In this study, a bridge seismic monitoring system was developed based on smartphones connected together in the same project as a sensor network using a cloud server for easy upload and access to data. Thus, a decentralized structural seismic monitoring network was established using easy-to-install smartphones as both sensing cells and intelligence neurons. A long-term field test of this system was performed on Japan’s Takamatsu bridge. Smartphones with the monitoring application were deployed at six different locations inside the bridge’s concrete box girder. The system was connected to a cloud server for real-time data uploading and remote control. Inconsistent sampling rates and faulty sensor readings were identified to be two major problems with the use of the proposed system; however, correction methods were also proposed accordingly. A few seismic acceleration response records of the Takamatsu bridge were captured during the more than one-year operation period. Dynamic properties extracted from this system were compared with those of reference seismometers to verify its viability and accuracy.

In this study, a simple and customizable convolution neural network framework was used to train a vibration classification model that can be integrated into the measurement application in order to realize accurate and real-time bridge vibration status on mobile platforms. The inputs for the network model are basically the multichannel time-series signals acquired from the built-in accelerometer sensor of smartphones, while the outputs are the predefined vibration categories. To verify the effectiveness of the proposed framework, data collected from long-term monitoring of bridge were used for training a model, and its classification performance was evaluated on the test set constituting the data collected from the same bridge but not used previously for training. An iOS application program was developed on the smartphone for incorporating the trained model with predefined classification labels so that it can classify vibration datasets measured on any other bridges in real-time. The results justify the practical feasibility of using a low-latency, high-accuracy smartphone-based system amid which bottlenecks of processing large amounts of data will be eliminated, and stable observation of structural conditions can be promoted.

近年汎用型の小型無人機（UAV）が個人所有するレベルまで安価となり，安定した飛行で，高品質な映像が容易に取得できるようになった．汎用型UAVのみでの自動パトロール点検などの維持管理手法も考えられるが，この手法の妥当性と活用方法を検討する必要がある．本研究では，橋梁の損傷を検出する効果を検証するため，UAVを用いて実橋梁の飛行撮影を行った．定期点検が実施された実橋梁9橋に対しUAV撮影と画像分類による損傷判定を行い，定期点検より検出した損傷箇所と比較することによって，UAV橋梁撮影による損傷検知手法の効果を検証した．さらに，点検報告書にて報告されている損傷とその画像を用いて，損傷画像分類データベースを作成し，深層学習を用いた橋梁損傷検知を試み，その精度の向上のための画像処理手法を検討した．