IRAQI JOURNAL OF COMPUTERS, COMMUNICATIONS, CONTROL AND SYSTEMS ENGINEERING

Artificial Neural Networks (ANN) and Neuro - Fuzzy controllers can
be used as intelligent controllers to control non-linear dynamic systems through
learning, which can easily accommodate the non-linearity’s, time dependencies, model
uncertainty and external disturbances. Modern power systems are complex and non-
linear and their operating conditions can vary over a wide range. The Nonlinear Auto-
Regressive Moving Average (NARMA-L2) model system is proposed as an effective
neural networks controller model to achieve the desired robust Automatic Voltage
Regulator (AVR) for Synchronous Generator (SG) to maintain constant terminal
voltage. The essential part of Neuro-Fuzzy comes from a common framework called
adaptive networks, which unifies both neural networks and fuzzy models. The fuzzy
models under the framework of adaptive networks are called Adaptive-Network-based
Fuzzy Inference System (ANFIS), which possess certain advantages over neural
networks. The concerned neural networks and Neuro - Fuzzy controllers for AVR is
examined on different models of SG and loads. The results show that the Neuro-
controllers and Neuro - Fuzzy controllers have excellent responses for all SG models
and loads in view point of transient response and system stability. Also it shows that the
margins of robustness for Neuro - Fuzzy controller are greater than Neuro-controller.

Water has become the most important problem in relations between
the countries of the Middle East in the recent years. It occupies an important place on
the agenda of several international organizations. Water control and reduction loss of
water discharge is a major challenge facing the design of new irrigation projects. A
downstream control algorithm for demand operation of irrigation system is proposed in
this paper through maintaining downstream end discharge of the canal at the target point
by manipulating the upstream sluice gate in real time. The control of the water level and
discharge for canal irrigation system has non-linear, time-varying and uncertainty
characteristics. This paper compares three control algorithms; conventional PID, fuzzy
neural network PID, and PID neural network control based on fuzzy neural network
model. The simulation results show that the first control has larger over-shoot, longer
adjusting time and poorer anti-interference ability. The second control overcomes
above-mentioned short-comings, small overshoot, faster response speed, very small
steady state error. Third control produces better effects than previous controllers in both
steady performance and dynamic performance, including shorter steady-state time, non-
overshot, no oscillator, and higher dynamic tracking rate.

Thermocouples are usually used for measuring temperatures in steel
industry, gas turbine, diesel engine and many industrial processes. Thermocouple
usually have nonlinear Temperature-Voltage relationship (mV=f(T˚)). However, on the
monitoring side, it is required to have the inverse relationship [T˚=f-1(mV)] to
determined the actual temperature sensed by the thermocouple. In this work the neural
network is fully utilized to represent the required inverse nonlinear relationship of
different and most popular thermocouples (K, J, B) Types. Levenberg Marquardt is used
as learning process to find these neural networks. It is found that each type of
thermocouples under test can be represented by a single neural network structure.
Moreover, the obtained results show the power of neural network in representing the
inverse static relationship of each thermocouple that gives less than 1% of the actual
measured temperature in the whole temperature range in comparison to polynomial
fitting method.

Physical disabilities such as full or partial loss of function in the shoulder
and elbow are a common impairment in the elderly and a secondary effect due to
strokes, trauma, sports and injuries. Rehabilitation programs are the main method to
promote functional recovery in these subjects. This work focuses on designing and
implementing a 3 DoF's non-wearable, light weight rehabilitation robot for rehabilitee
the human arm that can be used in hospitals or homes. This robot structure eliminates
arm singularity problem of the end effecter with respect to the robot base by adding an
offset link. The design includes an adjustable mechanism standing on a seat for robot
base and links to be adaptable for all body sizes and to align for all human arm lengths.
Intelligent PD-like Fuzzy Logic position controllers (FLCs) are designed for joints of
the 3 DoF's robot to follow the desired medical trajectories during limited time with
minimum overshoot and minimum oscillations in position response. These controllers
are implemented using MATLAB Simulink. The controllers control the rehabilitation
robot using Data Acquisition Card, (Advantech PCI-1712) that generates and reads the
required digital and analog signals for robot. The experimental results are acceptable in
terms of the practical application.

This paper presents the modeling and control simulation for Lab-Volt
5250 five degree of freedom robot manipulator based on the standard Denavit-
Hartenberg approach. The dynamic model of the robot derived using Euler- Lagrange
equation which is the energy balance equation. This dynamic model has a very high
nonlinearity that is represented by using MATLAB, m-file and simulation to run the
dynamic model in open and close loop. In this research, the close loop simulation is
done by using two types of control theory that applied to control each joint of the robot
manipulator independently, the first one is PD controller and the second one is an
intelligent controller which is PD-like fuzzy controller used to control the joint position.

In this paper, a new optimization method for the Reciprocal Velocity
Obstacles (RVO) is proposed. It uses the Artificial Bee Colony Optimization (ABC) for
navigation control of multiple mobile robots with kinematic constraints. RVO is used
for collision avoidance between the robots, while ABC is used to choose the best path
for the robot maneuver to avoid colliding with other robots and to get to its goal faster.
This method is applied on 24 mobile robots facing each other. Simulation results have
shown that this method outperformed the ordinary RVO when the path was arbitrarily
chosen.

In the next generation of wireless communications, Multiple Input Multiple
Output (MIMO) communication system will be a key technology to enhance the
communication efficiency. The popular method for estimating the direction of arrival of
sources impinging on an array of MIMO sensors is Multiple Signal Classification
(MUSIC) method which is a problem of great interest in MIMO communication system.
The iterative searching technique has been shown more likely to converge to a local
maximum, causing errors in Direction of arrival (DOA) estimation. A new system is
proposed to estimate direction of arrival of sources for Multiple Input Multiple Output
(MIMO) communication system by combining Genetic Algorithm and (MUSIC)
method. In the proposed model, by using Genetic algorithm the direction of arrival
angles can be selected automatically good response by fast convergence, efficiency and
yield more accuracy to estimate the direction of arrival of the sources over existing
conventional spectral searching methods which is shown by the result of computer
simulation for proposed system. The important feature of new system is that, it is
observed that Genetic Algorithm (GA) combined with MUSIC method is a powerful
alternative in online DOA estimation

The electronic throttling angle control system is the newly common
requirement trend in automotive technology. It is used to regulate the amount of air flow
into the engine. Due to the existence of multiple non-smooth nonlinearities, the
controller design to the electronic throttle valve becomes a difficult task. These
nonlinearities including stick–slip friction, backlash, and a discontinuous nonlinear
spring involved in the system. The designed controller in the present work consists of
the estimated perturbation term with a negative sign (used to cancel the perturbation
term) and a stabilizing term used to stabilize the nominal system model. The
perturbation term consists of the external unknown input and the uncertainty in throttle
valve model including the nonlinear terms. The utilized estimator uses the sliding mode
control theory and based on the equivalent control methodology. The simulation results
show the effectiveness of the proposed controller in estimating the perturbation term.
And then in forcing the angle of the throttle valve to follow the desired opening angle in
presence of nonlinearities and disturbances in throttle system model and the variation in
its parameters.