Temperature compensation to guided wave-based monitoring of bolt loosening using an attention-based multi-task network

Abstract

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.

A novel damage index integrating piezoelectric impedance and ultrasonic guided wave for damage monitoring of bolted joints

“…21,22 Thanks to the superior performance of piezoelectric sensing technology, the research on health monitoring of bolted joints supported by the piezoelectric vibration method, 23 ultrasonic guided wave (UGW) technique, 24 and electromechanical impedance (EMI) method 25 has burst into a series of valuable achievements in recent years. 26–36 Earlier, research on piezoelectric sensing-based health monitoring techniques for bolted joints focused on investigating the feasibility and effectiveness of piezoelectric sensing in various modes of damage monitoring. 26–28 Recently, the research focus has gradually shifted to developing new damage indices (DIs), 29,31 improving damage localization techniques, 30,35 developing new application-oriented sensor devices, 33 developing integrated damage monitoring techniques, 34 introducing machine learning for damage monitoring, 32,35,36 and investigating composite monitoring techniques that can monitor damage mode and severity.…”

“…26–36 Earlier, research on piezoelectric sensing-based health monitoring techniques for bolted joints focused on investigating the feasibility and effectiveness of piezoelectric sensing in various modes of damage monitoring. 26–28 Recently, the research focus has gradually shifted to developing new damage indices (DIs), 29,31 improving damage localization techniques, 30,35 developing new application-oriented sensor devices, 33 developing integrated damage monitoring techniques, 34 introducing machine learning for damage monitoring, 32,35,36 and investigating composite monitoring techniques that can monitor damage mode and severity. 32 These achievements have made significant efforts to advance the development of SHM techniques for bolted joints with significant results.…”

A few-shot electromechanical impedance monitoring method based on a modified prototype network

“…In recent years, deep learning (DL) methods, especially convolutional neural networks (CNN), have been gradually used in structural health monitoring (SHM) [14,15]. DL is a promising technique for accurate damage detection based on EMI, which does not need damage indices.…”

Research on the monitoring friction hysteresis for the bolted interface by electromechanical impedance

“…By now, the structural health monitoring studies of the bolted joints mostly aim at loosening detection for threaded fasteners [20][21][22][23], temperature [24], and tangential loading [25], few of them considered the contact evolution. However, many results show that interface evolution is of great significance to the service performance of mechanical equipment in various engineering scenarios, such as the interface slip of the aero-engine rotor [26][27][28], bolt loosening [29] and high strength concrete [30,31], etc.…”