<![CDATA[The Indonesian National Army (TNI) is a key element in maintaining national defense. However, challenges in the TNI's performance arise due to the need to modernize the main defense system equipment (alutsista) especially related to the condition of the NPS75 4x4 transport vehicle. One of the problems that often occurs is damage to wheel bearings, which can threaten personnel safety. Traditional methods such as listening to the sound of the engine and carrying out a physical inspection have been used before, but with the development of electronic technology, automatic devices can be created that monitor the condition of vehicle bearings using vibration detection. In this research, we propose the use of the Wemos D1 Mini which is connected to the driver's mobile phone via a WiFi network. This device uses the K-Nearest Neighbor (KNN) method to classify damage to bearings based on learning data. The aim is to assist in automatically detecting and classifying bearing damage categories on NPS75 4x4 transport vehicles, so that timely and targeted maintenance actions can be taken.]]>
Copyrights © 2024
