Just-In-Time Control of Image-Based Inverted Pendulum Systems with a Time-Delay

SICE Journal of Control, Measurement, and System Integration

2017

: Model-free predictive control directly computes the control input from massive input/output datasets and does not use a mathematical model. In contrast, conventional model predictive control relies on mathematical models. Although the underlying principle of model-free predictive control utilizes linear regression vectors comprising input/output data, it can also be applied to control nonlinear systems. In this study, the linear regression vectors are extended to polynomial regression vectors, improving the control performance. Using numerical simulations, we demonstrate the effectiveness of this approach.

Section: Introductionmentioning

confidence: 99%

Model-Free Predictive Control Using Polynomial Regressors

SICE Journal of Control, Measurement, and System Integration

2017

“…Although the vectors can be used to identify an auto-regressive model, they are instead used to estimate a short-length vector corresponding to future input sequences by using locally weighted averaging. The idea can also be seen in [4] and can be used to treat discretized input systems [5]. It has also been applied to an inverted pendulum system [6] and a parallel mechanism with pneumatic drives [7].…”

Section: Introductionmentioning

confidence: 99%

A model-free predictive control method based on polynomial regression

2016 SICE International Symposium on Control Systems (ISCS)

2016

This paper proposes a model-free predictive control method for nonlinear systems on the basis of polynomial regression. In contrast to conventional model predictive control, model-free predictive control does not require mathematical models. Instead, it uses the previous recorded input/output datasets of the controlled system to predict an optimal control input so as to achieve the desired output. The novel point in this paper is the improvement of existing model-free predictive control by adopting polynomial regression, which is a generalization of the so-called Volterra series expansion of nonlinear functions.

“…Although to select a weight for this weighted averaging, several methods can be used in the Just-In-Time modeling framework, control performance highly depends on the weights. Similar Just-In-Time control methods have been proposed in previous studies [18]- [20]. These studies also use nearest neighbor and locally weighted averaging (LWA) techniques, as in the Just-In-Time modeling method.…”

Section: Introductionmentioning

confidence: 99%

“…In [18] and [25], data-driven control is used to improve stabilizing feedback control. In contrast to these, since our main aim is to show that model-free predictive control has the ability to stabilize unstable systems, when we use model-free predictive control, we do not use the stabilizing controller, unlike in [18] and [25].…”

Section: Introductionmentioning

confidence: 99%

“…In contrast to these, since our main aim is to show that model-free predictive control has the ability to stabilize unstable systems, when we use model-free predictive control, we do not use the stabilizing controller, unlike in [18] and [25]. In addition to comparing model-free predictive control methods, we investigate the effect of database maintenance.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Comparative Study of Model-Free Predictive Control and Its Database Maintenance for Unstable Systems

Saputra

SICE Journal of Control, Measurement, and System Integration

2015

: This study provides a comparison of three methods, i.e., standard locally weighted averaging (LWA), leastnorm solutions, and 1 -minimization, for model-free predictive control based on Just-In-Time modeling and database maintenance for an unstable system. In contrast to conventional model predictive control, the model-free predictive control method does not use any mathematical model; rather, it uses the past input/output data stored in a database. Although conventional stabilizing feedback is used to obtain the input/output data of an unstable system, model-free predictive control is assumed to be used without it. Three methods based on standard LWA, least-norm solutions, and 1 -minimization are statistically compared using a simple model. The results show that the methods of least-norm solutions and 1 -minimization are superior to that of LWA. The method by 1 -minimization yields tracking errors smaller than that by least-norm solutions; however, the method by 1 -minimization requires a long computational time. In addition, the effectiveness of a method of database maintenance is illustrated by numerical simulations.