ARTIFICIAL NEURAL NETWORK AND FUZZY LOGIC BASED POWER SYSTEM STABILIZER
Active In SP
Joined: Mar 2010
02-04-2010, 11:56 AM
A fuzzy logic based adaptive power system stabilizer (PSS) is presented in this paper. The parameters of the fuzzy logic based PSS are tuned by neural networks. The system is divided into two subsystems, a recursive least square identifier with a variable forgetting factor for the generator and a fuzzy logic based adaptive controller to damp oscillations. The effectiveness of the proposed PSS in increasing the damping of local and inter area system; a two area 4 machine. The ANFIS PSS uses a zero order Sugeno type fuzzy logic controller whose membership functions and consequences of also tuned by the back propagation method. The detailed description of the procedure is given in the next sections. Simulation results for a one machine infinite-bus system and one multimachine system are presented to show the effectiveness of the neuro fuzzy-logic in power system stabilizers.
Use Search at http://topicideas.net/search.php wisely To Get Information About Project Topic and Seminar ideas with report/source code along pdf and ppt presenaion
Active In SP
Joined: Jul 2010
09-07-2010, 07:05 AM
hey this is a very useful topics from reasearch and study point of view
Active In SP
Joined: Feb 2011
26-04-2011, 04:52 PM
M. SAI KIRAN
ARTIFICIAL NEURAL NETWORK.doc (Size: 714 KB / Downloads: 142)
A fuzzy logic based adaptive power system stabilizer (PSS) is presented in this paper. The parameters of the fuzzy logic based PSS are tuned by neural networks. The system is divided into two subsystems, a recursive least square identifier with a variable forgetting factor for the generator and a fuzzy logic based adaptive controller to damp oscillations. The effectiveness of the proposed PSS in increasing the damping of local and inter area system; a two area 4 machine. The ANFIS PSS uses a zero order Sugeno type fuzzy logic
controller whose membership functions and consequences of also tuned by the back propagation method. The detailed description of the procedure is given in the next sections. Simulation results for a one machine infinite-bus system and one multimachine system are presented to show the effectiveness of the neuro fuzzy-logic in power system stabilizers.
Conventional control theory relies on the key assumption of small range operation for the linear model to be valid. When the operation range is large, a linear controller is likely to perform poorly or to be unstable, because the non-linearities in the system cannot be properly compensated for.
In controller systems there are many non linearities whose discontinuous nature does not allow linear approximation these non linearities include coulomb friction, valve hysteresis, reactor, dead zones, backlash etc. These effects cannot be derived from linear model, and need a nonlinear technique.
To implement high performance control systems when the plant dynamic characteristics are poorly known or when large and unpredictable variations occur, a new class of control systems called non linear control systems have evolved which provide potential solutions. The non linear controllers for this purpose are adaptive controllers, fuzzy logic controllers and neural controllers. This paper portrays the concepts of fuzzy logic adaptive fuzzy logic neural networks which plays a indispensable enactment in the design of “Power System Stabilizer”.
In recent years, new artificial intelligence-based approaches have been proposed to design adaptive PSS. These approaches include Fuzzy-Logic (FL), Neural Networks (NN) and Genetic Algorithm (GA). Fuzzy Logic Based PSS (FLPSS) shows great potential in increasing the damping of generator oscillations, especially when made adaptive tuned by neural network. In this paper, an Adaptive Neuro Fuzzy Inference System (ANFIS) based PSS is developed which uses the post disturbance valve of the electrical power and speed deviation as inputs.
ARTIFICIAL NEURAL NETWORKS
Artificial Intelligence (AI) is a machine emulation of the human thinking process. The brain is the most complex machine on the earth. The human brain is a source of natural intelligence and a truly remarkable parallel computer. At present, the knowledge available about the human brain is so inadequate and the research on this complex organ of the body will dominate in the next century to understand it better and it’s thinking process as well.
Artificial intelligence tools such as Neural Networks and Fuzzy logic are expected to usher a new era in Electrical Engineering. These technologies have advanced significantly in recent years and have found wide application in electrical engineering. The current interest in neural networks is largely a result of their ability to mimic natural intelligence. Neural networks have emerged as a powerful technique for pattern recognition, pattern classification. Function approximation, optimization, prediction and automatic control.
Definition: A neural network is a massively parallel distributed processor that has natural propensity for storing experimental knowledge and making it available for use.
It resembles the brain in two respects
1. Knowledge acquired by the network through a learning process
2. Inter neuron connection strength is known as synaptic weights are used to store the knowledge.
CHARACTERISTICS OF ARTIFICIAL NEURAL NETWORKS:
Artificial neural networks are biologically inspired; that is, they are composed of elements that perform in a manner that is analogous to the most elementary functions of the biological neuron. The artificial neural networks are organized in a way that may (or may not) be related to the anatomy of the brain. Despite this superficial resemblance, an artificial neural network exhibits a surprising number of brain’s characteristics. For example they learn from experience, generalize from previous examples to new one, and abstract characteristics from inputs containing irrelevant data.
BASICFEATURES OF THE ARTIFICIAL NEURAL NETWORKS:
The basic features of artificial neural networks are given below:
1. High computational rates due to massive parallelism
2. Fault tolerance (damage of few nodes does not significantly effect the over all performance).
3. Learning and Training (The network adapts itself based on the information received from the environment).
4. Goal seeking (The performance to achieve the goal is measured and used to self organize the system, program rules are not necessary).
5. Primitive computational elements resembles are simple logical neuron and can’t do much).
Joined: Jul 2011
06-02-2012, 11:53 AM
to get information about the topic Artificial Intelligence Neural Networks full report ,ppt and related topic refer the link bellow
topicideashow-to-artificial-neural-networks-download-seminar and presentation-report
topicideashow-to-artificial-neural-network-seminar and presentation-report
topicideashow-to-artificial-neural-network-seminar and presentation-report?page=3
topicideashow-to-artificial-neural-networks-seminar and presentation-ppt