Bolts are frequently subjected to loosening due to time varying external loads during service. The electromechanical impedance (EMI) technique based on piezoelectric ceramic wafers (PZT) is sensitive to the initial bolt preload looseness. However, the change in environmental temperature has a great effect on EMI monitoring. Deep convolutional neural network (CNN) is a promising technique for EMI monitoring. Nevertheless, it is difficult to train a deep CNN with limited training data to accurately identify damages under a wide range of temperature variations. To this end, this study proposes a multitask CNN for identifying bolts loosening. The network consists of a temperature compensation subnetwork to compensate for the temperature effect, and a lightweight damage identification subnetwork to identify bolt loosening states. The temperature compensation subnetwork is a modified Unet, and both the impedance and temperature are used as its input. The damage identification subnetwork is connected in series behind the temperature compensation subnetwork. A multiloss function is proposed in which a TV regularizer is used. Experimental results show that the validation accuracy of the multitask network is 97.71% when the network is trained by only about 30 samples from each loosening state. Moreover, the generalization abilities of the proposed multitask model to unexpected temperatures and bolt torques are investigated. The model is interpreted by the integrated gradients method, and is also compared with single-task damage identification CNNs. It is proved that the multitask network trained by limited samples can achieve accurate damage identification in temperature varying environments.

The significance of implementing online health monitoring (SHM) for aerospace structures under harsh service environments cannot be overemphasized. Deep learning has demonstrated a promising and effective means to achieve accommodate such a need. However, as envisaged, the performance of deep learning-facilitated SHM heavily relies on the scale of training dataset, degrading the practicability of the approach. To address this, we propose an improved Prototype Network and data augmentation methods for few-shot SHM using guided waves. In the improved Prototype Network, the weighted Euclidean distance is used for damage classification. An attention module is established to predict the weight coefficients. The Davies-Bouldin Index is used in the loss function to better separate the embedding vectors of different classes. Time masking and frequency masking are proposed for data augmentation of guided wave signals. As bolt joints are widely used in aerospace structures, the proposed approach is experimentally validated by quantifying the degree of bolt loosening in multi-bolt connection structures. The results are compared against those obtained from other classical Few-shot learning methods.

Online monitoring of bolt torque is critical to ensure the safe operation of bolted structures. Guided waves have been intensively explored for bolt loosening monitoring. Nevertheless, guided waves are excessively sensitive to fluctuation of ambient temperature. As a result of the complexity of wave transmitting across a bolted joint, it is highly challenging to compensate for the effect of temperature. To this end, an attention-based multi-task network is developed towards accurate detection of bolt loosening in multi-bolt connections over a wide range of temperature variation. By integrating improved attention gate modules in a modified U-Net architecture, an attention U-Net is configured for temperature compensation. A two-layer convolutional subnetwork is connected in series behind the attention U-Net to identify bolt loosening. Experimental validation is carried out on a bolt jointed lap plate simulating a real aircraft structure. The results have proved that the developed multi-task network achieves temperature compensation and accurate bolt loosening identification. To further understand the multi-task network, the Integrated Gradients method and a simplified structure of the bolt lap plate are used to interpret the developed network. It is proved that the A₀ mode is sensitive to bolt loosening, while the S₀ mode is not.

L-shaped bolt lap joints are commonly used in aerospace and civil structures. However, bolt joints are frequently subjected to loosening, and this has a significant effect on the safety and reliability of these structures. Therefore, bolt preload monitoring is very important, especially at the early stage of loosening. In this paper, a virtual time reversal guided wave method is presented to monitor preload of bolted L-shaped lap joints accurately and simply. In this method, a referenced reemitting signal (RRS) is extracted from the bolted structure in fully tightened condition. Then the RRS is utilized as the excitation signal for the bolted structure in loosening states, and the normalized peak amplitude of refocused wave packet is used as the tightness index (TI_A). The proposed method is experimentally validated by L-shaped bolt joints with single and multiple bolts. Moreover, the selections of guided wave frequency and tightness index are also discussed. The results demonstrate that the relationship between TI_A and bolt preload is linear. The detection sensitivity is improved significantly compared with time reversal (TR) method, particularly when bolt loosening is at its embryo stage. The results also show that TR method is an effective method for detection of the number of loosening bolts.