Research on flight technology evaluation based on machine learning algorithm

In China's civil aviation transportation industry, flight safety has been the focus of attention. this paper, a technology assessment model and an automated early warning are established for safety. First, data pre-processing is performed. Then suitable indicators continuously screened by multiple machine learning classifications, then fitted to screen indicators, aircraft found be more integrated classification model. Subsequently, three unoptimized optimal models were derived as LightGBM, XGboost Random Forest models. The results these fused Stacking combine their advantages build final prediction For mechanism, mechanism needs first subclassing with K-mean clustering visualizing key items such avg (COG NORM ACCEL) based on normal distribution, combined differentiated distribution each category set implausible level establish