To achieve intelligent manufacturing and improve the machining quality of machine tools, this paper proposes an interpretable machining size prediction model combining eXtreme Gradient Boosting (XGBoost), autoencoder (AE), and Shapley additive explanation (SHAP) analysis. In this study, XGBoost was used to establish an evaluation system for the actual machining size of computer numerical control (CNC) machine tools. The XGBoost model was combined with SHAP approximation to effectively capture local and global features in the data using autoencoders and transform the preprocessed data into more representative feature vectors. Grey correlation analysis (GRA) and principal component analysis (PCA) were used to reduce the dimensions of the original data features, and the synthetic minority overstimulation technique of the Gaussian noise regression (SMOGN) method was used to deal with the problem of data imbalance. Taking the actual size of the machine tool as the response parameter, based on the size parameters in the milling process of the CNC machine tool, the effectiveness of the model is verified. The experimental results show that the proposed AE-XGBoost model is superior to the traditional XGBoost method, and the prediction accuracy of the model is 7.11% higher than that of the traditional method. The subsequent SHAP analysis reveals the importance and interrelationship of features and provides a reliable decision support system for machine tool processing personnel, helping to improve processing quality and achieve intelligent manufacturing.

Avoiding collision of the towbarless aircraft towing system (TLATS), currently depends on manual vision. Improper manual operation and communication delays may lead to collisions between aircraft and other ground equipment and even casualties. To solve this problem, a collision avoidance model is proposed. Firstly, a novel kinematic model is proposed to determine the position and attitude of the TLATS. Secondly, the interval uncertainty analysis method is employed to measure the range of the kinematic characteristics of the system with input interval parameters. Thirdly, a Filter-Chebyshev (F-C) method is proposed by that the original approach of calculating the Chebyshev polynomial coefficients in the mentioned interval uncertainty analysis method is substituted with the Singular Value Decomposition Unscented Kalman Filter (SVDUKF) to improve the accuracy. The F-C method is able to measure the uncertainty bounds of the towing trajectory under interval uncertainty parameters. The uncertainty bounds reveal that how far away from the collision. The proposed method is compared with the existing scanning method and the Chebyshev method, and the results reflect the effectiveness of the proposed method. A reduced-scale model experiment is conducted, and the results confirm the validity of the F-C method.