Print Email Facebook Twitter Damage Classification of a Bolted Connection using Guided Waves and Explainable Artificial Intelligence Title Damage Classification of a Bolted Connection using Guided Waves and Explainable Artificial Intelligence Author Hu, M. (TU Delft Structural Integrity & Composites; Harbin Engineering University) Yue, N. (TU Delft Group Yue) Groves, R.M. (TU Delft Group Groves) Date 2024 Abstract With the improvements in computational power and advances in chip and sensor technology, the applications of machine learning (ML) technologies in structural health monitoring (SHM) are increasing rapidly. Compared with traditional methods, deep learning based SHM (Deep SHM) methods are more efficient and have a higher accuracy. However, due to the black box nature of deep learning, the trained models are usually difficult to interpret, which blocks their practical application. Therefore, it is of great importance to develop explainable artificial intelligence (XAI) methods to understand the internal decision-making mechanisms of damage classification in Deep SHM. In this paper, a novel XAI algorithm named Deep Gradient-weighted Class Activation Mapping (Deep Grad CAM) is proposed by combining the existing method Grad CAM with the convolutional neural network (CNN) deconvolution mechanism. In this paper, Deep Grad CAM is used to interpret a one-dimensional convolutional neural network trained to detect bolt loosening based on guided wave propagation. The interpretation performance of Deep Grad CAM is compared with Grad CAM, and their performances are quantified using Infidelity. The results show that the Infidelity of Deep Grad CAM is much smaller than that of Grad CAM, indicating significant improvements in explanation accuracy and reliability. Subject deep learningexplainable AI (XAI)guided wavesone-dimensional convolutional neural network (1D CNN)structural health monitoring (SHM) To reference this document use: http://resolver.tudelft.nl/uuid:71534aae-41f4-435a-8402-dd23e104483a DOI https://doi.org/10.1016/j.prostr.2023.12.023 ISSN 2452-3216 Source Procedia Structural Integrity, 52, 224-233 Event 21st International Conference on Fracture, Damage and Structural Health Monitoring, FDM 2023, 2023-09-12 → 2023-09-14, London, United Kingdom Part of collection Institutional Repository Document type journal article Rights © 2024 M. Hu, N. Yue, R.M. Groves Files PDF 1-s2.0-S2452321623007217-main.pdf 1.89 MB Close viewer /islandora/object/uuid:71534aae-41f4-435a-8402-dd23e104483a/datastream/OBJ/view