论文部分内容阅读
鉴于在坝体混凝土开仓前准确预测新浇筑混凝土最高温度对防止大坝开裂的重要性,基于BP神经网络原理,以混凝土浇筑温度和冷却水管布置方式、通水温度、通水流量及气温、浇筑层厚度、混凝土龄期7个因素作为输入层,以实测混凝土浇筑仓内最高温度为输出层,利用Matlab神经网络工具箱,建立了新浇筑混凝土最高温度的BP神经网络预测模型,并通过实例对模型进行了验证分析。结果表明,冬季、夏季浇筑仓内混凝土最高温度的预测值和实测值之间的误差均约为0.5℃,二者吻合较好,可见该模型满足实际工程要求,也说明了BP神经网络在预测新浇筑混凝土最高温度方面具有可行性和实用性。
Considering the importance of accurately predicting the maximum temperature of newly poured concrete to prevent dam cracking before the dam concrete opening, based on BP neural network theory, concrete placement temperature and cooling water pipe arrangement, water temperature, water flow and temperature, Pouring layer thickness and concrete age as input layer, the maximum temperature of concrete placing tank was measured as the output layer, and the BP neural network prediction model of the maximum pouring concrete temperature was established by Matlab neural network toolbox. Through the example The model was verified and analyzed. The results show that the error between the predicted value and the measured value of the concrete temperature in the pouring warehouse in winter and summer is about 0.5 ℃, which shows that the model meets the requirements of the actual project. It also shows that the BP neural network New pouring concrete maximum temperature is feasible and practical.