Fitness function determination of uav anomaly detection in large data set via pso

Fatimah, Daing Jamil (2022) Fitness function determination of uav anomaly detection in large data set via pso. College of Engineering, Universiti Malaysia Pahang.

EA18061_FATIMAH DAING JAMIL_THESIS - Fatimah Daing.pdf - Accepted Version

Download (2MB) | Preview


This project is based on fitness function determination of Unmanned Aerial Vehicle (UAV) anomaly detection in large data set. Fitness function is a solution to the issue as input and outputs how "fit" or "excellent" the answer is with regard to the problem under discussion. Based on previous research there are limited used of Particle Swarm Optimization (PSO). In this project, by using the PSO method define the fault of motor or blade by detecting it with acceleration, it is measure of how quickly speed changes with time. The measure of acceleration is expressed in units of (metres per second) per second or metres per second squared (m/s2). PSO method along with the monitoring based, can identify where exactly the fault has happened. Vibration velocity will be increase about two times from the normal velocity if the fault detected. To reduce the costing part of the Unmanned Aerial Vehicle (UAV) testing and detection of fault, the data is collected by using software in the loop with three program such as mission planner, ardupilot and flight gear. Through the simulation, that has been done it is verified by using PSO the fault occur at the motor/blade of UAV can be detected with a true positive detection rate of 76%.

Item Type: Undergraduates Project Papers
Additional Information: SV: Dr. Mohammad Fadhil Bin Abas
Uncontrolled Keywords: uav anomaly detection
Subjects: T Technology > TA Engineering (General). Civil engineering (General)
T Technology > TK Electrical engineering. Electronics Nuclear engineering
Faculty/Division: College of Engineering
Depositing User: Mr. Nik Ahmad Nasyrun Nik Abd Malik
Date Deposited: 25 Oct 2023 01:36
Last Modified: 25 Oct 2023 01:36
Download Statistic: View Download Statistics

Actions (login required)

View Item View Item