The study objective is to establish the learning curve model for precast component productivity in construction, verified using cross-validation empirical data for over 90% of these facilities’ precast component production activities over the past 5 years, with a total of 373,077 datasets across 14 production activities, sorted among a total of 4352 workers. By applying the learning curve theory to the analysis, the results show that relative to the straight-line model, the learning curve was established using exponential models. The exponential model can effectively mitigate the unreasonable fluctuations present in the cubic model’s representations of learning curves during initial training periods. This study therefore suggests the adoption of the Exponential model to model the learning curves for production workers learning to make precast components. The model has a satisfactory degree of fit (R² > 0.88), and the post-cross-validation results also show that the model has a highly accurate prediction capability (MAPE value < 10%). The finding can serve as an important reference for the creation of production personnel allocation plans, personnel reserve plans, and training plans at precast factories in the construction industry.

研究目的是建立建筑预制构件生产率的学习曲线模型，并使用交叉验证经验数据对过去五年中超过90％的这些设施的预制构件生产活动进行验证，该模型共有14个，共373,077个数据集。生产活动，共有4352名工人。通过将学习曲线理论应用到分析中，结果表明，相对于直线模型，学习曲线是使用指数模型建立的。指数模型可以有效地缓解在初始训练期间三次模型的学习曲线表示中出现的不合理波动。因此，这项研究建议采用指数模型为生产工人学习制造预制零件的学习曲线建模。该模型具有令人满意的拟合度（R ²  > 0.88），并且交叉验证后的结果也表明该模型具有高度准确的预测能力（MAPE值<10％）。该发现可为在建筑行业的预制工厂中创建生产人员分配计划，人员储备计划和培训计划提供重要参考。