Adaptive RISE Control of Hydraulic Systems With Multilayer Neural-Networks

Yao, Zhikai; Yao, Jianyong; Sun, Wei

doi:10.1109/tie.2018.2886773

Cited by 169 publications

(100 citation statements)

References 30 publications

Supporting

Mentioning

100

Contrasting

Order By: Relevance

“…To this end, previous works have proposed several disturbance-observers with different control schemes for some systems [34,35]. Neural networks have been presented as an appropriate tool for approximation of any unknown function [36,37]. Thus, using this advantage, several research studies have applied neural networks for control purposes [38][39][40].…”

Section: Introductionmentioning

confidence: 99%

Recurrent Neural Network-Based Robust Nonsingular Sliding Mode Control With Input Saturation for a Non-Holonomic Spherical Robot

et al. 2020

View full text Add to dashboard Cite

We develop a new robust control scheme for a non-holonomic spherical robot. To this end, the mathematical model of a pendulum driven non-holonomic spherical robot is first presented. Then, a recurrent neural network-based robust nonsingular sliding mode control is proposed for stabilization and tracking control of the system. The designed recurrent neural network is applied to approximate compound disturbances, including external interferences and dynamic uncertainties. Moreover, the controller is designed in a way that avoids the singularity problem in the system. Another advantage of the proposed scheme is its ability for tracking control while there exists control input saturation, which is a serious concern in robotic systems. Based on the Lyapunov theorem, the stability of the closed-loop system has also been confirmed. Lastly, the performance of the proposed control technique for the uncertain system in the presence of an external disturbance, unknown input saturation, and dynamic uncertainties has been investigated. Also, the proposed controller has been compared with a Fuzzy-PID one. Simulation results show the effectiveness and superiority of the developed control technique.

show abstract

Section: Introductionmentioning

confidence: 99%

Recurrent Neural Network-Based Robust Nonsingular Sliding Mode Control With Input Saturation for a Non-Holonomic Spherical Robot

et al. 2020

View full text Add to dashboard Cite

show abstract

“…In a different domain (hydraulic plants), one example of the use of neural networks for the control of highly nonlinear and difficult-to-model systems is given in [25]. The study adopts a neural network to estimate the discrepancy between the plant and a nominal plant model.…”

Section: Related Work a Deep Learning For Vehicle Controlmentioning

confidence: 99%

A Mental Simulation Approach for Learning Neural-Network Predictive Control (in Self-Driving Cars)

et al. 2020

View full text Add to dashboard Cite

This paper presents a novel approach to learning predictive motor control via "mental simulations". The method, inspired by learning via mental imagery in natural Cognition, develops in two phases: first, the learning of predictive models based on data recorded in the interaction with the environment; then, at a deferred time, the synthesis of inverse models via offline episodic simulations. Parallelism with human-engineered control-theoretic workflow (mathematical modeling the direct dynamics followed by optimal control inversion) is established. Compared to the latter human-directed synthesis, the mental simulation approach increases autonomy: a robotic agent can learn predictive models and synthesize inverse ones with a large degree of independence. Human modeling is still needed but limited to providing efficient templates for the forward and inverse neural networks and a few other directives. One could consider these templates as the efficient brain network typologies that evolution produced to permit live beings quickly and efficiently learning. The structure of the neural networks-both forward and inverse ones-is made of interpretable "local models", which follows the cerebellar organization (and are also similar to local model approaches known in the literature). We demonstrate the learning of a first-round model (contrasted to Model Predictive Control) for lateral vehicle dynamics. Then, we demonstrate a second learning iteration, where the forward/inverse neural models are significantly improved.

show abstract

“…According to the mean value theorem of multivariate function and noting (28), (31), one obtains where x 2 is a value between ̇x d and x 2 , and x 3 is a value between ẍ d and x 3 , It can be seen from (38) and (39) that the extent of N 1 and N 2 can be made arbitrarily small by tuning the gains of the proposed ESMO and robust controller.…”

Section: Compliance With Ethical Standardsmentioning

confidence: 99%

“…The residual estimation error of the observer may lead to inferior tracking performance. On the other hand, the parameter estimation can reduce parametric uncertainties to a large extent [28][29][30], and the task of the observer is thus alleviated. To this end, it is indispensable to integrate parameter-adaptive algorithm with the observer in order to develop an output feedback controller for the pneumatic system, so that the structured and unstructured uncertainties can be handled, respectively.…”

Section: Introductionmentioning

confidence: 99%

Output feedback motion control of pneumatic servo systems with desired compensation approach

Wei-ping

Meng

2020

J Braz. Soc. Mech. Sci. Eng.

View full text Add to dashboard Cite

In this study, an output feedback control strategy for the pneumatic asymmetric cylinder is established by integrating a robust controller with the proposed desired compensation adaptive law and extended sliding mode observer (ESMO). Specifically, in order to attenuate the parametric uncertainties, a desired compensation indirect-type estimation method, based on physical model and desired system states, is designed to achieve estimates of model parameters, and the parameter estimation error can be regarded as part of the lumped uncertainties. Since only displacement signal is available, both the unmeasured system states and lumped uncertainties are estimated by the proposed ESMO, and the global stability is guaranteed by the presented robust control law. As a result, structured (i.e., parametric uncertainties) and unstructured (i.e., lumped uncertainties such as unmodeled dynamics, external disturbance and parameter estimation error) uncertainties can be handled and compensated, respectively, in one controller. The comparative experimental results indicate that the prescribed tracking trajectory can be achieved by the proposed controller in the presence of time-varying uncertainties.

show abstract

Adaptive RISE Control of Hydraulic Systems With Multilayer Neural-Networks

Cited by 169 publications

References 30 publications

Recurrent Neural Network-Based Robust Nonsingular Sliding Mode Control With Input Saturation for a Non-Holonomic Spherical Robot

Recurrent Neural Network-Based Robust Nonsingular Sliding Mode Control With Input Saturation for a Non-Holonomic Spherical Robot

A Mental Simulation Approach for Learning Neural-Network Predictive Control (in Self-Driving Cars)

Output feedback motion control of pneumatic servo systems with desired compensation approach

Contact Info

Product

Resources

About