Vibration-Based Fault Detection in Drone Using Artificial Intelligence

Recent years have seen a huge increase in the study of drones. There is lot published articles regarding drone, focusing on control optimization, fault detection, safety mechanisms, etc. In most studies focused effects faulty propellers and rotors, there very limited academic research drone arms. this paper, detection based vibration multirotor arms using artificial intelligence (AI) proposed. are some cases which, due to accident, arm crack or loosen. This normally unnoticeable without disassembly, if not taken care of, it would likely resulted sudden loss flight stability, which will lead crash. Different types AI methods incorporated study, namely, fuzzy logic, neuro-fuzzy, neural network (NN). Their results compared determine best method predicting multirotor. Fuzzy logic neuro-fuzzy provided acceptable decision-making, but performance approach depend dataset used because overfit model might give incorrect decision-making. also applies NN technique. Because data collected laboratory environment consideration wind effect, framework more suitable for early prediction before flying outdoor environment.