Tuning of a neuro-fuzzy controller by genetic algorithms with an application to a coupled-tank liquid-level control system

Abstract. Since liquid tank systems are commonly used in industrial applications, system-related requirements results in many modeling and control problems because of their interactive use with other process control elements. Modeling stage is one of the most noteworthy parts in the design of a control system. Although nonlinear tank problems have been widely addressed in classical system dynamics, when designing intelligent control systems, the corresponding model for simulation should reflect the whole characteristics of the real system to be controlled. In this study, a coupled, interacting, nonlinear liquid leveling tank system is modeled using ANFIS (Adaptive-Network-Based Fuzzy Inference System), which will be further used to design and apply a fuzzy-PID control to this system. Firstly, mathematical modeling of the system is established and then, data gathered from this model is employed to create an ANFIS model of the system. Both mathematical and ANFIS model is compared, model consistencies are discussed, and flexibility of ANFIS modeling is shown.

show abstract

“…Fig.3. shows a simple double tank liquid-level system with a valve between [18]. Each tank has and outlet port with Q 2 and Q 4 flowrates.…”

Section: Modeling a Nonlinear Coupled-tank System With Anfismentioning

confidence: 99%

Modeling of a Coupled Industrial Tank System with ANFIS

Engin

Kuvulmaz

Omurlu

2004

MICAI 2004: Advances in Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…Simulation results showed that the proposed algorithm is more robust than the others. Lian et al designed a neuro-fuzzy logic controller (NFLC) that parameters are determined by GA for a coupled tank liquid level control system (Lian et al, 1998). Experimental results showed that the NFLC is more robust than the FLC and PID controller.…”

Section: Introductionmentioning

confidence: 99%

İkili Tank Sisteminin Sıvı Seviye Kontrolü için Genetik Algoritma Tabanlı PI+İleri Besleme Kontrolcü

Yilmaz

Can

Başçı

2021

Iğdır Üniversitesi Fen Bilimleri Enstitüsü Dergisi

View full text Add to dashboard Cite

One of the main problems in the control of the coupled tank liquid level systems, which are used frequently in water treatment systems and petrochemical industry today, is to determine the water flow rate between the two tanks. In this paper, proportional-integral +feed forward control method (PI+FF), whose parameters are determined using genetic algorithm (GA), one of the heuristic optimization methods, is used to solve this problem. In addition, in order to show the performance of the GA-based controller, the PI+FF controller that PI parameters obtained using the Ziegler-Nichols (Z-N) method are applied to the same system and the real-time application results of both controllers are compared. The experimental results showed that the controller, which parameters are determined by GA, reached the desired reference value with less settling time and less overshooting when it compared to the Z-N method based controller, and also it has given faster response to sudden changes in the system.

show abstract

“…In that sense, different control methods are proposed for liquid level control in tank systems. Various literature on backstepping controllers, adaptive controllers, intelligent controllers, fractional order controllers, and sliding mode controllers (SMCs) have already shown the performance of different control techniques in tracking a constant reference signal.…”

Section: Introductionmentioning

confidence: 99%

Sliding mode PI control with backstepping approach for MIMO nonlinear cross‐coupled tank systems

Aksu

Çoban

2019

Intl J Robust & Nonlinear

View full text Add to dashboard Cite

Summary The control of tank systems in industrial applications is an important issue for monitoring the chemical processes involved in the manufacture and delivery of product. The most important reason to control the tank systems is to keep the liquid level in the tanks constant and at the desired level for a specified period of time. In this study, the sliding mode control (SMC) with a repetitive approach called backstepping that is insensitive to uncertainties in system parameters and input disturbances is proposed and experimentally applied to a quadruple, cross‐coupled, uncertain, nonlinear, and multiple‐input/multiple‐output tank system. A proportional‐integral (PI) control is used to reduce the steady‐state error caused by the parameter variations and external noises. The traditional way of introducing PI usually leads to sliding surfaces. In this paper, the PI action is introduced to the control signal. The proposed backstepping sliding mode PI control (BSMPIC) is applied to such a complex tank system for the first time. The experimental results are compared with those of the SMC, sliding mode PI control, and backstepping sliding mode control to see the effect of the proposed BSMPIC on the system. As a result of the comparison, it is observed that less overshoot and tracking error, better tracking performance, and faster rise time in the transient regime is obtained by the BSMPIC.

show abstract

Tuning of a neuro-fuzzy controller by genetic algorithms with an application to a coupled-tank liquid-level control system

Cited by 46 publications

References 28 publications

Modeling of a Coupled Industrial Tank System with ANFIS

Modeling of a Coupled Industrial Tank System with ANFIS

İkili Tank Sisteminin Sıvı Seviye Kontrolü için Genetik Algoritma Tabanlı PI+İleri Besleme Kontrolcü

Sliding mode PI control with backstepping approach for MIMO nonlinear cross‐coupled tank systems

Contact Info

Product

Resources

About