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.

This research investigates the physical parameter identification of a nonlinear hysteretic structure with pinching behavior for real-time or rapid structural health monitoring (SHM) after a major seismic event. The identification procedure is based on the overall least squares linear regression and hypothesis testing. It is applied to a general, nonlinear slip-lock (SL) pinching model. In particular, the hysteresis loop is reconstructed using data available from current sensor technologies. The path dependent hysteresis response is first divided into different loading and unloading subhalf cycles with a single valued function. These subhalf cycles are then assumed to be piecewise linear, and the number of segments for each subhalf cycle is identified using the sup F type test. The overall least squares linear regression is finally applied to the identified subhalf cycles to compute the regression coefficients and breakpoints that yield the elastic stiffness, plastic stiffness, and cumulative plastic deformation. The performance and robustness of the proposed method is illustrated using a single degree of freedom shear-type reinforced concrete structure with 10% added root mean square noise and variable pinching behavior. The proposed method is shown to be computationally efficient and accurate in identifying the damage parameters within 10% of true values. These results indicate that the system is able to capture nonlinear behavior and structural parameters, such as preyielding stiffness, postyielding stiffness and cumulative plastic deformation, directly relevant to damage and performance using a computationally efficient and simple method. Finally, the method requires no user input and could thus be automated and performed in real time for each half cycle, with results available effectively immediately after an event, as well as during an event, if required.

In existing research on rotating machinery diagnosis using graph neural networks, most methods are based on vibration analysis under contact sensor monitoring. However, the gathered vibration signal is sensitive to the increased mass of the sensor, and after prolonged close contact, the vibration sensor may cause structural damage to the object. A multi-sensor fusion based on modal analysis and graph attention network (MFMAGAT) for bearing fault diagnosis is suggested as a solution to these issues. First, we proposed a phase-based full-field non-contact measurement method based on direction-controlled pyramids to extract phase information at different scales and directions and use the phase information to characterize the vibration of the structure. Then, based on the vibration and acoustic signals of the characterized structure, we constructed a kernel function that can fuse the heterogeneous information, and its singular value decomposition can jointly characterize the response of the structure at same frequency bands from the video data and the acoustic data. Finally, considering that the decomposed features are independent and orthogonal to each other, the graph attention network is introduced at this time to find the weights among the components to jointly characterize the structural damage and improve the damage recognition accuracy. Comparison results show that the proposed method is effective and performs better than other conventional graph neural network diagnosis methods.