The rod-fastened rotor is a critical component of heavy-duty gas turbines, and therefore, it is imperative to investigate its failure mechanisms and develop intelligent diagnostic techniques. The issue of effective cross-domain diagnosis has garnered significant interest considering the changing operating conditions of rod-fastened rotors. To mitigate the effects of limited data samples or high collection costs in the target domain, we introduce a fault diagnosis model named the task-generalization-based graph convolutional network (TG-GCN), which leverages adversarial perturbations within a meta-learning framework to enhance the robustness of prior knowledge incorporated into the graph convolutional network. Initially, the method involves generating adversarial training samples in proximity to the distribution of the source-domain data by optimizing the worst case formulation to enhance generalization to task distribution. Next, the support set and the query set are simultaneously fed into the feature extraction network, yielding corresponding feature vectors. Subsequently, similarities between feature vectors and the degree of dispersion are computed in the task space, serving as connection weights for constructing the graph network model aimed at executing fault diagnosis. The proposed TG-GCN framework employs the introduction of data augmentation during the iteration process, which helps to strengthen the vulnerable components of the network by connecting them with the worst case perturbations. Moreover, we employed a rod-fastened rotor experimental system to elucidate the underlying failure mechanisms and corroborate the superiority of the TG-GCN.

The folding wing deployment mechanisms of aircraft are constrained by weight and space limitations, necessitating fewer actuators, multiple outputs, compact designs, and high efficiency. However, existing folding wing mechanisms often overlook the impact of performance in configuration design. Additionally, they struggle to achieve the synchronous unfolding of multiple wings using a single drive. This paper presents a design methodology for multi-wing deployment mechanisms based on configuration topology and multiple performance indicators. Specifically, seventeen configurations of multi-wing deployment mechanisms are developed based on functional requirements, along with expression methods for performance indicators, including compactness, mechanism stiffness, dynamic sensitivity, motion transmission, and joint transmission efficiency. The optimal configuration for the multi-wing deployment mechanism is identified utilizing the fuzzy comprehensive evaluation. Moreover, the transmission efficiency of multiple configurations is calculated across different scale parameters. Simulation analyses and prototype experiments are conducted to validate the design. The results indicate that the transmission efficiency of the optimized configuration consistently exceeds that of the other configurations. Maximum efficiencies surpass those of the other configurations by 2.4% and 5.7%. Importantly, this study introduces a quantitative expression method for multiple performance indicators at the configuration design stage. This approach enables the integration of various performance metrics with configuration designs. Overall, this research provides a novel approach for the innovative design of multi-wing deployment mechanisms in aircraft. Additionally, considering performance in the selection of mechanism configurations during engineering design offers valuable insights and potential applications.