Tunnel Water Level Detection Using Deep Learning and Intermediary Server
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Tunnel construction sites face challenges in detecting and responding to emergency situations quickly due to the difficulty in monitoring workers in deep and dark environments, and the limitations of wireless communication devices, which can lead to delays in addressing critical situations such as increased water levels during rainfall.
Innovation Solution
A method and apparatus utilizing a deep learning-based system that estimates water levels in tunnels, determines emergency situations by comparing these levels with threshold values, and transmits warning messages to workers' devices, while controlling entrance/exit doors to ensure safety, using a server with location identification, water measurement, and communication units.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If wireless communication devices are used to notify workers in the tunnel, then emergency information can be transmitted to workers, but wireless communication devices do not work properly in the tunnel
Solution Approach 1:
The patent introduces a server as an intermediary between the water level sensor and workers. The server receives water level data, processes it, and sends notifications to workers through alternative communication channels that function reliably in the tunnel environment, bypassing the limitation of direct wireless communication between sensor and worker devices.
2Loss of information
If people go into the tunnel to inform workers of emergency situations, then critical information can be delivered directly to workers, but it is difficult to cope with emergency situations that change in real time
Solution Approach 1:
The system enables self-service emergency notification where the server automatically monitors water levels, detects emergency conditions, and notifies workers without requiring human intervention. This automated process responds instantly to changing conditions, eliminating the time delay associated with manual monitoring and communication.
Solution Approach 2:
The system implements continuous feedback through real-time water level monitoring. The server receives ongoing data from sensors, compares it against threshold values, and automatically adjusts notifications based on the current water level status, ensuring workers receive timely alerts as conditions evolve.
3Measurement precision
If deep learning based learning model is used to estimate water amount information, then water level estimation accuracy is improved, but device complexity increases
Solution Approach 1:
The server acts as an intermediary that hosts and executes the deep learning model remotely. This allows the complex model to run on powerful server infrastructure rather than requiring complex processing capabilities in the tunnel devices, maintaining measurement precision while reducing on-site device complexity.
Data Source
AI summary
Provided is a control method for preventing an accident in a tunnel. In this instance, the control method for preventing an accident in a tunnel includes estimating water amount information flowing into the tunnel based on at least one input information, determining whether it is an emergency situation based on the estimated water amount information, and when the emergency situation is determined, transmitting a warning message to an identification device, and controlling a device for opening and closing an entrance/exit of the tunnel. In this instance, the water amount information flowing into the tunnel is estimated through a deep learning based learning model, and the emergency situation is determined by comparing water level information of the tunnel with a threshold value.