Scholarlink

<p>During the construction of mass concrete, thermal cracking can occur due to temperature gradients, significantly affecting structural stability. To mitigate thermal cracking, accurately predicting concrete temperature and monitoring its internal thermal evolution during construction are essential. This study develops a PO-BP concrete temperature prediction model based on temperature monitoring data collected during the construction of an arch dam. The method employs a novel meta-heuristic algorithm called the Parrot Optimizer (PO) to perform global optimization of the initial weights and biases in the BP network. By analyzing factors influencing concrete temperature, six input parameters are selected: ambient temperature, initial concrete temperature, cooling water flow, inlet water temperature, concrete age, and adiabatic temperature rise. The influence of each input parameter on the concrete temperature is quantified using Sobol' global sensitivity analysis. Prediction accuracy of five models—PO-BP, BP, CNN, LSTM, and SVR—is compared using evaluation metrics. The results show that the PO-BP model delivers the best prediction accuracy and stability on the test set (R<sup>2</sup> = 0.983 ± 0.007, RMSE = 0.265 ± 0.037&#xa0;°C, MAE = 0.184 ± 0.022&#xa0;°C). This confirms its feasibility for predicting concrete temperature. Further detailed analysis of the PO-BP and BP prediction outcomes reveals that PO reduces extreme errors in the BP model and improves model stability. This study provides a high-accuracy predictive tool for concrete temperature during arch-dam construction. Using these predictions, it guides the implementation of temperature-control measures. This approach contributes to better prevention of thermal cracks in dam concrete. </p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Concrete temperature prediction model for arch dam construction based on a parrot optimizer-back propagation neural network

  • 期刊论文

  • 发表日期：

    2026年4月29日

查看全文
  • Haofeng Guo,
  • Feng Wang,
  • Xueli Liu,
  • Wenjie Zhou,
  • Wenjun Deng

摘要

During the construction of mass concrete, thermal cracking can occur due to temperature gradients, significantly affecting structural stability. To mitigate thermal cracking, accurately predicting concrete temperature and monitoring its internal thermal evolution during construction are essential. This study develops a PO-BP concrete temperature prediction model based on temperature monitoring data collected during the construction of an arch dam. The method employs a novel meta-heuristic algorithm called the Parrot Optimizer (PO) to perform global optimization of the initial weights and biases in the BP network. By analyzing factors influencing concrete temperature, six input parameters are selected: ambient temperature, initial concrete temperature, cooling water flow, inlet water temperature, concrete age, and adiabatic temperature rise. The influence of each input parameter on the concrete temperature is quantified using Sobol' global sensitivity analysis. Prediction accuracy of five models—PO-BP, BP, CNN, LSTM, and SVR—is compared using evaluation metrics. The results show that the PO-BP model delivers the best prediction accuracy and stability on the test set (R2 = 0.983 ± 0.007, RMSE = 0.265 ± 0.037 °C, MAE = 0.184 ± 0.022 °C). This confirms its feasibility for predicting concrete temperature. Further detailed analysis of the PO-BP and BP prediction outcomes reveals that PO reduces extreme errors in the BP model and improves model stability. This study provides a high-accuracy predictive tool for concrete temperature during arch-dam construction. Using these predictions, it guides the implementation of temperature-control measures. This approach contributes to better prevention of thermal cracks in dam concrete.