Development of an Intelligent Monitoring Framework for Concrete Tensioning Quality Based on the Radial Basis Function Neural Network

Traditional tensioning monitoring techniques for prestressed concrete structures often exhibit limitations in real-time performance, accuracy, and adaptability to complex stress distributions.To address these challenges, an intelligent monitoring framework is developed based on a Radial Basis Function (RBF) neural network.Using the Dongjiacun aqueduct as a case study, a comprehensive methodology is established, integrating numerical simulation, Machine Learning (ML), and real-time data processing.Initially, Finite Element Analysis (FEA) is conducted to simulate stress distribution during the tensioning process, allowing for the extraction of critical stress data at key structural locations.These data serve as the foundation for training the RBF neural network, which functions as a high-fidelity surrogate model capable of efficiently predicting stress variations with enhanced accuracy.By leveraging the network's strong generalization capabilities, the proposed framework ensures rapid and precise estimation of stress evolution throughout the tensioning process.Furthermore, an intelligent monitoring platform is designed, incorporating real-time data acquisition, automated stress prediction, and visualization functionalities.The platform facilitates prestress control and structural health assessment, contributing to the long-term safety and durability of prestressed concrete structures.Additionally, an interactive user interface is prototyped using Mock Plus to enhance usability and facilitate intuitive interpretation of stress-related insights.The proposed approach not only advances the automation and intelligence of tensioning monitoring but also provides a robust technical foundation for optimizing prestress management in large-scale infrastructure applications.