Neural Network Control of a Robot Interacting With an Uncertain Hunt-Crossley Viscoelastic Environment

The objective in this paper is to control a robot as it transitions from a non-contact to a contact state with an unactuated viscoelastic mass-spring system such that the mass-spring is regulated to a desired final position. A nonlinear Hunt-Crossley model, which is physically consistent with the real behavior of the system at contact, is used to represent the viscoelastic contact dynamics. A Neural Network feedforward term is used in the controller to estimate the environment uncertainties, which are not linear-in-parameters. The NN Lyapunov based controller is shown to guarantee uniformly ultimately bounded regulation of the system despite parametric and nonparametric uncertainties in the robot and the viscoelastic environment respectively. The proposed controller only depends on the position and velocity terms, and hence, obviates the need for measuring the impact force and acceleration. Further, the controller is continuous, and can be used for both non-contact and contact conditions.

Download Full-text

A Supervised Neural Network Control for Magnetorheological Damper in an Aircraft Landing Gear

Applied Sciences ◽

10.3390/app12010400 ◽

2021 ◽

Vol 12 (1) ◽

pp. 400

Author(s):

Quoc-Viet Luong ◽

Bang-Hyun Jo ◽

Jai-Hyuk Hwang ◽

Dae-Sung Jang

Keyword(s):

Neural Network ◽

Mr Damper ◽

Landing Gear ◽

Network Control ◽

Neural Network Control ◽

Hybrid Controller ◽

Aircraft Landing ◽

Aircraft Landing Gear ◽

Drop Tests ◽

The Impact

This paper adopts an intelligent controller based on supervised neural network control for a magnetorheological (MR) damper in an aircraft landing gear. An MR damper is a device capable of adjusting the damping force by changing the magnetic field generated in electric coils. Applying an MR damper to the landing gears of an aircraft could minimize the impact at landing and increase the impact absorption efficiency. Various techniques proposed for controlling the MR damper in aircraft landing gears require information on the damper force or the mass of the aircraft to determine optimal parameters and control commands. This information is obtained by estimation with a model in a practical operating environment, and the accompanying inaccuracies cause performance degradation. Machine learning-based controllers have also been proposed to address model dependency but require a large number of drop test data. Unlike simulations, which can conduct a large number of virtual drop tests, the cost and time are limited in the actual experimental environment. Therefore, a neural network controller with supervised learning is proposed in this paper to simulate the behavior of a proven controller only with system states. The experimental data generated by applying the hybrid controller with the exact mass and force information, which has demonstrated high performance among the existing techniques, are set as the target for supervised learning. To verify the effectiveness of the proposed controller, drop test experiments using the intelligent controller and the hybrid controller with and without exact information about aircraft mass and force are executed. The experimental results from the drop tests of a landing gear show that the proposed controller maintains superior performance to the hybrid controller without using explicit damper models or any information on the aircraft mass or strut force.

Download Full-text