基于粗糙集和熵权以及改进支持向量机的导弹备件消耗预测

在系统分析武器装备备件预测方法研究现状和导弹备件消耗特点的基础上，提出把粗糙集(RS)、熵权(EW)法、自适应粒子群优化(APSO)算法与加权最小二乘支持向量机(WLS-SVM)的组合预测模型应用于导弹备件消耗预测的构想。阐述了粗糙集、信息熵、自适应粒子群优化算法和WLS-SVM的基本原理，并改进了APSO的搜索方式和最小二乘支持向量机(LS-SVM)的加权方法；建立了基于RS、EW法和自适应粒子群优化WLS-SVM的导弹备件消耗预测模型，并分析了其实现过程。实例结果表明，所建立的组合预测模型在进行导弹备件消耗预测时具有较高的精度和重要的实用价值。

Consumption Forecasting of Missile Spare Parts Based on Rough Set, Entropy Weight and Improved SVM

On the basis of analyzing systemically present research condition of forecast method toward weapon and equipment spare parts and consumption characteristic of missile spare parts, the paper brought forward the thought of applying forecast model composed of rough set (RS), entropy weight (EW), and weighted least squares support vector machine (WLS-SVM) with adaptive particle swarm optimization (APSO) to consumption forecasting of missile spare parts. Firstly, the paper presentes basic theory, improves on search mode of APSO and weighted method of least squares support vector machine(LS-SVM); secondly , the consumption forecasting model of missile spareparts is established based on RS, EW and WLS-SVM with APSO, and realization process is analyzed. The example results show that the combinatorial forecasting model has better forecast precision and important applied value in the course of consumption forecasting of missile spare parts.