Electromechanical Impedance Temperature Compensation and Bolt Loosening Monitoring Based on Modified Unet and Multitask Learning

Du, Fei; Wu, Shiwei; Xu, Chao; Yang, Zhaohui; Su, Zhongqing

doi:10.1109/jsen.2021.3132943

Cited by 34 publications

(10 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By integrating the improved AG modules in a modified U-Net architecture, 54 a 1D attention U-Net is established for guided wave temperature compensation at various damage states. This network is named the compensation subnetwork (Comp-net).…”

Section: Attention-based Multi-task Network Considering Temperature V...mentioning

confidence: 99%

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

Xing

et al. 2022

Structural Health Monitoring

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Attention-based Multi-task Network Considering Temperature V...mentioning

confidence: 99%

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

Xing

et al. 2022

Structural Health Monitoring

Self Cite

View full text Add to dashboard Cite

show abstract

“…Ritdumrongkul's research also showed that some peak frequencies in the real part of the EMI signal corresponded to the vibration modes of the beam coupled with a PZT patch [9]. For the small size, light weight, and high accuracy of the PZT patch, measurement and monitoring based on the EMI have been widely applied by many researchers, such as in damage monitoring [10,11], bolt connection monitoring [12,13], grinding process monitoring [14,15], wear monitoring [16,17], soil monitoring [18,19], and stress monitoring [20,21]. Carbajo and his research team have preliminarily investigated the feasibility of determining the elastic moduli of several kinds of materials based on the EMI response of the PZT patch for the first time [22].…”

Section: Introductionmentioning

confidence: 99%

Determination of the Dynamic Modulus of Elasticity of Pine Based on the PZT Transducer

Li,

Xu,

Jiang

et al. 2024

Forests

View full text Add to dashboard Cite

A new method for the determination of the dynamic modulus of elasticity (Ed) of pine wood, based on the transverse vibration excitation and electromechanical impedance (EMI) response of the lead zirconate titanate (PZT) transducer is proposed. The influence of the length to thickness ratio of the pine specimen on the measurement accuracy was studied through modal simulation analysis. Based on the results of the modal simulation, the size of the pine specimen was optimized, and the scanning frequency range of the EMI response was determined. On this basis, the EMI simulation and test of the pine specimen coupled with a PZT patch were carried out to verify the effectiveness of the novel method. The impedance simulation results of three kinds of pine specimens show that a unique and significant formant appears in the real part of each EMI response curve, and the maximum relative errors of the rectangular PZT patch and circular PZT patch are 1.34% and 1.81%, respectively. The impedance test results of three kinds of pine specimens indicate that the maximum relative errors of the rectangular PZT patch and circular PZT patch are 1.41% and 1.68%, respectively, compared with the corresponding results obtained by the traditional transverse vibration method. Simulation and experimental results verify the validity of the proposed method for the elastic modulus determination of pine wood.

show abstract

“…However, only three different temperatures were considered. Du et al [20] proposed a multi-task U-Net CNN to carry out temperature compensation and bolt loosening condition monitoring of bolted structures based on EMI signals. It is proved that the DL based EMI damage monitoring method is effective and accurate in the temperature variation environment.…”

Section: Introductionmentioning

confidence: 99%

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

Weng³

et al. 2023

Smart Mater. Struct.

Self Cite

View full text Add to dashboard Cite

Bolt loosening monitoring is of great significance to warrant the reliability and safety of bolted structures. The electromechanical impedance (EMI)-based evaluation is effective to perceive bolt loosening. However, EMI signals are highly prone to contamination by temperature fluctuation. Deep learning (DL) based EMI is a promising technique for accurate damage detection in the temperature variation environment. However, DL needs a lot of data to train, which is usually very difficult to collect sufficient structural damage data in real word scenarios. This paper proposed a few-shot EMI monitoring method based on a modified prototype network for bolt looseness detection under temperature varying environment. The approach features a conversion method of the impedance signal to image based on the Hank matrix. A modified prototype network is then developed. Experimental study was carried out on a bolted joint. EMI signals under different bolt loosening conditions were measured in a temperature variation environment. An impedance analyzer and a self-made small lightweight monitoring device were both used to measure the EMI signals to test the cross domain scenario. The proposed method was compared with the transfer learning methods and other typical FSL methods. The experiment results show that the proposed few-shot EMI method can obviously improve the monitoring accuracy of bolt loosening with few samples.

show abstract

Electromechanical Impedance Temperature Compensation and Bolt Loosening Monitoring Based on Modified Unet and Multitask Learning

Cited by 34 publications

References 46 publications

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

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

Determination of the Dynamic Modulus of Elasticity of Pine Based on the PZT Transducer

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

Contact Info

Product

Resources

About