A systematic multidimensional assessment index system for digital twin models was created utilizing the goal-question-metric (GQM) method in response to the dearth of reference standards and unified evaluation techniques for intelligent manufacturing digital twin models. By combining the advantages of variable fuzzy recognition model and information entropy aggregation weight algorithm, a digital twin quality value evaluation method based on improved variable fuzzy model was constructed. In order to solve the problems of fuzziness and uncertainty in expert evaluation, the variable fuzzy recognition model is improved by using group decision theory, and the index weight is calculated by using information entropy on the basis of considering expert opinion preference. Finally, the quality, performance and value of a digital twin model of an aircraft manufacturing plant are evaluated. According to the example study, the digital twin model of the aircraft production facility has an evaluation level of “S₄ good,” although it tends to be “S₃ qualified,” and there is still opportunity for improvement. At the same time, the feasibility and rationality of improving the variable fuzzy recognition model are verified, and the method support is provided for the construction of standardized intelligent manufacturing digital twin model.

Hard landing may cause structural damage of aircraft or other potential accident causes and even crash and fatal flight accidents. In view of the lack of physical nature analysis in current hard landing risk assessment, combined with flight status analysis, a hard landing risk prediction model based on gradient boosting decision tree (GBDT) and grid search (GS) was proposed to effectively implement hard landing risk identification and grade criteria and improve pilots’ landing operation quality. Firstly, the flight kinematics equation of landing was established through the force analysis of aircraft, and five flight status parameters closely related to hard landing were determined. Then, flight status data was extracted from onboard quick access recorder (QAR) data to construct a data set. According to QAR parameter characteristics, the hard landing risk prediction model was constructed by the GBDT algorithm, and model parameters were optimized by GS. Finally, taking the Chengdu-Shenyang route operation of an airline as an example, the study selected 530 pieces of QAR data to train and test the model and compared the result of the model with those of random forest, recurrent neural networks (RNN), and Logistic multiple regression. The results show that the GBDT-GS method is better than other algorithms in predicting hard landing risk, and its prediction accuracy reaches 92%, which verifies the objective validity of the constructed model.