A Prediction Method for Concrete Mixing Temperature Based on the Fusion of Physical Models and Neural Networks

Lei Zheng^1,*, Hong Pan^2,3, Yuelei Ruan^2,4, Guoxin Zhang¹, Lei Zhang^1,*, Jianda Xin¹, Zhenyang Zhu¹, Jianyao Zhang^2,5, Wei Liu¹
1 State Key Laboratory of Water Cycle and Water Security, China Institute of Water Resources and Hydropower Research, Beijing, 100038, China
2 Zhejiang Jingling Reservoir Co., Ltd., Shaoxing, 312000, China
3 Shaoxing City Cao’e River Basin Management Center, Shaoxing, 312000, China
4 Shaoxing City Jingling Reservoir Management Center, Shaoxing, 312000, China
5 Shaoxing Water Resources and Hydropower Construction Investment Co., Ltd., Shaoxing, 312000, China
* Corresponding Author: Lei Zheng. Email: email ; Lei Zhang. Email: email
(This article belongs to the Special Issue: AI-Enhanced Computational Methods in Engineering and Physical Science)

Computer Modeling in Engineering & Sciences https://doi.org/10.32604/cmes.2025.074651

Received 15 October 2025; Accepted 17 November 2025; Published online 08 December 2025

Download PDF

Abstract

As a critical material in construction engineering, concrete requires accurate prediction of its outlet temperature to ensure structural quality and enhance construction efficiency. This study proposes a novel hybrid prediction method that integrates a heat conduction physical model with a multilayer perceptron (MLP) neural network, dynamically fused via a weighted strategy to achieve high-precision temperature estimation. Experimental results on an independent test set demonstrated the superior performance of the fused model, with a root mean square error (RMSE) of 1.59°C and a mean absolute error (MAE) of 1.23°C, representing a 25.3% RMSE reduction compared to conventional physical models. Ambient temperature and coarse aggregate temperature were identified as the most influential variables. Furthermore, the model-based temperature control strategy reduced costs by 0.81 CNY/m³, showing significant potential for improving resource efficiency and supporting sustainable construction practices.