Abstract: In this study, aeroelastic response and performance
analyses have been conducted for a 5MW-Class composite wind
turbine blade model. Advanced coupled numerical method based on
computational fluid dynamics (CFD) and computational flexible
multi-body dynamics (CFMBD) has been developed in order to
investigate aeroelastic responses and performance characteristics of
the rotating composite blade. Reynolds-Averaged Navier-Stokes
(RANS) equations with k-ω SST turbulence model were solved for
unsteady flow problems on the rotating turbine blade model. Also,
structural analyses considering rotating effect have been conducted
using the general nonlinear finite element method. A fully implicit
time marching scheme based on the Newmark direct integration
method is applied to solve the coupled aeroelastic governing equations
of the 3D turbine blade for fluid-structure interaction (FSI) problems.
Detailed dynamic responses and instantaneous velocity contour on the
blade surfaces which considering flow-separation effects were
presented to show the multi-physical phenomenon of the huge rotating
wind- turbine blade model.
Abstract: In the previous multi-solid models,¤ò approach is
used for the calculation of fugacity in the liquid phase. For the first
time, in the proposed multi-solid thermodynamic model,γ approach
has been used for calculation of fugacity in the liquid mixture.
Therefore, some activity coefficient models have been studied that
the results show that the predictive Wilson model is more appropriate
than others. The results demonstrate γ approach using the predictive
Wilson model is in more agreement with experimental data than the
previous multi-solid models. Also, by this method, generates a new
approach for presenting stability analysis in phase equilibrium
calculations. Meanwhile, the run time in γ approach is less than the
previous methods used ¤ò approach. The results of the new model
present 0.75 AAD % (Average Absolute Deviation) from the
experimental data which is less than the results error of the previous
multi-solid models obviously.
Abstract: Quantitative precipitation forecast (QPF) from
atmospheric model as input to hydrological model in an integrated
hydro-meteorological flood forecasting system has been operational
in many countries worldwide. High-resolution numerical weather
prediction (NWP) models with grid cell sizes between 2 and 14 km
have great potential in contributing towards reasonably accurate QPF.
In this study the potential of two NWP models to forecast
precipitation for a flood-prone area in a tropical region is examined.
The precipitation forecasts produced from the Fifth Generation Penn
State/NCAR Mesoscale (MM5) and Weather Research and
Forecasting (WRF) models are statistically verified with the observed
rain in Kelantan River Basin, Malaysia. The statistical verification
indicates that the models have performed quite satisfactorily for low
and moderate rainfall but not very satisfactory for heavy rainfall.
Abstract: This research was to study effect of rotational speed
and eccentric factors, which were affected on looseness of bearing.
The experiment was conducted on three rotational speeds and five
eccentric distances with 5 replications. The results showed that
influenced factor affected to looseness of bearing was rotational
speed and eccentric distance which showed statistical significant.
Higher rotational speed would cause on high looseness. Moreover,
more eccentric distance, more looseness of bearing. Using bearing at
high rotational with high eccentric of shaft would be affected
bearing fault more than lower rotational speed. The prediction
equation of looseness was generated by regression analysis. The
prediction has an effected to the looseness of bearing at 91.5%.
Abstract: In this paper we present an autoregressive model with
neural networks modeling and standard error backpropagation
algorithm training optimization in order to predict the gross domestic
product (GDP) growth rate of four countries. Specifically we propose
a kind of weighted regression, which can be used for econometric
purposes, where the initial inputs are multiplied by the neural
networks final optimum weights from input-hidden layer after the
training process. The forecasts are compared with those of the
ordinary autoregressive model and we conclude that the proposed
regression-s forecasting results outperform significant those of
autoregressive model in the out-of-sample period. The idea behind
this approach is to propose a parametric regression with weighted
variables in order to test for the statistical significance and the
magnitude of the estimated autoregressive coefficients and
simultaneously to estimate the forecasts.
Abstract: In this paper, the application of multiple Elman neural networks to time series data regression problems is studied. An ensemble of Elman networks is formed by boosting to enhance the performance of the individual networks. A modified version of the AdaBoost algorithm is employed to integrate the predictions from multiple networks. Two benchmark time series data sets, i.e., the Sunspot and Box-Jenkins gas furnace problems, are used to assess the effectiveness of the proposed system. The simulation results reveal that an ensemble of boosted Elman networks can achieve a higher degree of generalization as well as performance than that of the individual networks. The results are compared with those from other learning systems, and implications of the performance are discussed.
Abstract: This paper proposes a method that predicts attractive
evaluation objects. In the learning phase, the method inductively
acquires trend rules from complex sequential data. The data is
composed of two types of data. One is numerical sequential data.
Each evaluation object has respective numerical sequential data. The
other is text sequential data. Each evaluation object is described in
texts. The trend rules represent changes of numerical values related
to evaluation objects. In the prediction phase, the method applies
new text sequential data to the trend rules and evaluates which
evaluation objects are attractive. This paper verifies the effect of the
proposed method by using stock price sequences and news headline
sequences. In these sequences, each stock brand corresponds to an
evaluation object. This paper discusses validity of predicted attractive
evaluation objects, the process time of each phase, and the possibility
of application tasks.
Abstract: Improvement in CAE methods has an important role for shortening of the vehicle product development time. It is provided that validation of the design and improvements in terms of durability can be done without hardware prototype production. In recent years, several different methods have been developed in order to investigate fatigue damage of the vehicle. The intended goal among these methods is prediction of fatigue damage in a short time with reduced costs. This study developed a new fatigue damage prediction method in the automotive sector using power spectrum densities of accelerations. This study also confirmed that the weak region in vehicle can be easily detected with the method developed in this study which results were compared with conventional method.
Abstract: User-based Collaborative filtering (CF), one of the
most prevailing and efficient recommendation techniques, provides
personalized recommendations to users based on the opinions of other
users. Although the CF technique has been successfully applied in
various applications, it suffers from serious sparsity problems. The
cloud-model approach addresses the sparsity problems by
constructing the user-s global preference represented by a cloud
eigenvector. The user-based CF approach works well with dense
datasets while the cloud-model CF approach has a greater
performance when the dataset is sparse. In this paper, we present a
hybrid approach that integrates the predictions from both the
user-based CF and the cloud-model CF approaches. The experimental
results show that the proposed hybrid approach can ameliorate the
sparsity problem and provide an improved prediction quality.
Abstract: In this work, bending fatigue life of notched
specimens with various notch geometries and dimensions is
investigated by experiment and Manson-Caffin theoretical method. In
this theoretical method, fatigue life of notched specimens is
calculated using the fatigue life obtained from the experiments for
plain specimens (without notch). Three notch geometries including
∪-shape, ∨-shape and C -shape notches are considered in this
investigation. The experiments are conducted on a rotary bending
Moore machine. The specimens are made of a low carbon steel alloy,
which has wide application in industry. The stress- life curves are
captured for all notched specimen by experiment. The results indicate
that Manson-Caffin analytical method cannot adequately predict
the fatigue life of notched specimen. However, it seems that the
difference between the experiments and Manson-Caffin predictions
can be compensated by a proportional factor.
Abstract: Cognitive models allow predicting some aspects of utility
and usability of human machine interfaces (HMI), and simulating
the interaction with these interfaces. The action of predicting is based
on a task analysis, which investigates what a user is required to do
in terms of actions and cognitive processes to achieve a task. Task
analysis facilitates the understanding of the system-s functionalities.
Cognitive models are part of the analytical approaches, that do not
associate the users during the development process of the interface.
This article presents a study about the evaluation of a human
machine interaction with a contextual assistant-s interface using ACTR
and GOMS cognitive models. The present work shows how these
techniques may be applied in the evaluation of HMI, design and
research by emphasizing firstly the task analysis and secondly the
time execution of the task. In order to validate and support our
results, an experimental study of user performance is conducted at
the DOMUS laboratory, during the interaction with the contextual
assistant-s interface. The results of our models show that the GOMS
and ACT-R models give good and excellent predictions respectively
of users performance at the task level, as well as the object level.
Therefore, the simulated results are very close to the results obtained
in the experimental study.
Abstract: The prediction of financial time series is a very
complicated process. If the efficient market hypothesis holds, then the predictability of most financial time series would be a rather
controversial issue, due to the fact that the current price contains already all available information in the market. This paper extends
the Adaptive Neuro Fuzzy Inference System for High Frequency
Trading which is an expert system that is capable of using fuzzy reasoning combined with the pattern recognition capability of neural networks to be used in financial forecasting and trading in high
frequency. However, in order to eliminate unnecessary input in the
training phase a new event based volatility model was proposed.
Taking volatility and the scaling laws of financial time series into consideration has brought about the development of the Intraday Seasonality Observation Model. This new model allows the observation of specific events and seasonalities in data and subsequently removes any unnecessary data. This new event based
volatility model provides the ANFIS system with more accurate input
and has increased the overall performance of the system.
Abstract: Prediction of viscosity of natural gas is an important parameter in the energy industries such as natural gas storage and transportation. In this study viscosity of different compositions of natural gas is modeled by using an artificial neural network (ANN) based on back-propagation method. A reliable database including more than 3841 experimental data of viscosity for testing and training of ANN is used. The designed neural network can predict the natural gas viscosity using pseudo-reduced pressure and pseudo-reduced temperature with AARD% of 0.221. The accuracy of designed ANN has been compared to other published empirical models. The comparison indicates that the proposed method can provide accurate results.
Abstract: This research presented in this paper is an on-going
project of an application of neural network and fuzzy models to
evaluate the sociological factors which affect the educational
performance of the students in Sri Lanka. One of its major goals is to
prepare the grounds to device a counseling tool which helps these
students for a better performance at their examinations, especially at
their G.C.E O/L (General Certificate of Education-Ordinary Level)
examination. Closely related sociological factors are collected as raw
data and the noise of these data are filtered through the fuzzy
interface and the supervised neural network is being utilized to
recognize the performance patterns against the chosen social factors.
Abstract: In this paper discrete choice models, Logit and Probit
are examined in order to predict the economic recession or expansion
periods in USA. Additionally we propose an adaptive neuro-fuzzy
inference system with triangular membership function. We examine
the in-sample period 1947-2005 and we test the models in the out-of
sample period 2006-2009. The forecasting results indicate that the
Adaptive Neuro-fuzzy Inference System (ANFIS) model outperforms
significant the Logit and Probit models in the out-of sample period.
This indicates that neuro-fuzzy model provides a better and more
reliable signal on whether or not a financial crisis will take place.
Abstract: The paper investigates the potential of support vector
machines and Gaussian process based regression approaches to
model the oxygen–transfer capacity from experimental data of
multiple plunging jets oxygenation systems. The results suggest the
utility of both the modeling techniques in the prediction of the
overall volumetric oxygen transfer coefficient (KLa) from operational
parameters of multiple plunging jets oxygenation system. The
correlation coefficient root mean square error and coefficient of
determination values of 0.971, 0.002 and 0.945 respectively were
achieved by support vector machine in comparison to values of
0.960, 0.002 and 0.920 respectively achieved by Gaussian process
regression. Further, the performances of both these regression
approaches in predicting the overall volumetric oxygen transfer
coefficient was compared with the empirical relationship for multiple
plunging jets. A comparison of results suggests that support vector
machines approach works well in comparison to both empirical
relationship and Gaussian process approaches, and could successfully
be employed in modeling oxygen-transfer.
Abstract: The present paper was concerned primarily with the
analysis, simulation of the air flow and thermal patterns in a lecture
room. The paper is devoted to numerically investigate the influence
of location and number of ventilation and air conditioning supply and
extracts openings on air flow properties in a lecture room. The work
focuses on air flow patterns, thermal behaviour in lecture room where
large number of students. The effectiveness of an air flow system is
commonly assessed by the successful removal of sensible and latent
loads from occupants with additional of attaining air pollutant at a
prescribed level to attain the human thermal comfort conditions and
to improve the indoor air quality; this is the main target during the
present paper. The study is carried out using computational fluid
dynamics (CFD) simulation techniques as embedded in the
commercially available CFD code (FLUENT 6.2). The CFD
modelling techniques solved the continuity, momentum and energy
conservation equations in addition to standard k – ε model equations
for turbulence closure.
Throughout the investigations, numerical validation is carried out by
way of comparisons of numerical and experimental results. Good
agreement is found among both predictions.
Abstract: Addition of milli or micro sized particles to the heat
transfer fluid is one of the many techniques employed for improving
heat transfer rate. Though this looks simple, this method has
practical problems such as high pressure loss, clogging and erosion
of the material of construction. These problems can be overcome by
using nanofluids, which is a dispersion of nanosized particles in a
base fluid. Nanoparticles increase the thermal conductivity of the
base fluid manifold which in turn increases the heat transfer rate.
Nanoparticles also increase the viscosity of the basefluid resulting in
higher pressure drop for the nanofluid compared to the base fluid. So
it is imperative that the Reynolds number (Re) and the volume
fraction have to be optimum for better thermal hydraulic
effectiveness. In this work, the heat transfer enhancement using
aluminium oxide nanofluid using low and high volume fraction
nanofluids in turbulent pipe flow with constant wall temperature has
been studied by computational fluid dynamic modeling of the
nanofluid flow adopting the single phase approach. Nanofluid, up till
a volume fraction of 1% is found to be an effective heat transfer
enhancement technique. The Nusselt number (Nu) and friction factor
predictions for the low volume fractions (i.e. 0.02%, 0.1 and 0.5%)
agree very well with the experimental values of Sundar and Sharma
(2010). While, predictions for the high volume fraction nanofluids
(i.e. 1%, 4% and 6%) are found to have reasonable agreement with
both experimental and numerical results available in the literature.
So the computationally inexpensive single phase approach can be
used for heat transfer and pressure drop prediction of new nanofluids.
Abstract: The problem of FIR system parameter estimation has been considered in the paper. A new robust recursive algorithm for simultaneously estimation of parameters and scale factor of prediction residuals in non-stationary environment corrupted by impulsive noise has been proposed. The performance of derived algorithm has been tested by simulations.
Abstract: The purpose of this paper is to present two different
approaches of financial distress pre-warning models appropriate for
risk supervisors, investors and policy makers. We examine a sample
of the financial institutions and electronic companies of Taiwan
Security Exchange (TSE) market from 2002 through 2008. We
present a binary logistic regression with paned data analysis. With
the pooled binary logistic regression we build a model including
more variables in the regression than with random effects, while the
in-sample and out-sample forecasting performance is higher in
random effects estimation than in pooled regression. On the other
hand we estimate an Adaptive Neuro-Fuzzy Inference System
(ANFIS) with Gaussian and Generalized Bell (Gbell) functions and
we find that ANFIS outperforms significant Logit regressions in both
in-sample and out-of-sample periods, indicating that ANFIS is a
more appropriate tool for financial risk managers and for the
economic policy makers in central banks and national statistical
services.