Prof LIU Cheng

Prof LIU Cheng

Physics-Guided Deep Learning, Structural Health Monitoring, Structural Digital Twin, Smart Materials and Structures, CFRP Composites

Posts by Collection

portfolio

publications

Lamb Wave-based Damage Detection of Composite Structures using CNN and Continuous Wavelet Transform

Published in Composite Structures, 2021

This paper proposes a novel method for detecting the internal delamination of the carbon fiber reinforced plastics by combining deep convolutional neural network and continuous wavelet transform.

Recommended citation: Wu J, Xu X, Liu, C, et al. Lamb wave-based damage detection of composite structures using deep convolutional neural network and continuous wavelet transform [J]. Composite Structures, 2021, 276: 114590.
Download Paper

Design of Active Sensing Smart Skin for Incipient Slip Detection in Robotics Applications

Published in IEEE/ASME Transactions on Mechatronics, 2022

In this article, a novel active sensing smart skin was developed for incipient slip detection, which leverages piezoelectric transducers as actuators/sensors.

Recommended citation: Liu, C, et al. "Design of active sensing smart skin for incipient slip detection in robotics applications." IEEE/ASME Transactions on Mechatronics 28.3 (2022): 1766-1777.
Download Paper

Deep transfer learning-based damage detection of composite structures by fusing monitoring data with physical mechanism

Published in Engineering Applications of Artificial Intelligence, 2023

This study proposes a deep transfer learning-based model, called MDAAN, for the damage detection of CFRP composite structures. MDAAN learns the physical mechanism of fatigue damage from the simulation data generated by the finite element model, and can then transfer this knowledge to real-world experimental data to detect and locate the fatigue damage.

Recommended citation: Liu, C., Xu, X., Wu, J., Zhu, H., & Wang, C. (2023). Deep transfer learning-based damage detection of composite structures by fusing monitoring data with physical mechanism. Engineering Applications of Artificial Intelligence, 123, Article 106245. https://doi.org/10.1016/j.engappai.2023.106245
Download Paper

Few-shot meta transfer learning-based damage detection of composite structures

Published in Smart Materials and Structures, 2024

To address these challenges of few training data and the scarcity of damage samples, this paper proposes a few-shot meta transfer learning (FMTL)-based approach for damage detection in CFRP composite structures.

Recommended citation: Chen, Y., Xu, X., & Liu, C. (2024). Few-shot meta transfer learning-based damage detection of composite structures. Smart Materials and Structures, 33(2), Article 025027. https://doi.org/10.1088/1361-665X/ad1ded
Download Paper

Physics-guided deep learning for damage detection in CFRP composite structures

Published in Composite Structures, 2024

This paper proposes a physics-guided deep learning framework to integrate physics into data-driven models. This physics-guided convolutional neural network leverages structural degradation trend and physical consistency by combining the output of the physical model with the observed feature in a hybrid model. This hybrid model uses an additional branch to observe the information of stiffness degradation, which is the input into the physical model to describe the damage growth in structures by establishing a relationship with the power spectral density change in the guided wave signals.

Recommended citation: Xu, X., & Liu, C. (2024). Physics-guided deep learning for damage detection in CFRP composite structures. Composite Structures, 331, Article 117889. https://doi.org/10.1016/j.compstruct.2024.117889.
Download Paper

Network for robust and high-accuracy pavement crack segmentation

Published in Automation in Construction, 2024

This study proposes a pavement crack segmentation algorithm called MixCrackNet. MixCrackNet leverages deformable convolution, weighted loss functions, an efficient multi-scale attention module, and the Mix Structure to identify pavement cracks.

Recommended citation: Zhang, Y., & Liu, C. (2024). Network for robust and high-accuracy pavement crack segmentation. Automation in Construction, 162, Article 105375. https://doi.org/10.1016/j.autcon.2024.105375
Download Paper

Real-Time Pavement Damage Detection With Damage Shape Adaptation

Published in IEEE Transactions on Intelligent Transportation Systems, 2024

This paper proposes a fast damage detection algorithm named FPDDN to achieve real-time and high-accuracy pavement damage detection.

Recommended citation: Zhang, Y., & Liu, C. (2024). Real-Time Pavement Damage Detection With Damage Shape Adaptation. IEEE Transactions on Intelligent Transportation Systems.
Download Paper

talks

teaching