Weathering tests using monitored steel plates are a widely applied method for evaluating the atmospheric corrosion rate in Japan. To calculate the regional corrosion rate, the corrosion layer on the surface of the steel plate needs to be removed to determine the thinning. However, the process of removing the corrosion layer is time and labor consuming. To tackle this issue, this study proposed an image recognition method based on convolutional neural networks (CNNs) to evaluate the thinning of weathering test samples. To this end, the existing data collected from the weathering tests were reused to generate a dataset named “Corrosion-Fukui” that consisted of 77 raw images labeled with their numerical extent of thinning. To generate more samples for training, a criteria based on thinning extent that classified the raw images into six corrosion levels were defined to implement cropping operation on the raw images with uniform corrosion morphology. Correspondingly, the raw images of the corroded samples with uniform corrosion morphology were chosen as “training” and “validation samples” to be cropped into small pieces labeled with the corrosion levels, whereas other raw images with nonuniform corrosion morphology were chosen as “test samples.” The performance of the proposed baseline model VGGGAP as well as three state-of-art CNN models was cross-validated on the augmented dataset and tested upon the test images using a sliding window method. The evaluation results of the 17 testing samples indicated that the corrosion thinning of the weathering test samples can be directly evaluated more efficiently from digital images using CNNs than using conventional corrosion removal methods.

市町村は多くのインフラを管理しているが，そのメンテナンスに苦労している．特に北陸地方のコンクリート構造物では，塩害やASRによる劣化が生じやすく，早急な対応が望まれる．このような背景を踏まえて本稿では，地元の大学・高専教員が連携して，市町村が管理する道路橋を対象にした，メンテナンスの合理化に向けた支援について論ずる．はじめに，新潟県上越地区・富山県・石川県・福井県の41市町に対してヒアリング調査を実施し，課題とニーズを抽出した．次に，これらを改善すべく，コンクリート橋に対する点検・診断・措置の手順案を策定し，また技術展示会を開催し，さらに実橋を用いた補修効果の評価に取り掛かった．以上により，市町村の実情を起点とした，官学連携による道路橋の維持管理の合理化に向けた実績とその評価を整理した．

This study develops a method to visualize the state of steel-concrete interface with ultrasonic testing. Scattered waves are obtained by the UT pitch-catch mode from the surface of the concrete. Discrete wavelet transform is applied in order to extract echoes scattered from the steel-concrete interface. Then Linearized Inverse Scattering Methods are used for imaging the interface. The results show that LISM with Born and Kirchhoff approximation provide clear images for the target.

This study evaluates the effect of reduction in plate thickness for a steel plate existing in concrete on guided ultrasonic SH (g-SH) waves. It has been found that the time of flight (TOF) increases if the plate thickness is reduced. The parameter investigated in this study is a delay time obtained from a TOF comparison between a healthy and a damaged plate. The wave propagation is simulated by dynamic Finite Element Analysis (FEA). The resulting data are then used to propose a theoretical equation for predicting TOF. The prediction of delay time obtained from the proposed equation is found to be in general agreement, with an error of 10% (or less), when compared with the experiment results, if the thickness reduction is over 3.65mm.