research centers


Search results: Found 5

Listing 1 - 5 of 5
Sort by

Article
Design of an Auto-Tuning PID Controller for Systems based on Slice Genetic Algorithm

Author: Khulood E. Dagher
Journal: IRAQI JOURNAL OF COMPUTERS,COMMUNICATION AND CONTROL & SYSTEMS ENGINEERING المجلة العراقية لهندسة الحاسبات والاتصالات والسيطرة والنظم ISSN: 18119212 Year: 2013 Volume: 13 Issue: 3 Pages: 1-9
Publisher: University of Technology الجامعة التكنولوجية

Loading...
Loading...
Abstract

Abstract – This paper introduces the Slice Genetics Algorithm SGA which representsthe proposed modification to the classic Genetic Algorithm GA scheme. The proposedalgorithm has reduced the population size and maximum iteration in order to get fastand an optimal solution. This algorithm has been used for determining the optimalproportional- integral- derivative PID controller parameters. The proposed algorithmhas versatile features, including, fast, stable rate convergence characteristic also it hasgood computational efficiency in improving the dynamic behavior for the system interm of reducing the maximum overshoot, rise time, settling time and steady-stateserror. The algorithm not only has benefit to improve the convergence characteristic,accuracy but it also shortened the processing time towards the optimal value basedreducing the number of iteration from 40 to 4 or 6 iteration as clear in the MATLABsimulation results..


Article
A Cognitive PID Neural Controller Design for Mobile Robot Based on Slice Genetic Algorithm
تصميم مسيطر عصبي تناسبي تكاملي تفاضلي مدرك لإنسان آلي متنقل مبني على أساس خوارزمية الشرائح الجينية

Author: Ahmed Sabah Al-Araji
Journal: Engineering and Technology Journal مجلة الهندسة والتكنولوجيا ISSN: 16816900 24120758 Year: 2015 Volume: 33 Issue: 1 Part (A) Engineering Pages: 208-222
Publisher: University of Technology الجامعة التكنولوجية

Loading...
Loading...
Abstract

The main core of this paper is to design a trajectory tracking control algorithm for mobile robot using a cognitive PID neural controller based slice genetic optimization in order to follow a pre-defined a continuous path. Slice Genetic Optimization Algorithm (SGOA) is used to tune the cognitive PID neural controller's parameters in order to find best velocities control actions of the right wheel and left wheel for the mobile robot. Pollywog wavelet activation function is used in the structure of the cognitive PID neural controller. Simulation results and experimental work show the effectiveness of the proposed cognitive PID neural tuning control algorithm; This is demonstrated by the minimized tracking error and the smoothness of the velocity control signal obtained, especially with regards to the external disturbance attenuation problem.

أن المحور الرئيسي لهذا البحث هو تصميم خوارزمية مسيطر تتابع مسار لإنسان آلي متنقل باستخدام مسيطر عصبي تناسبي تكاملي تفاضلي أساسه أمثلية الشرائح الجينية لكي يتبع مسار مستمر معرف مسبقا.لقد تم استخدام خوارزمية الشرائح الجينية لتنغيم عناصر المسيطر العصبي التناسبي التكاملي التفاضلي المدرك لكي يجد أفضل أشارة سرعة للإنسان الآلي المتحرك. أن الدالة الفعالة التي استخدمت في هيكلية المسيطر العصبي التناسبي التكاملي التفاضلي المدرك هي (Pollywog wavelet).من خلال نتائج المحاكاة والأعمال التجريبية, أن فعالية خوارزمية تنغيم المسيطر المقترح تقوم بتقليل الخطأ ألتتابعي لمسار الإنسان الآلي المتحرك مع توليد أشارة سرعة ناعمة, برغم من وجود التأثير الاضطرابي الخارجي.


Article
A Nonlinear Neural Controller Design for the Single Axis Magnetic Ball Levitation System Based on Slice Genetic Algorithm
تصميم مسيطر عصبي لاخطي لنظام تعليق الكرة المغناطيسية احادية الأتجاه مبني على اساسة خوارزمية الشرائح الجنية

Authors: Ahmed Sabah Al-Araji --- Ahmed Ibraheem Abdulkareem
Journal: Engineering and Technology Journal مجلة الهندسة والتكنولوجيا ISSN: 16816900 24120758 Year: 2016 Volume: 34 Issue: 1 Part (A) Engineering Pages: 22-32
Publisher: University of Technology الجامعة التكنولوجية

Loading...
Loading...
Abstract

This paper presents a ball position tracking control tuning algorithm for single axis magnetic levitation system using slice genetic optimization technique based nonlinear neural controller. As simple and fast tuning technique, slice genetic optimization algorithm is used to tune the nonlinear neural controller's parameters in order to get the best control action for the magnetic levitation system through the tracking of pre-defined location of the steel ball. Pollywog wavelet activation function is used in the structure of the nonlinear neural controller. The obtained results (using MATLAB program) show that the effectiveness of the proposed controller in minimizing the tracking error to zero value and also, in the softness of the control action with the lowest amount of fitness evaluation number.

ان هذا البحث يقدم خوارزمية تنغيم المسيطر تتابع موقع كرة لنظام التعليق المغناطيسي احادي الأتجاه بستخدام تقنية الشرائح الجنية الأمثلية اساسها المسيطر العصبي اللاخطي. لقد تم استخدام خوارزمية الشرائح الجنية لانها تقنية سهلة و سريعة في تنغيم عناصر المسيطر العصبي اللاخطي لكي يحصل على افضل فعل للمسيطر لنظام التعليق المغناطيسي من خلال تتابع الموقع المعرف مسبقا لكرة الأستيل. ان الدالة الفعالة (Polywog Wavelet)استخدمت في هيكلية المسيطر العصبي اللاخطي. لقد تم الحصول على النتائج بأستخدام الحقيبة البرمجة ماتلاب وتبينت فعالية المسيطر المقترح في تقليل الخطأ التتابعي الى قيمة الصفر وكذلك فينعومة فعل المسيطر مع اقل عدد ممكن لأستدعاء دالة التقيم.


Article
Development of a Swing-Tracking Sliding Mode Controller Design for Nonlinear Inverted Pendulum System via Bees-Slice Genetic Algorithm

Author: Ahmed Sabah Al-Araji
Journal: Engineering and Technology Journal مجلة الهندسة والتكنولوجيا ISSN: 16816900 24120758 Year: 2016 Volume: 34 Issue: 15 Part (A) Engineering Pages: 2897-2910
Publisher: University of Technology الجامعة التكنولوجية

Loading...
Loading...
Abstract

A new development of a swing-tracking control algorithm for nonlinear inverted pendulum system presents in this paper. Sliding mode control technique is used and guided by Lyapunov stability criterion and tuned by Bees-slice genetic algorithm (BSGA). The main purposes of the proposed nonlinear swing-tracking controller is to find the best force control action for the real inverted pendulum model in order to stabilize the pendulum in the inverted position precisely and quickly. The Bees-slice genetic algorithm (BSGA) is carried out as a stable and robust on-line auto-tune algorithm to find and tune the parameters for the sliding mode controller. Sigmoid function is used as signum function for sliding mode in order to eliminate the chattering effect of the fast switching surface by reducing the amplitude of the function output. MATLAB simulation results and LabVIEW experimental work are confirmed the performance of the proposed tuning swing-tracking control algorithm in terms of the robustness and effectiveness that is overcame the undesirable boundary disturbances, minimized the tracking angle error to zero value and obtained the smooth and best force control action for the pendulum cart, with fast and minimum number of fitness evaluation.


Article
A Cognitive Neural Linearization Model Design for Temperature Measurement System based on Optimization Algorithm

Author: Dr. Hayder Abd Dahad
Journal: IRAQI JOURNAL OF COMPUTERS,COMMUNICATION AND CONTROL & SYSTEMS ENGINEERING المجلة العراقية لهندسة الحاسبات والاتصالات والسيطرة والنظم ISSN: 18119212 Year: 2015 Volume: 15 Issue: 1 Pages: 61-71
Publisher: University of Technology الجامعة التكنولوجية

Loading...
Loading...
Abstract

Abstract – The main core of this paper is to design an experimental method for estimating of the nonlinearity, calibrating and testing of the different types of thermocouples temperature sensors (J, K, T, S and R) using multi-layer perceptron (MLP) neural network based on slice genetic (SG) optimization learning algorithm. Temperature sensor has a nonlinearity behavior nature in its output response but it requires a linear behavior output with accepts approximation in accuracy level, noise and measurement errors. Therefore, neural network topology is proposed with five main steps algorithm to reduce the effected noise and minimize the measured errors. Matlab simulation results and laboratory work (LabVIEW) validate the preciously of the proposed cognitive neural linearization algorithm in terms of calculating the temperature from the different types of thermocouples temperature sensors and minimizing the error between the actual temperature output and neural linearization temperature output as well as overcoming the problem of the over learning in the linearization model with the minimum number of fitness evaluation for the learning algorithm..

Listing 1 - 5 of 5
Sort by
Narrow your search

Resource type

article (5)


Language

English (5)


Year
From To Submit

2016 (2)

2015 (2)

2013 (1)