Validating Energy Efficient Structural Health Monitoring through Experimental Analysis in Self-Compacting Concrete Beam Column Joint Incorporated with Steel Fibres Using Artificial Neural Network

Beam-column joints play a vital role in self-compacting concrete (SCC) structures as they transfer loads and ensure overall structural integrity. To achieve the most desirable structural properties, steel fibres are incorporated into SCC as combination design; the fibre type and the quantity introduced must all be meticulously considered. This study aims to employ artificial neural network (ANN) models to detect subtle changes in joint behaviour that could potentially indicate damage or degeneration. This study improves the methods of assessment of the behaviour of beam-column joints under varied load application and environmental factors. The proposed neural network model shows strong predictive performance with R and R^² increasing by 9.3% and 17.9% and MAE, MSE, and RMSE decreasing by 31.7%, 67.7%, and 43.5%, respectively, for exterior joints without lateral reinforcement. For transversely reinforced joints, R and R^² improved by 1.7% and 3.7%, while error metrics dropped up to 23.3%, confirming the model's accuracy and reliability across all joint types evaluated. Employing structural health monitoring techniques, it is possible to constantly monitor the health state of these structures and get data on their performance over time that help in proper determination of failure indicators or necessity of maintenance. This integration enhances the effectiveness of structural monitoring by the removal of dependency on manual inspections as it cuts costs and chances of costly human errors. This research is novel in advancing the energy-efficiency and environmentally sustainable methods in construction and infrastructure industry.