Delachaux, M. Grégoire (2024) Deep learning for an autonomous brake squeal controller PRE - Research Project, ENSTA.

Full text not available from this repository.

Abstract

This report explores the implementation of a brake controller able to generate a braking instruction optimizing braking efficiency, while avoiding dynamic instabili- ties, including brake squealing. Despite the research and progress made on the modeling of brake squeal, many aspects of the phenomenon remain currently unknown, due to the high dimension of this type of problem, This implies that applied research on brake squealing remains mainly experimental. The objective of this project is to apply different machine learning methods to model and solve problems involving brake squealing, solve an optimization problem too: maximize braking efficiency, minimizing brake squeal. In this study, we will firstly try to show that it is possible to use machine learning techniques to create a brake controller that avoids squealing. Then we will focus on the optimization/control part, which will use reinforcement learning techniques to try to predict a complete braking path by optimizing different parameters that will be determined during the study.

Item Type:Thesis (PRE - Research Project)
Uncontrolled Keywords:Braking, squealing, reinforcement learning, data science
Subjects:Information and Communication Sciences and Technologies
ID Code:10123
Deposited By:Grégoire DELACHAUX
Deposited On:03 sept. 2024 09:15
Dernière modification:03 sept. 2024 09:15

Repository Staff Only: item control page