An ANN-Based Short-Term Temperature Forecast Model for Mass Concrete Cooling Control

Concrete temperature control during dam construction (e.g., concrete placement and curing) is important for cracking prevention. In this study, a short-term forecast model mass cooling developed using artificial neural networks (ANN). The development workflow the consists of data integration, preprocessing, construction, application. More than 80 000 monitoring samples are collected by intelligent system in Baihetan Arch Dam, which largest hydropower project world under construction. Machine learning algorithms, including ANN, support vector machines, long memory networks, decision tree structures, compared prediction, ANN determined to be best model. Furthermore, an framework with two hidden layers at intervals one day. root mean square error precision 0.15 °C on average. application blocks verifies that ANN-based can used