Goran Andonovski

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

Graphical abstractDisplay Omitted HighlightsAn improved version of the Robust Evolving Cloud-based Controller (RECCo).Performance comparison with classical PID controller.Practical implementation and on-line control for real heat-exchanger plant.Evolving structure and adaptive law deal with the uncertainty of the system.Very basic information of the controlled process is required. 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 a comparison study with classical PID controller was performed on a model of a plate heat-exchanger (PHE). Tuning 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 sensors and actuators 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.

Robust Evolving Cloud-based Controller in normalized data space for heat-exchanger plant

This paper presents an improved version and a modification of Robust Evolving Cloud-based Controller (RECCo). The first modification is normalization of data space in RECCo. As a consequence, some of the evolving and adaptation parameters become independent of the range of the process output signal. Thus the controller tuning is simplified which makes the approach more appealing for the use in practical applications. The data space normalization is general and is used with Euclidean norm, but other distance metrics could also be used. Beside the normalization new adaptation scheme of the controller gain is proposed which improves the control performance in the case of a negative initial error in starting phase of the evolving process. At the end, different simulation scenarios are tested and analyzed for further practical implementation of the Cloud-based controller into real environments. For that reason a detail simulation study of a plate heat exchanger is performed and different scenarios were analyzed.

Analysis of adaptation law of the robust evolving cloud-based controller

In this paper we propose a performance analysis of the robust evolving cloud-based controller (RECCo) according to the different initial scenarios. RECCo is a controller based on fuzzy rule-based (FRB) systems with non-parametric antecedent part and PID type consequent part. Moreover, the controller structure (the fuzzy rules and the membership function) is created in online manner from the data stream. The advantage of the RECCo controller is that do not require any a priory knowledge of the controlled system. The algorithm starts with zero fuzzy rules (zero data clouds) and evolves/learns during the process control. Also the PID parameters of the controller are initialed with zeros and are adapted in online manner. According to the zero initialization of the parameters the new adaptation law is proposed in this article to solve the problems in the starting phase of the process control. Several initial scenarios were theoretically propagated and experimentally tested on the model of a heat-exchanger plant. These experiments prove that the proposed adaptation law improve the performance of the RECCo control algorithm in the starting phase.

A Comparison of RECCo and FCPFC Controller on Nonlinear Chemical Reactor

The objective of this paper was to present a performance comparison between a new fuzzy (cloud-based) predictive functional control (FCPFC) and the Robust Evolving Cloud-based controller (RECCo). Both methods use the same type of fuzzy cloud-based system (the same antecedent part). The clouds are used for partitioning the data space and dealing with the non-linearity of the processes. In case of FCPFC the fuzzy cloud-based model is used to identify the process model while the control signal is analytically calculated to minimize some criterion. In case of RECCo algorithm the clouds are used to identify the operating region and the control signal is adapted in online manner. The controllers were tested on a second order nonlinear, locally oscillating, chemical process CSTR (Continuous Stirred Tank Reactor). The performance and control effort of the methods were compared according to several criteria. The results show that the proposed controller FCPFC has slightly faster response but longer settling time than the RECCo controller.

Robust evolving cloud-based control for the distributed solar collector field

This paper presents robust evolving cloud-based controller (RECCo) for the distributed solar collector field (DSCF). The main issue of the DSCF is that the primary energy source (variable) cannot be manipulated. Beside this, unpredictable changing of environmental conditions (outlet temperature, cloudiness, solar radiation) on the daily basis strongly influence the dynamics of the whole process. According to this, the RECCo controller is robust enough to cope with the high levels of uncertainty present in the DSCF plant. RECCo is a fuzzy rule-based type of controller based on parameter-free premise (IF) part while the PID-type control consequent is used. Algorithm starts with zero fuzzy rules (zero clouds in data space). During operation it evolves its structure (adding new data clouds) and adapts the PID parameters for each data cloud while preforming the control of the plant. This means that no a-priori knowledge of the controlled process is required. Moreover, the ability of the learning is tested on the different operating points which cover the majority of the operating range of the DSCF plant.

Evolving model identification for process monitoring and prediction of non-linear systems

This paper tackles the problem of model identification for monitoring of non-linear processes using evolving fuzzy models. To ensure a high production quality and to match the economic requirements, industrial processes are becoming increasingly complicated in both their structure and their degree of automation. Therefore, evolving systems, because of their data-driven and adaptive nature, appear to be a useful tool for modeling such complex and non-linear processes. In this paper the identification of evolving cloud-based fuzzy models is treated for process monitoring purposes. Moreover, the evolving part of the algorithm was improved with the inclusion of some new cloud-management mechanisms. To evaluate the proposed method two different processes, but both complex and non-linear, were used. The first one is a simulated Tennessee Eastman benchmark process model, while the second one is a real water-chiller plant.

Evolving cloud-based system for the recognition of drivers’ actions

Abstract This paper presents an evolving cloud-based algorithm for the recognition of drivers’ actions. The general idea is to detect different manoeuvres by processing the standard signals that are usually measured in a car, such as the speed, the revolutions, the angle of the steering wheel, the position of the pedals, and others, without additional intelligent sensors. The primary goal of this investigation is to propose a concept that can be used to recognise various driver actions. All experiments are performed on a realistic car simulator. The data acquired from the simulator are pre-processed and then used in the evolving cloud-based algorithm to detect the basic elementary actions, which are then combined in a prescribed sequence to create tasks. Finally, the sequences of different tasks form the most complex action, which is called a manoeuvre. As shown in this paper, the evolving cloud-based algorithm can be very efficiently used to recognise the complex driver’s action from raw signals obtained by typical car sensors.

Evolving fuzzy model based performance identification for production control

In this paper we present a fuzzy cloud-based model identification method tested on realistic input/output data signals acquired from simulated Tennessee Eastman (TE) benchmark process. The cloud-based method uses simplified antecedent (IF) part based on the local density of the clouds and functional consequent (THEN) part. Number of clouds (fuzzy rules) in the IF part evolves such that when certain criteria are satisfied a new cloud is added. In this paper we use simple density threshold complemented with protecting mechanism for outliers. The parameters of the consequent part were identified using recursive Weight Least Square method. The proposed method was tested on TE process where three models were identified for the chosen, most representative, production Performance Indicators (pPIs). The provided results (quality measures) of the proposed method were compared with the results obtained using eFuMo identification tool.

Robust evolving controller for simulated surge tank and for real two-tank plant

Abstract This paper presents a robust evolving cloud-based controller named RECCo. The controller has an evolving fuzzy structure and the rules are represented by data clouds. The evolving part of the algorithm allows adding of new rules (clouds) and moreover, the robust adaptive law using the steepest (gradient) descent method adapts the PID-R parameters of each cloud. There are also some protective mechanisms introduced which improve the robustness of the algorithm. The effectiveness of the controller was tested on the simulated surge tank model and on the real two tank plant. Both plants have quite similar structure but they have different nonlinear dynamics. Using the same initializing procedure the RECCo controller efficiently control both plants.

Robust Evolving Cloud-based Controller (RECCo)

This paper presents an autonomous Robust Evolving Cloud-based Controller (RECCo). The control algorithm is a fuzzy type with non-parametric (cloud-based) antecedent part and adaptive PID-R consequent part. The procedure starts with zero clouds (fuzzy rules) and the structure evolves during performing the process control. The PID-R parameters of the first cloud are initialized with zeros and furthermore, they are adapted on-line with a stable adaptation mechanism based on Lyapunov approach. The RECCo controller does not require any mathematical model of the controlled process but just basic information such as input and output range and the estimated value of the dominant time constant. Due to the problem space normalization the design parameters are fixed. The proposed controller with the same initial design parameters was tested on two different simulation examples. The experimental results show the convergence of the adaptive parameters and the effectiveness of the proposed algorithm.