Skip to Main Content
As a powerful global optimization approach, genetic algorithms (GA)can solve a variety of optimization problems in which the objective function is discontinuous, non-differentiable, or highly non-linear, to produce high convergence speed and vast search space. In this thesis, Genetic algorithm and BP algorithm can be combined to achieve complementary advantages in order to help solve the problem better. Genetic neural network applied to the comprehensive evaluation of water quality without the need for building complex parameter equation, in the circumstance that without any simplification and assumption that can carry on non-linear mapping, models are of powerful self-learning ability, and the structure is simple and practical. To the greatest degree of exclusion of more traditional evaluation methods reflect human disturbances to the greatest degree of increase assessment objectivity, reliability, thus resulting water quality of the evaluation results more in line with the actual situation.