Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userUsing Evolutionary Programming Algorithm for Designing a Robust Neural Model for a Class of Control Systems
استخدام خوارزمية البرمجة التطورية لتصميم نموذج عصبوني صلد لفئة من نظم التحكم
2366
0 317
0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
يهدف هذا البحث للحصول على نموذج عصبوني لفئة من النظم الخطية و اللاخطية و ذلك باستخدام خوارزمية البرمجة التطورية Evolutionary programming(EP لاختيار التركيب البنيوي الأمثل للشبكة العصبونية. استخدمنا برنامج ماتلاب Matlab لتصميم الشبكات العصبونية باستخدام EP, لما يملك من مرونة و سهولة في تمثيل المصفوفات (الأنساق الخلوية Cell Arrays و الأنساق متعددة الأبعادMulti Dimension Arrays ). و قد أثبتت النتائج العملية كفاءة الخوارزمية المستخدمة في الوصول إلى شبكة عصبونية مثلى. تم اختبار أداء و صلادة النموذج الناتج و ذلك بحذف إحدى عصبونات الطبقة المخفية للشبكة التي نتجت عن تطبيق EP و دراسة تأثير هذا الحذف على خرج النموذج الناتج, و قد أكدت الدراسة على فعالية الخوارزمية و ذلك بالنسبة لفئة النظم المستخدمة.
This study aims to design a neural model for a linear or nonlinear systems by using an Evolutionary Programming algorithm (EP) to choose the optimal structural construction for the network. We have used Matlab to design Neural Networks using (EP), because of its flexibility and ability to represent matrices (Cell Arrays, Multi Dimension Arrays). The experimental results confirm the efficiency with which this algorithm (EP) obtains the optimal network. We have tested the algorithm performance and the resulting model robustness by canceling one of the hidden layer nodes of the best net resulting from applying (EP). The effectiveness of that canceling on the resulting model output is also tested, and this study has shown the efficiency of the algorithm (EP) for the class of systems used.
References used
CANGELOSI, A;ELMAN, J.L. Gene regulation and biological development in neural networks :an exploratory model. Technical Report, CRL-UCSD, University of California San Diego, 1995
HAYKIN, S. Neural Networks :A Comprehensive Foundation. 2nd, Ed, London, prentice-Hall, 1999
FUJITA, O. statistical estimation of the number of hidden units for feed forward neural networks. neural networks11(5), 1988, 851-859
MONTANA, D; DAVIS, L. Training feed forward neural networks using genetic algorithms. In: Proceedings of the 11th International Joint Conference on AI, Detroit, MI, 1989,762–767
KITANO, H. Designing neural networks using genetic algorithms with graph generation system.Complex Systems4(4), 1990, 461–476
rate research
Read More
This paper presents the possibility of replacing the mathematical
optimizer in the Model Predictive Control Algorithm (MPC) with a
Feedforward Neural Network Optimizer (FNNO). The optimizer
trained offline to reduce the cost function. This maintai
n the system
model of the system, which is essential in MPC to get accepted
accuracy. we solve optimization problem faster than the algorithms
of traditional optimization, which we built, based on digital
computing.
This research aims to achieve the observability of any electrical network by the
possibility compensation the lost measurements due to a defect, allowing the possibility of
state estimation of the electrical network ,ie, obtaining a single solution
for a state
estimation. This is done by means of the network observability analysing using the
available set of measurements and adding virtual pseudo-measurements if the network is
not observable. this is done using a numerical algorithm that ensures obtaining the
minimum and optimal number of added critical pseudo-measurements so that the result of
state estimation was not adversely affected. The algorithm depends on solving the
equation of the linear state estimation and the analysing to the triangular factors of the gain
matrix and an easy way to arrange the axis of the jacobian matrix ,ie, the measurements
matrix to ensure getting the minimum set of candidate pseudo- measurements to be added
to real measurements, the numerical algorithm was acheived by environment in the
MATLAB and tested to present the results on the network observabilty analysing and
adding the pseudo-measurements algorithm on state estimation .The results of the program
were tested on IEEE-14 network, and they showed that if a number of measurements were
lost, they would be compensated by critical and pseudo-measurements. The results of state
estimation showed small error ratio between estimated values using the real measurements
and the estimated values after added the critical pseudo-measurements.
The Quality of Service (QoS) term is refer to capability of network to prioritization and service distinguish for providing
better service to some service classes and call types.
Because of the lack of resources, from one side, and user's mobility
from the other, provision of QoS guarantees is considered at the head of the challenges that wireless cellular mobile network systems face.
Call Admission Control (CAC) is used for providing and achieving QoS guarantees in wireless systems.
This paper proposes a new CAC algorithm with priority index for providing and achieving QoS guarantees on the call level in
wireless systems in terms of new call blocking probabilities using multiple thresholds to determinate the number of acceptable new calls of each type of service.
Results of simulation provided in this paper show that the application of proposed new CAC algorithm with priority index on
the New Call Bounding Scheme (NCBS) provides a new CAC scheme which has better performance in terms of new call blocking
Probabilities and guarantees any desired level of QoS for new call types with the keeping priority of handoff calls.
This paper presents the proposed Method for designing fuzzy
supervisory controller model for Proportional Integral Differential
controller (PID) by Fuzzy Reasoning Petri Net (FRPN),the Features
of Method shows the fuzzification value for each prop
erty of
membership function for each input of fuzzy supervisory controller,
and determine the total number of rules required in designing the
controller before enter the appropriate rules in the design phase of
the rules, and determine the value of the inputs of the rule that has
been activated, and assembly variables that have the same property
and show the value for each of them programmatically, and
determine the deffuzification value using deffuzification methods.
In Artificial Intelligence field, Knowledge Engineering phase is considered
the most crucial phase of the development life cycle of the Knowledge Base
Systems [1]. In fact, Formal Logic in general and Modus Ponens specifically has
been the dominan
t tools for structuring this knowledge [3]. This led for forming
a gap between the knowledge area and the information area, which depends
structurally on the Set Theory in general and on the Relational Algebra in
particular [1]. Thus, trying to introduce a bridge to pass this gap in structuring
and treating knowledge, we have conducted a new knowledge representation
model that depends structurally on (Classical and Fuzzy) Set Theory. Then we
used it as the base for conducting an inference model that attempt, using a set
of algebraic operations and by going through a series of stages, to reach a
solution of the problem under study, in a manner very close to the one that
humans usually use in treating their knowledge, taking into consideration the
speed and accuracy as much as the problem allows.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
