基于实测数据的RCC重力坝浇筑块最高温度预测  

Maximum Temperature Prediction of Pouring Blocks of RCC Gravity Dam Based on Real Data

作　　者：张社荣[1] 史跃洋 孙钰杰 ZHANG She-rong;SHI Yue-yang;SUN Yu-jie(State Key Laboratory of Hydraulic Engineering Simulation and Safety, Tianjin University, Tianjin 300072,China;Power China Beijing Engineering Corporation Limited, Beijing 100024 , China)

机构地区：[1]天津大学水利工程仿真与安全国家重点实验室,天津300072 [2]中国电建集团北京勘测设计研究院有限公司,北京100024

出　　处：《水电能源科学》2019年第9期63-66,82,共5页Water Resources and Power

基　　金：国家自然科学基金创新研究群体科学基金(51321065);国家重点研发计划(2018YFC0406900);天津市应用基础与前沿技术研究计划青年项目(15JCQNJC08000)

摘　　要：混凝土浇筑块内部温度是RCC重力坝施工期重要控制指标之一。浇筑块内部温度过高则形成较大温度梯度,从而产生较大温度应力,导致混凝土表面开裂。控制最高温度以减小温度应力是施工现场常用方法之一。依托施工期实测数据,建立MySQL温度数据库,采用Rough集理论约简条件属性得到最小规则集,并作为预测算法的输入;基于BP神经网络理论建立预测模型,实现对RCC重力坝施工期浇筑块最高温度的预测,并进行预警。模型预测结果可指导施工,做到"事前"感知,提升RCC重力坝浇筑质量。The internal temperature of concrete pouring blocks is one of the important quality control indicators during the construction of RCC gravity dam.High temperature in concrete blocks results in large temperature gradient,which results in large thermal stress and surface cracking of concrete.Keeping the maximum temperature to reduce temperature stress is one of the common methods during on-site construction.Based on the observed data,the MySql temperature database were established.The rough set theory was used to reduce the conditional attributes to get the minimum set,which was used as the input of the algorithm.The BP neural network was used to establish model for predicting the maximum temperature of concrete pouring blocks.The platform could forewarn when temperature exceeded standard.The study can provide guidance for construction,control before construction and improve the pouring quality of RCC gravity dam.

关 键 词：RCC重力坝 大坝温控 最高温度预测 ROUGH集理论 BP神经网络 

分 类 号：TV642.3[水利工程—水利水电工程]