scholarly journals An Online Iterative Linear Quadratic Approach for a Satisfactory Working Point Attainment at FERMI

Information ◽  
2021 ◽  
Vol 12 (7) ◽  
pp. 262
Author(s):  
Niky Bruchon ◽  
Gianfranco Fenu ◽  
Giulio Gaio ◽  
Simon Hirlander ◽  
Marco Lonza ◽  
...  
Keyword(s):  
Neural Network ◽  
Predictive Control ◽  
Free Electron ◽  
Free Electron Laser ◽  
Model Identification ◽  
Linear Quadratic Regulator ◽  
Particle Accelerators ◽  
Linear Quadratic ◽  
Model Accuracy ◽  
The Neural Network

The attainment of a satisfactory operating point is one of the main problems in the tuning of particle accelerators. These are extremely complex facilities, characterized by the absence of a model that accurately describes their dynamics, and by an often persistent noise which, along with machine drifts, affects their behaviour in unpredictable ways. In this paper, we propose an online iterative Linear Quadratic Regulator (iLQR) approach to tackle this problem on the FERMI free-electron laser of Elettra Sincrotrone Trieste. It consists of a model identification performed by a neural network trained on data collected from the real facility, followed by the application of the iLQR in a Model-Predictive Control fashion. We perform several experiments, training the neural network with increasing amount of data, in order to understand what level of model accuracy is needed to accomplish the task. We empirically show that the online iLQR results, on average, in fewer steps than a simple gradient ascent (GA), and requires a less accurate neural network to achieve the goal.

scholarly journals Adaptive dynamic programming-based controller with admittance adaptation for robot–environment interaction

2020 ◽  
Vol 17 (3) ◽  
pp. 172988142092461
Author(s):  
Hong Zhan ◽  
Dianye Huang ◽  
Zhaopeng Chen ◽  
Min Wang ◽  
Chenguang Yang
Keyword(s):  
Neural Network ◽  
Dynamic Programming ◽  
Linear Quadratic Regulator ◽  
Adaptive Dynamic Programming ◽  
Environment Interaction ◽  
Linear Quadratic ◽  
Adaptive Dynamic ◽  
The Neural Network ◽  
Network Weight ◽  
The Stability

The problem of optimal tracking control for robot–environment interaction is studied in this article. The environment is regarded as a linear system and an admittance control with iterative linear quadratic regulator method is obtained to guarantee the compliant behaviour. Meanwhile, an adaptive dynamic programming-based controller is proposed. Under adaptive dynamic programming frame, the critic network is performed with radial basis function neural network to approximate the optimal cost, and the neural network weight updating law is incorporated with an additional stabilizing term to eliminate the requirement for the initial admissible control. The stability of the system is proved by Lyapunov theorem. The simulation results demonstrate the effectiveness of the proposed control scheme.

scholarly journals Neural Network Based Contact Force Control Algorithm for Walking Robots

Sensors ◽  
2021 ◽  
Vol 21 (1) ◽  
pp. 287
Author(s):  
Byeongjin Kim ◽  
Soohyun Kim
Keyword(s):  
Neural Network ◽  
Contact Force ◽  
Force Control ◽  
Control Algorithm ◽  
Position Control ◽  
Linear Quadratic Regulator ◽  
Walking Robots ◽  
Test Model ◽  
Linear Quadratic ◽  
Contact Force Control

Walking algorithms using push-off improve moving efficiency and disturbance rejection performance. However, the algorithm based on classical contact force control requires an exact model or a Force/Torque sensor. This paper proposes a novel contact force control algorithm based on neural networks. The proposed model is adapted to a linear quadratic regulator for position control and balance. The results demonstrate that this neural network-based model can accurately generate force and effectively reduce errors without requiring a sensor. The effectiveness of the algorithm is assessed with the realistic test model. Compared to the Jacobian-based calculation, our algorithm significantly improves the accuracy of the force control. One step simulation was used to analyze the robustness of the algorithm. In summary, this walking control algorithm generates a push-off force with precision and enables it to reject disturbance rapidly.

Fuzzy neural network control algorithm for asymmetric building structure with active tuned mass damper

2020 ◽  
Vol 26 (21-22) ◽  
pp. 2037-2049
Author(s):  
Xiao Yan ◽  
Zhao-Dong Xu ◽  
Qing-Xuan Shi
Keyword(s):  
Neural Network ◽  
Control System ◽  
Fuzzy Neural Network ◽  
Linear Quadratic Regulator ◽  
Tuned Mass Damper ◽  
Linear Quadratic ◽  
Mass Damper ◽  
Fuzzy Neural ◽  
Neural Network Algorithm ◽  
Damper Control

Asymmetric structures experience torsional effects when subjected to seismic excitation. The resulting rotation will further aggravate the damage of the structure. A mathematical model is developed to study the translation and rotation response of the structure during seismic excitation. The motion equations of the structures which cover the translation and rotation are obtained by the theoretical derivations and calculations. Through the simulated computation, the translation and rotation response of the structure with the uncontrolled system, the tuned mass damper control system, and active tuned mass damper control system using linear quadratic regulator algorithm are compared to verify the effectiveness of the proposed active control system. In addition, the linear quadratic regulator and fuzzy neural network algorithm are used to the active tuned mass damper control system as a contrast group to study the response of the structure with different active control method. It can be concluded that the structure response has a significant reduction by using active tuned mass damper control system. Furthermore, it can be also found that fuzzy neural network algorithm can replace the linear quadratic regulator algorithm in an active control system. Because fuzzy neural network algorithm can control the process on an uncertain mathematical model, it has more potential in practical applications than the linear quadratic regulator control method.

scholarly journals Optimal Attack against Autoregressive Models by Manipulating the Environment

2020 ◽  
Vol 34 (04) ◽  
pp. 3545-3552
Author(s):  
Yiding Chen ◽  
Xiaojin Zhu
Keyword(s):  
Predictive Control ◽  
Linear Models ◽  
Nonlinear Models ◽  
Linear Quadratic Regulator ◽  
Black Box ◽  
Combine System ◽  
Linear Quadratic ◽  
Time Series Forecast ◽  
Forecast Models ◽  
Adversarial Attack

We describe an optimal adversarial attack formulation against autoregressive time series forecast using Linear Quadratic Regulator (LQR). In this threat model, the environment evolves according to a dynamical system; an autoregressive model observes the current environment state and predicts its future values; an attacker has the ability to modify the environment state in order to manipulate future autoregressive forecasts. The attacker's goal is to force autoregressive forecasts into tracking a target trajectory while minimizing its attack expenditure. In the white-box setting where the attacker knows the environment and forecast models, we present the optimal attack using LQR for linear models, and Model Predictive Control (MPC) for nonlinear models. In the black-box setting, we combine system identification and MPC. Experiments demonstrate the effectiveness of our attacks.

DEPTH CONTROL OF AN UNDERWATER REMOTELY OPERATED VEHICLE USING NEURAL NETWORK PREDICTIVE CONTROL

2015 ◽  
Vol 74 (9) ◽  
Author(s):  
Mohd Shahrieel Mohd Aras ◽  
Shahrum Shah Abdullah ◽  
Ahmad Fadzli Nizam Abdul Rahman ◽  
Norhaslinda Hasim ◽  
Fadilah Abdul Azis ◽  
...  
Keyword(s):  
Neural Network ◽  
Predictive Control ◽  
Fuzzy Logic Controller ◽  
Pi Controller ◽  
System Response ◽  
Linear Quadratic ◽  
Remotely Operated Vehicle ◽  
Depth Control ◽  
Linear Quadratic Regulation ◽  
Neural Network Predictive Control

This paper investigates the depth control of an unmanned underwater remotely operated vehicle (ROV) using neural network predictive control (NNPC). The NNPC is applied to control the depth of the ROV to improve the performances of system response in terms of overshoot. To assess the viability of the method, the system was simulated using MATLAB/Simulink by neural network predictive control toolbox. In this paper also investigates the number of data samples (1000, 5000 and 10,000) to train neural network. The simulation reveals that the NNPC has the better performance in terms of its response, but the execution time will be increased. The comparison between other controller such as conventional PI controller, Linear Quadratic Regulation (LQR) and fuzzy logic controller also covered in this paper where the main advantage of NNPC is the fastest system response on depth control. 

scholarly journals Trajectory Tracking and Stabilization of a Quadrotor Using Model Predictive Control of Laguerre Functions

2015 ◽  
Vol 2015 ◽  
pp. 1-11 ◽  
Author(s):  
Mapopa Chipofya ◽  
Deok Jin Lee ◽  
Kil To Chong
Keyword(s):  
State Space ◽  
Predictive Control ◽  
Trajectory Tracking ◽  
Linear Quadratic Regulator ◽  
Laguerre Functions ◽  
Linear Quadratic ◽  
Model Predictive Controller ◽  
Predictive Controller ◽  
Linear State ◽  
Quadrotor System

This paper presents a solution to stability and trajectory tracking of a quadrotor system using a model predictive controller designed using a type of orthonormal functions called Laguerre functions. A linear model of the quadrotor is derived and used. To check the performance of the controller we compare it with a linear quadratic regulator and a more traditional linear state space MPC. Simulations for trajectory tracking and stability are performed in MATLAB and results provided in this paper.

scholarly journals LQR optimized BP neural network PI controller for speed control of brushless DC motor

2020 ◽  
Vol 12 (10) ◽  
pp. 168781402096898
Author(s):  
Tingting Wang ◽  
Hongzhi Wang ◽  
Huangshui Hu ◽  
Chuhang Wang
Keyword(s):  
Neural Network ◽  
Back Propagation ◽  
Linear Quadratic Regulator ◽  
Speed Control ◽  
Response Speed ◽  
Back Propagation Neural Network ◽  
Pi Controller ◽  
Bldc Motor ◽  
Linear Quadratic ◽  
Brushless Dc

This paper proposes a linear quadratic regulator (LQR) optimized back propagation neural network (BPNN) PI controller called LN-PI for the speed control of brushless direct current (BLDC) motor. The controller adopts BPNN to adjust the gain [Formula: see text] and [Formula: see text] of PI, which improves the dynamic characteristics and robustness of the controller. Moreover, LQR is adopted to optimize the output of BPNN so as to make it close to the target PI gains. Finally, the optimized control output is inputted into the BLDC motor system to achieve speed control. The performance analysis of the proposed controller is presented to compare with traditional PI controller, neural network PI controller and LQR optimized PI controller under MATLAB/Simulink, the results shows that the proposed controller effectively improves the response speed, reduces the steady-state error and enhances the anti-interference ability.

EXPERIMENTAL ANALYSIS OF HOMEOSTATIC-INSPIRED MOTION CONTROLLER FOR A HYBRID-DRIVEN AUTONOMOUS UNDERWATER GLIDER

2015 ◽  
Vol 74 (9) ◽  
Author(s):  
Khalid Isa ◽  
M. R. Arshad
Keyword(s):  
Predictive Control ◽  
Stable State ◽  
Linear Quadratic Regulator ◽  
Water Current ◽  
Underwater Glider ◽  
Motion Controller ◽  
Linear Quadratic ◽  
Controller Performance ◽  
The Face ◽  
Autonomous Underwater Glider

This paper presents a homeostatic controller algorithm and its performance, which controls motion of a hybrid-driven underwater glider. The homeostatic controller is inspired from a biological process known as homeostasis, which maintains a stable state in the face of massively dynamics conditions. The objective is to obtain a better control performance of the glider motion control system with a presence of disturbance, which is the water current. The algorithm was simulated by using MatlabTM. According to the simulation results, in order to achieve the desired pitch angle, the homeostatic controller was able to optimize the glider’s ballast mass and distance of the glider’s sliding mass by reducing the ballast mass up to 17.7% and shortening the sliding mass distance up to 53.7% when compared with the linear-quadratic regulator (LQR) and model predictive control (MPC). Furthermore, validation analyses of the homeostatic controller performance between the simulation and experimental results have shown very satisfactory performance.  

Sign in / Sign up

Export Citation Format

Share Document