Based on the technical status and development trend of civil aircraft operation reliability research, the requirements of civil aircraft operation reliability research were expounded according to the current type design, development and actual situation of in-service aircraft. By reviewing the research progress and engineering application status of civil aircraft operational reliability theory, the research status and problems of civil aircraft operational reliability are elaborated from six aspects: operation data acquisition and processing, operational reliability analysis method, operational reliability prediction feedback technology, optimization design based on operational reliability, optimize maintenance tasks, and comprehensive management platform for operational reliability. The future development direction of operation reliability research of civil aircraft is prospected.

Although deep learning based black-box models demonstrate high efficiency and accuracy in establishing input-output mappings for composite bolted joint strength prediction, their inherent lack of physical interpretability obscures model decision logic, ultimately compromising reliability and generalizability. Based on the fusion of physical law constraints of composite materials and nonlinear identification constraints, a Multi-Constraint Identification Physics-Informed Neural Network (MCI-PINN) is proposed. Firstly, the constraints of physical laws apply the engineering estimation formula for the extrusion strength of composite material bolt connections. Secondly, using linear, polynomial, power, exponential, and logarithmic functions as basic functional forms, nonlinear relationships between material parameters, mechanical parameters, structural parameters, and extrusion strength are established, and the mapping relationship with the highest accuracy is identified to serve as a constraint for nonlinear identification. Then, the physical law constraints and nonlinear identification constraints are embedded in the neural network in the form of loss functions to guide the model training. Finally, in the case verification, the single-pin connection extrusion strength prediction of two layers of X850 material was carried out. The analysis results show that the prediction error index MRE of the extrusion strength of the two layers is 1.24% and 1.27% respectively. In terms of discreteness prediction, interpretability and generalization ability, MCI-PINN shows superiority compared with ANN and PINN.

To accomplish the reliability analyses of the correlation of multi-analytical objectives, an innovative framework of Dimensional Synchronous Modeling (DSM) and correlation analysis is developed based on the stepwise modeling strategy, cell array operation principle, and Copula theory. Under this framework, we propose a DSM-based Enhanced Kriging (DSMEK) algorithm to synchronously derive the modeling of multi-objective, and explore an adaptive Copula function approach to analyze the correlation among multiple objectives and to assess the synthetical reliability level. In the proposed DSMEK and adaptive Copula methods, the Kriging model is treated as the basis function of DSMEK model, the Multi-Objective Snake Optimizer (MOSO) algorithm is used to search the optimal values of hyperparameters of basis functions, the cell array operation principle is adopted to establish a whole model of multiple objectives, the goodness of fit is utilized to determine the forms of Copula functions, and the determined Copula functions are employed to perform the reliability analyses of the correlation of multi-analytical objectives. Furthermore, three examples, including multi-objective complex function approximation, aeroengine turbine bladed-disc multi-failure mode reliability analyses and aircraft landing gear system brake temperature reliability analyses, are performed to verify the effectiveness of the proposed methods, from the viewpoints of mathematics and engineering. The results show that the DSMEK and adaptive Copula approaches hold obvious advantages in terms of modeling features and simulation performance. The efforts of this work provide a useful way for the modeling of multi-analytical objectives and synthetical reliability analyses of complex structure/system with multi-output responses.

To improve the computational efficiency and accuracy of multi-objective reliability estimation for aerospace engineering structural systems, the Intelligent Vectorial Surrogate Modeling (IVSM) concept is presented by fusing the compact support region, surrogate modeling methods, matrix theory, and Bayesian optimization strategy. In this concept, the compact support region is employed to select effective modeling samples; the surrogate modeling methods are employed to establish a functional relationship between input variables and output responses; the matrix theory is adopted to establish the vector and cell arrays of modeling parameters and synchronously determine multi-objective limit state functions; the Bayesian optimization strategy is utilized to search for the optimal hyperparameters for modeling. Under this concept, the Intelligent Vectorial Neural Network (IVNN) method is proposed based on deep neural network to realize the reliability analysis of multi-objective aerospace engineering structural systems synchronously. The multi-output response function approximation problem and two engineering application cases (i.e., landing gear brake system temperature and aeroengine turbine blisk multi-failures) are used to verify the applicability of IVNN method. The results indicate that the proposed approach holds advantages in modeling properties and simulation performances. The efforts of this paper can offer a valuable reference for the improvement of multi-objective reliability assessment theory.

The establishment of aircraft inspection intervals requires the support of detection reliability, but the evaluation of detection reliability is influenced by many factors during the detection process. Among them, human and environment have the characteristics of multi-dimensional indicators and difficulty in quantifying their levels, making it difficult to quantitatively model them. Based on the quantitative evaluation for the impact of two types of factors using HF factors, a detection reliability model considering the impact of human and environment was established to address this issue. Firstly, feature analysis was conducted on the HF factors and its mathematical model was proposed based on A400M detection data. At the same time, verification was carried out using detection test data that considered work experience and operational lighting. Next, the comprehensive quantification for the levels of two types of factors was carried out through fuzzy comprehensive evaluation. On this basis, a mapping relationship between the comprehensive quantification results and the HF factor model was established. Finally, an application analysis was conducted using visual inspection data of flat plate cracks, verifying the applicability and effectiveness of the model. The proposed detection reliability model has the potential to reduce experimental costs while ensuring the accuracy of the results.