PERANCANGAN NEUROREGULATOR PADA SISTEM PENGEREMAN ANTILOCK

• Main Author: Cordova, Hendra
• Format: Theses
• Language: Indonesia
• Subjects: Teknik (Rekayasa, enjinering dan kegiatan berkaitan)
• Online Access: https://digilib.itb.ac.id/gdl/view/4791
• Institution: Institut Teknologi Bandung

<b>Abstract :</b><p align=\"justify\">ABS (Antilock Brake System) is braking system that avoid the wheels of the car unlock. The performance such as braking time and distance will more further if the wheels of car lock and slip.The main reason is the fiction coefficients between tyre and road surface will degrade when the brakes are applied on slippery surface or during panic braking. The control algorithms have limitid ability to learn how to compensate for wide variety of road conditions. The learning controllers can take enabling in compensate for adverse road conditions. <br /> <br /> These research is a solution for problem above by apply the controller that able to learn based on artificial neural network The advantage of neural network\'s concept in this paper do not learn the rovers dynamics of the plant controlled as usual for control system based neural network controller. The design concept results from the belief that the main objective of the control system design is to \'Jeannine the controller that generate the proper signal to achieve the best performance output plant. Therefore the neural networks training just take a little time (about 300-500 periode) the neural network can get the desired error target (0,02). <br /> <br /> The regulator concept based on neural networks have been applied and take good perfouaace on braking standart such as 20% slip\'s value and keep the maksimum point of braking coefficient for variety adverse road conditions. Instead of this The neuroregulator can keep the l0%-30%o slip. .