Researchers in the artificial intelligence community view system identification as a training task, while those with a control background see it as a parameter estimation problem. A third and more general perspective ...
Researchers in the artificial intelligence community view system identification as a training task, while those with a control background see it as a parameter estimation problem. A third and more general perspective is to view it as an optimization problem in which a performance index is minimised with respect to the parameters being identified. While these diverse interpretations result in differing terminologies and representations, the algorithms involved are essentially equivalent. Here the optimization perspective will be adopted. From this perspective neural modelling structures (NARX or NARMAX) can be classified as linear, nonlinear or mixed linear-nonlinear (hybrid) in the parameters. Linear, nonlinear or hybrid optimization techniques are then used for identification.
Summary form only given. The use of suction to reduce the drag force on an aircraft will, of course, only be worth doing if the energy saved is greater than the energy required to drive the suction system. In particul...
Summary form only given. The use of suction to reduce the drag force on an aircraft will, of course, only be worth doing if the energy saved is greater than the energy required to drive the suction system. In particular, it is possible to suck too hard and hence the suction system consumes more energy than it saves. Hence if we wish to achieve a specified transition position (dictated by the aerodynamics of the implementation) we must seek the suction distribution which achieves the desired result for the minimum energy cost. Also it is highly desirable not just to show an energy profit but to maximize it. Given these requirements, the route to design is obviously via an appropriately formulated nonlinear constrained optimization problem and in the work to-date we have used a number of methods of solving such problems, namely gradient descent based algorithms, genetic algorithms, simulated annealing. In this presentation, we will cover the following aspects; background and problem formulation; solution algorithms and relative performance comparisons; experimental facilities and comparisons of predicted and measured performance; and on-going research.
This conference proceedings contains 11 papers. The main subjects are unconstrained and constrained optimizationmethods, integrated system optimization and parameter optimization, optimization of project control usin...
详细信息
This conference proceedings contains 11 papers. The main subjects are unconstrained and constrained optimizationmethods, integrated system optimization and parameter optimization, optimization of project control using heuristic techniques, optimal satellite trajectories, optimal engine performance, and water system optimization.
暂无评论