Deep Deterministic Policy Gradient-based intelligent control scheme design for DC-DC circuit

In this paper, a new design of the model reference control scheme is proposed in a class of nonlinear strict-feedback system. First, the system is analyzed using Lyapunov stability analysis. Next, a model reference is used to improve system performance. Then, the Integral Square Error (ISE) is considered as a cost function to drive the error between the reference model and the system to zero. After that, a powerful metaheuristic optimization method is used to optimize the parameters of the proposed controller. Finally, the results show that the proposed controller can effectively compensate for the strictly-feedback nonlinear system with more desirable performance.

Download Full-text

Deep Deterministic Policy Gradient Based on Double Network Prioritized Experience Replay

IEEE Access ◽

10.1109/access.2021.3074535 ◽

2021 ◽

pp. 1-1

Author(s):

Chaohai Kang ◽

Chuiting Rong ◽

Weijian Ren ◽

Fengcai Huo ◽

Pengyun Liu

Keyword(s):

Double Network ◽

Policy Gradient ◽

Experience Replay ◽

Gradient Based

Download Full-text

Inverse design of grating couplers using the policy gradient method from reinforcement learning

Nanophotonics ◽

10.1515/nanoph-2021-0332 ◽

2021 ◽

Vol 0 (0) ◽

Author(s):

Sean Hooten ◽

Raymond G. Beausoleil ◽

Thomas Van Vaerenbergh

Keyword(s):

Neural Network ◽

Reinforcement Learning ◽

Gradient Method ◽

Photonic Devices ◽

Inverse Design ◽

Grating Couplers ◽

Electromagnetic Devices ◽

Policy Gradient ◽

Gradient Based ◽

Local Gradient

Abstract We present a proof-of-concept technique for the inverse design of electromagnetic devices motivated by the policy gradient method in reinforcement learning, named PHORCED (PHotonic Optimization using REINFORCE Criteria for Enhanced Design). This technique uses a probabilistic generative neural network interfaced with an electromagnetic solver to assist in the design of photonic devices, such as grating couplers. We show that PHORCED obtains better performing grating coupler designs than local gradient-based inverse design via the adjoint method, while potentially providing faster convergence over competing state-of-the-art generative methods. As a further example of the benefits of this method, we implement transfer learning with PHORCED, demonstrating that a neural network trained to optimize 8° grating couplers can then be re-trained on grating couplers with alternate scattering angles while requiring >10× fewer simulations than control cases.

Download Full-text

Wind Shear Encountered Landing Control Based on CMACs

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.284-287.2351 ◽

2013 ◽

Vol 284-287 ◽

pp. 2351-2355 ◽

Cited By ~ 1

Author(s):

Jih Gau Juang ◽

Chung Ju Cheng ◽

Teng Chieh Yang

Keyword(s):

Intelligent Control ◽

Adaptive Learning ◽

Wind Shear ◽

Learning Rule ◽

Lyapunov Theory ◽

Intelligent Control System ◽

Automatic Landing ◽

Control Scheme ◽

Shear Condition ◽

Landing Control

This paper presents an intelligent control scheme that uses different cerebellar model articulation controllers (CMACs) in aircraft automatic landing control. The proposed intelligent control system can act as an experienced pilot and guide the aircraft landed safely in wind shear condition. Lyapunov theory is applied to obtain adaptive learning rule and stability analysis is also provided. Furthermore, the proposed controllers are implemented in a DSP. The simulations by MatLab are demonstrated.

Download Full-text