The damage investigation and inspection methods for infrastructures performed in small-scale (type III) facilities usually involve a visual examination by an inspector using surveying tools (e.g., cracking, crack microscope, etc.) in the field. These methods can interfere with the subjectivity of the inspector, which may reduce the objectivity and reliability of the record. Therefore, a new image analysis technique is needed to automatically detect cracks and analyze the characteristics of the cracks objectively. In this study, an image analysis technique using deep learning is developed to detect cracks and analyze characteristics (e.g., length, and width) in images for small-scale facilities. Three stages of image processing pipeline are proposed to obtain crack detection and its characteristics. In the first and second stages, two-dimensional convolutional neural networks are used for crack image detection (e.g., classification and segmentation). Based on convolution neural network for the detection, hierarchical feature learning architecture is applied into our deep learning network. After deep learning-based detection, in the third stage, thinning and tracking algorithms are applied to analyze length and width of crack in the image. The performance of the proposed method was tested using various crack images with label and the results showed good performance of crack detection and its measurement.

Typically, the operational lifetime of underground concrete structures is several decades. At present, many such structures are approaching their original life expectancy. In this stage, the essential functionality of the structures may be considerably degraded, leading to various safety hazards such as collapse roof and tunnel flooding. In general, to overcome such problems, the maintenance of underground structures has been conducted through manual subjective inspections so far. However, recently, several objective inspection technologies have been actively developed by fusing artificial intelligence and imaging techniques recently. In particular, deep learning algorithms have been developed to detect concrete cracks, based on a large amount of data for supervised learning, including numerous labeled images. Such data acquisition requires considerable time and effort. To reduce these costs, in this study, multiscale and adversarial learning techniques were applied to realize crack detection. A total of 1,200 labeled data and 3,000 unlabeled data were used to implement and verify the proposed method. The multiscale segmentation neural network, discriminator neural network, and adversarial learning technique were used to realize accurate crack detection, enhance the learning performance, and ensure the efficiency of training data, respectively. The resulting algorithm had a pixel accuracy, mean intersection over union, frequency weighted intersection over union, and F1 score of 98.176%, 88.936%, 96.525%, and 88.789%, respectively. The proposed technique can be used to examine the conditions to ensure the safe maintenance of aging structures.

The functional performance of concrete structures degrades over time as a result of continuous loads, stress fatigue, and external environmental changes. Thus, periodic diagnoses and inspections are essential because such conditions can eventually lead to disaster. Hence, the detection of cracks in concrete is a key component of structural management. In recent years, deep-learning-based computer vision technologies have emerged as a promising trend and have been actively used for crack detection. Unfortunately, the performance of existing crack detection technologies decreases under environmental conditions that vary widely. To resolve this issue, we propose a new deep neural network that applies an optimal mixing ratio of training data to improve recognition performance alongside an adversarial learning-based balanced ensemble discriminator network. Furthermore, a method to reconstruct the 3-dimensional shape of cracks is proposed using a stereo-vision-based triangulation measurement technique that determines the size of detected cracks. Experimental results show that the proposed algorithm achieved a crack detection performance with a mean intersection-over-union of 84.53% and an F1 score of 82.91%. The proposed inspection technology for concrete structures is expected to be implemented in the future in connection with various automation techniques.

Fill dam structures are generally considered safe, but frequent heavy rainfall in recent years due to climate change has increased their risk of collapse. Technologies for the monitoring and safety management of these structures have attracted considerable attention, and methods to utilize technologies such as artificial intelligence (AI) and Internet of Things (IoT) for maintenance have been investigated. However, the measurement and communication processes of sensors used in the IoT technology are prone to measurement errors. Moreover, the communication environment and frequency range used by unlicensed operators vary within a country. Technologies for accurate interpretation of measurement results and optimal communication are required to address these issues. In this study, a technology for dam safety management and communication environment optimization was developed using AIoT (AI+IoT), and its field applicability was verified.

The new Austrian tunnelling method (NATM) and tunnel boring machine (TBM) are methods for excavating underground spaces. The NATM construction method has noise and vibration problems, and excavation using TBM has the disadvantage of high initial cost and is limited by ground conditions. A parallel TBM and NATM construction method has been developed to overcome these limitations. However, research on the TBM and NATM parallel construction method is lacking, and it is crucial to identify the applicability of the TBM and NATM parallel construction method in advance by applying it to various ground and blasting conditions. In this study, based on the vibration measurement data of the excavation site using the NATM construction method, the vibration measurement values generated when excavating the top surface using the existing NATM construction method and the TBM and NATM parallel construction methods were compared. Lastly, the vibration reduction effect of the two construction methods was analysed according to the tunnel excavation depth and tunnel size through 3D numerical analysis. As the depth of tunnel excavation increases, the vibration at the ground surface is reduced by up to 83%. In addition, as the ratio of the size of the blasting surface with NATM and the excavation surface with TBM is closer to 1.0, the vibration decreases.