USING REAL-CODED GENETIC ALGORITHMS FOR WEIBULL PARAMETER-ESTIMATION

Genetic algorithms (GAs) represent a class of adaptive search techniqu es based on a direct analogy, to Darwinian natural selection and mutat ions in biological systems. ''Standard'' GAs have emphasized the utili zation of binary codes. However, recent empirical, results have indica ted that a chromosome representation which utilizes real values have e nhanced the performance of these GAs in certain engineering problems. A real-valued Generic Algorithm method described in this paper estimat es the parameter values from an unconstrained population of data point s for a Weibull distribution function using a simultaneous random sear ch function by integrating the principles of the Generic Algorithm and the method of Maximum Likelihood Estimation. The results of the real coded GA technique for parameter estimation are compared to the result s of the Newton-Raphson Algorithm.