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

Abstract

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.

Keywords

• rebar diameter|gwo|svr|reverse learning strategy|random differential mutation strategy