Optical interference filters that have continuously modulated refractive indices throughout their thickness (rugates) are designed and fabricated using microwave plasma-assisted chemical vapour decomposition technique...
详细信息
The proceedings contain 94 papers. The special focus in this conference is on Fuzzy systems, Neural Networks, geneticalgorithms and Reasoning. The topics include: Formalisations of uncertain reasoning;a fuzzy knowled...
ISBN:
(纸本)3540660763
The proceedings contain 94 papers. The special focus in this conference is on Fuzzy systems, Neural Networks, geneticalgorithms and Reasoning. The topics include: Formalisations of uncertain reasoning;a fuzzy knowledge representation and acquisition scheme for diagnostic systems;towards an affirmative interpretation of linguistically denied fuzzy properties in knowledge-based systems;design of fuzzy sliding controller based on cerebellar learning model;testing the performance of a neural networks-based adaptive call admission controller with multimedia traffic;a combined neural network and mathematical morphology method for computerized detection of microcalcifications;a generation method to produce GA with GP capabilities for signal modeling;using self organizing maps and geneticalgorithms for model selection in multilevel optimization;geneticalgorithms in solving graph partitioning problem;a study of a genetic classifier system based on the Pittsburgh approach on a medical domain;a new gradient-based search method;speeding the vector search algorithm for regional color channel features based indexing and retrieval systems;cost-based abduction using binary decision diagrams;a real world application of qualitative model-based decision tree generation for diagnosis;towards task-oriented user support for failure mode and effects analysis;incremental and integrated evaluation of rule-based systems;a compositional process control model and its application to biochemical processes and using extended logic programming for alarm-correlation in cellular phone networks.
Multi-objective geneticalgorithms (MOGA) are, a powerful decision-making aid for the control system designer. It is possible to search for many Pareto-optimal solutions concurrently, while concentrating on relevant r...
Multi-objective geneticalgorithms (MOGA) are, a powerful decision-making aid for the control system designer. It is possible to search for many Pareto-optimal solutions concurrently, while concentrating on relevant regions of the Pareto set. Also, a human decision maker may interactively supply preference information to the algorithm as it runs. Applications described include the design of controllers for flight dynamics, gas turbine engines and active magnetic bearings. Design problem characteristics include non-linear system descriptions, incorporation of H-infinity approaches and online use of the MOGA tool.
Scheduling optimization problems provide much potential for innovative solutions by geneticalgorithms. The complexities, constraints and practicalities of the scheduling process motivate the development of genetic al...
详细信息
The proceedings contains 10 papers from the ieecolloquium on Optimization in control: Methods and Applications: Topics discussed include: evolutionary methods for engineeringsystems optimization;optimization using p...
详细信息
The proceedings contains 10 papers from the ieecolloquium on Optimization in control: Methods and Applications: Topics discussed include: evolutionary methods for engineeringsystems optimization;optimization using population-based incremental learning;adaptive simulated annealing for controller design;neural network identification by gradient based methods;second variation method and optimal control;boundary layer transition control;missile guidance algorithms generation;neuromorphic remotely operated vehicle propulsion control;nonlinear stabilization and regulation via optimal gain schedule;and geneticalgorithms for active controls optimization in railway vehicles.
The use of Evolutionary Methods for the optimization of engineeringsystems is reviewed and a number of the most common methods are compared in terms of their philosophical basis and implementation. The use of these a...
详细信息
The use of Evolutionary Methods for the optimization of engineeringsystems is reviewed and a number of the most common methods are compared in terms of their philosophical basis and implementation. The use of these approaches, including geneticalgorithms, Evolutionary Programming, Evolutionary Strategies, Simulated Annealing and Population Based Incremental Learning, are illustrated using the shape optimization problem of a steel plate with buckling and stress constraints. The solutions obtained using the various methods are compared.
This paper presents optimizations of active control designs for railway vehicle suspensions using geneticalgorithms. genetic Algorithm (GA in short) is a stochastic process aimed at providing global optimization solu...
详细信息
This paper presents optimizations of active control designs for railway vehicle suspensions using geneticalgorithms. genetic Algorithm (GA in short) is a stochastic process aimed at providing global optimization solutions for a wide range of applications. In this paper, two active suspension controls are designed for the railway vehicles with the aid of GA. The paper first studies the controls for actively steering wheelsets of railway vehicles. The basic aim of a controller is to stabilize the potentially unstable vehicles and to improve the ride quality without interfering with the natural curving action of the solid axle wheelsets. The genetic Algorithm is used to assist the design of an optimal controller by choosing the weighting factors in order to achieve the best performance with the minimum interference to curving. In the second study, `classical controllers' controlling the front and rear ideal actuators of a flexible vehicle body are investigated. The aim is to minimize the flexible effect of the railway vehicle thereby improving the ride quality. GA is used to fine-tune the gains of the controllers in order to obtain the best overall ride quality of the entire vehicle body.
The use of evolutionary methods for the optimisation of engineeringsystems is reviewed and a number of the most common methods are compared in terms of their philosophical basis and implementation. The use of these a...
The use of evolutionary methods for the optimisation of engineeringsystems is reviewed and a number of the most common methods are compared in terms of their philosophical basis and implementation. The use of these approaches, including geneticalgorithms, evolutionary programming, evolutionary strategies, simulated annealing and population-based incremental learning, are illustrated using the shape optimisation problem of a steel plate with buckling and stress constraints. The solutions obtained using the various methods are compared.
This paper presents optimisations of active control designs for railway vehicle suspensions using geneticalgorithms. genetic algorithm (GA) is a stochastic process aimed at providing global optimisation solutions for...
This paper presents optimisations of active control designs for railway vehicle suspensions using geneticalgorithms. genetic algorithm (GA) is a stochastic process aimed at providing global optimisation solutions for a wide range of applications. In this paper, two active suspension controls are designed for the railway vehicles with the aid of GA. The paper first studies the controls for actively steering wheelsets of railway vehicles. The basic aim of a controller is to stabilise the potentially unstable vehicles and to improve the ride quality without interfering with the natural curving action of the solid axle wheelsets. The genetic algorithm is used to assist the design of an optimal controller by choosing the weighting factors in order to achieve the best performance with the minimum interference to curving. In the second study, 'classical controllers' controlling the front and rear ideal actuators of a flexible vehicle body are investigated. The aim is to minimise the flexible effect of the railway vehicle thereby improving the ride quality. GA is used to fine-tune the gains of the controllers in order to obtain the best overall ride quality of the entire vehicle body.
Progress in the application of mixed-integer nonlinear programming techniques to the selection of process control system structure as well as to the simultaneous selection of process and control system structures is d...
Progress in the application of mixed-integer nonlinear programming techniques to the selection of process control system structure as well as to the simultaneous selection of process and control system structures is discussed. In order to apply an approach based on optimisation, it is necessary to choose an objective function to be maximised, identify variables selection of whose values determines the key decisions to be made, as well as constraints limiting the set of allowed decisions. Finally, it is necessary to devise suitable algorithms to solve the problem formulated. Each of these aspects is briefly considered, before examples illustrating the approach are presented.
暂无评论