Digital and Predictive Quality Assurance of Ready-Mix Concrete in Large-Scale Construction Projects: Recent Advances and an Integrated Framework

Abstract

Ready-mix concrete (RMC) is a critical construction material for high-rise buildings, bridges, metro systems, airports, industrial facilities and other large-scale projects. Although centralised production improves uniformity and productivity, the final quality of RMC is influenced by variations in constituent materials, aggregate moisture, batching accuracy, admixture dosage, transportation time, concrete temperature, workability loss, placement, compaction and curing. Conventional quality assurance and quality control (QA/QC), based mainly on periodic sampling and compressive-strength testing, remains essential but provides only discrete observations of a continuously varying production and construction process. Recent advances in automated batching, Internet of Things (IoT) sensing, computer vision, artificial intelligence (AI), machine learning (ML), concrete maturity monitoring, Building Information Modelling (BIM) and Digital Twins are creating opportunities to transform RMC quality management from reactive inspection to continuous and predictive assurance. This paper critically reviews these developments and proposes an Integrated Predictive Quality Assurance and Quality Control Framework (IPQCF) for large-scale construction projects. The framework combines material qualification, smart batching, digital batch traceability, transportation monitoring, site acceptance, sensor-assisted curing, statistical process control, predictive analytics and BIM/Digital Twin-based lifecycle documentation. Recent industrial research using 9,007 genuine RMC production records demonstrates the practical feasibility of early compressive-strength prediction, while plant-scale deep-learning studies show the potential of computer vision for continuous workability assessment. The proposed framework is intended to complement, rather than replace, code-prescribed acceptance testing. Integration of established testing procedures with digital monitoring and predictive analytics can improve traceability, identify quality deviations earlier, reduce rework and support more reliable and sustainable concrete construction. Keywords: Ready-mix concrete; quality assurance; quality control; artificial intelligence; machine learning; Internet of Things; computer vision; digital twin; concrete maturity; construction quality.