波形
材料科学
分层(地质)
压缩(物理)
卷积神经网络
压力(语言学)
结构工程
小波变换
抗压强度
声发射
计算机科学
声学
现象学模型
复合材料
小波
人工神经网络
模式(计算机接口)
过程(计算)
碳纤维增强聚合物
动态范围压缩
断裂力学
数字图像相关
作者
Davide Biagini,John-Alan Pascoe,René C. Alderliesten
标识
DOI:10.1016/j.ijfatigue.2026.109754
摘要
Fatigue damage propagation in impacted composites is still not fully understood, as some studies report steady delamination growth, while others show sudden, rapid growth at the end of fatigue life, even under similar test conditions. This study combines ultrasound scanning, digital image correlation, and acoustic emissions to characterize the fatigue-after-impact process across various load levels. Acoustic emissions were analyzed via wavelet transform and classified using a convolutional neural network (CNN) to isolate the contributions of individual damage modes throughout fatigue life. Results show that varying maximum compressive stress significantly influences compression after impact (CAI) fatigue behavior. Depending on the stress level, distinct damage propagation phases occur, each with different damage mode activity. Altering compressive stress affects not only the propagation rate and fatigue life but also the sequence of damage evolution. These findings offer a more complete phenomenological description of CAI fatigue and help resolve inconsistencies in previous studies.
科研通智能强力驱动
Strongly Powered by AbleSci AI