Print ISSN: 1681-6900

Online ISSN: 2412-0758

Keywords : Particle Swarm Optimization


Design PID Neural Network Controller for Trajectory Tracking of Differential Drive Mobile Robot Based on PSO

Mohamed J. Mohamed; Mohammed K. Hamza

Engineering and Technology Journal, 2019, Volume 37, Issue 12A, Pages 574-583
DOI: 10.30684/etj.37.12A.12

This paper introduces a nonlinear (Proportional-Integral-Derivative Neural Network) (PID NN) controller for a differential wheeled mobile robot trajectory tracking problem. This neural controller is built based on the principles of neural network (NN) and the equation of conventional structure of PID controller and is applied on kinematic model of the mobile robot. The particle swarm optimization algorithm (PSO) is utilized to find the best values of three PID NN parameters and connection weights that minimize the error between the reference path and the actual path. The results illustrate that the PID NN controller has a satisfied ability to make the mobile robot tracking any path with good performance, high accuracy and acceptable robustness.

A Cognitive Nonlinear Trajectory Tracking Controller Design for Wheeled Mobile Robot based on Hybrid Bees-PSO Algorithm

A.S. Al-Araji; N.Q. Yousif

Engineering and Technology Journal, 2017, Volume 35, Issue 6, Pages 609-616

The aim of the work for this paper is a comparative study of different types of on-line cognitive algorithms for the proposed nonlinear controller of the trajectory tracking for dynamic wheeled mobile robot that has a capability to track a continuous desired path. Three optimization algorithms are used (Bees, PSO and proposed hybrid Bees-PSO) in order to find and tune the values of the control gains of the neural controller as simple on-line with fast tuning techniques. The best torques control actions of the right wheel and left wheel for the cart mobile robot are generated on-line from the proposed controller. Simulation results (Matlab Package) show that the proposed nonlinear neural controller with hybrid Bees-PSO cognitive algorithm is more accurate in terms of fast on-line finding and tuning parameters of the controller; obtaining smoothness control action as well as minimizing tracking error of the wheeled mobile robot than PSO or Bees optimization algorithms.

PSO-Based EKF Estimator Design for PMBLDC Motor

Ahmed Hammood Abed; Mohammed Moanes E. Ali

Engineering and Technology Journal, 2016, Volume 34, Issue 8, Pages 1651-1665

The estimation of motor state variables is an important criterion in the drive performance, especially for high accuracy required, for that reason it’s-necessary to estimate rotor-position-continuously not for sixty-electrical-degrees as in most existing methods. In this work the speed and position for the rotor of Permanent Magnet Brushless DC Motor (PMBLDCM) was estimated by using extended Kalman filter (EKF), this work is divided into two parts, the first one deals with design and simulation of PMBLDCM with EKF as an estimator, the results are introduced by manually selected EKF parameters (Q & R) matrices, The second one deals with investigation the performance of the use of PSO technique to optimize the performance and operation of EKF, the main use of PSO here is to optimize value for EKF parameters (Q and R), the results proved that by tuning the EKF parameters by PSO the estimated values for speed and position is very-close-to the actual value-(estimation-accuracy is increased). The resultant error clearly decreases when tuned by EKF parameters for example at full load case the speed RMS error is 0.24 for 10μs sampling time, although the RMS error is 9 for 10μs sampling time trial and error selected EKF parameters.

Protection Coordination with Distributed Generation in Electrical System of Iraqi Distribution Grid

Rashid H. Al-Rubayi; Ammar Abbas Majeed

Engineering and Technology Journal, 2016, Volume 34, Issue 6, Pages 1161-1181

The nature characteristic in conventional distribution networks is radial by single source supplying a downstream network. The interest about the environmental impacts and development in technologies have led to increase distributed generation (DG) interconnected in distribution networks. Protective device coordination will be affected by adding DGs to the existing network through participating to the change in direction of power flow and fault current values and direction which cause loss in settings and mis-coordination for protective devices, especially over current relays.
The effect of DG on coordination depend upon number, location and size of DG, so in this work, the Particle Swarm Optimization (PSO) technicality utilization to locate optimal location and sizeof DG to obtain minimum active power losses.The Time Current Characteristic (TCC) curves represented which depended on the over current protection relays parameters to find settings and limited any loss in it, in order to reset these relays to obtained the proper operation without intersections in time of operation and satisfy optimal coordination between primary and pack up over current protection relays.
In this work two soft wares are used, the first is Matlab R2014a for implementation of the PSO algorithm while the second software is CYMDist program for load flow analysis, short circuit current calculation and protection coordination device analysis. To verify the developed algorithm parts from Iraqi distribution network (Baghdad Al-Rusafa 33KV distribution networks). So, used two DG units with total capacity 50MW distributed in 33kV of South Al-Rusafa distribution network which represented about 9.4% from the total load of this network 533.5MW, the total active power losses reduced from 11.597MW to 6.658MW with losses reduction 6.96MW about 43% from total losses.

Direct Torque Control for Permanent Magnet Synchronous Motor Based on NARMA-L2 controller

Huda B. Ahmed; Ali H. Almukhtar; Abdulrahim T. Humod

Engineering and Technology Journal, 2016, Volume 34, Issue 3, Pages 464-482

This paper investigates the improvement of the speed and torque dynamic responses of three phase Permanent Magnet Synchronous Motor (PMSM) using Direct Torque Control (DTC) technique. Different torques are applied to PMSM at different speeds during operation to ensure the robustness of the controller for wide torque variations. Optimal PI controller is used to modify the response of DTC. The optimal gains of PI controller are tuned by Particle Swarm Optimization (PSO) technique. Neural Network controller is called the Nonlinear Autoregressive-Moving Average (NARMA-L2) which is trained based on optimal PI controller (PI-PSO) data. The results show the superiority performance of using NARMA-L2 controller on PI-PSO controller for different speeds and load change. The overall simulation and design of the scheme are implemented Using MATLAB/Simulink program.

Optimal Identification of Doubly Fed Induction Generator Parameters in Wind Power System using Particle Swarm Optimizationand Artificial Neural Network

Kanaan A. Jalal; Hussain Kassim Ahmad

Engineering and Technology Journal, 2014, Volume 32, Issue 5, Pages 1308-1322

Wind energy became one of the techniques that attracted much attention worldwide. The induction generator is used in the exploitation of this energy and converts it into electrical energy because of the advantages that distinguish it from other types of generators. In this paper, an optimal identification of induction generator parameters is proposed. Particle Swarm Optimization technique (PSO) trained using Artificial Neural Network (ANN) is used to identify the main parameters of the induction generator in cases of wind speed change, load change and fault cases.
The simulation results obtained indicate that the particle swarm optimization is suitable for neural networks training for controlling of the voltage, frequency and generated power. The simulation programming is implemented using MATLAB.

Effect of Some Vegetables (Carrots, Onion, Parsley, and Red radish) on Corrosion Behavior of Amalgam Dental Filling in Artificial Saliva

Slafa Ismael Ibrahim; Nemir Ahmed Al-Azzawi; Shatha Mizhir Hasan; Hussein H. Karim; Ammar M. M. Al-Qaissi; Ahmed Chyad Kadhim; Mehdi Munshid Shellal; Sinan Majid Abdul Satar; Wahid S. Mohammad; Assad Oda Jassim; Khalid salem Shibib; Karema Assi Hamad; Haqui Ismael Qatta; Hayder Hadi Abbas; Kanaan A. Jalal; Hussain Kassim Ahmad; Makram A. Fakhri; Mohanned M.H. AL-Khafaji; Hussam Lefta Alwan; Baraa M.H. Albaghdadi

Engineering and Technology Journal, 2014, Volume 32, Issue 5, Pages 1216-1226

This work involves study corrosion behavior of amalgam in presence of some vegetables including (Carrots, Onion, Parsley, and Red radish) which were chosen because they require mastication process by teeth and taking enough time that make them in a contact with amalgams filling in artificial saliva.
The corrosion parameters were interpreted in artificial saliva at pH (5.1) and (37±1oC) by adding (50 ml/l) of vegetable juice to artificial saliva, which involve corrosion potential (Ecorr), corrosion current density (icorr), Cathodic and anodic Tafel slopes (bc & ba ) and polarization resistance, the results of (Ecorr) and (icorr) indicate that the medium of saliva and (50 ml/l) onion is more corrosive than the other media. Cathodic and anodic tafel slopes were used to calculate the polarization resistance (Rp) to know which medium more effective on amalgam of dental filling, this study shows that the increasing in polarization resistance through the decreasing in corrosion rate values, the results of (Rp) take the sequence:
Rp:( saliva+ parsley) >( saliva+ red radish)> saliva>(saliva+ carrots) >(saliva+ onion).
While corrosion rates (CR ) take the sequence:
CR: (Saliva+Parsley) Keywords

Amalgam
---
Corrosion in saliva
---
Potentiostatic measurements

Design of a Nonlinear PID Neural Trajectory Tracking Controller for Mobile Robot based on Optimization Algorithm

Khulood E. Dagher; Ahmed Al-Araji

Engineering and Technology Journal, 2014, Volume 32, Issue 4, Pages 973-985

This paper presents a trajectory tracking control algorithm for a non-holonomic wheeled mobile robot using optimization technique based nonlinear PID neural controller in order to follow a pre-defined a continuous path. As simple and fast tuning algorithms, particle swarm optimization algorithm is used to tune the nonlinear PID neural controller's parameters to find best velocity control actions for the mobile robot. Simulation results show the effectiveness of the proposed nonlinear PID 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.

Designing a Nonlinear PID Neural Controller of Differential Braking System for Vehicle Model Based on Particle Swarm Optimization

Ahmed Sabah Al-Araji

Engineering and Technology Journal, 2014, Volume 32, Issue 1, Pages 197-214

This paper presents a nonlinear PID neural controller for the 2-DOF vehicle model in order to improve stability and performances of vehicle lateral dynamics by achieving required yaw rate and reducing lateral velocity in a short period of time to prevent vehicle from sliding out the curvature. The scheme of the discrete-time PID control structure is based on neural network and tuned the parameters of the nonlinear
PID neural controller by using a particle swarm optimization PSO technique as a simple and fast training algorithm. The differential braking system and front wheel steering angle are the outputs of the nonlinear PID neural controller that has automatically controlled the vehicle lateral motion when the vehicle rotates the curvatures. Simulation results show the effectiveness of the proposed control
algorithm in terms of the best transient state outputs of the system and minimum tracking errors as well as smoothness control signals obtained with bounded external disturbances.

Direct Torque Control of Induction Motor Based on Neurofuzzy

Abdulrahim T. Humod; Wiam I. Jabbar

Engineering and Technology Journal, 2013, Volume 31, Issue 17, Pages 3259-3273

The main objective of this work is to improve the speed and torque responses of
three phase Induction Motor (IM) during different loads and speeds conditions.
Induction Motor is most commonly used in different industrial applications, that
require fast dynamic response and accurate control over wide speed ranges.
Therefore, this work proposes Direct Torque Control (DTC). Particle Swarm
Optimization (PSO) technique is used for optimal gains tuning of PI. The results
show the improvement in the speed response of DTC, in terms of reducing steady
state error, ripple reduction in the torque and speed responses. Neurofuzzy
(ANFIS) controller is used to improve the performance of PI-PSO controller.
ANFIS controller is trained by using PI-PSO data. The results of the ANFIS
controller are better than PI-PSO in terms of torque ripple minimization, less
steady state error in the speed response and more robustness. The simulation of the
overall drive system is performed using MATLAB/Simulink program version 7.10
(R2010a).

PSO-FL Controller of Separately Excited DC Motor

Hawraa Q. Hameed

Engineering and Technology Journal, 2013, Volume 31, Issue 11, Pages 2128-2140

This paper presents an application of highbrid controller of a Separately Exited DC Motor (SEDM) using PSO-FL techniques. The controller is designed depending on fuzzy logic rules are such that the systems are fundamentally robust. These rules have capability learning, can learn and tune rapidly, even if the motor parameters are varied. But, adapting fuzzy controller parameters is very complex and depends on operator experience. Therefore a Particle Swarm Optimization technique was adapted for obtaining the centers and the width of triangle inputs membership functions. The FL method is represented too. The complete mathematical model and simulation of a separately excited dc motor is represented using MATLAB10a/SIMULINK. The simulation results demonstrate that the proposed PSO-FL speed controller realizes a good dynamic behavior of the SEDM with very good speed tracking.

ECG Signal Diagnoses Using Intelligent Systems Based on FPGA

Ali M. Abdul Kareem; Hanan A.R. Akkar

Engineering and Technology Journal, 2013, Volume 31, Issue 7, Pages 1351-1364

This paper presents the use of Particle Swarm Optimization (PSO), neural networks with the most promising supervised learning algorithms for automatic detection of cardiac arrhythmias based on analysis of the Electrocardiogram (ECG). Artificial Neural Network (ANN) has three layers with ten nodes in the input layer, five nodes in the hidden layer and five nodes in the output layer, which is trained using the PSO algorithm. The trained network was able to classify the ECG signal in normal signal, atrial flutter, ventricular tachycardia, sever conducting tissue and wandering a trial pacemaker. Field Programmable Gate Arrays (FPGAs) have been used to implement ANN trained by the supervised learning algorithms and PSO, because of their speed benefits, as well as the re-programmability of the FPGAs which can support the reconfiguration necessary to program a neural network. A VHDL Design of ANN platform is proposed to evolve the architecture ANN circuits using FPGA-Spartan 6 Evaluation board. The VHDL design platform creates ANN design files using WebPACKTM ISE 13.3 program. All the algorithms used to train the ANN showed high effectiveness with 100% classification.

Particle Swarm Optimization and Genetic Algorithm for Tuning PID Controller of Synchronous Generator AVR System

Fadhil A. Hassan; Lina J. Rashad

Engineering and Technology Journal, 2011, Volume 29, Issue 16, Pages 3256-3270

Proportional Integral Derivative (PID) controllers are widely used in
many fields because they are simple and effective. Tuning of the PID
controller parameters is not easy and does not give the optimal required
response, especially with non-liner system. In the last two decades many
intelligent optimization techniques were took attention of researchers like:Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) techniques. This paper represented the non-linear mathematical model and simulation of the synchronous generator with closed loop PID controller of AVR system. The traditional PID tuning technique is proposed as a point of comparison. Two of intelligent optimization techniques: PSO and GA are proposed in this paper to tune the PID controller parameters. The obtained results of the closed loop PSO-PID and GA-PID controller response to the unit step input signal shows excellent performance with respect to the traditional trial and
error tuning of the PID controller.

A Particle Swarm Optimization (PSO) Based Optimum of Tuning PID Controller for a Separately Excited DC Motor (SEDM)

Alia J. Mohammed

Engineering and Technology Journal, 2011, Volume 29, Issue 16, Pages 3331-3344

The PID algorithm is the most popular feedback controller used within the process industries. It is robust easily understood algorithm that can provide excellent control performance despite the varied dynamic characteristics of process plant. But the tuning of the PID controller parameters is not easy and does not give the optimal required response, especially with non-liner systems. In the last years emerged
several new intelligent optimization techniques like, Particle Swarm Optimization (PSO) techniques. This paper deals the non-liner mathematical model and simulation for speed control of separately excited D.C. motor with closed loop PID controller. The conventional PID tuning technique is represented as a point of comparison. The
intelligent optimization technique: PSO is proposed to tune the PID controller parameters. The obtained results of the closed loop PSO-PID Controller response shows the excellent response with comparing to the conventional PID, a good results gives in PSO-PID Controller. The simulation results presented in this paper show the effectiveness of the proposed method, which has got a wide number of advantages.

Particle Swarm Optimization for Adapting Fuzzy Logic Controller of SPWM Inverter Fed 3-Phase I.M.

Fadhil A. Hassan; Lina J. Rashad

Engineering and Technology Journal, 2011, Volume 29, Issue 14, Pages 2912-2925

According to the high performance demand of speed control of an induction motor, Fuzzy Logic Controller (FLC) gives superior behavior over wide range of speed variation. Fuzzy logic is a robust controller for linear and non-linear system, even if good mathematical representation of the system is not available. But, adapting
fuzzy controller parameters is very complex and depends on operator experience. Particle Swarm Optimization (PSO) algorithm is proposed in this paper as an optimization technique for adapting centers and width of triangle inputs membership functions. The ordinary adapting method of FLC is represented too. Meanwhile, based on the concept of optimization, ways of defining the fitness function of the
PSO including different performance criteria are also illustrated. The complete mathematical model and simulation of an induction motor and inverter are represented in this paper. The simulation results demonstrate that the proposed PSOFL speed controller realizes a good dynamic behavior of the I.M with very good speed tracking.

Particle Swarm Optimization for Total Operating Cost Minimization in Electrical Power System

Mohammed H. al-khafaji; Shatha S.Abdulla al-kabragyi

Engineering and Technology Journal, 2011, Volume 29, Issue 12, Pages 2539-2550

This paper presents solution of economic dispatch problem via a particle swarm optimization algorithm (PSO). The objective is to minimize the total generation fuel cost and keep the power flows within the security limits. The PSO is simple in concept, easy in implementation .It does not require any derivative information, sure and fast convergence, Moreover; it is needs less computational time than other heuristic methods. These features increase the applicability of the PSO, particularly in power system applications .The effectiveness of the proposed algorithm is demonstrated on the IEEE 37-bus system and their performances are compared with the results of genetic algorithm (GA). The results show that PSO can converge to optimum solution with higher accuracy in comparison with GA.

Training Artificial Neural Network Using Back-Propagation & Particle Swarm Optimization for Image Skin Diseases

Hanan A. R. Akkar; Samem Abass Salman

Engineering and Technology Journal, 2011, Volume 29, Issue 13, Pages 2739-2755

This work is devoted to compression Image Skin Diseases by using Discrete Wavelet Transform (DWT) and training Feed-Forward Neural Networks (FFNN) by using Particle Swarm Optimization(PSO) and compares it with Back-Propagation (BP) neural networks in terms of convergence rate and accuracy of results .The comparison between the two techniques will be mentioned. A MATLAB 6.5 program is used in simulation.
The structure Artificial Neural Network (ANN) of training image skin diseases is proposed as follows: 1- The proposed structure of NN that performs three compressions Images Skin training by BP algorithms with log sigmoid activation function, and three neurons in output layer.
2- The proposed structure of FFNN using PSO that performs three compressions Images Skin with hardlim activation function, and three neurons in output layer. The results obtained using PSO are compared to those obtained using BP. Learning iterations (602-4700 epoch), convergence time (1sec.- 100 sec.), number of initial
weights (1set - 75set), number of derivatives (0 - 38 derivatives) and accuracy (60% - 100%) are used as performance measurements. The obtained Mean Square Error (MSE) is 7 10 - to check the performance of algorithms. The results of the proposed neural networks performed indicate that PSO can be a superior training algorithm for
neural networks, which is consistent with other research in the area.

Al - Kalij Sub-Station: Feeder Reconfiguration by Particle Swarm Optimization

Qais M. Alias; Rana Ali Abttan

Engineering and Technology Journal, 2011, Volume 29, Issue 12, Pages 2375-2385

This paper presents the solution approach for the optimal reconfiguration problem
in distribution networks implementing Particle Swarm Optimization (PSO)
technique.
Network reconfiguration in distribution system is changing the status of
sectionalizing switches to reduce the power loss in the system. The main objective of
network reconfiguration is to find the network topology which is having the
minimum losses during any conditions exists in the network. A network
configuration is a valid solution to the problem if it satisfies reliability, security and
other operation constraints.
Particle Swarm Optimization is a robust stochastic evolutionary computation
technique, which is based on the movement and intelligence of swarms.
A standard particle swarm optimization algorithm is adapted and used in this work.
The primary case study is a part of the Baghdad area distribution network. It consists
of four feeders and 102 buses. The algorithm validity is verified first via application
to standard systems. Results show that the standard particle swarm optimization is
suitable for off-line reconfiguration studies.

Training Artificial Neural Networks by PSO to Perform Digital Circuits Using Xilinx FPGA

Hanan A. R. Akkar; Firas R. Mahdi

Engineering and Technology Journal, 2011, Volume 29, Issue 7, Pages 1329-1344

One of the major constraints on hardware implementations of Artificial Neural
Networks (ANNs) is the amount of circuitry required to perform the multiplication
process of each input by its corresponding weight and there subsequent addition. Field
Programmable Gate Array (FPGA) is a suitable hardware IC for Neural Network (NN)
implementation as it preserves the parallel architecture of the neurons in a layer and
offers flexibility in reconfiguration and cost issues. In this paper the adaption of the
ANN weights is proposed using Particle Swarm Optimization (PSO) as a mechanism
to improve the performance of ANN and also for the reduction in the ANN hardware.
For this purpose we modified the MATLAB PSO toolbox to be suitable for the taken
application. In the proposed design training is done off chip then the fully trained
design is download into the chip, in this way less circuitry is required. This paper
executes four bit Arithmetic Logic Unit (ALU) implemented using Xilinx schematic
design entry tools as an example for the implementation of digital circuits using ANN
trained by PSO algorithm.