Perancangan Fault Tolerant Electronic Speed Control pada UAV Menggunakan Neuro-PID

Risabury, Adzany Tealent (2024) Perancangan Fault Tolerant Electronic Speed Control pada UAV Menggunakan Neuro-PID. Other thesis, Institut Teknologi Sepuluh Nopember.

[thumbnail of 5022201019-Undergraduate_Thesis.pdf] Text
5022201019-Undergraduate_Thesis.pdf - Accepted Version
Restricted to Repository staff only until 1 October 2026.

Download (3MB) | Request a copy

Abstract

Pada era ini, UAV atau Unmanned Aerial Vehicle merupakan pesawat nirawak yang dapat dijalankan secara otomatis dan telah ada banyak perkembangan terkait penelitian tentang topik ini. Salah satu jenis UAV adalah tipe quadcopter yang mana menggunakan empat penggerak rotor untuk menciptakan gaya angkat. Model quadcopter dapat dimodelkan secara matematis menggunakan dinamika posisi dan orientasi dari quadcopter. Pada penelitian ini dirancang sebuah sistem respon terhadap kegagalan menggunakan neural network dan PID. Fungsi dari neural network ini adalah melakukan tuning terhadap controller PID agar dapat diberikan nilai Kp, Ki, dan Kd yang diberikan untuk mengkompensasi kegagalan. Pemodelan terbagi menjadi airframe model yang terdiri dari model kecepatan angular, percepatan angular, dan percepatan linear. Bagian kedua merupakan controller yang terdapat PID sebagai kompensator terhadap masukan sinyal error. Pemodelan terhadap motor juga dilakukan dengan model matematis motor. Pemodelan dan pengujian dilakukan dengan MATLAB/Simulink. Fault Tolerant Controller memiliki masukan sinyal yang diinginkan, sinyal aktual, serta sinyal error dengan keluaran berupa Kp, Ki, dan Kd sebagai tuning PID. Hasil yang didapatkan cukup baik dengan rata-rata MSE terbesar adalah E-04. Performa berjalan dengan cukup baik dan lebih adaptif terhadap kegagalan daripada PID Konvensional.
======================================================================================================================================
In this era, UAVs or Unmanned Aerial Vehicles are unmanned aircraft that can be operated automatically, and there have been many developments related to research on this topic. One type of UAV is the quadcopter, which uses four rotor drives to generate lift. The quadcopter model can be mathematically modeled using the dynamics of the quadcopter's position and orientation. In this study, a system was designed to respond to errors using a neural network and PID controller. The function of the neural network is to tune the PID controller to provide the Kp, Ki, and Kd values needed to compensate for the error. The modeling is divided into an airframe model consisting of the angular velocity model, angular acceleration model, and linear acceleration model. The second part is the controller, which includes the PID as a compensator for the error signal input. The motor is also modeled with a mathematical motor model. Modeling and testing were carried out with MATLAB/Simulink. The Fault Tolerant Controller has desired signal inputs, actual signals, and error signals with outputs in the form of Kp, Ki, and Kd for PID tuning. The results obtained were quite good, with the largest average MSE being E-04. The performance ran quite well and was more adaptive to errors compared to the conventional PID.

Item Type: Thesis (Other)
Uncontrolled Keywords: Fault Tolerant, Unmanned Aerial Vehicle, Artificial Neural Network, Proportional-Integral-Derivative
Subjects: T Technology > T Technology (General) > T57.62 Simulation
T Technology > TJ Mechanical engineering and machinery > TJ217 Adaptive control systems
T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7882.P3 Pattern recognition systems
T Technology > TL Motor vehicles. Aeronautics. Astronautics
T Technology > TL Motor vehicles. Aeronautics. Astronautics > TL152.8 Vehicles, Remotely piloted. Autonomous vehicles.
T Technology > TL Motor vehicles. Aeronautics. Astronautics > TL776 .N67 Quadrotor helicopters--Automatic control
T Technology > TL Motor vehicles. Aeronautics. Astronautics > TL521.3 Automatic Control
Divisions: Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Electrical Engineering > 20201-(S1) Undergraduate Thesis
Depositing User: Adzany Tealent Risabury
Date Deposited: 30 Jul 2024 07:33
Last Modified: 30 Jul 2024 07:33
URI: http://repository.its.ac.id/id/eprint/110359

Actions (login required)

View Item View Item