• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.427-427
• /
• 2021

During the rainy season, heavy downpours are always a source of concern for the world. Flooding and heavy rains can devastate communities, disrupt agriculture, and contribute to traffic accidents.. Weir and flow hall effect sensors are the conventional analytical methods for measuring flow rate; in this paper, we analyzed manhole flowrate statistics. The measurement of the flow rate of a notch/weir is a time-consuming task that necessitates continuous mathematical analysis. . We created three types of IoT sensors in this study: (HC-SR04 ultrasonic, YF-S201 magnetic, and HB100 radar), which take the sensor's real-time input signal and estimate the flow using a notch equation and a previously calibrated optimized coefficient of discharge. The proposed systems are cost-effective, but in terms of accuracy, we found that the HC-SR04 ultrasonic sensor is the best of the three systems

• Smart Structures and Systems
• /
• v.24 no.6
• /
• pp.745-757
• /
• 2019

Road surface deteriorations such as potholes have caused motorists heavy monetary damages every year. However, effective road condition monitoring has been a continuing challenge to road owners. Depth cameras have a small field of view and can be easily affected by vehicle bouncing. Traditional image processing methods based on algorithms such as segmentation cannot adapt to varying environmental and camera scenarios. In recent years, novel object detection methods based on deep learning algorithms have produced good results in detecting typical objects, such as faces, vehicles, structures and more, even in scenarios with changing object distances, camera angles, lighting conditions, etc. Therefore, in this study, a Deep Learning Pothole Detector (DLPD) based on the deep region-based convolutional neural network is proposed for autonomous detection of potholes from images. About 900 images with potholes and road surface conditions are collected and divided into training and testing data. Parameters of the network in the DLPD are calibrated based on sensitivity tests. Then, the calibrated DLPD is trained by the training data and applied to the 215 testing images to evaluate its performance. It is demonstrated that potholes can be automatically detected with high average precision over 93%. Potholes can be differentiated from manholes by training and applying a manhole-pothole classifier which is constructed using the convolutional neural network layers in DLPD. Repeated detection of the same potholes can be prevented through feature matching of the newly detected pothole with previously detected potholes within a small region.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.11a
• /
• pp.141-143
• /
• 2014

스마트빌딩에서는 시설물에 대한 효과적인 관리체계 및 안전관리체계를 구축하는 것이 매우 중요하다. 지하 매설관의 경우에는 유속, 유량계 등의 센서를 설치하여 관로 흐름을 상시 감시하며, 노후되거나 슬러지가 축적된 관로는 문제가 발생하기 전에 교체 공사를 지시 할 수 있어야 한다. 본 논문에서는 하수(오수, 우수)도 맨홀 내 정보를 감지하여 실시간으로 전달, 판단, 처리 및 제어 할 수 있는 M2M/IOT 기반의 하수(오수, 우수)도 맨홀 내 모니터링 시스템을 설계 구현한다.

• Journal of Korean Society of Water and Wastewater
• /
• v.28 no.6
• /
• pp.647-655
• /
• 2014

To perform long-term sewer monitoring, It is important to understand the nature of the wastewater flow that occurs at the point on early stage of the monitor and to prevent in advance a problem which may caused. We can infer the flow properties and external factors by analyzing the scatter graph obtained from the measured data flow rate monitoring data since an field external factor affecting the sewage flow is reflected in the flow rate monitoring data. In this study, Selecting the three points having various external factors, and we Inferred the sewer flow characteristics from depth-velocity scatter graph and determined the analysis equation for the dry-weather flow rate data. At the'point 1' expected non-pressure flow, we were able to see the drawdown effect caused by the free fall in the manhole section. At the'point 2', existed weir and sediments, there was backwater effect caused by them, and each of size calculated from the scatter graph analysis were 400 mm and 130 mm. At the'Point 3', there is specific flow pattern that is coming from flood wave propagation generated by the pump station at upstream. In common, adequate equations to explain the dry weather flow data are flume equation and modified manning equation(SS method), and the equations had compatibility for explaining the data because all of $R^2$ values are over 0.95.