武器系统研制费投资分布规律的仿真研究

针对大型项目多峰、复杂费用分布的传统仿真建模方法模型选取过于复杂、且难以达到精度要求等不足,提出将一种基于支持向量机的机器学习方法应用于大型复杂武器系统研制费投资分布研究.计算结果表明,这种方法有效弥补了传统建模方法的缺陷,有更好的泛化能力和实用性,因而可以作为研究此类问题的一种新方法.

Simulation research on investment distribution law of development fee of weapon system

Aiming at the shortcoming of complex model choice and bad precision about traditional (simulation) modeling method of many apexes and complex expensedistribution of big items, a machine learning method based on support vector machine, which can be applied on the research of the investment distribution of development fee of thebig and complex weapon system, is put forward. The result shows that this method can efficiently make up the deficiencyof traditional method, and has better extension and practicality than the traditional ones. Therefore, it can be viewed as a new approach to study this kind of problem.