Early crack detection using modified spectral clustering method assisted with FE analysis for distress anticipation in cement-based composites

Abstract The present work reports an efficient way of capturing real-time crack propagation in concrete structures. modified spectral analysis based algorithm and finite element modeling (FEM) were utilised for detection quantitative propagation. Crack was captured cement-based composite (CBC) containing saw dust M20 grade under compressive loading using a simple inexpensive 8-megapixel mobile phone camera. randomly selected images showing initiation CBCs demonstrated the capability developed algorithm. A measure oriented energy provided at edges to develop similarity spatial relationship among pairwise pixels. FE modelling used distress anticipation, by analysing stresses during test constituents CBCs. jointly with algorithm, can provide inputs from crack-prone areas useful early structures preventive support management.