A practical implementation of Robust Evolving Cloud-based Controller with normalized data space for heat-exchanger plant

Abstract

The RECCo control algorithm, presented in this article, is based on the fuzzy rule-based (FRB) system named ANYA which has non-parametric antecedent part. It starts with zero fuzzy rules (clouds) in the rule base and evolves its structure while performing the control of the plant. For the consequent part of RECCo PID-type controller is used and the parameters are adapted in an online manner. The RECCo does not require any off-line training or any type of model of the controlled process (e.g. differential equations). Moreover, in this article we propose a normalization of the cloud (data) space and an improved adaptation law of the controller. Due to the normalization some of the evolving parameters can be fixed while the new adaptation law improves the performance of the controller in the starting phase of the process control. To assess the performance of the RECCo algorithm, firstly an comparison study with classical PID controller was performed on a model of a plate heat-exchanger (PHE). Tunning the PID parameters was done using three different techniques (Ziegler-Nichols, Cohen-Coon and pole placement). Furthermore, a practical implementation of the RECCo controller for a real PHE plant is presented. The PHE system has nonlinear static characteristic and a time delay. Additionally, the real sensor's and actuator's limitations represent a serious problem from the control point of view. Besides this, the RECCo control algorithm autonomously learns and evolves the structure and adapts its parameters in an online unsupervised manner.

Gain-Scheduling Control Solutions for Magnetic Levitation Systems

“…The second GS version is based on a Cauchy kernel distance metric [25][26][27] resulting in the Cauchy GS control solution. As shown in (13), this approach directly takes into account all previous data samples: (17) and CGS is Cauchy GS version.…”

“…GS deals in [25] and [26] with the adaptation of gains of a robust evolving cloud-based controller (RECCo) designed for a class of nonlinear processes; the robust modification of the adaptive laws and the performance analysis are introduced. A practical implementation of RECCo with normalized data space for a heatexchanger plant is reported in [27]. Other interesting adaptive GS control techniques for real practical applications are given in [28][29][30][31].…”

A Comparison of RECCo and FCPFC Controller on Nonlinear Chemical Reactor

“…Robust evolving cloud-based controller (RECCo) is presented in detail in [26], therefore, in this section we will present only the general structure and the principle of the algorithm. The algorithm presents a type of fuzzy rulebased system named AnYa [32].…”

“…The second presented method, is the RECCo controller [26], which is fully on-line and does not require any off-line training or any type of model of the controlled process. It is actually a type of direct adaptive fuzzy controller.…”

Robust Evolving Cloud-based Controller (RECCo)

“…In this case the data point is normalized and due to this the evolving parameter can be fixed. Please refer to [5], [6] for more details about the problem space normalization.…”