This paper proposes a new VLSI placement method using genetic algorithm considering the hierarchical structure of solution space. In the proposed method, we introduce a special solution encoding which represents the hierarchical structure of solution space, and new crossover operators which can main
Placement of sensors/actuators on civil structures using genetic algorithms
β Scribed by Makola M. Abdullah; Andy Richardson; Jameel Hanif
- Publisher
- John Wiley and Sons
- Year
- 2001
- Tongue
- English
- Weight
- 153 KB
- Volume
- 30
- Category
- Article
- ISSN
- 0098-8847
- DOI
- 10.1002/eqe.57
No coin nor oath required. For personal study only.
β¦ Synopsis
Abstract
The optimal design and placement of controllers at discrete locations is an important problem that will have impact on the control of civil engineering structures. Though algorithms exist for the placement of sensor/actuator systems on continuous structures, the placement of controllers on discrete civil structures is a very difficult problem. Because of the nature of civil structures, it is not possible to place sensors and actuators at any location in the structure. This usually creates a nonβlinear constrained mixed integer problem that can be very difficult to solve. Using genetic algorithms in conjunction with gradientβbased optimization techniques will allow for the simultaneous placement and design of an effective structural control system. The introduction of algorithms based on genetic search procedures should increase the rate of convergence and thus reduce the computational time for solving the difficult control problem. The newly proposed method of simultaneously placing sensors/actuators will be compared to a commonly used method of sensors/actuators placement where sensors/actuators are placed sequentially. The savings in terms of energy requirements and cost will be discussed. Copyright Β© 2001 John Wiley & Sons, Ltd.
π SIMILAR VOLUMES
In discussing self-organizing neural networks, to some extent a large-scale network is assumed in order to achieve generality and adaptability. This paper discusses an optimal structurization method for a nonlinear network, based on a self-organizing algorithm with a two-layer structure. The basic s