This dissertation introduces advanced artificial intelligence based algorithm for detecting and classifying faults on the power system transmission line. The proposed algorithm is aimed at substituting classical relays susceptible to possible performance deterioration during variable power system operating and fault conditions. The new concept relies on a principle of pattern recognition and detects the existence of the fault, identifies fault type, and estimates the transmission line faulted section. The approach utilizes self-organized, Adaptive Resonance Theory (ART) neural network, combined with fuzzy decision rule for interpretation of neural network outputs. Neural network learns the mapping between inputs and desired outputs through processing a set of example cases. Training of the neural network is based on the combined use of unsupervised and supervised learning methods. During training, a set of input events is transformed into a set of prototypes of typical input events. During application, real events are classified based on the interpretation of their matching to the prototypes through fuzzy decision rule. This study introduces several enhancements to the original version of the ART algorithm: suitable preprocessing of neural network inputs, improvement in the concept of supervised learning, fuzzyfication of neural network outputs, and utilization of on-line learning. A selected model of an actual power network is used to simulate extensive sets of scenarios covering a variety of power system operating conditions as well as fault and disturbance events. Simulation results show improved recognition capabilities compared to a previous version of ART neural network algorithm, Multilayer Perceptron (MLP) neural network algorithm, and impedance based distance relay. Simulation results also show exceptional robustness of the novel ART algorithm for all operating conditions and events studied, as well as superior classification capabilities compared to the other solutions. Consequently, it is demonstrated that the proposed ART solution may be used for accurate, high-speed distinction among faulted and unfaulted events, and estimation of fault type and fault section.

The topic of the work for Master’s degree is: “The formation of fuzzy logic links and structural models”. The purpose of this work is to design a calculator, which would make arithmetic operations with the elements of fuzzy logic. This programme would allow to make such operations with fussy logic elements: addition (+), substraction (–), multiplication (×), division ( : ). Five main parts are presented in the work: analytical one, designed one, the documentation of the consumer, the evaluation of fuzzy logic calculator, the conclusions. In the first part the analysis of fussy arithmetic operation is made, the operations which can be applied in designing are given. In the second part the requirements of the consumer are analyzed and functional requirements are given. The specification of the system is made. The schedule of the project performance is set. The measures of project hazard and prevention are set. The testing, which has been made is described. The plan of system developing is presented. In the third part the documentation of consumer is written. In the fourth part a thorough analysis of calculator working is made, its advantages and disadvantages, fields of application are singled out. The fifth part is the conclusions. Fussy logic makes it possible to achieve much better management characteristics than by traditional methods. One may use the designed calculator by teaching the course of “Calculating methods with indefinite sets” and will help students to master... [to full text]

The eulachon (Thaleichthys pacificus), a small anadromous smelt (Family Osmeridae) found only along the Northwest Pacific Coast, is poorly understood. Many spawning populations have suffered declines but as their historic status is relatively unknown and the fisheries poorly documented, it is difficult to study the contributing factors. This thesis provides a survey of eulachon fisheries throughout its geographical range and three analyses aimed at improving our understanding of past and present fisheries, coast-wide abundance status, and the factors which may be impacting these populations. An in-depth view of the Nuxalk Nation eulachon fishery on the Bella Coola River, Central Coast, BC, is provided. The majority of catches were used for making eulachon grease, a food item produced by First Nations by fermenting, then cooking the fish to release the grease. Catch statistics were kept yearly from 1945-1989 but have since, rarely been recorded. Using traditional and local ecological knowledge, catches were reconstructed based on estimated annual grease production. Run size trends were also created using local Fisheries Officers and Nuxalk interview comments. A fuzzy logic expert system was designed to estimate the relative abundance of fifteen eulachon systems. The expert system uses catch data to determine the exploitation status of a fishery and combines it with other data sources (e.g., CPUE) to estimate an abundance status index. The number of sources depended on the existing data and varied from one to eight. Using designed heuristic rules and by adjusting weighting parameters a final index was produced. Results suggest that there have been recent and extended declines in several eulachon rivers particularly the Klamath, California; Bella Coola, BC; Wannock, BC; and Kitimat, BC. Seven of the fifteen abundance time-series were used to evaluate the potential relationships between the declines and some of the factors that impact eulachon. Results suggest increases in shrimp and hake catches, seal and sea lion abundance, and sea surface temperatures were weakly associated with the declines. But contrary to expectations, adult hake biomass showed a positive association with four eulachon relative abundance time-series, suggesting that common environmental factors influenced both species.

One of the most essential objectives in WSNs is to determine the spatial coordinates of a source or a sensor node having information. In this study, the problem of range measurement-based localization of a signal source or a sensor is revisited. The main challenge of the problem results from the non-convexity associated with range measurements calculated using the distances from the set of nodes with known positions to a xed sen- sor node. Such measurements corresponding to certain distances are non-convex in two and three dimensions. Attempts recently proposed in the literature to eliminate the non- convexity approach the problem as a non-convex geometric minimization problem, using techniques to handle the non-convexity. This study proposes a new fuzzy range-free sensor localization method. The method suggests using some notions of Euclidean geometry to convert the problem into a convex geometric problem. The convex equivalent problem is built using convex fuzzy sets, thus avoiding multiple stable local minima issues, then a gradient based localization algorithm is chosen to solve the problem. Next, the proposed algorithm is simulated considering various scenarios, including the number of available source nodes, fuzzi cation level, and area coverage. The results are compared with an algorithm having similar fuzzy logic settings. Also, the behaviour of both algorithms with noisy measurements are discussed. Finally, future extensions of the algorithm are suggested, along with some guidelines.

Various established and emerging applications of RFID technology have been and are being implemented by companies in different parts of the world. However, RFID technology is susceptible to a variety of security and privacy concerns, as it is prone to attacks such as eavesdropping, denial of service, tag cloning and user tracking. This is mainly because RFID tags, specifically low-cost tags, have low computational capability to support complex cryptographic algorithms. Tag cloning is a key problem to be considered since it leads to severe economic losses. One of the possible approaches to address tag cloning is using an intrusion detection system. Intrusion detection systems in RFID networks, on top of the existing lightweight cryptographic algorithms, provide an additional layer of protection where other security mechanisms may fail. This thesis presents an intrusion detection mechanism that detects anomalies caused by one or more cloned RFID tags in the system. We make use of a Hybrid Fuzzy Genetics-Based Machine Learning algorithm to design an intrusion detection model from RFID system-generated event logs. For the purpose of training and evaluation of our proposed approach, part of the RFID system-generated dataset provided by the University of Tasmania’s School of Computing and Information Systems was used, in addition to simulated datasets. The results of our experiments show that the model can achieve high detection rates and low false positive rates when identifying anomalies caused by one or more cloned tags. In addition, the model yields linguistically interpretable rules that can be used to support decision making during the detection of anomaly caused by the cloned tags.

A fuzzy logic controller (FLC) for the dissolved oxygen (DO) concentration of a wastewater bioreactor is presented. The FLC is developed and tested based on simulations using first order plus dead time models obtained from experiments with an actual wastewater bioreactor. The FLC uses feedback of the error in DO concentration and rate of change of the DO concentration and manipulates the stem position of the flow control valves (FCVs) supplying air to the bioreactor. The proposed FLC is tested for robustness across several process models, two of which include proposed worst-case process conditions. The performance of the proposed hand tuned FLC is compared to that of a similarly tuned proportional-integral-derivative controller. The FLC is implemented as a lookup table for speed and ease of deployment. The disturbances present in the experimental step testing data are characterized and used as the basis for disturbing the control loop during controller performance testing. A low-pass filter is then included to subsequently smooth the feedback signal. The nonlinear relationship between the FCV stem position and output flow is modelled and included in the controller performance testing. A genetic algorithm (GA) is developed that manipulates the membership functions of the FLC to yield an optimal controller for the ensemble of process models. The ability of the GA to converge on an optimal FLC is verified through repeated trials. The performance of the GA optimized FLC is observed under realistic process conditions and is benchmarked against a manually optimized PID controller.

No description available.

No description available.

The Internet has experienced a tremendous growth over the past two decades and with that growth have come severe congestion problems. Research efforts to alleviate the congestion problem can broadly be classified into three groups: Cl) Router based congestion detection; (2) Generation and transmission of congestion notification signal to the traffic sources; (3) End-to-end algorithms which control the flow of traffic between the end hosts. This dissertation has largely addressed the first two groups which are basically router initiated. Router based congestion detection mechanisms, commonly known as Active Queue Management (AQM), can be classified into two groups: conventional mathematical analytical techniques and fuzzy logic based techniques. Research has shown that fuzzy logic techniques are more effective and robust compared to the conventional techniques because they do not rely on the availability of a precise mathematical model of Internet. They use linguistic knowledge and are, therefore, better placed to handle the complexities associated with the non-linearity and dynamics of the Internet. In spite of all these developments, there still exists ample room for improvement because, practically, there has been a slow deployment of AQM mechanisms. In the first part of this dissertation, we study the major AQM schemes in both the conventional and the fuzzy logic domain in order to uncover the problems that have hampered their deployment in practical implementations. Based on the findings from this study, we model the Internet congestion problem as a multi-objective problem. We propose a Fuzzy Logic Congestion Detection (FLCD) which synergistically combines the good characteristics of the fuzzy approaches with those of the conventional approaches. We design the membership functions (MFs) of the FLCD algorithm automatically by using Multi-objective Particle Swarm Optimization (MOPSO), a population based stochastic optimization algorithm. This enables the FLCD algorithm to achieve optimal performance on all the major objectives of Internet congestion control. The FLCD algorithm is compared with the basic Fuzzy Logic AQM and the Random Explicit Marking (REM) algorithms on a best effort network. Simulation results show that the FLCD algorithm provides high link utilization whilst maintaining lower jitter and packet loss. It also exhibits higher fairness and stability compared to its basic variant and REM. We extend this concept to Proportional Differentiated Services network environment where the FLCD algorithm outperforms the traditional Weighted RED algorithm. We also propose self learning and organization structures which enable the FLCD algorithm to achieve a more stable queue, lower packet losses and UDP traffic delay in dynamic traffic environments on both wired and wireless networks. In the second part of this dissertation, we present the congestion notification mechanisms which have been proposed for wired and satellite networks. We propose an FLCD based dual explicit congestion notification algorithm which combines the merits of the Explicit Congestion Notification (ECN) and the Backward Explicit Congestion Notification (BECN) mechanisms. In this proposal, the ECN mechanism is invoked based on the packet marking probability while the BECN mechanism is invoked based on the BECN parameter which helps to ensure that BECN is invoked only when congestion is severe. Motivated by the fact that TCP reacts to tbe congestion notification signal only once during a round trip time (RTT), we propose an RTT based BECN decay function. This reduces the invocation of the BECN mechanism and resultantly the generation of reverse traffic during an RTT. Compared to the traditional explicit notification mechanisms, simulation results show that the new approach exhibits lower packet loss rates and higher queue stability on wired networks. It also exhibits lower packet loss rates, higher good-put and link utilization on satellite networks. We also observe that the BECN decay function reduces reverse traffic significantly on both wired and satellite networks while ensuring that performance remains virtually the same as in the algorithm without BECN traffic reduction. / Thesis (M.Sc.Eng.)-University of KwaZulu-Natal, 2006.

Conventional power system stabilisers (PSS) are designed to eliminate poorly damped, low frequency power oscillations that occur between remote generating pools or power stations, due to different types and settings of the automatic voltage regulators at different power stations. The supplementary control of the PSS is exerted on the power system through a generator's excitation system to which the PSS is attached. In order to design these conventional power system stabilisers , requires accurate system data and an in-depth knowledge of classical control theory. This thesis investigates the use of an intelligent, non-linear PSS that utilises fuzzy logic techniques. Others have proposed the concept of such a PSS, since it does not require accurate system data. This thesis describes the basic aspects of power system stability . Thereafter the methods of modelling synchronous machines in a multi-machine power system are presented. The sample power system being studied and the simulation packages used in the investigations are introduced and the methods involved to design and tune a conventional power system stabiliser using classical control theory and design methods proposed by others, are discussed. The general concept of fuzzy logic is introduced and the application of fuzzy logic techniques to controller design is explained. Using the principles of fuzzy logic controller design, a fuzzy logic power system stabiliser utilising 9 rules is designed and tuned for the multi-machine power system under investigation. The fuzzy logic stabiliser is then applied to a synchronous motor in a pump storage scheme. Previous work has applied fuzzy logic stabilisers only to synchronous generators . To further compare the performance of the 9 rule fuzzy stabiliser, a 49 rule stabiliser developed by other researchers, and adapted to operate on the synchronous motor, is evaluated. Computer simulated results of each of the stabiliser's performances are presented. The results of the 9 rule fuzzy stabiliser are compared with the performance of a conventional linear stabiliser as well as with a 49 rule fuzzy stabiliser. The robustness properties of the fuzzy stabilisers are evaluated. The results further prove that with proper membership function selection, a simple fuzzy stabiliser that demands very little computational overheads can be achieved to provide adequate system damping. / Thesis (M.Sc. Eng.)-University of Natal, Durban, 2003.