基于改进灰狼算法优化SVR的混凝土中钢筋直径检测方法

Detection Method of Rebar in Concrete Diameter Based on Improved Grey Wolf Optimizer-based SVR

传统钢筋混凝土检测方法通过线性拟合或标准值查表法只能对钢筋直径做大致估算,无法精确测量。针对钢筋直径检测中样本数据较少、检测结果受到钢筋埋深及相邻钢筋间距的影响而非表现出非线性回归变化的情况,提出了基于改进灰狼算法(Improved Grey Wolf Optimizer,IGWO)优化的支持向量回归机(Support Vector Regression,SVR)检测方法(IGWO-SVR)。首先,通过反向学习策略优化初始化种群分布,改善了灰狼优化算法(Grey Wolf Optimizer,GWO)的全局搜索能力,通过随机差分变异策略扩大狼群动态搜索范围,避免了灰狼优化算法陷入局部最优;然后,将改进后的灰狼优化算法应用于支持向量回归机的核心参数寻优,以改良算法模型的检测性能;最后,与另外3种算法模型的实验结果进行对比分析,结果表明了所提方法在钢筋直径检测中的精度以及优化模型与实际值的拟合度都得到了有效提升。

The traditional reinforced concrete detection method uses linear fitting or standard value look-up table method,which can only roughly estimate the diameter of rebar.In view of the fact that there are few sample data of the diameter detection,and the detection result changes non-linearly due to the influences of the buried depth and the distance between adjacent rebars,a SVR detection method based on IGWO is proposed(IGWO-SVR).Firstly,the inverse learning strategy is used to optimize the initial population distribution,which improves the GWO global search ability.And he random differential mutation strategy is used to expand the search range,which can avoid the GWO algorithm from falling into the local optimum.Then,the IGWO algorithm is applied to the core parameter optimization of the SVR to improve the detection performance.Finally,the comparison and analysis of experimental results with the other three algorithm models show that the accuracy of the proposed method in the detection of rebar diameter has been effectively improved.