Abstract In this paper, the feasibility of using deep learning models (DLMs) for evaluation of bridges with overlay systems is investigated. Several laboratory-made concrete specimens with artificial subsurface defects and overlay systems (bonded and debonded) made of cement and asphalt overlay materials were tested using impact echo (IE). One-dimensional (1D) and two-dimensional (2D) convolutional neural networks (CNNs) were developed, trained, and tested on the IE data. The proposed 1D CNN was the most successful in detecting debonding and subsurface defects; it achieved an average accuracy of 0.68 on the cement overlay specimens and 0.58 for asphalt overlay specimens. Maps of the defects and debonding were generated using the DLMs and were compared to the conventional method for analyzing the IE data. The 1D CNN produced the most accurate defect maps while successfully detected sound, debonded, and defected regions, particularly on the specimens with cement overlay.

中文翻译：

---

使用冲击回波（一种深度学习方法）评估具有覆盖层的桥面

摘要 本文研究了使用深度学习模型 (DLM) 评估具有覆盖系统的桥梁的可行性。使用冲击回波 (IE) 测试了几个实验室制造的具有人工地下缺陷的混凝土试样和由水泥和沥青覆盖材料制成的覆盖系统（粘合和脱粘）。在 IE 数据上开发、训练和测试一维 (1D) 和二维 (2D) 卷积神经网络 (CNN)。提议的 1D CNN 在检测脱粘和次表面缺陷方面最为成功；它在水泥覆盖层试样上达到了 0.68 的平均精度，在沥青覆盖层试样上达到了 0.58 的平均精度。缺陷和脱粘图是使用 DLM 生成的，并与分析 IE 数据的传统方法进行比较。