Research on Function Module Clustering Based on the Rule-Immunity Algorithm for Complex Product

摘要

A two-step strategy was proposed to solve the problems that inefficiency and inaccuracy of function modules clustering for complex product. Firstly, the three principles were proposed that weldment simplification, outsourcing simplification and borrowed component reduction to preprocess and simplify complex product. Then the complex product preprocessed can be clustered into different function modules by using the advanced Immune Algorithm amalgamated with heuristic rule(R-Immunity). By comparing the efficiency, accuracy and robustness of function modules clustering among the Genetic Algorithm, the Immune Algorithm and the R-Immunity Algorithm, we consider that the R-Immunity Algorithm is more efficient and precise to solve the problems related to function modules clustering. Finally, starting with the structure properties of complex product, the clustering results were optimized for the purposes of reducing coupling between modules and satisfying configuration requirements of customer.