Accurate and timely diagnosis of faults is essential for the reliability and security of power grid operation and maintenance. The emergence of big data has enabled the incorporation of a vast amount of information in order to create custom fault datasets and improve the diagnostic capabilities of existing frameworks. Intelligent systems have been successful in incorporating big data to improve diagnostic performance using computational intelligence and machine learning based on fault datasets. Among these systems are fuzzy inference systems with the ability to tackle the ambiguities and uncertainties of a variety of input data such as climate data. This makes these systems a good choice for extracting knowledge from energy big data. In this thesis, qualitative climate information is used to construct a fault dataset. A fuzzy inference system is designed whose parameters are optimized using a single layer artificial neural network. This fault diagnosis framework maps the relationship between fault variables in the fault dataset and fault types in real-time to improve the accuracy and cost efficiency of the framework. / Graduate

En el presente artículo se investiga la implementación de las Redes Neuronales Artificiales como un tipo de Inteligencia Artificial con la finalidad de reducir los costos de concreto armado. Por esto, se propuso el uso de este tipo de algoritmo con el objetivo de optimizar las secciones de los muros de corte en edificaciones de 6 pisos sin irregularidades. Se configuraron 10 redes neuronales distintas con el fin de elegir la que se adapte mejor a los datos empleados para el entrenamiento. En cada algoritmo se establecieron como variables de entrada el ancho y largo de la edificación; y la distancia entre luz máxima del eje X e Y. Sin embargo, el número de capas ocultas y el de neuronas en cada una de ellas fue distinto. En la etapa de entrenamiento se emplearon 30 casos con dimensiones optimizadas, con esto se obtuvo que la red neuronal predice la longitud total de la placa y su espesor con un error del 10%. / This article investigates the use of Artificial Neural Networks as a type of Artificial Intelligence in order to reduce the costs of reinforced concrete. For this reason, the use of this type of algorithm was proposed with the objective of optimizing the sections of the shear walls in 6-story buildings without irregularities. Ten different neural networks were configured in order to choose the one that best suits the data used for training. In each algorithm, the width and length of the building; and the distance between maximum span of the X and Y axis were established as input variables. However, the number of hidden layers and the number of neurons in each of them was different. In the training stage, 30 cases with optimized dimensions were used, with this it was obtained that the neuronal network predicts the total length of the shear wall and its thickness with an error of 10%. / Trabajo de investigación

Colony Collapse Disorder (CCD) has been a major threat to bee colonies around the world which affects vital human food crop pollination. The decline in bee population can have tragic consequences, for humans as well as the bees and the ecosystem. Bee health has been a cause of urgent concern for farmers and scientists around the world for at least a decade but a specific cause for the phenomenon has yet to be conclusively identified. This work uses Artificial Intelligence and Computer Vision approaches to develop and analyze techniques to help in continuous monitoring of bee traffic which will further help in monitoring forager traffic. Bee traffic is the number of bees moving in a given area in front of the hive over a given period of time. And, forager traffic is the number of bees entering and/or exiting the hive over a given period of time. Forager traffic is an important variable to monitor food availability, food demand, colony age structure, impact of pesticides, etc. on bee hives. This will lead to improved remote monitoring and general hive status and improved real time detection of the impact of pests, diseases, pesticide exposure and other hive management problems.

Indiana University-Purdue University Indianapolis (IUPUI) / Thermoregulation system in mammal keeps their body temperature in a vital and yet narrow range of temperature by adjusting two main activities, heat generation, and heat loss. Also, these activities get triggered by other causes such as exercise or certain drugs. As a result, thermoregulation system will respond and try to bring back the body temperature to the normal range. Although these responses are very well experimentally explored, they often can be unpredictable and clinically deadly. Therefore, this thesis aims to analytically characterize the neural circuitry components of the system that control the heat generation and heat loss. This modeling approach can help us to analyze the relationship between different components of the thermoregulation system without directly measuring them and explain its complex responses in mathematical form. The first chapter of the thesis is dedicated to introducing a mathematical modeling approach of the circuitry components of the thermoregulation system in response to Methamphetamine which was first published in [1]. Later, in other chapters, we will expand this mathematical framework to study the other components of this system under different conditions such as different circadian phases, various pharmacological interventions, and exercise. This thesis is composed by materials from the following papers. ‎CHAPTER 1 uses the main idea, model, and figures from References [1]. Meanwhile, ‎CHAPTER 2 is based on [2] coauthored with me and is reformatted according to Purdue University Thesis guidelines. Also, ‎CHAPTER 3 interpolates materials from reference [3] coauthored and is reformatted to comply with Purdue University Thesis guidelines. ‎CHAPTER 4 is inserted from the reference [4] and is reformatted according to Purdue University Thesis guidelines. Finally, ‎CHAPTER 5 is based on Reference [5] and is reformatted according to Purdue University Thesis guidelines. Some materials from each of these references have been used in the introduction Chapter.

No description available.

Indiana University-Purdue University Indianapolis (IUPUI) / Design optimization of composite structures is of importance in the automotive, aerospace, and energy industry. The majority of optimization methods applied to laminated composites consider linear or simplified nonlinear models. Also, various techniques lack the ability to consider the composite failure criteria. Using artificial neural networks approximates the objective function to make it possible to use other techniques to solve the optimization problem. The present work describes an optimization process used to find the optimum design to meet crashworthiness requirements which includes minimizing peak crushing force and specific energy absorption for a square tube. The design variables include the number of plies, ply angle and ply thickness of the square tube. To obtain an effective approximation an artificial neural network (ANN) is used. Training data for the artificial neural network is obtained by crash analysis of a square tube for various samples using LS DYNA. The sampling plan is created using Latin Hypercube Sampling. The square tube is considered to be impacted by the rigid wall with fixed velocity and rigid body acceleration, force versus displacement curves are plotted to obtain values for crushing force, deceleration, crush length and specific energy absorbed. The optimized values for the square tube to fulfill the crashworthiness requirements are obtained using an artificial neural network combined with Multi-Objective Genetic Algorithms (MOGA). MOGA finds optimum values in the feasible design space. Optimal solutions obtained are presented by the Pareto frontier curve. The optimization is performed with accuracy considering 5% error.

No description available.

No description available.

No description available.

No description available.