SISTEM KONTROL GERAKAN GANTRY PADA RUBBER TYRED GANTRY CRANE BERBASIS MACHINE LEARNING

Abstract

This research aims to design and develop an automatic object recognition system that can control the gantry movement of a Rubber Tyred Gantry Crane (RTGC) using image processing technology based on machine learning. The proposed system consists of several stages, including Red Green Blue (RGB) image processing, object detection within the area using YOLOv5, early warning for detected objects, and relay control based on the detection results. The object detection data is used to control the gantry movement by measuring the distance of the object from the RTGC by defining the object detection area. This control mechanism is implemented through relay settings that activate or deactivate control signals on the Programmable Logic Controller (PLC), which then triggers the slow down and stop functions of the RTGC. The research results show that the designed system is capable of achieving an average detection accuracy of 91.67%. Thus, this system is effective in controlling the relay On-Off based on the objects detected within the RTGC path. Keywords: Crane, Object Detection, Relay Control, Machine Learning