There have been frequent fatal accidents of firefighters at fire scenes. A firefighting robot can be an alternative to humans at a fire scene to reduce accidents. As a critical function of the firefighting robot, it is mandatory to autonomously detect a fire spot and shoot water. In this research, a deep learning model called YOLOv7 was employed based on thermal images to recognize the shape and temperature information of the fire. Based on the results of the test images, which were not used for learning purposes, a recognition rate of 99% was obtained. To track the recognized fire spot, a 2-DOF pan-tilt actuation system with cameras was developed. By using the developed system, a moving target can be tracked with an error of 5%, and a variable target tracking test by alternately covering two target braziers showed that it takes about 1.5 seconds to track changing targets. Through extinguishment experiments with a water spray mounted on the pan-tilt system, it was observed that the temperature of the brazier dropped from 600 degrees to 13 degrees. Based on the obtained data, the feasibility of a robotic firefighting system using image recognition was confirmed.

The large gas turbine rotor used for power generation has a structural characteristic comprising a shaft, disk, and blade assembled to the disk. Because the start/stop is repeated, the tightening force may be reduced in the process of repeating the tightening force between the tie rod and the disk. When the tightening force falls below the threshold, changing the critical speed, increasing the vibration, or in extreme cases, the rotor may loosen and cause a major accident. Also, it is imperative to continuously maintain the proper tightening force because the thread of the tie rod is damaged when the tightening force exceeds the yield stress condition of the tie rod. In this paper, the gas turbine rotor system is modeled and simplified to identify the control variable of the tightening force of the tie rod bolts of the rotor. For verification, a simplified model of the gas turbine rotor was designed, manufactured, and verification tests were conducted to confirm the adequacy of the calculation method. As a result, the tightening force decreased as the stiffness of the pressing disk decreased, so the stiffness of the pressing disk should have a stiffness range similar to that of the tie rod.