Vibration-Based Fault Detection in Drone using Artificial Intelligence
Mohd Ghazali, Mohamad Hazwan (2021), Vibration-Based Fault Detection in Drone using Artificial Intelligence, Dryad, Dataset, https://doi.org/10.5061/dryad.b5mkkwhdf
Recent years have seen a huge increase in the study of drones. There is a lot of published articles regarding drone, focusing on control optimization, fault detection, safety mechanisms, etc. In fault detection, most of the studies focused on the effects of faulty propellers and rotors, and there is very limited academic research on drone arms. In this paper, a fault detection based on the vibration of the multirotor arms using artificial intelligence (AI) is proposed. There are some cases where due to an accident, the arm
of the multirotor crack or loose. This is normally unnoticeable without disassembly and if not taken care of, it would have likely resulted in a sudden loss of flight stability, which will lead to a crash.
Two types of AI methods are incorporated in this study, namely, fuzzy logic and neuro-fuzzy, using the fuzzy logic and ANFIS toolbox in the MATLAB software, respectively. For the neuro-fuzzy approach, we use 100 and 1000 datasets to determine the effects of the dataset size on the neuro-fuzzy performance. Both datasets are divided into training (80%), testing (10%), and checking data (10%). The guidelines for constructing the AI algorithms are based on the experimental data for five experimental conditions; (i) (a) Original multirotor condition without modifying the multirotor arms, (b) 100% screwed multirotor arms condition (full tighten), (c) 50% screwed multirotor
arms condition (half tighten), (d) 10% screwed multirotor arms condition, and (e) Unscrewed multirotor arm conditions.
Their results are compared to determine the best method in predicting the safety of the multirotor. Both methods provided acceptable decision making but the neuro-fuzzy approach depends on the dataset used as overfit model might give incorrect decision making. Because the vibration data are collected in an indoor environment, this framework is more suitable for early prediction before flying the multirotor outdoor. A video demonstrating the real-time deployment of our proposed method is included in the mp4 format.
For the neuro-fuzzy technique, the input data are randomly generated by the MATLAB software, whereas the output data are determined by the user, based on the experimental works and data. These experimental data are the vibration output data of the multirotor, obtained using the SW420 vibration sensors, placed at the multirotor arms.
|NeuroFuzzy_100_Dataset.xlsx||Contains 100 datasets in the Excel format used to train and evaluate the neuro-fuzzy algorithm|
|NeuroFuzzy_1000_Dataset.xlsx||Contains 1000 datasets in the Excel format used to train and evaluate the neuro-fuzzy algorithm|
|Experimental_Data.xlsx||Contains the raw experimental vibration data in the Excel format|
|AUTHOR_DATASET__ReadmeTemplate.txt||Contains further information regarding the datasets of this study|
|MultirotorDetection.mp4||A video in the mp4 format demonstrating the real-time deployments of our AI algorithms|