论文部分内容阅读
通过对航空发动机机载数据结构以及几种常用的航空发动机故障检测方法的深入分析,提出采用关联规则挖掘来实现航空发动机故障检测。针对常用的关联规则挖掘算法——Apriori在应对数据量较大的数据库时存在效率瓶颈的问题,对该算法进行了改进。改进后的算法可以不断降低数据库规模和候选项集的数量。通过对航空发动机实际试车数据的挖掘实验,证明了改进算法更加高效简洁。
Through the in-depth analysis of the aero-engine airborne data structure and several commonly used aeroengine fault detection methods, the association rule mining is proposed to realize the aeroengine fault detection. Aiming at the commonly used algorithm of association rules mining, Apriori has the bottleneck of efficiency in dealing with the large amount of data, this algorithm is improved. The improved algorithm can continuously reduce the size of the database and the number of candidate itemsets. Through the actual test data of the aeroengine excavation experiment, it proves that the improved algorithm is more efficient and concise.