论文部分内容阅读
为高效准确挖掘航空器空中相撞事故与相应事故致因因素间的规律,利用事故数据,提出一种基于粗糙集和遗传算法的分析模型。首先运用粗糙集理论对SHELL模型提供的第一层次因素进行重要性程度排序,并确定其权重;然后分析事故中各环节的具体因素,结合遗传算法对这些子因素进行约简,约简时重点考虑重要度高的主因素,确定最终的事故因素及其决策规则;最后,实例分析得出导致事故的主要因素为机组违规、管制差错与违规、气象和空域。实例分析结果表明,该模型与算法能适应航空事故数据特点,能客观描述几个主要因素与事故发生之间的关联关系。
In order to efficiently and accurately mine the law of aircrafts collision and the causal factors of the corresponding accidents, an analysis model based on rough sets and genetic algorithms was proposed based on accident data. First of all, we use the rough set theory to rank the importance of the first level of factors provided by the SHELL model and determine its weight. Then, we analyze the specific factors of each link in the accident, and combine the genetic algorithm to reduce these sub-factors. Considering the main factors with high importance, the final accident factors and their decision rules are determined. Finally, the case analysis shows that the main factors leading to the accident are unit violation, control error and violation, weather and airspace. The case study shows that the model and algorithm can adapt to the characteristics of aviation accident data and can objectively describe the relationship between several major factors and the accident.