Optimisasi steering control mobil listrik auto pilot menggunakan adaptive neuro-fuzzy inference system (ANFIS) dan imperalist competitive algorithm (ICA)

Ali, Machrus (2015) Optimisasi steering control mobil listrik auto pilot menggunakan adaptive neuro-fuzzy inference system (ANFIS) dan imperalist competitive algorithm (ICA). Masters thesis, Institut Teknologi Sepuluh Nopember.

[img]
Preview
Text
undergraduated thesis.pdf

Download (6MB) | Preview

Abstract

Steering Control adalah sistem kemudi yang dirancang untuk akurasi pergerakan steer terhadap lintasan kendaraan dan memperingan sistem kemudi. Pada penelitian ini sistem kemudi menggunakan Adaptive Neuro-Fuzzy Inference System (ANFIS). ANFIS dituning dari data training Proportional Integral Derivative (PID) dengan Imperalist Competitive Algorithm (ICA). Adaptive Neuro-Fuzzy Inference System (ANFIS) digunakan untuk mengendalikan Lateral Motion pada model kendaraan. Pada penelitian ini akan dikembangkan model Fully Automatic Steer By Wire System menggunakan 10 Degree Of Freedom (DOF) terdiri dari 7-DOF Vehicle Ride Model dan 3-DOF Vehicle Handling Model. Dari hasil ICA dibandingkan dengan Firefly Algorithm (FA), Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO), Bat Algorithm (BA) menujukkan hasil yang paling baik. Dari hasil simulasi didapatkan bahwa PIDICA jika dibandingkan dengan Firefly Algorithm (FA), Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO), Bat Algorithm (BA) menujukkan hasil yang paling baik. Pada kecepatan default (13.8 km/h) didapatkan nilai kp = 584,0150, ki = 4,1046, kd = 0,2014 dan mampu mengontrol dengan kecpatan mencapai 69,0 km/h dengan overshot terkecil, yaitu 0,00621 pada C-RMS Error. Jika dibandingkan dengan hasil ANFIS hasil trainning data PID-ICA, hasil ANFIS hampir sama atau sedikit lebih halus dengan overshot 0,00507 pada C-RMS Error meskipun ANFIS bertahan sampai kecepatan dibawah 69,0 km/h. ================================================================================================== Steering Control is a steering system designed to steer the movement accuracy of the trajectory of the vehicle and lighten the steering system. In this study, the steering system using Adaptive Neuro-Fuzzy Inference System (ANFIS). ANFIS tuned Proportional Integral Derivative (PID) of training data with Imperialist Competitive Algorithm (ICA). Adaptive Neuro-Fuzzy Inference System (ANFIS) is used to control the Lateral Motion on the vehicle model. This research will be developed models Fully Automatic Steer By Wire System is represented in a simulation of the active steering control using vehicle models with 10 Degree Of Freedom (DOF) is composed of 7-DOF Model Vehicle Ride and Handling 3-DOF Vehicle Model. ICA results compared with Firefly Algorithm (FA), Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO), Bat Algorithm (BA) showed the best result. From the simulation results showed that the PID-ICA When compared with Firefly Algorithm (FA), Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO), Bat Algorithm (BA) showed the best result. In the default speed (13.8 km/h) obtained value Kp = 584,0150, Ki = 4,1046, Kd = 0,2014 and able to control the speed reaches 69.0 Km/h with the smallest overshot, that is 0.00621 on C-RMS Error. When compared with the results of ANFIS training results of data PID-ICA, the results of ANFIS softer with 0.00507 overshot the C-RMS Error although ANFIS lasted until the speed below 69,0 Km/h.

Item Type: Thesis (Masters)
Additional Information: RTE 629.831 2 Ali o
Uncontrolled Keywords: Vehicle, Lateral Motion, PID, ANFIS, ICA ============================================================================================== Vehicle, Lateral Motion, PID, ANFIS, ICA
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK1001 Production of electric energy or power
T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK2785 Electric motors, Induction.
Divisions: Faculty of Electrical Technology > Electrical Engineering > 20101-(S2) Master Thesis
Depositing User: - Taufiq Rahmanu
Date Deposited: 01 Apr 2019 02:57
Last Modified: 01 Apr 2019 02:57
URI: http://repository.its.ac.id/id/eprint/62658

Actions (login required)

View Item View Item