Iterative Feedback and Learning Control. Servo Systems Applications

Preitl, Ștefan; Precup, Radu; Preitl, Zsuzsa; Vaivoda, S.; Kilyeni, Stefan; Tar, J.K.

doi:10.3182/20070709-3-ro-4910.00004

Cited by 84 publications

(31 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many learning methods such as iterative learning control (ILC) and reinforcement learning (RL) have been proposed in different fields. This brings a promising approach for the adaptive energy management control of PHEV in uncertain circumstance.…”

Section: Introductionmentioning

confidence: 99%

Self‐learning energy management for plug‐in hybrid electric bus considering expert experience and generalization performance

Guo¹,

Zhao²,

Guo³

et al. 2020

Int J Energy Res

View full text Add to dashboard Cite

A self-learning energy management is proposed for plug-in hybrid electric bus, by combining Q-Learning (QL) and Pontryagin's minimum principle algorithms. Different from the existing strategies, the expert experience and generalization performance are focused in the proposed strategy. The expert experience is designed as the approximately optimal reference state-of-charge (SOC) trajectories, and the generalization performance is enhanced by a multiply driving cycle training method. In specific, an efficient zone of SOC is firstly designed based on the approximately optimal reference SOC trajectories. Then, the agent of the QL is trained off-line by taking the expert experience as reference SOC trajectories.Finally, an adaptive strategy is proposed based on the well-trained agent. Specially, two different reward functions are defined. That is, the reward function in the off-line training mainly considers the tracking performance between the expert experience and the SOC, while mainly considering the punishment in the adaptive strategy. Simulation results show that the proposed strategy has good generalization performance and can improve the fuel economy by 22.49%, compared to a charge depleting-charge sustaining (CDCS) strategy. K E Y W O R D Senergy management, expert experience, generalization performance, plug-in hybrid electric bus, Q-learning

show abstract

Section: Introductionmentioning

confidence: 99%

Self‐learning energy management for plug‐in hybrid electric bus considering expert experience and generalization performance

Guo¹,

Zhao²,

Guo³

et al. 2020

Int J Energy Res

View full text Add to dashboard Cite

show abstract

“…In [28], to attain optimal control and meet requirements of constraints, the particle swarm optimization (PSO) algorithm is integrated into the receding horizon optimization of GPC. However, most of optimization algorithms usually require iterative calculation with the cost of high computation intensity [29]. In [30], the Lagrange multiplier is proposed to solve the control law of GPC with the constraints of inputs and leads to the insignificant computation labor.…”

Section: Introductionmentioning

confidence: 99%

Design of an Improved Implicit Generalized Predictive Controller for Temperature Control Systems

et al. 2020

View full text Add to dashboard Cite

In this study, an implicit proportional-integral-based generalized predictive controller (PIGPC) is proposed to effectively control temperatures of industrial systems with time-varying delay. The controller is designed to optimize the target function with the proportional-integral structure for improving the controlling performance of implicit PIGPC. Meanwhile, the recursive least square method is leveraged to directly identify the parameters of controller. Compared with the conventional implicit generalized predictive controller, the process of parameter identification converges faster. The Lagrange multiplier method is introduced to solve the optimal control law of implicit PIGPC by considering the input constraints of system. An approximate decoupling controller for multivariable systems is proposed to eliminate the coupling effects. Simulation and experimental results manifest the effectiveness and feasibility of the proposed controller in temperature control systems. INDEX TERMS Decoupling control, input constraint, proportional-integral generalized predictive controller (PIGPC), Lagrange multiplier method, temperature control system.

show abstract

“…In [ 2 ] the authors use a surrogate Kriging Model to represent bridge structures. In [ 3 ], surrogate models have been used for control design and feedback prediction. They have alsobeen used in pedestrian detection in [ 4 ] or for process analysis in industrial plants in [ 5 ].…”

Section: Introductionmentioning

confidence: 99%

ASAMS: An Adaptive Sequential Sampling and Automatic Model Selection for Artificial Intelligence Surrogate Modeling

Duchanoy

Calvo

Moreno-Armendáriz

2020

Sensors

View full text Add to dashboard Cite

Surrogate Modeling (SM) is often used to reduce the computational burden of time-consuming system simulations. However, continuous advances in Artificial Intelligence (AI) and the spread of embedded sensors have led to the creation of Digital Twins (DT), Design Mining (DM), and Soft Sensors (SS). These methodologies represent a new challenge for the generation of surrogate models since they require the implementation of elaborated artificial intelligence algorithms and minimize the number of physical experiments measured. To reduce the assessment of a physical system, several existing adaptive sequential sampling methodologies have been developed; however, they are limited in most part to the Kriging models and Kriging-model-based Monte Carlo Simulation. In this paper, we integrate a distinct adaptive sampling methodology to an automated machine learning methodology (AutoML) to help in the process of model selection while minimizing the system evaluation and maximizing the system performance for surrogate models based on artificial intelligence algorithms. In each iteration, this framework uses a grid search algorithm to determine the best candidate models and perform a leave-one-out cross-validation to calculate the performance of each sampled point. A Voronoi diagram is applied to partition the sampling region into some local cells, and the Voronoi vertexes are considered as new candidate points. The performance of the sample points is used to estimate the accuracy of the model for a set of candidate points to select those that will improve more the model’s accuracy. Then, the number of candidate models is reduced. Finally, the performance of the framework is tested using two examples to demonstrate the applicability of the proposed method.

show abstract

Iterative Feedback and Learning Control. Servo Systems Applications

Cited by 84 publications

References 36 publications

Self‐learning energy management for plug‐in hybrid electric bus considering expert experience and generalization performance

Self‐learning energy management for plug‐in hybrid electric bus considering expert experience and generalization performance

Design of an Improved Implicit Generalized Predictive Controller for Temperature Control Systems

ASAMS: An Adaptive Sequential Sampling and Automatic Model Selection for Artificial Intelligence Surrogate Modeling

Contact Info

Product

Resources

About