For the operation of refuse incineration plant, the major difficulties with trash are the unstable nature and the uncertainty. The complexity of trash ingredient causes the traditional control method fail to obtain a stable combustion condition and steam flow rate. It is necessary to seek a new control method to adapt to the volatile combustion features of refuse incinerator. Based on correlation literature research [2], the fuzzy control theory is proposed to provide a good combustion condition to stabilize the steam flow rate for the combustion control of refuse furnace, and effectively reduce the rate of personnel involvement. Different from the rule based fuzzy theory, the Direct Action type Fuzzy Proportion-Integral-Differential control theory (Direct Action type Fuzzy PID) is designed to combine a single input variable and three-rule fuzzy inference system. With a traditional PID controller, the DA type Fuzzy PID controller will have a simple structure as well as the nonlinear output property. Object of control is a reverse-acting grate type incinerator. Establishment of the model is done with estimates of the value of LHV and steam flow rate, coordinating the actual structure of furnace to infer the speed variable feeder model. Establishment and simulation of the control system works under the MATLAB environment. Parameter-tuning of the controller uses the Genetic Algorithm (GA) for optimization. By joining the furnace model and the controller for simulation, it proves that the Direct Action type Fuzzy PID controller has good performance and is feasible to the combustion control for refuse incineration plant.

The idea for this research work is to use the fuzzy logic as a novel technique for modelling infantry tactics and doctrine that are currently being documented in flow charts. In flow charts we can only have yes-no decisions where one query branches either to another query (if the answer is no) or branches to an action (if the answer is yes). In such methods there are no various degrees of reasoning, just crisp yes or crisp no. This is not the way that humans usually reason. Hence, the introduction of fuzzy logic gives more flexibility in modelling human decision making process. / On the other hand, the knowledge-based systems are designed to mimic the performance of a human expert by transferring his/her expertise in a specific field to a computer-based model most oftenly in the form of a software package. This knowledge is often imprecise, or not all facts are available. Still humans are capable of making good decisions within such uncertain environment. / It was decided to use fuzzy logic for modelling infantry tactics and doctrine because fuzzy logic provides a basis for representing uncertain and imprecise knowledge and forms a basis for human reasoning and decision making in such incompletely defined systems. Therefore the fuzzy logic seems a suitable choice in modelling infantry tactics and doctrine. / In this research work we first show how selected infantry tactics could be modelled utilising MATLAB® Fuzzy Toolbox. Then we develop a software package in Java programming language, which is then used to model the same infantry tactics. Using Java is necessary as the final aim of this project is to implement the developed models in the intelligent agent software (Jack). / The first part of this thesis is an overview of the fuzzy logic as one of the artificial intelligence paradigms. This part also briefly introduces intelligent agents, what they are and what they are not. The second part of this thesis shows the implementation of fuzzy reasoning in modelling selected infantry tactics and doctrine. The simulation results from all applications are also presented. / Thesis MEng(ElectronicEngineering byResearch)--University of South Australia, 2055.

Thesis (M. Phil.)--Hong Kong University of Science and Technology, 2004. / Includes bibliographical references (leaves 48-52). Also available in electronic version. Access restricted to campus users.

This thesis is concerned with the extraction of dense three-dimensional depth maps from sequences of two-dimensional greyscale images using correlation based matching. In particular the thesis is focused on the noise processes that occur in the depth map and the removal of that noise using nonlinear filters based on fuzzy systems. The depth from stereo algorithm is reviewed and a widely used correlation based matcher, the Sum Squared Difference (SSD) matcher, is introduced together with an established method of measuring sub-pixel disparities in stereo pairs of images. The noise in the disparity map associated with this matcher is investigated. The conjecture is made that a fuzzy inferencing system can be trained to perform a nonlinear filtering process which is more effective than conventional filters at removing the mixed impulsive and Gaussian-like noise present in the depth map. Six methods of training fuzzy systems of the Sugeno type based on the simulated annealing algorithm are proposed and tested by training fuzzy systems to approximate a simple function of two variables The thesis reviews existing fuzzy logic based filters and proposes a taxonomy for such systems. This distinguishes between direct and indirect acting fuzzy filters. An indirect acting fuzzy filter is applied to the task of smoothing a disparity map. The first order Sugeno fuzzy system is then proposed as an architecture that would be suitable as the basis for a direct acting fuzzy filter. This architecture is then applied to the task of smoothing depth maps derived from real and simulated data. The main contributions of the thesis are the identification of the Sugeno fuzzy system as a form of filter, the proposed training techniques, and the application of fuzzy filters to depth map smoothing.

Orientadores: Marko Antonio Rojas Medar, Maria Dolores Jimenez Gamero / Tese (doutorado) - Universidade Estadual de Campinas, Instituto de Matematica, Estatistica e Computação Cientifica / Made available in DSpace on 2018-08-03T19:12:39Z (GMT). No. of bitstreams: 1 ChalcoCano_Yurilev_D.pdf: 674734 bytes, checksum: a96086c399eb7547f5f8601b438a8edd (MD5) Previous issue date: 2004 / Doutorado / Doutor em Matemática

Various notions of compactness in a fuzzy topological space have been introduced by different authors. The aim of this thesis is to compare them. We find that in a T₂ space (in the sense that no fuzzy net converges to two fuzzy points with different supports) all these notions are equivalent for the whole space. Furthermore, for N-compactness and f-compactness (being the only notions that are defined for an arbitrary fuzzy subset) we have equivalence under a stronger condition, namely, a T₂ space in the sense that every prime prefilter has an adherence that is non-zero in at most one point

Eigen fuzzy sets of fuzzy relation can be used for the estimation of highest and lowest levels of involved variables when applying max-min composition on fuzzy relations. By the greatest eigen fuzzy sets (set which can be greater anymore) maximum membership degrees of any fuzzy set can be found, with the help of least eigen fuzzy set (set which can be less anymore) minimum membership degrees of any fuzzy sets can be found as well.The lowest and highest level, impact or e ffect of anything can be found by applying eigen fuzzy set theory. The implicational aspect of this research study is medical and customer satisfaction level measurement. By applying methods of eigen fuzzy set theory the e ffectiveness of medical cure and customer satisfaction can be found with high precision.

Univ., Habil.-Schr.--Stuttgart, 2005. / Literaturverz. S. [245] - 252.

Thesis (M.Sc. (Mathematics)) - Rhodes University, 2009.

The project objective in this work is to create an accurate cost estimate for NASA engine tests at the John C. Stennis Space Center testing facilities using various combinations of fuzzy and neural systems. The data set available for this cost prediction problem consists of variables such as test duration, thrust, and many other similar quantities, unfortunately it is small and incomplete. The first method implemented to perform this cost estimate uses the locally linear embedding (LLE) algorithm for a nonlinear reduction method that is then put through an adaptive network based fuzzy inference system (ANFIS). The second method is a two stage system that uses various ANFIS with either single or multiple inputs for a cost estimate whose outputs are then put through a backpropagation trained neural network for the final cost prediction. Finally, method 3 uses a radial basis function network (RBFN) to predict the engine test cost.