A Machine Learning Framework for Concrete Workability Estimation

混凝土是澳大利亚最常用的建筑材料。该项目旨在开发一种系统，使用先进的机器视觉和机器学习来测量搅拌车运输过程中混凝土的和易性，并提供一种可靠的替代方案，以取代目前由认证测试人员目视测试混凝土和易性的做法。混凝土不符合和易性要求是建筑工地拒收的最常见原因之一，导致大量成本、浪费和延误。多模式数据源将用于提供真实的可靠的工作性估计，使施工团队能够识别和纠正运输过程中的工作性问题，同时持续监测调整效果。

Concrete is the most used construction material in Australia. The project aims to develop a system to measure the workability of concrete in transit in agitator trucks using advanced machine vision and machine learning, and provide a reliable alternative to the current practice of visually testing concrete workability by certified testers. Concrete that fails to meet workability requirements is one of the most frequent reasons for rejection at construction sites, resulting in significant costs, waste, and delays. Multimodal data sources will be used to provide a reliable workability estimate in real time, enabling construction teams to identify and rectify workability issues in transit while continuously monitoring the adjustments effects.