Point Estimation Optimization Model of Life Distribution Parameters Based on Genetic Algorithm

Life distribution is the base of reliability analysis and calculation. A novel model of point estimation optimization of life distribution parameter is proposed based on genetic algorithm. In the model, parameters' confidence intervals are taken as coding space of genetic chromosome, and the reciprocal of error between empirical distribution function and the distribution function with parameters to optimize is chosen as fitness function. Application instances is given combined with units whose life distribution is exponential and normal, and also a stand by system; the results indicate that the estimating precision of the GA based model is better than maximum likelihood method in most situations.