基于参数约简和免疫算法的飞行规则自动提取方法

模拟机自动评分系统对飞行员数据进行评分的时候需要量化飞行规则，针对规则量化困难的问题，提出了一种基于参数约简和免疫算法的飞行规则自动提取方法。用该方法对某航空公司提供的正常爬升科目的大量飞行数据进行了规则提取，将提取到的规则对正反例样本之外多个飞行数据进行判读，结果表明均未出现误判。与没有采用参数约简的方法相比，用该方法提取到的规则更简洁、更准确，对专家制定用于自动评分系统中量化的飞行规则具有很好的参考价值。

An Approach for Automatic Extraction of Flight Rules Based on Parameter Reduction and Immune Algorithm

Automatic scoring system for the simulator requires quantitative flight rules when scoring the pilot data. Aimed at the problem that the rules are difficult to quantify,an approach is proposed for automatic extraction of flight rules based on parameter reduction and immune algorithm. The approach is used to extract the rule from the flight data of normal climb subject provided by airlines. We verify the rule by using some flight data except positive and negative cases samples,the results show no misjudgment. Compared with the approach without parameter reduction,rules extracted by using the approach proposed in this paper are more concise and more accurate and yield highly reference values for experts to develop quantitative flight rules for automatic scoring system.