Evolutionary computing and algorithms are well known tools of optimization that are utilized for various areas of analogue electronic circuits design and diagnosis. This paper presents the possibility of using two evolutionary algorithms - genetic algorithm and evolutionary strategies - for the purpose of analogue circuits yield and cost optimization. Terms: technologic and parametric yield are defined. Procedures of parametric yield optimization, such as a design centring, a design tolerancing, a design centring with tolerancing, are introduced. Basics of genetic algorithm and evolutionary strategies are presented, differences between these two algorithms are high-lighted, certain aspects of implementation are discussed. Effectiveness of both algorithms in parametric yield optimization has been tested on several examples and results have been presented. A share of evolutionary algorithms computation cost in a total optimization cost is analyzed.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.