Mohamed M. Ismail

Adaptation of PID controller using AI technique for speed control of isolated steam turbine

It is known that PID controller is employed in every facet of industrial automation. The application of PID controller span from small industry to high technology industry. Tuning the parameters of a PID controller is very important in PID control. Ziegler and Nichols proposed the well-known Ziegler-Nichols method to tune the coefficients of a PID controller. This tuning method is very simple, but cannot guarantee to be always effective. For this reason, this paper investigates the design of self tuning for a PID controller. For this study, the model selected is of isolated turbine speed control system. Isolated turbine system means that the turbine is not connected to the grid. The reason for this is that this model is often encountered in refineries in a form of steam turbine that uses hydraulic governor to control the speed of the turbine. The PID controller of the model will be designed using the adaptive fuzzy control method and the results analyzed. The same model will be redesigned using GA, PSO and ANFIS methods. The results of design methods will be compared, analyzed and conclusion will be drawn out of the simulation made.

Applications of ANFIS and Fuzzy Algorithms for Improvement of the DTC Performance for the Three Phase Saturated Model of Induction Motor

Direct torque control (DTC) of an induction motor fed by a voltage source inverter is a simple scheme that doesn’t need long computation time. The motor terminal voltages and currents are sampled to estimate the motor flux linkage and electromagnetic torque using a flux observer. The main advantage of DTC technique is that it isn’t sensitive to the variation in motor parameters except the stator resistance in its flux observer especially at low speed operation. In this paper, two observers are used for online stator resistance identification for the DTC flux observer, one observer based on fuzzy logic while the other is based on ANFIS algorithm. The saturated p model of the induction motor is used which is more practical than the approximate linear model especially in the large motors. The authors also introduced a speed observer based on Lyapunov design and compared with another observer based on ANFIS design as well as the classical flux observer used with DTC technique. Simulation results show that the observers are validated and give a good performance in the different operating conditions. Also the authors have found that the ANFIS observer gives good performance as well as the Lyapunov and fuzzy observers.

Using Positive and Negative Sequence Components of Currents and Voltages for High Impedance Fault Analysis via ANFIS

High Impedance Faults are defined as unwanted electrical contact between an energized conductor and a non-conducting foreign object. Non-conducting foreign object present high impedances to current flow due to their material, so a fault of this type will not appear to the classical protection equipment as abnormal conditions. Presented is an approach for detection, classification, and location of high impedance faults in a distribution system using Adaptive Neuro Fuzzy Inference System (ANFIS) based on positive and negative sequence components of voltages and currents. The proposed scheme was trained by data from simulation of a distribution system under different faults conditions and different distances in a short and long transmission lines. Details of the design procedure and the results of performance using the proposed method are discussed in this paper.

Improving the performance of the DTC saturated model of the induction motor in case of two level and three level VSI using GA and PSO algorithms

The problem of controlling the π-model induction motor with magnetic saturation is considered in this proposed research. Direct Torque Control (DTC) of induction motor has been developed since three decades. Furthermore many techniques have been proposed to improve the performance of the induction machines that using the DTC drives in industry. However, all the previous models are based on the linear model of the machine for approximation. This is not the exact model and there is no guarantee that the process will work outside the saturation region of the flux, especially in large rating of induction machines. In this paper, two types of voltage source inverters are applied on the saturated model of induction motor. We study the performance of the induction machine response in the two cases using MATLAB SIMULINK one is by using torque control and the other is by using speed control. GA and PSO are used for improvement of the speed control for the two and three level inverters.

PID controller tunning scheme for TRMS using AI techniques

This paper presents a new intelligent control scheme which utilizes genetic algorithm and particle swarm optimization (PSO) for off-line tuning of proportional-integral-derivative (PID) controller for the twin rotor multi-input multi-output system (TRMS). The control objective is to make the beam of the TRMS move quickly and accurately to the desired attitudes. The TRMS exhibits MIMO characteristics, high order non-linearity, significant cross coupling and inaccessibility of some of its states and outputs for measurements. PSO Algorithm is successfully implemented to this problem. Experimental and simulated results of the developed PID controller for a twin rotor system are given to demonstrate its effectiveness. Satisfactory results are anticipated in the experimental as well as in the simulation results. In an attempt to evaluate the performance of the developed controller an experimental and simulated comparative assessments with the conventionally PID tuned method (Ziegler-Nichols method) has been conducted. The results of the PID controller based PSO reveals better performances indices than GA method and the ZN method.

Adaptive Output Feedback Voltage-Based Control of Magnetically-Saturated Induction Motors

The problem of controlling the induction motor -model with magnetic saturation is considered. An adaptive controller is developed under the assumption of measurable stator currents and speed only with unknown rotor resistance and load torque. All the unknown parameters are assumed constant or slowly varying and are estimated online by the controller. Simulation results are provided for illustration.

Speed Sensorless observer using Lyapnov design and ANFIS for DTC of magnetically saturated induction motor

The problem of controlling the π-model induction motor with magnetic saturation is considered in this proposed research. DTC of induction motor have been developed since 1980, many techniques have been proposed to improve the performance of the induction machines that using the DTC drives in industry but all the previous models are using the linear model of the machine for approximation which is not the exact model and we are not garantee that the process is not work in the saturation region of the flux specially in large rating of induction machines. In this paper we introduce an speed observer using lyapnov design and compared with a one using ANFIS design as well as the classical flux observer that used with DTC technique. Simulation result show that the speed observer have a good performance with variation of speed reference.