Data-Driven Based State Recognition Method for Airliner Fuselage Join

To accurately recognize the fuselage joining state is a great challenge in automation process. The accumulation of joining data and the development of machine learning methods have greatly facilitated it. In this paper, a data-driven based state recognition method is proposed for airliner fuselage join. Firstly, combined with the actual process of the fuselage join, the state labeling of joining data is completed by means of PCA and k-means clustering. Secondly, a Random Forest classifier is trained based on the labeled data, and the accuracy of the classifier is evaluated by cross validation. The results show that the proposed method can effectively label different fuselage joining states and achieve accurate state recognition for fuselage join.