Modern power systems operate much closer to their stability limits than before. With the introduction of highly sensitive industrial and residential loads, the loss of system stability becomes increasingly costly. Reinforcing the power grid by installing additional transmission lines, creating more complicated meshed networks and increasing the voltage level are among the effective, yet expensive solutions. An alternative approach is to improve the performance of the existing power system components by incorporating more intelligent control techniques. This can be achieved in two ways: introducing intelligent local controllers for the existing components in the power network in order to employ their utmost capabilities, and implementing global intelligent schemes for optimizing the performance of multiple local controllers based on an objective function associated with the overall performance of the power system. Both these aspects are investigated in this thesis. In the first section, artificial neural networks are adopted for designing an optimal nonlinear controller for a static compensator (STATCOM) connected to a multimachine power system. The neurocontroller implementation is based on the adaptive critic designs (ACD) technique and provides an optimal control policy over the infinite horizon time of the problem. The ACD based neurocontroller outperforms a conventional controller both in terms of improving the power system dynamic stability and reducing the control effort required. The second section investigates the further improvement of the power system behavior by introducing an ACD based neurocontroller for hierarchical control of a multimachine power system. The proposed wide area controller improves the power system dynamic stability by generating optimal control signals as auxiliary reference signals for the synchronous generators automatic voltage regulators and the STATCOM line voltage controller. This multilevel hierarchical control scheme forces the different controllers throughout the power system to optimally respond to any fault or disturbance by reducing a predefined cost function associated with the power system performance.

Recently there has been a tremendous growth of research emphasizing control of unmanned aerial vehicles (UAVs) either in isolation or in teams. As a matter of fact, UAVs increasingly find their way to applications, especially in military and law enforcement (e.g., reconnaissance, remote delivery of urgent equipment/material, resource assessment, environmental monitoring, battlefield monitoring, ordnance delivery, etc.). This trend will continue in the future, as UAVs are poised to replace the human-in-the-loop during dangerous missions. Civilian applications of UAVs are also envisioned such as crop dusting, geological surveying, search and rescue operations, etc. In this thesis we propose a new online multiresolution path planning algorithm for a small UAV with limited on-board computational resources. The proposed approach assumes that the UAV has detailed information of the environment and the obstacles only in its vicinity. Information about far-away obstacles is also available, albeit less accurately. The proposed algorithm uses the fast lifting wavelet transform (FLWT) to get a multiresolution cell decomposition of the environment, whose dimension is commensurate to the on-board computational resources. A topological graph representation of the multiresolution cell decomposition is constructed efficiently, directly from the approximation and detail wavelet coefficients. Dynamic path planning is sequentially executed for an optimal path using the A* algorithm over the resulting graph. The proposed path planning algorithm is implemented on-line on a small autopilot. Comparisons with the standard D*-lite algorithm are also presented. We also investigate the problem of generating a smooth, planar reference path from a discrete optimal path. Upon the optimal path being represented as a sequence of cells in square geometry, we derive a smooth B-spline path that is constrained inside a channel that is induced by the geometry of the cells. To this end, a constrained optimization problem is formulated by setting up geometric linear constraints as well as boundary conditions. Subsequently, we construct B-spline path templates by solving a set of distinct optimization problems. For an application to the UAV motion planning, the path templates are incorporated to replace parts of the entire path by the smooth B-spline paths. Each path segment is stitched together while preserving continuity to obtain a final smooth reference path to be used for path following control. The path following control for a small fixed-wing UAV to track the prescribed smooth reference path is also addressed. Assuming the UAV is equipped with an autopilot for low level control, we adopt a kinematic error model with respect to the moving Serret-Frenet frame attached to a path for tracking controller design. A kinematic path following control law that commands heading rate is presented. Backstepping is applied to derive the roll angle command by taking into account the approximate closed-loop roll dynamics. A parameter adaptation technique is employed to account for the inaccurate time constant of the closed-loop roll dynamics during actual implementation. Finally, we implement the proposed hierarchical path control of a small UAV on the actual hardware platform, which is based on an 1/5 scale R/C model airframe (Decathlon) and the autopilot hardware and software. Based on the hardware-in-the-loop (HIL) simulation environment, the proposed hierarchical path control algorithm has been validated through the on-line, real-time implementation on a small micro-controller. By a seamless integration of the control algorithms for path planning, path smoothing, and path following, it has been demonstrated that the UAV equipped with a small autopilot having limited computational resources manages to accomplish the path control objective to reach the goal while avoiding obstacles with minimal human intervention.

Implementing self-management for enterprise systems is difficult. First, the scale and complexity of such systems makes it hard to understand and interpret system behavior or worse, the root causes of certain behaviors. Second, it is not clear how the goals specified at a system-level translate to component-level actions that drive the system. Third, the dynamic environments in which such systems operate requires self-management techniques that not only adapt the system but also adapt their own decision making processes. Finally, to build a self-management solution that is acceptable to administrators, it should have the properties of tractability and trust, which allow an administrator to both understand and fine-tune self-management actions. This dissertation work introduces, implements, and evaluates iManage, a novel system state-space based framework for enabling self-management of enterprise-scale systems. The system state-space, in iManage, is defined to be a collection of monitored system parameters and metrics (termed system variables). In addition, from amongst the system variables, it identifies the variables of interest, which determine the operational status of a system, and the controllable variables, which are the ones that can be deterministically modified to affect the operational status of a system. Using this formal representation, we have developed and integrated into iManage techniques that establish a probabilistic model relating the variables of interest and the controllable variables under the prevailing operational conditions. Such models are then used by iManage to determine corrective actions in case of SLA violations and/or to determine per-component ranges for controllable variables, which if independently adhered to by each component, lead to SLA compliance. To address the issue of scale in determining system models, iManage makes use of a novel state-space partitioning scheme that partitions the state-space into smaller sub-spaces thereby allowing us to more precisely model the critical system aspects. Our chosen modeling techniques are such that the generated models can be easily understood and modified by the administrator. Furthermore, iManage associates each proposed self-management action with a confidence-attribute that determines whether the action in question merits autonomic enforcement or not.

[Truncated abstract] This thesis analyses the problem of Intelligent Control for large industrial plants and suggests a hierarchical, distributed, object-oriented architecture for Intelligent Control. The architecture is called MLIAC (Multi Level Intelligent Adaptive Control) Architecture. The MLIAC architecture is inspired by biological control systems (which are flexible, and are capable of adapting to unstructured environments with ease) and the success of the distributed architecture SCADA (Supervisory Control and Data Acquisition) Systems. The MLIAC Architecture structures the decision and control mechanism for the real-time properties namely safety, liveliness, and timeliness . . . In addition, three case studies have been reported. The case studies cover the control of a Flexible Manufacturing System and the Mine Products Quality Control. The results show that MLIAC Knowledge Representation model meets the requirements of the Roth-Hayes benchmark regarding Knowledge Representation. The decisions taken are logically tractable. The software architecture is effective and easily implemented. The actual performance has been found to depend upon a number of factors discussed in this thesis. For the specification and design of Potline MLIAC software, a CASE package ("Software Through Pictures") has been used. The Potline MLIAC software has been developed using C⁄C++, SQL, 4 GL and RDBMS based on a Client-Server model. For computer simulation the Potline MLIAC software has been integrated with the MATLAB⁄SIMULINK package.

Thesis (M.Sc. [i.e. M.C.M.S.])--University of Waikato, 2006. / Includes bibliographical references (p. 167-173) Also available via the World Wide Web.

Thesis (MEng)--Stellenbosch University, 2014. / ENGLISH ABSTRACT: Machine learning techniques have been around for a few decades now and are being established as a pre-dominant feature in most control applications. Elevators create a unique control application where traffic flow is controlled and directed according to certain control philosophies. Machine learning techniques can be implemented to predict and control every possible traffic flow scenario and deliver the best possible solution. Various techniques will be implemented in the elevator application in an attempt to establish a degree of artificial intelligence in the decision making process and to be able to have increased interaction with the passengers at all times. The primary objective for this thesis is to investigate the potential of machine learning solutions and the relevancy of such technologies in elevator control applications. The aim is to establish how the research field of machine learning, specifically neural network science, can be successfully utilised with the goal of creating an artificial intelligent (AI) controller. The AI controller is to adapt to its existing state and change its control parameters as required without the intervention of the user. The secondary objective for this thesis is to develop an elevator model that represents every aspect of the real-world application. The purpose of the model is to improve the accuracy of existing theoretical and simulated models, by modulating previously unknown and complex variables and constraints. The aim is to create a complete and fully functional testing platform for developing new elevator control philosophies and testing new elevator control mechanisms. To achieve these objectives, the main focus is directed to how waiting time, probability theory and power consumption predictions can be optimally utilised by means of machine learning solutions. The theoretical background is provided for these concepts and how each subject can potentially influence the decision making process. The reason why this approach has been difficult to implement in the past, is possibly mainly due to the lack of adequate representation for these concepts in an online environment without the continuous feedback from an Expert System. As a result of this thesis, the respective online models for each of these concepts were successfully developed in order to deal with the identified shortcomings. The developed online models for projected waiting times, probability networks and power consumption feedback were then combined to form a new Intelligent Elevator Controller (IEC) structure as opposed to the Expert System approach, mostly used in present computer based elevator controllers. / AFRIKAANSE OPSOMMING: Masjienleertegnieke bestaan al vir 'n paar dekades en is 'n oorwegende kenmerk in hedendaagse beheertoestelle. Hysbakke skep 'n unieke beheertoepassing, waar verkeersvloei beheer en gerig kan word volgens sekere beheer loso e. Masjienleertegnieke kan geïmplementeer word om elke moontlike verkeersvloei situasie te voorspel en te beheer en die beste moontlike oplossing te lewer. Verskeie tegnieke sal in die tesis ondersoek word in 'n poging om 'n mate van kunsmatige intelligensie in die besluitneming proses te skep asook verhoogte interaksie met die passasiers te alle tye. Die prim^ere doel van hierdie tesis is om die potensiaal van 'n masjienleer oplossing en die toepaslikheid van dit in hysbakbeheertoepassings te ondersoek. Die doel is om vas te stel hoe die navorsing in die veld van die masjienleer, spesi ek in neurale netwerk wetenskappe, suksesvol aangewend kan word met die doel om 'n kunsmatige intelligente beheerder te skep. Die kunsmatige intelligente beheerder moet kan aanpas by sy onmidelike omgewing en sy beheer parameters moet kan verander soos nodig sonder die ingryping van die gebruiker. Die sekond^ere doelwit vir hierdie tesis is om 'n hysbakmodel, wat elke aspek van die werklike w^ereld verteenwoordig, te ontwikkel. Die doel van die model is om die akkuraatheid van die bestaande teoretiese en gesimuleerde modelle te verbeter deur voorheen onbekende en komplekse veranderlikes en beperkings in ag te neem. Die doel is om 'n funksionele toetsplatform te skep vir die ontwikkeling van nuwe hysbakbeheer loso e en vir die toets van nuwe hysbakbeheermeganismes. Om hierdie doelwitte te bereik, is die hoo okus gerig om wagtyd, waarskynlikheidsteorie en kragverbruik voorspellings optimaal te gebruik deur middel van die masjienleer oplossings. Die teoretiese agtergrond is voorsien vir hierdie konsepte en hoe elke konsep potensieel die besluitneming kan beïnvloed. Die rede waarom hierdie benadering moeilik was om te implementeer tot hede, is moontlik te wyte aan die gebrek aan voldoende verteenwoordiging vir hierdie konsepte in 'n aanlynomgewing sonder die voortdurende terugvoer van 'n Deskundige Stelsel. As gevolg van hierdie tesis word die onderskeie aanlynmodelle vir elk van hierdie konsepte suksesvol ontwikkel om die geïdenti seerde tekortkominge te oorkom. Die ontwikkelde aanlynmodelle vir geprojekteerde wagtye, waarskynlikheidsnetwerke en kragverbruik terugvoer is dan gekombineer om 'n nuwe intelligente hysbakbeheerder struktuur te skep, in teenstelling met die Deskundige Stelsel benadering in die huidige rekenaar gebaseerde hysbakbeheerders.

Conselho Nacional do Desenvolvimento Científico e Tecnológico (CNPq) / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) / Fundação Araucária de Apoio ao Desenvolvimento Científico e Tecnológico do Paraná / Nos dias atuais, um enfoque considerável tem sido dado por pesquisas científicas aos acionamentos de motores elétricos, em destaque aos motores de indução trifásicos com rotor gaiola de esquilo, por serem comumente empregados em aplicações do dia-a-dia, principalmente em ambientes industriais, devido às suas inúmeras e bem conhecidas vantagens. Dentre algumas estratégias existentes para o acionamento destes motores, encontra-se o Controle Direto de Torque, um acionamento vetorial que proporciona um bom desempenho para aplicações de médias e baixas potências. Uma topologia dessa estratégia que envolve a utilização de um algoritmo de Modulação por Vetores Espaciais, denominada de DTC-SVM, tem sido amplamente considerada devido às suas vantagens frente à estrutura convencional. Contudo, em seu algoritmo existem malhas de controle de torque, fluxo e velocidade, que adotam geralmente controladores Proporcional-Integral. Neste trabalho, um estimador de fluxo baseado em modelo de tensão e corrente é considerado, no qual sua estrutura também contém um controlador Proporcional- Integral. Diante desse cenário, este trabalho visa contribuir com o aspecto de sintonia destes controladores, empregando metaheurísticas de otimização para efetuar o ajuste otimizado dos ganhos. Três algoritmos metaheurísticos são considerados: a Otimização por Colônia de Formigas, o Evolução Diferencial e a Otimização por Enxame de Partículas. Basicamente, intervalos de busca para as variáveis envolvidas, ou seja, os ganhos dos controladores, assim como uma função objetivo, que relacione os principais aspectos desejados de melhoria do sistema, devem ser definidos para o processo de otimização, o qual é realizado via simulação computacional. Visando avaliar a eficiência da metodologia proposta, neste trabalho são feitas algumas análises do sistema de acionamento DTC-SVM operando com as sintonias otimizadas e também com uma sintonia inicial, obtida com base em ajustes empíricos. Tais análises são feitas tanto em um ambiente de simulações computacionais, utilizando o software MATLAB/Simulink, quanto em um ambiente experimental, considerando um protótipo desenvolvido, no qual o sistema opera com reversão de velocidade, assim como com distúrbios de carga. Os resultados evidenciam desempenhos eficientes do acionamento operando com as sintonias otimizadas, principalmente durante os regimes transitórios e em operações de baixas velocidades. / Nowadays, a considerable focus has been given by scientific research to the electric motors drive, particularly to the three-phase induction motors with squirrel cage rotor, being commonly used in day-to-day applications, especially in industrial environments, due to its numerous and well known advantages. Among some strategies surveyed for driving these motors, there is the Direct Torque Control, a vector drive which provides good performance for medium and low power applications. A topology of this strategy involving the use of a Space Vector Modulation algorithm, called DTC-SVM, has been considered due to its advantages in comparison to conventional structure. However, in their algorithm there are torque, flux and speed control loops which generally consider Proportional-Integral controllers. In this work, a stator linkage flux estimator based on model of voltage and current is considered, in which its structure also contains a Proportional-Integral controller. Given this scenario, this work aims to contribute with the tuning aspect of these controllers, employing optimization metaheuristics aiming an optimized adjustment of the gains. Three metaheuristic algorithms are considered: Ant Colony Optimization, Differential Evolution and Particle Swarm Optimization. Basically, search ranges to the variables involved, ie. Proportional-Integral controller gains, as well as an objective function, which lists the main desired aspects of improving the system, must be set to the optimization process, which is performed by the computational simulation. Aiming to evaluate the effectiveness of this proposed methodology, in this work were made some analysis at the DTC-SVM drive system operating with the optimized tunings and a initial tuning, obtained by empiric adjusts. Such analysis were carried out either in a computer simulation environment, using MATLAB/Simulink software, as in a laboratory environment, considering a prototype developed, in which the system operates with speed reversal, as well as load disturbances. The results show efficient performances of the drive operating with the optimized tunings, especially during the transient periods and low speed operations.

Made available in DSpace on 2014-06-11T19:28:21Z (GMT). No. of bitstreams: 0 Previous issue date: 2011-12-20Bitstream added on 2014-06-13T19:16:08Z : No. of bitstreams: 1 euzebio_csg_me_bauru.pdf: 3031848 bytes, checksum: 6b7741a092864eabaa133ffdbcd4eed8 (MD5) / A necessidade de reduções de custos aliada ao aumento de qualidade das peças produzidas requer a implementação de sistemas inteligentes em ambientes industriais. O controle dos danos causados no processo de retificação é de interesse direto da indústria dependente desse processo. O objetivo deste trabalho é a proposição de modelos fuzzy empregados na detecção da queima de peças de aço SAE 1020 no processo de retificação plana. Foram realizados doze testes para diferentes condições de usinagem. Para cada teste foram coletados dados referentes a potência elétrica e emissão acústica (sinal puro). Os níveis de queima das peças foram analisados visualmente e com o auxílio computacional. A partir dos sinais de emissão acústica, potência de corte e parâmetros utilizando esses dois sinais, regras linguísticas foram estabelecidas para as diversas situações de queima (leve, média, severa) com a aplicação da lógica nebulosa utilizando-se o Toolbox do MATLAB. Quatro modelos práticos de sistema fuzzy foram desenvolvidos. O primeiro modelo com duas entradas apenas resultam num processo de simples análise. O segundo modelo possui a entrada adicional da estatística do desvio do valor médio (MVD), associando uma nova informação e precisão. Esse modelo é baseado em um sistema de inferência de três entradas, combinados dois a dois. O terceiro modelo, com 64 regras, baseia-se nas mesmas três entradas utilizadas no segundo modelo, combinadas três a três. Esses dois modelos diferem entre si pela base de regras desenvolvidas. O quarto modelo difere do terceiro devido ao número de regras e a entrada adicional baseada na potência de corte, do desvio padrão da mesma e do sinal RMS de emissão acústica. Apresentando respostas válidas, os quatro modelos desenvolvidos mostraram eficiência, precisão, confiabilidade e... / The need of costs reduction and quality increase of the produced pieces requires the implementation of intelligent systems in industrial environments. The control of damages caused during the grinding process is interesting to the industry that depends on such process. This work uses fuzzy logic as tool to classify and estimate burn levels in the grinding process in order to help controlling such process. Twelve tests were performed for different grinding conditions. For each test, data were concerning electrical power and acoustic emission (raw signal). The levels of burning parts were analyzed visually and with computer assistance. Based on acoustic emission signals, cutting power, and statistics using these two signals, liguistic rules were established for the various burn situations (slight, intermediate, sever) by applying fuzzy logic using the MATLAB toolbox. Four practical fuzzy system models were developed. This first model with two inputs resulted only in a simple analysis process. The second model has an additional MVD statistic input, associating information and precision. This model is base d on an inference system of three inputs, combined two by two. The third model with 64 rules is based on the same three inputs used in the second model, differ by the rule base developed. The forth model is different from the third one due to the number of rules, the additional input based on the cutting power, the standard deviation and the acoustic emission RMS signal. The four developed models presented valid responses, proving effective, accurate, reliable and easy to use for the determination of ground workpiece burn. In this analysis... (Complete abstract click electronic access below)

Thesis (MTech (Faculty of Engineering))--Cape Peninsula University of Technology, 2009.Included bibliographical references (p. 98-99).

Thesis (MTech (Information Technology))--Cape Peninsula University of Technology, 2005. / This thesis explores the design and implementation of an intelligent semantic machine control system with specific reference to human-machine interface design. The term "intelligent" refers to machines that can execute some level of decision taking in context. The term "semantic" refers to a structured language that allows user and machine to communicate. This study will explore all the key concepts about an intelligent semantic machine control system with human-machine interface. The key concepts to be investigated will include Artificial Intelligence, Intelligent Control, Semantics, Intelligent Machine Architecture, Human-Machine Interaction, Information systems and Graphical User Interface. The primary purpose of this study is to develop a methodology for designing a machine control system and its related human-machine interface.