Abstract: In this paper, a method based on Non-Dominated
Sorting Genetic Algorithm (NSGA) has been presented for the Volt /
Var control in power distribution systems with dispersed generation
(DG). Genetic algorithm approach is used due to its broad
applicability, ease of use and high accuracy. The proposed method is
better suited for volt/var control problems. A multi-objective
optimization problem has been formulated for the volt/var control of
the distribution system. The non-dominated sorting genetic algorithm
based method proposed in this paper, alleviates the problem of tuning
the weighting factors required in solving the multi-objective volt/var
control optimization problems. Based on the simulation studies
carried out on the distribution system, the proposed scheme has been
found to be simple, accurate and easy to apply to solve the multiobjective
volt/var control optimization problem of the distribution
system with dispersed generation.
Abstract: The purpose of this paper is to perform a multidisciplinary design and analysis (MDA) of honeycomb panels used in the satellites structural design. All the analysis is based on clamped-free boundary conditions. In the present work, detailed finite element models for honeycomb panels are developed and analysed. Experimental tests were carried out on a honeycomb specimen of which the goal is to compare the previous modal analysis made by the finite element method as well as the existing equivalent approaches. The obtained results show a good agreement between the finite element analysis, equivalent and tests results; the difference in the first two frequencies is less than 4% and less than 10% for the third frequency. The results of the equivalent model presented in this analysis are obtained with a good accuracy. Moreover, investigations carried out in this research relate to the honeycomb plate modal analysis under several aspects including the structural geometrical variation by studying the various influences of the dimension parameters on the modal frequency, the variation of core and skin material of the honeycomb. The various results obtained in this paper are promising and show that the geometry parameters and the type of material have an effect on the value of the honeycomb plate modal frequency.
Abstract: In order to improve control performance and eliminate steady, a coupling compensation for 6-DOF parallel robot is presented. Taking dynamic load Tank Simulator as the research object, this paper analyzes the coupling of 6-DOC parallel robot considering the degree of freedom of the 6-DOF parallel manipulator. The coupling angle and coupling velocity are derived based on inverse kinematics model. It uses the mechanism-model combined method which takes practical moving track that considering the performance of motion controller and motor as its input to make the study. Experimental results show that the coupling compensation improves motion stability as well as accuracy. Besides, it decreases the dither amplitude of dynamic load Tank Simulator.
Abstract: This research’s objective is to select the model with
most accurate value by using Neural Network Technique as a way to
filter potential students who enroll in IT course by Electronic learning
at Suan Suanadha Rajabhat University. It is designed to help students
selecting the appropriate courses by themselves. The result showed
that the most accurate model was 100 Folds Cross-validation which
had 73.58% points of accuracy.
Abstract: Judgment is affected by many agents and distortion in this assessment is unpreventable. Personality dimensions are among those factors that interfere with the distortion. In this research, the relations between personality dimensions of subject and his judgment on friends- personality dimensions is investigated. One-hundred friend couples completed both NEO Five Factor Inventory (NEOFFI) and Ahvaz Reality Distortion Inventory (ARDI) to make judgments about themselves and their friends. Observations show that judge-s Agreement and Neuroticism dimensions are impressed by reality distortion. On the other hand, this reality distortion interferes with one-s evaluation of his friend-s Agreement, Neuroticism, and Conscientiousness dimensions. Conscientiousness with suppressive effect on judge-s other dimensions plays the irrelevant role on personality judgment. Therefore, observer-rating tools which are used as a conventional criterion seem to be not valid because of the reality distortion due to judge-s personality dimensions.
Abstract: Initial values of reference vectors have significant influence on recognition accuracy in LVQ. There are several existing techniques, such as SOM and k-means, for setting initial values of reference vectors, each of which has provided some positive results. However, those results are not sufficient for the improvement of recognition accuracy. This study proposes an ACO-used method for initializing reference vectors with an aim to achieve recognition accuracy higher than those obtained through conventional methods. Moreover, we will demonstrate the effectiveness of the proposed method by applying it to the wine data and English vowel data and comparing its results with those of conventional methods.
Abstract: This paper was aimed at developing a computer aided
design and manufacturing system for spatial cylindrical cams. In the
proposed system, a milling tool with a diameter smaller than that of the
roller, instead of the standard cutter for traditional machining process,
was used to generate the tool path for spatial cams. To verify the
feasibility of the proposed method, a multi-axis machining simulation
software was further used to simulate the practical milling operation of
spatial cams. It was observed from computer simulation that the tool
path of small-sized cutter were within the motion range of a standard
cutter, no occurrence of overcutting. Examination of a finished cam
component clearly verifies the accuracy of the tool path generated for
small-sized milling tool. It is believed that the use of small-sized cutter
for the machining of the spatial cylindrical cams can generate a better
surface morphology with higher accuracy. The improvement in
efficiency and cost for the manufacturing of the spatial cylindrical cam
can be expected through the proposed method.
Abstract: The harmonic Arnoldi method can be used to find interior eigenpairs of large matrices. However, it has been shown that this method may converge erratically and even may fail to do so. In this paper, we present a new method for computing interior eigenpairs of large nonsymmetric matrices, which is called weighted harmonic Arnoldi method. The implementation of the method has been tested by numerical examples, the results show that the method converges fast and works with high accuracy.
Abstract: The behavior of Radial Basis Function (RBF) Networks greatly depends on how the center points of the basis functions are selected. In this work we investigate the use of instance reduction techniques, originally developed to reduce the storage requirements of instance based learners, for this purpose. Five Instance-Based Reduction Techniques were used to determine the set of center points, and RBF networks were trained using these sets of centers. The performance of the RBF networks is studied in terms of classification accuracy and training time. The results obtained were compared with two Radial Basis Function Networks: RBF networks that use all instances of the training set as center points (RBF-ALL) and Probabilistic Neural Networks (PNN). The former achieves high classification accuracies and the latter requires smaller training time. Results showed that RBF networks trained using sets of centers located by noise-filtering techniques (ALLKNN and ENN) rather than pure reduction techniques produce the best results in terms of classification accuracy. The results show that these networks require smaller training time than that of RBF-ALL and higher classification accuracy than that of PNN. Thus, using ALLKNN and ENN to select center points gives better combination of classification accuracy and training time. Our experiments also show that using the reduced sets to train the networks is beneficial especially in the presence of noise in the original training sets.
Abstract: Segmentation and quantification of stenosis is an
important task in assessing coronary artery disease. One of the main
challenges is measuring the real diameter of curved vessels.
Moreover, uncertainty in segmentation of different tissues in the
narrow vessel is an important issue that affects accuracy. This paper
proposes an algorithm to extract coronary arteries and measure the
degree of stenosis. Markovian fuzzy clustering method is applied to
model uncertainty arises from partial volume effect problem. The
algorithm employs: segmentation, centreline extraction, estimation of
orthogonal plane to centreline, measurement of the degree of
stenosis. To evaluate the accuracy and reproducibility, the approach
has been applied to a vascular phantom and the results are compared
with real diameter. The results of 10 patient datasets have been
visually judged by a qualified radiologist. The results reveal the
superiority of the proposed method compared to the Conventional
thresholding Method (CTM) on both datasets.
Abstract: Oxygen transfer, the process by which oxygen is
transferred from the gaseous to liquid phase, is a vital part of the
waste water treatment process. Because of low solubility of
oxygen and consequent low rate of oxygen transfer, sufficient
oxygen to meet the requirement of aerobic waste does not enter
through normal surface air water interface. Many theories have
come up in explaining the mechanism of gas transfer and
absorption of non-reacting gases in a liquid, of out of which, Two
film theory is important. An exiting mathematical model
determines approximate value of Overall Gas Transfer coefficient.
The Overall Gas Transfer coefficient, in case of Penetration theory,
is 1.13 time more than that obtained in case of Two film theory.
The difference is due to the difference in assumptions in the two
theories.
The paper aims at development of mathematical model which
determines the value of Overall Gas Transfer coefficient with
greater accuracy than the existing model.
Abstract: In many data mining applications, it is a priori known
that the target function should satisfy certain constraints imposed
by, for example, economic theory or a human-decision maker. In this
paper we consider partially monotone prediction problems, where the
target variable depends monotonically on some of the input variables
but not on all. We propose a novel method to construct prediction
models, where monotone dependences with respect to some of
the input variables are preserved by virtue of construction. Our
method belongs to the class of mixture models. The basic idea is to
convolute monotone neural networks with weight (kernel) functions
to make predictions. By using simulation and real case studies,
we demonstrate the application of our method. To obtain sound
assessment for the performance of our approach, we use standard
neural networks with weight decay and partially monotone linear
models as benchmark methods for comparison. The results show that
our approach outperforms partially monotone linear models in terms
of accuracy. Furthermore, the incorporation of partial monotonicity
constraints not only leads to models that are in accordance with the
decision maker's expertise, but also reduces considerably the model
variance in comparison to standard neural networks with weight
decay.
Abstract: In this paper, we propose a direct method based on the
real Schur factorization for solving the projected Sylvester equation
with relatively small size. The algebraic formula of the solution of
the projected continuous-time Sylvester equation is presented. The
computational cost of the direct method is estimated. Numerical
experiments show that this direct method has high accuracy.
Abstract: The use of externally bonded Carbon Fiber
Reinforced Polymer (CFRP) reinforcement has proven to be an
effective technique to strengthen steel structures. An experimental
study on CFRP bonded steel plate with double strap joint has been
conducted and specimens are tested under tensile loadings. An
empirical model has been developed using stress-based approach to
predict ultimate capacity of the CFRP bonded steel structure. The
results from the model are comparable with the experimental result
with a reasonable accuracy.
Abstract: Artificial Intelligence (AI) methods are increasingly being used for problem solving. This paper concerns using AI-type learning machines for power quality problem, which is a problem of general interest to power system to provide quality power to all appliances. Electrical power of good quality is essential for proper operation of electronic equipments such as computers and PLCs. Malfunction of such equipment may lead to loss of production or disruption of critical services resulting in huge financial and other losses. It is therefore necessary that critical loads be supplied with electricity of acceptable quality. Recognition of the presence of any disturbance and classifying any existing disturbance into a particular type is the first step in combating the problem. In this work two classes of AI methods for Power quality data mining are studied: Artificial Neural Networks (ANNs) and Support Vector Machines (SVMs). We show that SVMs are superior to ANNs in two critical respects: SVMs train and run an order of magnitude faster; and SVMs give higher classification accuracy.
Abstract: Nowadays predicting political risk level of country
has become a critical issue for investors who intend to achieve
accurate information concerning stability of the business
environments. Since, most of the times investors are layman and
nonprofessional IT personnel; this paper aims to propose a
framework named GECR in order to help nonexpert persons to
discover political risk stability across time based on the political
news and events.
To achieve this goal, the Bayesian Networks approach was
utilized for 186 political news of Pakistan as sample dataset.
Bayesian Networks as an artificial intelligence approach has been
employed in presented framework, since this is a powerful technique
that can be applied to model uncertain domains. The results showed
that our framework along with Bayesian Networks as decision
support tool, predicted the political risk level with a high degree of
accuracy.
Abstract: In this paper we developed the Improved Runge-Kutta Nystrom (IRKN) method for solving second order ordinary differential equations. The methods are two step in nature and require lower number of function evaluations per step compared with the existing Runge-Kutta Nystrom (RKN) methods. Therefore, the methods are computationally more efficient at achieving the higher order of local accuracy. Algebraic order conditions of the method are obtained and the third and fourth order method are derived with two and three stages respectively. The numerical results are given to illustrate the efficiency of the proposed method compared to the existing RKN methods.
Abstract: Understanding driving behavior is a complicated
researching topic. To describe accurate speed, flow and density of a
multiclass users traffic flow, an adequate model is needed. In this
study, we propose the concept of standard passenger car equivalent
(SPCE) instead of passenger car equivalent (PCE) to estimate the
influence of heavy vehicles and slow cars. Traffic cellular automata
model is employed to calibrate and validate the results. According to
the simulated results, the SPCE transformations present good
accuracy.
Abstract: Due to their high power-to-weight ratio and low cost, pneumatic actuators are attractive for robotics and automation applications; however, achieving fast and accurate control of their position have been known as a complex control problem. The paper presents a methodology for obtaining controllers that achieve high position accuracy and preserve the closed-loop characteristics over a broad operating range. Experimentation with a number of conventional (or "classical") three-term controllers shows that, as repeated operations accumulate, the characteristics of the pneumatic actuator change requiring frequent re-tuning of the controller parameters (PID gains). Furthermore, three-term controllers are found to perform poorly in recovering the closed-loop system after the application of load or other external disturbances. The key reason for these problems lies in the non-linear exchange of energy inside the cylinder relating, in particular, to the complex friction forces that develop on the piston-wall interface. In order to overcome this problem but still remain within the boundaries of classical control methods, we designed an auto selective classicaql controller so that the system performance would benefit from all three control gains (KP, Kd, Ki) according to system requirements and the characteristics of each type of controller. This challenging experimentation took place for consistent performance in the face of modelling imprecision and disturbances. In the work presented, a selective PID controller is presented for an experimental rig comprising an air cylinder driven by a variable-opening pneumatic valve and equipped with position and pressure sensors. The paper reports on tests carried out to investigate the capability of this specific controller to achieve consistent control performance under, repeated operations and other changes in operating conditions.
Abstract: Data mining incorporates a group of statistical
methods used to analyze a set of information, or a data set. It operates
with models and algorithms, which are powerful tools with the great
potential. They can help people to understand the patterns in certain
chunk of information so it is obvious that the data mining tools have
a wide area of applications. For example in the theoretical chemistry
data mining tools can be used to predict moleculeproperties or
improve computer-assisted drug design. Classification analysis is one
of the major data mining methodologies. The aim of thecontribution
is to create a classification model, which would be able to deal with a
huge data set with high accuracy. For this purpose logistic regression,
Bayesian logistic regression and random forest models were built
using R software. TheBayesian logistic regression in Latent GOLD
software was created as well. These classification methods belong to
supervised learning methods.
It was necessary to reduce data matrix dimension before construct
models and thus the factor analysis (FA) was used. Those models
were applied to predict the biological activity of molecules, potential
new drug candidates.