Impact monitoring of large size complex metal structures based on sparse sensor array and transfer learning.

During aircraft operations, the impact events experienced by the aircraft may cause damage to the structure, thus posing a safety hazard. Therefore, an accurate determination of where the impact occurred and the time history of the impact force can provide an important basis for assessing the condition of the aircraft. However, modern aircraft structures are often large and complex, and relying on dense arrays of sensors for monitoring adds additional weight to the aircraft and reduces the economics of aircraft operation. This paper proposes a region-to-point monitoring strategy. First, a Convolutional Neural Network (CNN) model with region localization capability is trained using the sparse sensor array acquisition data. Then, the weighted center algorithm is used to determine the specific location where the impact occurs, in which the added fuzzy genetic algorithm can provide the ability to adjust weights to improve localization accuracy adaptively. As for the impact force prediction, this paper adopts a model based on a Convolutional Neural Network-Gated Recurrent Unit combined with a Squeeze-Excitation attention mechanism (CNN-GRU-SE), which is capable of predicting the impact force occurring in the flat plate and reinforced structure region of the aircraft under different energy conditions. Finally, the impact of incorporating a transfer learning approach on model performance and training cost is investigated for fuselage regions with different structures.