures occur is an important area of study since man came to be replaced by machines. However, no technique studied to date can solve definitively the problem. Differences in dynamic systems, whether linear, nonlinear, variant or invariant in time, with physical or analytical redundancy, hamper research in order to obtain a unique solution . In this paper, a technique for fault detection and diagnosis (FDD) will be presented in dynamic systems using state observers in conjunction with other tools in order to create a hybrid FDD. A modified state observer is used to create a residue that allows also the detection and diagnosis of faults. A bank of faults signatures will be created using statistical tools and finally an approach using mean squared error ( MSE ) will assist in the study of the behavior of fault diagnosis even in the presence of noise . This methodology is then applied to an educational plant with coupled tanks and other with industrial instrumentation to validate the system.

Mecanismo de tolerância a falhas através de escalonamento para uma arquitetura reconfigurável de grão grosso

The continuous evolution of integrated circuit technology has allowed integrating thousands of transistors on a single chip. This is due to the miniaturization process, which reduces the diameter of wires and transistors. One drawback of this process is that the circuit becomes more fragile and susceptible to break, making the circuit more susceptible to permanent faults during the manufacturing process as well as during their lifetime. Coarse Grained Reconfigurable Architectures (CGRAs) have been used as an alternative to traditional architectures in an attempt to tolerate such faults due to its intrinsic hardware redundancy and high performance. This work proposes a fault tolerance mechanism in a CGRA in order to increase the architecture fault tolerance even considering a high fault rate. The proposed mechanism was added to the scheduler, which is the mechanism responsible for mapping instructions onto the architecture. The instruction mapping occurs at runtime, translating binary code without the need for recompilation. Furthermore, to allow faster implementation, instruction mapping is performed using a greedy module scheduling algorithm, which consists of a software pipeline technique for loop acceleration. The results show that, even with the proposed mechanism, the time for mapping instructions is still in order of microseconds. This result allows that instruction mapping process remains at runtime. In addition, a study was also carried out mapping scheduler rate. The results demonstrate that even at fault rates over 50% in functional units and interconnection components, the scheduler was able to map instructions onto the architecture in most of the tested applications.

Influência da estratigrafia mecânica no desenvolvimento de falhas distensionais em bacias do tipo Rifte: contribuição da modelagem física

In the last decades, analogue modelling has been used in geology to improve the knowledge of how geological structures are nucleated, how they grow and what are the main important points in such processes. The use of this tool in the oil industry, to help seismic interpretations and mainly to search for structural traps contributed to disseminate the use of this tool in the literature. Nowadays, physical modelling has a large field of applications, since landslide to granite emplacement along shear zones. In this work, we deal with physical modelling to study the influence of mechanical stratifications in the nucleation and development of faults and fractures in a context of orthogonal and conjugated oblique basins. To simulate a mechanical stratigraphy we used different materials, with distinct physical proprieties, such as gypsum powder, glass beads, dry clay and quartz sand. Some experiments were run along with a PIV (Particle Image Velocimetry), an instrument that shows the movement of the particles to each deformation moment. Two series of experiments were studied: i) Series MO: We tested the development of normal faults in a context of an orthogonal (to the extension direction) basin. Experiments were run taking into account the change of materials and strata thickness. Some experiments were done with sintectonic sedimentation. We registered differences in the nucleation and growth of faults in layers with different rheological behavior. The gypsum powder layer behaves in a more competent mode, which generates a great number of high angle fractures. These fractures evolve to faults that exhibit a higher dip than when they cross less competent layers, like the one of quartz sand. This competent layer exhibits faulted blocks arranged in a typical domino-style. Cataclastic breccias developed along the faults affecting the competent layers and showed different evolutional history, depending on the deforming stratigraphic sequence; ii) Series MOS2: Normal faults were analyzed in conjugated sub-basins (oblique to the extension direction) developed in a sequence with and without rheological contrast. In experiments with rheological contrast, two important grabens developed along the faulted margins differing from the subbasins with mechanical stratigraphy. Both experiments developed oblique fault systems and, in the area of sub-basins intersection, faults traces became very curved.

FTE-LEACH: um protocolo energeticamente eficiente e tolerante a falhas aplicado às redes industriais de sensores sem fio

A Wireless Sensor Network (WSN) consists of distributed devices in an area in order to monitor physical variables such as temperature, pressure, vibration, motion and environmental conditions in places where wired networks would be difficult or impractical to implement, for example, industrial applications of difficult access, monitoring and control of oil wells on-shore or off-shore, monitoring of large areas of agricultural and animal farming, among others. To be viable, a WSN should have important requirements such as low cost, low latency, and especially low power consumption. However, to ensure these requirements, these networks suffer from limited resources, and eventually being used in hostile environments, leading to high failure rates, such as segmented routing, mes sage loss, reducing efficiency, and compromising the entire network, inclusive. This work aims to present the FTE-LEACH, a fault tolerant and energy efficient routing protocol that maintains efficiency in communication and dissemination of data.This protocol was developed based on the IEEE 802.15.4 standard and suitable for industrial networks with limited energy resources

Evolução dos sistemas de falhas de borda do Rifte Potiguar com base em curvas de crescimento de falhas

The discussion about rift evolution in the Brazilian Equatorial margin during the South America-Africa breakup in the Jurassic/Cretaceous has been focused in many researches. But rift evolution based on development and growth of faults has not been well explored. In this sense, we investigated the Cretaceous Potiguar Basin in the Equatorial margin of Brazil to understand the geometry of major faults and the influence of crustal heterogeneity and preexisting structural fabric in the evolution of the basin internal architecture. Previous studies pointed out that the rift is an asymmetrical half-graben elongated along the NE-SW direction. We used 2D seismic, well logs and 3D gravity modeling to analyze four major border fault segments and determine their maximum displacement (Dmax) and length (L) ratio in the Potiguar Rift. We constrained the 3D gravity modeling with well data and the interpretation of seismic sections. The difference of the fault displacement measured in the gravity model is in the order of 10% compared to seismic and well data. The fault-growth curves allowed us to divide the faulted rift border into four main fault segments, which provide roughly similar Dmax/L ratios. Fault-growth curves suggest that a regional uniform tectonic mechanism influenced growth of the rift fault segments. The variation of the displacements along the fault segments indicates that the fault segments were formed independently during rift initiation and were linked by hard and soft linkages. The latter formed relay ramps. In the interconnection zones the Dmax/L ratios are highest due to interference of fault segment motions. We divided the evolution of the Potiguar Rift into five stages based on these ratios and correlated them with the major tectonic stages of the breakup between South America and Africa in Early Cretaceous.

Evolução dos sistemas de falhas de borda do Rifte Potiguar com base em curvas de crescimento de falhas

The discussion about rift evolution in the Brazilian Equatorial margin during the South America-Africa breakup in the Jurassic/Cretaceous has been focused in many researches. But rift evolution based on development and growth of faults has not been well explored. In this sense, we investigated the Cretaceous Potiguar Basin in the Equatorial margin of Brazil to understand the geometry of major faults and the influence of crustal heterogeneity and preexisting structural fabric in the evolution of the basin internal architecture. Previous studies pointed out that the rift is an asymmetrical half-graben elongated along the NE-SW direction. We used 2D seismic, well logs and 3D gravity modeling to analyze four major border fault segments and determine their maximum displacement (Dmax) and length (L) ratio in the Potiguar Rift. We constrained the 3D gravity modeling with well data and the interpretation of seismic sections. The difference of the fault displacement measured in the gravity model is in the order of 10% compared to seismic and well data. The fault-growth curves allowed us to divide the faulted rift border into four main fault segments, which provide roughly similar Dmax/L ratios. Fault-growth curves suggest that a regional uniform tectonic mechanism influenced growth of the rift fault segments. The variation of the displacements along the fault segments indicates that the fault segments were formed independently during rift initiation and were linked by hard and soft linkages. The latter formed relay ramps. In the interconnection zones the Dmax/L ratios are highest due to interference of fault segment motions. We divided the evolution of the Potiguar Rift into five stages based on these ratios and correlated them with the major tectonic stages of the breakup between South America and Africa in Early Cretaceous.

Análise de falhas em rolamentos por análise de vibração aplicado a aerogeradores

With the heavy use of bearings in various segments of the industry, there are a large number of necessary interruptions in industrial processes to perform maintenance on these devices, with the case study wind turbines. The growth of the wind energy sector, encouraged to conduct research that helps to solve this problem. To contribute to predictive maintenance has been carried out a signal analysis using techniques which allow detection and location of the problem in order to prevent accidents caused and losses due to unexpected equipment failures, whereas low system rotation complicates the detection of the failure. To work around this problem, there was the indication of standard signals for defects in the bearings, making diagnosis of possible failures. With this diagnosis can be performed predictive maintenance, identifying the failure of the system that were tested, such as the introduction of grains of sand in the bearing, wear on the outer race of the bearing and bearing rust. By processing signals it is possible to construct graphs developing a mapping of defects by different peaks in the frequency band.