Abstract: This study aimed at developing an inverse heat transfer approach for predicting the time-varying freezing front and the temperature distribution of tumors during cryosurgery. Using a temperature probe pressed against the layer of tumor, the inverse approach is able to predict simultaneously the metabolic heat generation and the blood perfusion rate of the tumor. Once these parameters are predicted, the temperature-field and time-varying freezing fronts are determined with the direct model. The direct model rests on one-dimensional Pennes bioheat equation. The phase change problem is handled with the enthalpy method. The Levenberg-Marquardt Method (LMM) combined to the Broyden Method (BM) is used to solve the inverse model. The effect (a) of the thermal properties of the diseased tissues; (b) of the initial guesses for the unknown thermal properties; (c) of the data capture frequency; and (d) of the noise on the recorded temperatures is examined. It is shown that the proposed inverse approach remains accurate for all the cases investigated.
Abstract: This study presents a simple inverse heat transfer procedure for predicting the wall erosion and the time-varying thickness of the protective bank that covers the inside surface of the refractory brick wall of a melting furnace. The direct problem is solved by using the Finite-Volume model. The melting/solidification process is modeled using the enthalpy method. The inverse procedure rests on the Levenberg-Marquardt method combined with the Broyden method. The effect of the location of the temperature sensors and of the measurement noise on the inverse predictions is investigated. Recommendations are made concerning the location of the temperature sensor.
Abstract: This study presents an inverse analysis for predicting the thermal conductivities and the heat flux of a high-temperature metallurgical reactor simultaneously. Once these thermal parameters are predicted, the time-varying thickness of the protective phase-change bank that covers the inside surface of the brick walls of a metallurgical reactor can be calculated. The enthalpy method is used to solve the melting/solidification process of the protective bank. The inverse model rests on the Levenberg-Marquardt Method (LMM) combined with the Broyden method (BM). A statistical analysis for the thermal parameter estimation is carried out. The effect of the position of the temperature sensors, total number of measurements and measurement noise on the accuracy of inverse predictions is investigated. Recommendations are made concerning the location of temperature sensors.
Abstract: Mumbai, being traditionally the epicenter of India's
trade and commerce, the existing major ports such as Mumbai and
Jawaharlal Nehru Ports (JN) situated in Thane estuary are also
developing its waterfront facilities. Various developments over the
passage of decades in this region have changed the tidal flux
entering/leaving the estuary. The intake at Pir-Pau is facing the
problem of shortage of water in view of advancement of shoreline,
while jetty near Ulwe faces the problem of ship scheduling due to
existence of shallower depths between JN Port and Ulwe Bunder. In
order to solve these problems, it is inevitable to have information
about tide levels over a long duration by field measurements.
However, field measurement is a tedious and costly affair;
application of artificial intelligence was used to predict water levels
by training the network for the measured tide data for one lunar tidal
cycle. The application of two layered feed forward Artificial Neural
Network (ANN) with back-propagation training algorithms such as
Gradient Descent (GD) and Levenberg-Marquardt (LM) was used to
predict the yearly tide levels at waterfront structures namely at Ulwe
Bunder and Pir-Pau. The tide data collected at Apollo Bunder, Ulwe,
and Vashi for a period of lunar tidal cycle (2013) was used to train,
validate and test the neural networks. These trained networks having
high co-relation coefficients (R= 0.998) were used to predict the tide
at Ulwe, and Vashi for its verification with the measured tide for the
year 2000 & 2013. The results indicate that the predicted tide levels
by ANN give reasonably accurate estimation of tide. Hence, the
trained network is used to predict the yearly tide data (2015) for
Ulwe. Subsequently, the yearly tide data (2015) at Pir-Pau was
predicted by using the neural network which was trained with the
help of measured tide data (2000) of Apollo and Pir-Pau. The analysis of measured data and study reveals that: The
measured tidal data at Pir-Pau, Vashi and Ulwe indicate that there is
maximum amplification of tide by about 10-20 cm with a phase lag
of 10-20 minutes with reference to the tide at Apollo Bunder
(Mumbai). LM training algorithm is faster than GD and with increase
in number of neurons in hidden layer and the performance of the
network increases. The predicted tide levels by ANN at Pir-Pau and
Ulwe provides valuable information about the occurrence of high and
low water levels to plan the operation of pumping at Pir-Pau and
improve ship schedule at Ulwe.
Abstract: Brain-Computer Interfaces (BCIs) measure brain
signals activity, intentionally and unintentionally induced by users,
and provides a communication channel without depending on the
brain’s normal peripheral nerves and muscles output pathway.
Feature Selection (FS) is a global optimization machine learning
problem that reduces features, removes irrelevant and noisy data
resulting in acceptable recognition accuracy. It is a vital step
affecting pattern recognition system performance. This study presents
a new Binary Particle Swarm Optimization (BPSO) based feature
selection algorithm. Multi-layer Perceptron Neural Network
(MLPNN) classifier with backpropagation training algorithm and
Levenberg-Marquardt training algorithm classify selected features.
Abstract: This paper presents an optimization method for
reducing the number of input channels and the complexity of the
feed-forward NARX neural network (NN) without compromising the
accuracy of the NN model. By utilizing the correlation analysis
method, the most significant regressors are selected to form the input
layer of the NN structure. An application of vehicle dynamic model
identification is also presented in this paper to demonstrate the
optimization technique and the optimal input layer structure and the
optimal number of neurons for the neural network is investigated.
Abstract: The number of Ground Motion Prediction Equations
(GMPEs) used for predicting peak ground acceleration (PGA) and
the number of earthquake recordings that have been used for fitting
these equations has increased in the past decades. The current PF-L
database contains 3550 recordings. Since the GMPEs frequently
model the peak ground acceleration the goal of the present study was
to refit a selection of 44 of the existing equation models for PGA in
light of the latest data. The algorithm Levenberg-Marquardt was used
for fitting the coefficients of the equations and the results are
evaluated both quantitatively by presenting the root mean squared
error (RMSE) and qualitatively by drawing graphs of the five best
fitted equations. The RMSE was found to be as low as 0.08 for the
best equation models. The newly estimated coefficients vary from the
values published in the original works.
Abstract: This paper aims at finding a suitable neural network
for monitoring congestion level in electrical power systems. In this
paper, the input data has been framed properly to meet the target
objective through supervised learning mechanism by defining normal
and abnormal operating conditions for the system under study. The
congestion level, expressed as line congestion index (LCI), is
evaluated for each operating condition and is presented to the NN
along with the bus voltages to represent the input and target data.
Once, the training goes successful, the NN learns how to deal with a
set of newly presented data through validation and testing
mechanism. The crux of the results presented in this paper rests on
performance comparison of a multi-layered feed forward neural
network with eleven types of back propagation techniques so as to
evolve the best training criteria. The proposed methodology has been
tested on the standard IEEE-14 bus test system with the support of
MATLAB based NN toolbox. The results presented in this paper
signify that the Levenberg-Marquardt backpropagation algorithm
gives best training performance of all the eleven cases considered in
this paper, thus validating the proposed methodology.
Abstract: The direct synthesis process of dimethyl ether (DME)
from syngas in slurry reactors is considered to be promising because
of its advantages in caloric transfer. In this paper, the influences of
operating conditions (temperature, pressure and weight hourly space
velocity) on the conversion of CO, selectivity of DME and methanol
were studied in a stirred autoclave over Cu-Zn-Al-Zr slurry catalyst,
which is far more suitable to liquid phase dimethyl ether synthesis
process than bifunctional catalyst commercially. A Langmuir-
Hinshelwood mechanism type global kinetics model for liquid phase
DME direct synthesis based on methanol synthesis models and a
methanol dehydration model has been investigated by fitting our
experimental data. The model parameters were estimated with
MATLAB program based on general Genetic Algorithms and
Levenberg-Marquardt method, which is suitably fitting experimental
data and its reliability was verified by statistical test and residual
error analysis.
Abstract: Design for cost (DFC) is a method that reduces life
cycle cost (LCC) from the angle of designers. Multiple domain
features mapping (MDFM) methodology was given in DFC. Using
MDFM, we can use design features to estimate the LCC. From the
angle of DFC, the design features of family cars were obtained, such
as all dimensions, engine power and emission volume. At the
conceptual design stage, cars- LCC were estimated using back
propagation (BP) artificial neural networks (ANN) method and
case-based reasoning (CBR). Hamming space was used to measure the
similarity among cases in CBR method. Levenberg-Marquardt (LM)
algorithm and genetic algorithm (GA) were used in ANN. The
differences of LCC estimation model between CBR and artificial
neural networks (ANN) were provided. ANN and CBR separately
each method has its shortcomings. By combining ANN and CBR
improved results accuracy was obtained. Firstly, using ANN selected
some design features that affect LCC. Then using LCC estimation
results of ANN could raise the accuracy of LCC estimation in CBR
method. Thirdly, using ANN estimate LCC errors and correct errors in
CBR-s estimation results if the accuracy is not enough accurate.
Finally, economically family cars and sport utility vehicle (SUV) was
given as LCC estimation cases using this hybrid approach combining
ANN and CBR.
Abstract: In the oil and gas industry, energy prediction can help
the distributor and customer to forecast the outgoing and incoming
gas through the pipeline. It will also help to eliminate any
uncertainties in gas metering for billing purposes. The objective of
this paper is to develop Neural Network Model for energy
consumption and analyze the performance model. This paper
provides a comprehensive review on published research on the
energy consumption prediction which focuses on structures and the
parameters used in developing Neural Network models. This paper is
then focused on the parameter selection of the neural network
prediction model development for energy consumption and analysis
on the result. The most reliable model that gives the most accurate
result is proposed for the prediction. The result shows that the
proposed neural network energy prediction model is able to
demonstrate an adequate performance with least Root Mean Square
Error.
Abstract: In this study four Holstein steers with rumen fistula
fed 7 kg of dry matter (DM) of diets differing in concentrate to
alfalfa hay ratios as 60:40, 70:30, 80:20, and 90:10 in a 4 × 4 latin
square design. The pH of the ruminal fluid was measured before
the morning feeding (0.0 h) to 8 h post feeding. In this study, a
two-layered feed-forward neural network trained by the
Levenberg-Marquardt algorithm was used for modelling of ruminal
pH. The input variables of the network were time, concentrate to
alfalfa hay ratios (C/F), non fiber carbohydrate (NFC) and neutral
detergent fiber (NDF). The output variable was the ruminal pH.
The modeling results showed that there was excellent agreement
between the experimental data and predicted values, with a high
determination coefficient (R2 >0.96). Therefore, we suggest using
these model-derived biological values to summarize continuously
recorded pH data.
Abstract: Gas chromatography (GC) is the most widely used
technique in analytical chemistry. However, GC has high initial cost
and requires frequent maintenance. This paper examines the
feasibility and potential of using a neural network model as an
alternative whenever GC is unvailable. It can also be part of system
verification on the performance of GC for preventive maintenance
activities. It shows the performance of MultiLayer Perceptron (MLP)
with Backpropagation structure. Results demonstrate that neural
network model when trained using this structure provides an
adequate result and is suitable for this purpose. cm.
Abstract: Minimization methods for training feed-forward networks with Backpropagation are compared. Feedforward network training is a special case of functional minimization, where no explicit model of the data is assumed. Therefore due to the high dimensionality of the data, linearization of the training problem through use of orthogonal basis functions is not desirable. The focus is functional minimization on any basis. A number of methods based on local gradient and Hessian matrices are discussed. Modifications of many methods of first and second order training methods are considered. Using share rates data, experimentally it is proved that Conjugate gradient and Quasi Newton?s methods outperformed the Gradient Descent methods. In case of the Levenberg-Marquardt algorithm is of special interest in financial forecasting.
Abstract: Financial forecasting is an example of signal processing problems. A number of ways to train/learn the network are available. We have used Levenberg-Marquardt algorithm for error back-propagation for weight adjustment. Pre-processing of data has reduced much of the variation at large scale to small scale, reducing the variation of training data.
Abstract: In this paper a modification on Levenberg-Marquardt algorithm for MLP neural network learning is proposed. The proposed algorithm has good convergence. This method reduces the amount of oscillation in learning procedure. An example is given to show usefulness of this method. Finally a simulation verifies the results of proposed method.
Abstract: This paper presents a critical study about the
application of Neural Networks to ion-exchange process. Ionexchange
is a complex non-linear process involving many factors
influencing the ions uptake mechanisms from the pregnant solution.
The following step includes the elution. Published data presents
empirical isotherm equations with definite shortcomings resulting in
unreliable predictions. Although Neural Network simulation
technique encounters a number of disadvantages including its “black
box", and a limited ability to explicitly identify possible causal
relationships, it has the advantage to implicitly handle complex
nonlinear relationships between dependent and independent
variables. In the present paper, the Neural Network model based on
the back-propagation algorithm Levenberg-Marquardt was developed
using a three layer approach with a tangent sigmoid transfer function
(tansig) at hidden layer with 11 neurons and linear transfer function
(purelin) at out layer. The above mentioned approach has been used
to test the effectiveness in simulating ion exchange processes. The
modeling results showed that there is an excellent agreement between
the experimental data and the predicted values of copper ions
removed from aqueous solutions.
Abstract: Training neural networks to capture an intrinsic
property of a large volume of high dimensional data is a difficult
task, as the training process is computationally expensive. Input
attributes should be carefully selected to keep the dimensionality of
input vectors relatively small.
Technical indexes commonly used for stock market prediction
using neural networks are investigated to determine its effectiveness
as inputs. The feed forward neural network of Levenberg-Marquardt
algorithm is applied to perform one step ahead forecasting of
NASDAQ and Dow stock prices.
Abstract: Levenberg-Marquardt method (LM) was proposed to
be applied as a non-linear least-square fitting in the analysis of a
natural gamma-ray spectrum that was taken by the Hp (Ge) detector.
The Gaussian function that composed of three components, main
Gaussian, a step background function and tailing function in the lowenergy
side, has been suggested to describe each of the y-ray lines
mathematically in the spectrum. The whole spectrum has been
analyzed by determining the energy and relative intensity for the
strong y-ray lines.
Abstract: In this study a neural network (NN) was proposed to
predict the sorption of binary mixture of copper-cobalt ions into
clinoptilolite as ion-exchanger. The configuration of the
backpropagation neural network giving the smallest mean square
error was three-layer NN with tangent sigmoid transfer function at
hidden layer with 10 neurons, linear transfer function at output layer
and Levenberg-Marquardt backpropagation training algorithm.
Experiments have been carried out in the batch reactor to obtain
equilibrium data of the individual sorption and the mixture of coppercobalt
ions. The obtained modeling results have shown that the used
of neural network has better adjusted the equilibrium data of the
binary system when compared with the conventional sorption
isotherm models.