The Effects of Fiber Inclusion on the Evolution of Desiccation Cracking in Soil-Cement

Desiccation cracking frequently occurs in mud, clay, and pavement. Understanding the evolution of desiccation cracking may facilitate the development of techniques to mitigate cracking and even prevent it from developing altogether. In this study, experimental investigations were performed focusing on the effects of fibers on the evolution of desiccation cracking in soil-cement. Varied types of fibers (i.e., jute fiber and polyvinyl alcohol fiber (PVA)) and fiber contents (i.e., 0%, 0.25%, 0.5%, and 1%) were involved. The digital image correlation (DIC) method was employed to capture the evolution and propagation of cracks in the soil-cement specimens when subjected to desiccation. The results show that the presence of fibers imposes significant effects on the crack propagation pattern as well as the area and length of the cracks in the soil-cement during shrinkage. The addition of fibers, however, insignificantly affects the evaporation rate of the specimens. The crack area and crack length of the specimens decreased significantly when more fibers were included. There were no macroscopic cracks observed in the specimens where the fiber content was 1%. The DIC method effectively helped to determine the evolution of displacement and strain field on the specimens’ surface during the drying process. The DIC method is therefore useful for crack monitoring.

Concrete Cracks Monitoring using Deep Learning-based Multiresolution Analysis

In this paper, we propose a new methodology for crack monitoring in concrete structures. This approach is based on a n this paper, we propose a new methodology for monitoring cracks in concrete structures. This approach is based on a multi-resolution analysis of a sample or a specimen of the studied material subjected to several types of solicitation. The image obtained by ultrasonic investigation and processing by a dedicated wavelet will be analyzed according to several scales in order to detect internal cracks and crack initiation. The ultimate goal of this work is to propose an automatic crack type identification scheme based on convolutional neural networks (CNN). In this context, crack propagation can be monitored without access to the concrete surface and the goal is to detect cracks before they are visible on the concrete surface. The key idea allowing such a performance is the combination of two major data analysis tools which are wavelets and Deep Learning. This original procedure allows to reach a high accuracy close to 0.90. In this work, we have also implemented another approach for automatic detection of external cracks by deep learning from publicly available datasets.