To address the issue of inefficient refueling vehicle scheduling during airport flight support operations, this study establishes dual constraints for flight refueling time windows and permissible commencement time windows while prioritizing flight safety. It creates three integer programming models that optimize refueling vehicle allocation under these two limitations, standardizes stand designations and apron positions, and looks at key variables in three operational situations. According to the actual operation of the airport, a genetic optimization algorithm with elite strategy was proposed to solve the model according to the actual operation of the airport. In the first stage of independent scheduling, an evaluation mechanism that takes into account the two abilities of adaptability and population diversity was designed to ensure the diversity of the population. In the second and third stages of collaborative scheduling, a penalty factor introduction algorithm is designed, which can effectively avoid the emergence of populations that do not meet the target constraints. The simulation results show that compared with the traditional manual scheduling and genetic algorithm, the number of dispatched fuel trucks is reduced by 27.6% and 21.8% on average, which can provide effective decision support for airport fuel truck scheduling.

A data imputation algorithm based on a graph neural network is proposed to address the issue of missing flight ground support data. Firstly, to reduce the impact of noise in the original data on training denoising autoencoder is applied to enhance the reliability of feature extraction. Secondly, a graph representation learning framework is established to get the first embedding, using aggregation functions to aggregate the features of nodes within the sampling interval to achieve state updating. Furthermore, a long and short-term memory neural network is constructed to embed the temporal feature of flights to obtain the final state space of the hidden layer. Lastly, a loss function is suggested to iterate the deconvolution neural network, which is employed for feature restoration. The final flight ground operation data imputation result was acquired after numerous iterations, and the technique was evaluated using ground operation data from a specific airport in Southwest China from April to June 2018. The results showed that compared to other algorithms, the proposed algorithm imputation error decreased by an average of about 74% at low missing rates. At higher missing rates, the imputation proposed algorithm error decreased by an average of about 68%. When the number of iterations of the proposed algorithm is about 100 and the regularization coefficient is about 0.5, the imputation error reaches the lowest.