Generalizing infrastructure inspection: step transfer learning aided extreme learning machine for automated crack detection in concrete structures

Abstract

Identification of damage and selection of a restoration strategy in concrete structures is contingent upon automatic inspection for crack detection and assessment. Most research on deep learning models for autonomous inspection has focused solely on measuring crack dimensions, omitting the generalization power of a model. This research utilizes a novel step transfer learning aided extreme learning machine (STELM) approach to develop an automatic assessment strategy for surface cracks in concrete structures. Step transfer learning (STL) is helpful in mining generalized abstract features from different sets of source images, and extreme learning machine (ELM) helps the proposed model overcome the optimization limitations of traditional artificial neural networks. The proposed model achieved at least 2.5%, 4.8%, and 0.8% improvement in accuracy, recall, and precision, respectively, in comparison to the other studies, indicating that the proposed model could aid in the automated inspection of concrete structures, ensuring high generalization ability.

Erosion depth prediction of chloride ions under stray current using FEM based CNNs

“…Currently, advanced data processing methods are bringing revolutionary changes to the engineering field, especially in the assessment of concrete structure strength [16][17][18]. It is worth noting that the strength of concrete structures is inversely proportional to the depth of Cl − erosion.…”