IGA-RBPNN-Based Sludge Compost Maturity Degree Evaluation Method

摘要

Considering the issues that the relationship between the compost maturity degree and evaluation parameters is a nonlinear and uncertainty, a compost maturity degree evaluation method based on improved genetic algorithm (IGA) and radial basis probabilistic neural network (RBPNN) is presented. The fitness function, genetic operator and encoded mode of genetic algorithm are improved. The index of compost maturity degree is selected and the high temperature duration, moisture content, volatile solids, the value of fecal bacteria, germination index are adopted as the evaluation parameters in this method. The structure of RBPNN is constructed and the improved genetic algorithm is adopted to optimize network structure. With the ability of strong pattern classification and function approach and fast convergence of radial basis probabilistic neural network, the evaluation method can truly evaluate the maturity degree by learning the index information of sludge compost maturity degree. The experimental results show that this method is feasible and effective.