基于粗糙集规则提取的导弹武器质量性能评估方法研究  

Research on Evaluation Method for Quality and Performance of Missile Weapon Based on Rough Set Rule Extraction

作　　者：李俊[1] 孟涛[1] 张立新[1] 赵韶平[1] 

机构地区：[1]第二炮兵装备研究院,北京100085

出　　处：《兵工学报》2013年第12期1529-1535,共7页Acta Armamentarii

基　　金：中国博士后科学基金项目(20090461473)

摘　　要：传统的评估方法在指标体系获取、模型建立及专家资源数量等方面都会受到各种主观因素的影响和制约,从而降低评估结果的客观性及正确性。为了克服传统方法的缺点,基于粗糙集理论并结合相关机器学习算法,以导弹武器在寿命周期中的质量数据为基础,从中自动分析、提取导弹武器的质量性能评估规则,进而对导弹武器当前的质量状况给出评估。阐述了该评估方法的理论依据,设计并实现了规则提取及评估中的算法步骤。该评估方法以客观的质量信息为基础,不依赖于任何先验知识,不受专家资源制约,规避了主观因素的介入,有效提高了评估结论的客观性和正确性。通过小子样数据和大子样数据2种情形下的算例分别对整机级和部件级的武器质量性能进行了模拟评估,评估结果验证了该方法的有效性和正确性。In order to overcome the shortcomings of classical methods, a new quality performance evaluation method for missile weapon is proposed based on the rough set theory, other related machine learning methods and the quality data of missile weapon in its life cycle. It is used to automatically analyze and extract the evaluation rules from the quality data and evaluate the current quality and performance of missile weapon. The theoretical foundation of the evaluation method is described and the algorithm is designed and implemented. The evaluation results of two calculation examples in small data sets and large data sets are used to verify the validity and correctness of the proposed method.

关 键 词：系统评估与可行性分析 导弹武器 评估 质量性能 粗糙集 

分 类 号：E927[军事—军事装备学]