Made available in DSpace on 2014-12-17T14:54:55Z (GMT). No. of bitstreams: 1 MarconiCR_TESE.pdf: 2377871 bytes, checksum: c798a5eab76defef17ac0fe081e2453d (MD5) Previous issue date: 2010-03-16 / Coordena??o de Aperfei?oamento de Pessoal de N?vel Superior / This paper presents a new multi-model technique of dentification in ANFIS for nonlinear systems. In this technique, the structure used is of the fuzzy Takagi-Sugeno of which the consequences are local linear models that represent the system of different points of operation and the precursors are membership functions whose adjustments are realized by the learning phase of the neuro-fuzzy ANFIS technique. The models that represent the system at different points of the operation can be found with linearization techniques like, for example, the Least Squares method that is robust against sounds and of simple application. The fuzzy system is responsible for informing the proportion of each model that should be utilized, using the membership functions. The membership functions can be adjusted by ANFIS with the use of neural network algorithms, like the back propagation error type, in such a way that the models found for each area are correctly interpolated and define an action of each model for possible entries into the system. In multi-models, the definition of action of models is known as metrics and, since this paper is based on ANFIS, it shall be denominated in ANFIS metrics. This way, ANFIS metrics is utilized to interpolate various models, composing a system to be identified. Differing from the traditional ANFIS, the created technique necessarily represents the system in various well defined regions by unaltered models whose pondered activation as per the membership functions. The selection of regions for the application of the Least Squares method is realized manually from the graphic analysis of the system behavior or from the physical characteristics of the plant. This selection serves as a base to initiate the linear model defining technique and generating the initial configuration of the membership functions. The experiments are conducted in a teaching tank, with multiple sections, designed and created to show the characteristics of the technique. The results from this tank illustrate the performance reached by the technique in task of identifying, utilizing configurations of ANFIS, comparing the developed technique with various models of simple metrics and comparing with the NNARX technique, also adapted to identification / Este trabalho apresenta uma nova t?cnica de identifica??o multimodelos baseada em ANFIS para sistemas n?o lineares. Nesta t?cnica, a estrutura utilizada ? do tipo fuzzy Takagi-Sugeno cujos consequentes s?o modelos lineares locais que representam o sistema em diferentes pontos de opera??o e os antecedentes s?o fun??es de pertin?ncia cujos ajustes s?o realizados pela fase de aprendizagem da t?cnica neuro-fuzzy ANFIS. Modelos que representem o sistema em diferentes pontos de opera??o podem ser encontrados com t?cnicas de lineariza??o como, por exemplo, o m?todo dos M?nimos Quadrados que ? robusto a ru?dos e de simples aplica??o. Cabe ? fase de implica??o do sistema fuzzy informar a propor??o de cada modelo que deve ser empregada, utilizando, para isto, as fun??es de pertin?ncia. As fun??es de pertin?ncia podem ser ajustadas pelo ANFIS com o uso de algoritmos de redes neurais, como o de retropropaga??o do erro, de modo que os modelos encontrados para cada regi?o sejam devidamente interpolados e, assim, definam-se a atua??o de cada modelo para as poss?veis entradas do sistema. Em multimodelos a defini??o de atua??o de modelos ? conhecida por m?trica e, como neste trabalho ? realizada pelo ANFIS, ser? denominada de m?trica ANFIS. Desta forma, uma m?trica ANFIS ? utilizada para interpolar v?rios modelos, compondo o sistema a ser identificado. Diferentemente do ANFIS tradicional, a t?cnica desenvolvida necessariamente representa o sistema em v?rias regi?es bem definidas por modelos inalter?veis que, por sua vez, ter?o sua ativa??o ponderada a partir das fun??es de pertin?ncia. A sele??o de regi?es para a aplica??o do m?todo dos M?nimos Quadrados ? realizada manualmente a partir da an?lise gr?fica do comportamento do sistema ou a partir do conhecimento de caracter?sticas f?sicas da planta. Esta sele??o serve como base para iniciar a t?cnica definindo modelos lineares e gerando a configura??o inicial das fun??es de pertin?ncia. Experimentos s?o realizados em um tanque did?tico, com m?ltiplas se??es, projetado e desenvolvido com a finalidade de mostrar caracter?sticas da t?cnica. Os resultados neste tanque ilustram o bom desempenho alcan?ado pela t?cnica na tarefa de identifica??o, utilizando, para isto, v?rias configura??es do ANFIS, comparando a t?cnica desenvolvida com m?ltiplos modelos de m?trica simples e comparando com a t?cnica NNARX, tamb?m adaptada para identifica??o

Electric vehicles have received substantial attention in the past few years since they provide a more sustainable, efficient, and greener transportation alternative in comparison to conventional fossil-fuel powered vehicles. Lithium-Ion batteries represent the most important component in the electric vehicle powertrain and thus require accurate monitoring and control. Many challenges are still facing the mass market production of electric vehicles; these challenges include battery cost, range anxiety, safety, and reliability. These challenges can be significantly mitigated by incorporating an efficient battery management system. The battery management system is responsible for estimating, in real-time, the battery state of charge, state of health, and remaining useful life in addition to communicating with other vehicle components and subsystems. In order for the battery management system to effectively perform these tasks, a high-fidelity battery model along with an accurate, robust estimation strategy must work collaboratively at various power demands, temperatures, and states of life. Lithium ion batteries are considered in this research. For these batteries, electrochemical models represent an attractive approach since they are capable of modeling lithium diffusion processes and track changes in lithium concentrations and potentials inside the electrodes and the electrolyte. Therefore, electrochemical models provide a connection to the physical reactions that occur in the battery thus favoured in state of charge and state of health estimation in comparison to other modeling techniques. The research presented in this thesis focuses on advancing the development and implementation of battery models, state of charge, and state of health estimation strategies. Most electrochemical battery models have been verified using simulation data and have rarely been experimentally applied. This is because most electrochemical battery model parameters are considered proprietary information to their manufacturers. In addition, most battery models have not accounted for battery aging and degradation over the lifetime of the vehicle using real-world driving cycles. Therefore, the first major contribution of this research is the formulation of a new battery state of charge parameterization strategy. Using this strategy, a full-set of parameters for a reduced-order electrochemical model can be estimated using real-world driving cycles while accurately calculating the state of charge. The developed electrochemical model-based state of charge parameterization strategy depends on a number of spherical shells (model states) in conjunction with the final value theorem. The final value theorem is applied in order to calculate the initial values of lithium concentrations at various shells of the electrode. Then, this value is used in setting up constraints for the optimizer in order to achieve accurate state of charge estimation. Developed battery models at various battery states of life can be utilized in a real-time battery management system. Based on the developed models, estimation of the battery critical surface charge using a relatively new estimation strategy known as the Smooth Variable Structure Filter has been effectively applied. The technique has been extended to estimate the state of charge for aged batteries in addition to healthy ones. In addition, the thesis introduces a new battery aging model based on electrochemistry. The model is capable of capturing battery degradation by varying the effective electrode volume, open circuit potential-state of charge relationship, diffusion coefficients, and solid-electrolyte interface resistance. Extensive experiments for a range of aging scenarios have been carried out over a period of 12 months to emulate the entire life of the battery. The applications of the proposed parameterization method combined with experimental aging results significantly improve the reduced-order electrochemical model to adapt to various battery states of life. Furthermore, online and offline battery model parameters identification and state of charge estimation at various states of life has been implemented. A technique for tracking changes in the battery OCV-R-RC model parameters as battery ages in addition to estimation of the battery SOC using the relatively new Smooth Variable Structure Filter is presented. The strategy has been validated at both healthy and aged battery states of life using driving scenarios of an average North-American driver. Furthermore, online estimation of the battery model parameters using square-root recursive least square (SR-RLS) with forgetting factor methodology is conducted. Based on the estimated model parameters, estimation of the battery state of charge using regressed-voltage-based estimation strategy at various states of life is applied. The developed models provide a mechanism for combining the standalone estimation strategy that provide terminal voltage, state of charge, and state of health estimates based on one model to incorporate these different aspects at various battery states of life. Accordingly, a new model-based estimation strategy known as the interacting multiple model (IMM) method has been applied by utilizing multiple models at various states of life. The method is able to improve the state of charge estimation accuracy and stability, when compared with the most commonly used strategy. This research results in a number of novel contributions, and significantly advances the development of robust strategies that can be effectively applied in real-time on-board of a battery management system. / Thesis / Doctor of Philosophy (PhD)

Predicting evaporation is essential for managing water resources in basins. Improvement of the prediction accuracy is essential to identify adequate inputs on evaporation. In this study, artificial neural network (ANN) is coupled with several evolutionary algorithms, i.e., capuchin search algorithm (CSA), firefly algorithm (FFA), sine cosine algorithm (SCA), and genetic algorithm (GA) for robust training to predict daily evaporation of seven synoptic stations with different climates. The inclusive multiple model (IMM) is then used to predict evaporation based on established hybrid ANN models. The adjusting model parameters of the current study is a major challenge. Also, another challenge is the selection of the best inputs to the models. The IMM model had significantly improved the root mean square error (RMSE) and Nash Sutcliffe efficiency (NSE) values of all the proposed models. The results for all stations indicated that the IMM model and ANN-CSA could outperform other models. The RMSE of the IMM was 18, 21, 22, 30, and 43% lower than those of the ANNCSA, ANN-SCA, ANN-FFA, ANN-GA, and ANN models in the Sharekord station. The MAE of the IMM was 0.112 mm/day, while it was 0.189 mm/day, 0.267 mm/day, 0.267 mm/day, 0.389 mm/day, 0.456 mm/day, and 0.512 mm/day for the ANN-CSA, ANN-SCA, and ANN-FFA, ANN-GA, and ANN models, respectively, in the Tehran station. The current study proved that the inclusive multiple models based on improved ANN models considering the fuzzy reasoning had the high ability to predict evaporation.