Ensemble Machine Learning-Based Approach for Predicting of FRP–Concrete Interfacial Bonding

Developments in fiber-reinforced polymer (FRP) composite materials have created a huge impact on civil engineering techniques. Bonding properties of FRP led to its wide usage with concrete structures for interfacial bonding. FRP materials show great promise for rehabilitation of existing infrastructure by strengthening concrete structures. Existing machine learning-based models for predicting the FRP–concrete bond strength have not attained maximum performance in evaluating the bond strength. This paper presents an ensemble machine learning approach capable of predicting the FRP–concrete interfacial bond strength. In this work, a dataset holding details of 855 single-lap shear tests on FRP–concrete interfacial bonds extracted from the literature is used to build a bond strength prediction model. Test results hold data of different material properties and geometrical parameters influencing the FRP–concrete interfacial bond. This study employs CatBoost algorithm, an improved ensemble machine learning approach used to accurately predict bond strength of FRP–concrete interface. The algorithm performance is compared with those of other ensemble methods (i.e., histogram gradient boosting algorithm, extreme gradient boosting algorithm, and random forest). The CatBoost algorithm outperforms other ensemble methods with various performance metrics (i.e., lower root mean square error (2.310), lower covariance (21.8%), lower integral absolute error (8.8%), and higher R-square (96.1%)). A comparative study is performed between the proposed model and best performing bond strength prediction models in the literature. The results show that FRP–concrete interfacial bonding can be effectively predicted using proposed ensemble method.

Robust hydrogel-integrated microsystems enabled by enhanced interfacial bonding strength

Noncovalent hydrogels, compared to covalent hydrogels, have distinctive advantages including biocompatibility and self-healing property but tend to have poor mechanical robustness, thus restricting their application spectrum. A clue to increase utility of such soft hydrogels without chemical bulk modification can be witnessed in biological organ walls where soft mucous epithelial layers are juxtaposed with tough connective tissues. Perhaps, similarly, bonding noncovalent hydrogels to stronger materials, such as tough hydrogels, might be a viable approach for increasing stability and scalability as well as creating novel functions for hydrogel-based systems. However when attempting to bond these two materials, each of the four existing hydrogel-hydrogel bonding method has practical shortcomings. In this work, we introduce a mucosa-inspired bonding method that realizes interfacial bonding of noncovalent hydrogels to tough, hybrid hydrogels without external glue or bulk modification of the noncovalent gel while preserving interfacial micropatterns. The procedure is simple and we confirmed broad applicability with various noncovalent hydrogels and tough hydrogels. We demonstrated the utility of our bonding method with novel applications regarding in vitro assay, soft robotics and biologically inspired systems.