基于改进Mask R-CNN的硬化混凝土离析程度评价  

Evaluation of segregation degree of hardening concrete using improved Mask R-CNN

作　　者：任炳昱[1] 叶钲军 王栋[1] 吴斌平[1] 谭尧升 REN Bingyu;YE Zhengjun;WANG Dong;WU Binping;TAN Yaosheng(State Key Laboratory of Hydraulic Engineering Simulation and Safety,Tianjin University,Tianjin 300072;China Three Gorges Projects Development Co.,Ltd.,Chengdu 610041;China Three Gorges Group Corporation,Beijing 100038)

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]中国三峡建工(集团)有限公司,成都610041 [3]中国长江三峡集团有限公司,北京100038

出　　处：《水力发电学报》2022年第5期93-102,共10页Journal of Hydroelectric Engineering

基　　金：国家自然科学基金(51879186,51839007);中国三峡建设管理有限公司科研项目资助(BHT/0835)。

摘　　要：水工混凝土钻孔图像中骨料的精准分割对于硬化混凝土离析评价至关重要。然而,传统的骨料图像分割方法存在精度低和泛化性能差的问题。针对上述问题,本文提出了一种改进Mask R-CNN的硬化混凝土骨料分割模型,通过在Mask R-CNN模型的主干网络中引入高效通道注意力模块(efficient channel attention,ECA)与空间注意力模块(stage attention module,SAM),实现卷积网络对通道与空间权重的自适应调整,从而提升模型对目标骨料边界与位置分布的检测性能;进一步提出硬化混凝土离析程度定量评价方法,通过量化目标骨料的面积、边界以及在高程方向上的分布,实现混凝土离析程度的定量评价。工程案例表明,所提骨料分割模型平均精度(m AP@0.5)达到了0.8752,相比未改进模型提高了4.19%,在多种复杂环境下的分割效果均优于传统骨料图像分割方法,且混凝土离析程度定量评价平均误差仅为4.85%,验证了所提方法的有效性与优越性,为混凝土离析程度科学评价提供了新的技术手段。Accurate segmentation of aggregates in a drilling image of hydraulic concrete is very important for evaluating hardened concrete segregation,but traditional aggregate segmentation methods suffer drawbacks in low accuracy and weak generalization capability.This paper develops an improved Mask R-CNN model for segmenting hardened concrete aggregates by introducing an efficient channel attention module(ECAM)and a stage attention module(SAM)into the backbone Mask R-CNN network,so that its convolutional network can adaptively adjust the weights of the channel and space,significantly improving its capability of detecting the boundary and location distribution of target aggregate.And we work out a new method for the segregation degree of hardened concrete,realizing quantitative evaluation by quantifying the area and boundary of target aggregate and its distribution over different elevation.A case study shows that our aggregate segmentation model has an average accuracy of 0.875,or 4.2%higher than that of Mask R-CNN.In various complicated applications,its segmentation effect is better than that of traditional aggregate segmentation,and its errors of segregation degree is only 4.9%on average,verifying its effectiveness and superiority as a new tool for hardening concrete evaluation.

关 键 词：硬化混凝土 Mask R-CNN 骨料分割 混凝土离析 定量评价 

分 类 号：TV523[水利工程—水利水电工程]