scholarly journals Combining support vector machines with linear quadratic regulator adaptation for the online design of an automotive active suspension system

2008 ◽  
Vol 96 ◽  
pp. 012095
Author(s):  
J-S Chiou ◽  
M-T Liu
Keyword(s):  
Support Vector Machines ◽  
Linear Quadratic Regulator ◽  
Active Suspension ◽  
Suspension System ◽  
Support Vector ◽  
Linear Quadratic ◽  
Vector Machines ◽  
Online Design

Improvement on Ride Comfort of Quarter-Car Active Suspension System Using Linear Quadratic Regulator

2018 ◽  
pp. 431-441
Author(s):  
Sharifah Munawwarah Syed Mohd Putra ◽  
Fitri Yakub ◽  
Mohamed Sukri Mat Ali ◽  
Noor Fawazi Mohd Noor Rudin ◽  
Zainudin A. Rasid ◽  
...  
Keyword(s):  
Ride Comfort ◽  
Linear Quadratic Regulator ◽  
Active Suspension ◽  
Suspension System ◽  
Linear Quadratic ◽  
Quarter Car

scholarly journals Online Reinforcement Learning-Based Control of an Active Suspension System Using the Actor Critic Approach

2020 ◽  
Vol 10 (22) ◽  
pp. 8060
Author(s):  
Ahmad Fares ◽  
Ahmad Bani Younes
Keyword(s):  
Reinforcement Learning ◽  
Least Squares Method ◽  
Linear Quadratic Regulator ◽  
Active Suspension ◽  
Suspension System ◽  
Recursive Least Squares ◽  
Linear Quadratic ◽  
Reward Function ◽  
Road Profile ◽  
The One

In this paper, a controller learns to adaptively control an active suspension system using reinforcement learning without prior knowledge of the environment. The Temporal Difference (TD) advantage actor critic algorithm is used with the appropriate reward function. The actor produces the actions, and the critic criticizes the actions taken based on the new state of the system. During the training process, a simple and uniform road profile is used while maintaining constant system parameters. The controller is tested using two road profiles: the first one is similar to the one used during the training, while the other one is bumpy with an extended range. The performance of the controller is compared with the Linear Quadratic Regulator (LQR) and optimum Proportional-Integral-Derivative (PID), and the adaptiveness is tested by estimating some of the system’s parameters using the Recursive Least Squares method (RLS). The results show that the controller outperforms the LQR in terms of the lower overshoot and the PID in terms of reducing the acceleration.

Comparing Classification Methods for Longitudinal fMRI Studies

2010 ◽  
Vol 22 (11) ◽  
pp. 2729-2762 ◽  
Author(s):  
Tanya Schmah ◽  
Grigori Yourganov ◽  
Richard S. Zemel ◽  
Geoffrey E. Hinton ◽  
Steven L. Small ◽  
...  
Keyword(s):  
Support Vector Machines ◽  
Binary Classification ◽  
Stroke Recovery ◽  
Support Vector ◽  
Linear Quadratic ◽  
Restricted Boltzmann Machines ◽  
K Nearest Neighbors ◽  
Vector Machines ◽  
Out Of Sample ◽  
Classification Tasks

We compare 10 methods of classifying fMRI volumes by applying them to data from a longitudinal study of stroke recovery: adaptive Fisher's linear and quadratic discriminant; gaussian naive Bayes; support vector machines with linear, quadratic, and radial basis function (RBF) kernels; logistic regression; two novel methods based on pairs of restricted Boltzmann machines (RBM); and K-nearest neighbors. All methods were tested on three binary classification tasks, and their out-of-sample classification accuracies are compared. The relative performance of the methods varies considerably across subjects and classification tasks. The best overall performers were adaptive quadratic discriminant, support vector machines with RBF kernels, and generatively trained pairs of RBMs.

Optimal Controller Design For A Railway Vehicle Suspension System Using Particle Swarm Optimization

2012 ◽  
Author(s):  
Arfah Syahida Mohd Nor ◽  
Hazlina Selamat ◽  
Ahmad Jais Alimin
Keyword(s):  
Particle Swarm Optimization ◽  
Particle Swarm ◽  
Linear Quadratic Regulator ◽  
Active Suspension ◽  
Suspension System ◽  
Railway Vehicle ◽  
Linear Quadratic ◽  
Swarm Optimization ◽  
Suspension Control ◽  
Trial And Error Method

This paper presents the design of an active suspension control of a two–axle railway vehicle using an optimized linear quadratic regulator. The control objective is to minimize the lateral displacement and yaw angle of the wheelsets when the vehicle travels on straight and curved tracks with lateral irregularities. In choosing the optimum weighting matrices for the LQR, the Particle Swarm Optimization (PSO) method has been applied and the results of the controller performance with weighting matrices chosen using this method is compared with the commonly used, trial and error method. The performance of the passive and active suspension has also been compared. The results show that the active suspension system performs better than the passive suspension system. For the active suspension, the LQR employing the PSO method in choosing the weighting matrices provides a better control performance and a more systematic approach compared to the trial and error method. Key words: active suspension control, two–axle railway vehicle, linear quadratic regulator, particle swarm optimization

scholarly journals Quarter car model optimization of active suspension system using fuzzy PID and linear quadratic regulator controllers

2021 ◽  
Vol 6 (3) ◽  
pp. 088-097
Author(s):  
Abdussalam Ali Ahmed
Keyword(s):  
Control System ◽  
Linear Quadratic Regulator ◽  
Active Suspension ◽  
Suspension System ◽  
Fuzzy Pid ◽  
Linear Quadratic ◽  
Fuzzy Pid Control ◽  
Quarter Car Model ◽  
Car Model ◽  
Quarter Car

The primary objective of this paper is to improve the performance of a car's active suspension system and control the vibrations that occurred in the car's using two well-known control technologies, namely the Linear Quadratic Regulator (LQR) and fuzzy PID control. When the car suspension is designed, a quarter car model with two degrees of freedom is used. A complete control system is needed to provide the desired suspension performance and characteristics such as passenger comfort, road handling, and suspension deflection, this control system performed using the MATLAB/SIMULINK and includes three parts: input signals (actuator force and road profile), Controller part, and the suspension system model. The simulation results from the implemented Simulink models show a comparison between the uncontrolled suspension system and the suspension system with a fuzzy PID controller and the active suspension system of the car based on the linear-quadratic regulator, and it is explained thoroughly.

scholarly journals OPTIMAL CONTROLLER DESIGN FOR ACTIVE SUSPENSION SYSTEM ON CARS

2020 ◽  
Vol 225 (13) ◽  
pp. 107-113
Author(s):  
Vũ Văn Tấn
Keyword(s):  
Controller Design ◽  
Linear Quadratic Regulator ◽  
Active Suspension ◽  
Suspension System ◽  
Optimal Controller ◽  
Linear Quadratic ◽  
Linear Quadratic Gaussian

Hệ thống treo là một trong những bộ phận quan trọng nhất trong thiết kế ô tô và là yếu tố quyết định đến sự thoải mái của lái xe, hành khách (độ êm dịu) và giữ được bám giữa lốp và mặt đường (độ an toàn). Bài báo này giới thiệu một mô hình ¼ ô tô có 2 bậc tự do sử dụng hệ thống treo chủ động với hai bộ điều khiển tối ưu: linear quadratic regulator và linear quadratic gaussian (linear quadratic regulator kết hợp với bộ quan sát Kalman-Bucy). Bằng cách sử dụng bộ quan sát Kalman-Bucy, số lượng cảm biến dùng để đo đạc các tín hiệu đầu vào của bộ điều khiển linear quadratic regulator đã được giảm thiểu tối đa chỉ còn các cảm biến thông thường như gia tốc của khối lượng được treo. Độ êm dịu và an toàn chuyển động khi ô tô sử dụng hệ thống treo chủ động được so sánh với ô tô sử dụng hệ thống treo bị động thông thường thông qua dịch chuyển của khối lượng được treo và gia tốc của nó. Kết quả mô phỏng đã thể hiện rõ giá trị sai lệch bình phương trung bình của gia tốc dịch chuyển thân xe với hệ thống treo tích cực điều khiển tối ưu linear quadratic regulator, linear quadratic gaussian đã giảm khoảng 20% so với ô tô sử dụng hệ thống treo bị động.

Sign in / Sign up

Export Citation Format

Share Document