scholarly journals Physics-Based Neural Network Methods for Solving Parameterized Singular Perturbation Problem

Computation ◽  
2021 ◽  
Vol 9 (9) ◽  
pp. 97
Author(s):  
Tatiana Lazovskaya ◽  
Galina Malykhina ◽  
Dmitry Tarkhov
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Neural Network Approach ◽  
Architecture Model ◽  
Perturbation Problem ◽  
Digital Twins ◽  
Network Methods ◽  
Fixed Parameter ◽  
Input Variables ◽  
Parameter Values

This work is devoted to the description and comparative study of some methods of mathematical modeling. We consider methods that can be applied for building cyber-physical systems and digital twins. These application areas add to the usual accuracy requirements for a model the need to be adaptable to new data and the small computational complexity allows it to be used in embedded systems. First, we regard the finite element method as one of the “pure” physics-based modeling methods and the general neural network approach as a variant of machine learning modeling with physics-based regularization (or physics-informed neural networks) and their combination. A physics-based network architecture model class has been developed by us on the basis of a modification of classical numerical methods for solving ordinary differential equations. The model problem has a parameter at some values for which the phenomenon of stiffness is observed. We consider a fixed parameter value problem statement and a case when a parameter is one of the input variables. Thus, we obtain a solution for a set of parameter values. The resulting model allows predicting the behavior of an object when its parameters change and identifying its parameters based on observational data.

An artificial neural network approach to discrete-event simulation

1995 ◽  
Vol 9 (1) ◽  
pp. 37-49 ◽  
Author(s):  
Ian Flood ◽  
Kenneth Worley
Keyword(s):  
Neural Network ◽  
Discrete Event Simulation ◽  
Network Architecture ◽  
Discrete Event ◽  
Network Approach ◽  
Neural Network Approach ◽  
Event Simulation ◽  
The Neural Network ◽  
Component Processes ◽  
And Performance

AbstractThis paper proposes and evaluates a neural network-based method for simulating manufacturing processes that exhibit both noncontinuous and stochastic behavior processes more conventionally modeled, using discrete-event simulation algorithms. The incentive for developing the technique is its potential for rapid execution of a simulation through parallel processing, and facilitation of the development and improvement of models particularly where there is limited theory describing the dependence between component processes. A brief introduction is provided to a radial-Gaussian neural network architecture and training process, the system adopted for the work presented in this paper. A description of the basic approach proposed for applying this technology to simulation is then described. This involves the use of a modularized neural network approach to model construction and the prediction of the occurrence of events using information retained from several previous states of the simulation. A class of earth-moving systems, comprising a push-dozer and a fleet of scrapers, is used as the basis for assessing the viability and performance of the proposed approach. A series of experiments show the neural network to be capable of both capturing the characteristic behavior and making an accurate prediction of production rates of scraper-based earth-moving systems. The paper concludes with an indication of some areas for further development and evaluation of the technique.

Prediction of Remaining Life Time Based on Measurements of Stress for Thermal Barrier Coatings

2001 ◽  
Author(s):  
E. H. Jordan ◽  
W. Xie ◽  
M. Gell ◽  
L. Xie ◽  
F. Tu ◽  
...  
Keyword(s):  
Neural Network ◽  
Optical Measurement ◽  
Life Time ◽  
Remaining Life ◽  
Neural Network Approach ◽  
Regression Methods ◽  
Signal Features ◽  
The Neural Network ◽  
Network Methods ◽  
Non Destructive

Abstract Non-destructive determination of the remaining life of coatings of gas turbine parts is highly desirable. The present paper describes early attempts to prove the feasibility of doing this based on the optical measurement of the stress in the oxide that attaches the coating to the metal component. Both regression methods and neural network methods are compared and it was found that the neural network approach was superior for the case where multiple signal features were present. All methods provide useful predictions for the idealized case considered. Challenges presented by more complicated thermal cycles are discussed briefly.

FEEDFORWARD NEURAL NETWORK WITH ADAPTIVE REFERENCE PATTERN LAYER

1999 ◽  
Vol 09 (01) ◽  
pp. 1-9
Author(s):  
MIKKO LEHTOKANGAS
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Neural Network Architecture ◽  
Reference Pattern ◽  
Hybrid Neural Network ◽  
Rbf Networks ◽  
Pattern Layer ◽  
Input Variables ◽  
Hidden Layer ◽  
Efficient Learning

A hybrid neural network architecture is investigated for modeling purposes. The proposed hybrid is based on the multilayer perceptron (MLP) network. In addition to the usual hidden layers, the first hidden layer is selected to be an adaptive reference pattern layer. Each unit in this new layer incorporates a reference pattern that is located somewhere in the space spanned by the input variables. The outputs of these units are the component wise-squared differences between the elements of a reference pattern and the inputs. The reference pattern layer has some resemblance to the hidden layer of the radial basis function (RBF) networks. Therefore the proposed design can be regarded as a sort of hybrid of MLP and RBF networks. The presented benchmark experiments show that the proposed hybrid can provide significant advantages over standard MLPs and RBFs in terms of fast and efficient learning, and compact network structure.

scholarly journals Hard Turning on JIS S45C Structural Steel: An Experimental, Modelling and Optimisation Approach

2019 ◽  
Vol 16 (4) ◽  
pp. 7315-7340 ◽  
Author(s):  
R. Kumar ◽  
A. Modi ◽  
A. Panda ◽  
A. K. Sahoo ◽  
A. Deep ◽  
...  
Keyword(s):  
Neural Network ◽  
Structural Steel ◽  
Network Architecture ◽  
Cutting Speed ◽  
Process Efficiency ◽  
Depth Of Cut ◽  
Experimental Modelling ◽  
Architecture Model ◽  
Coated Carbide ◽  
Level 2

The present research is performed while turning of JIS S45C hardened structural steel with the multilayered (TiN-TiCN-Al2O3-TiN) CVD coated carbide insert by experimental, modelling and optimisation approach. Herein, cutting speed, feed rate, and depth of cut are regarded as input process factors whereas flank wear, surface roughness, chip morphology are considered to be measured responses. Abrasion and built up-edge are the more dominant mode of tool-wear at low and moderate cutting speed while the catastrophic failure of tool-tip is identified at higher cutting speed condition. Moreover, three different Modelling approaches namely regression, BNN, and RNN are implemented to predict the response variables. A Back-propagation neural network with a 3-8-1 network architecture model is more appropriate to predict the measured output responses compared to Elman recurrent neural network and regression model. The minimum mean absolute error for VBc, Ra and CRC is observed to be as 1.36% (BNN with 3- 8-1 structure), 1.11% (BNN with 3-8-1 structure) and 0.251 % (RNN with 3-8-1 structure). A multi-performance Optimisation approach is performed by employing the weighted principal component analysis. The optimal parametric combination is found as the depth of cut at level 2 (0.3 mm)-feed at level 1 (0.05 mm/rev) – cutting speed at level 2 (120 m/min) considered as favourable outcomes. The predicted results were validated through a confirmatory trial providing the process efficiency. The significant improvement for S/N ratio of CQL is observed to be 9.3586 indicating that the process is well suited to predict the machining performances. In conclusion, this analysis opens an avenue in the machining of medium carbon low alloy steel to enhance the machining performance of multi-layered coated carbide tool more effectively and efficiently.

scholarly journals Dissolved oxygen modelling using artificial neural network: a case of River Nzoia, Lake Victoria basin, Kenya

2016 ◽  
Vol 2 (1) ◽  
Author(s):  
Kanda Edwin Kimutai ◽  
Kipkorir Emmanuel Chessum ◽  
Kosgei Job Rotich
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Dissolved Oxygen ◽  
Network Architecture ◽  
Lake Victoria ◽  
Agricultural Runoff ◽  
Lake Victoria Basin ◽  
Artificial Neural ◽  
Input Variables ◽  
Artificial Neural Network Ann

River Nzoia in Kenya, due to its role in transporting industrial and municipal wastes in addition to agricultural runoff to Lake Victoria, is vulnerable to pollution. Dissolved oxygen is one of the most important indicators of water pollution. Artificial neural network (ANN) has gained popularity in water quality forecasting. This study aimed at assessing the ability of ANN to predict dissolved oxygen using four input variables of temperature, turbidity, pH and electrical conductivity. Multilayer perceptron network architecture was used in this study. The data consisted of 113 monthly values for the input variables and output variable from 2009–2013 which were split into training and testing datasets. The results obtained during training and testing were satisfactory with R2 varying from 0.79 to 0.94 and RMSE values ranging from 0.34 to 0.64 mg/l which imply that ANN can be used as a monitoring tool in the prediction of dissolved oxygen for River Nzoia considering the non-correlational relationship of the input and output variables. The dissolved oxygen values follow seasonal trend with low values during dry periods.

scholarly journals Early Detection of Alzheimer’s Disease using Convolutional Neural Network Architecture

2021 ◽  
Vol 8 (2) ◽  
pp. 48-57
Author(s):  
Deepthi Kamath ◽  
Misba Firdose Fathima ◽  
Monica K. P ◽  
Kusuma Mohanchandra
Keyword(s):  
Neural Network ◽  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Convolutional Neural Network ◽  
Network Architecture ◽  
Brain Mri ◽  
Memory Loss ◽  
Neural Network Approach ◽  
The Neural Network ◽  
Mri Scans

Alzheimer's disease is an extremely popular cause of dementia which leads to memory loss, problem-solving and other thinking abilities that are severe enough to interfere with daily life. Detection of Alzheimer’s at a prior stage is crucial as it can prevent significant damage to the patient’s brain. In this paper, a method to detect Alzheimer’s  Disease from Brain MRI images is proposed. The proposed approach extracts shape features and texture of the Hippocampus region from the MRI scans and a Neural Network is used as a Multi-Class Classifier for detection of AD. The proposed approach is implemented and it gives better accuracy as compared to conventional approaches. In this paper, Convolutional Neural Network is the Neural Network approach used for the detection of AD at a prodromal stage.

Use of Binary Sigmoid Function And Linear Identity In Artificial Neural Networks For Forecasting Population Density

2017 ◽  
Vol 1 (1) ◽  
pp. 43 ◽  
Author(s):  
Anjar Wanto ◽  
Agus Perdana Windarto ◽  
Dedy Hartama ◽  
Iin Parlina
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Network ◽  
Population Density ◽  
Network Architecture ◽  
Activation Function ◽  
Sigmoid Function ◽  
Backpropagation Algorithm ◽  
Architecture Model ◽  
Artificial Neural

Artificial Neural Network (ANN) is often used to solve forecasting cases. As in this study. The artificial neural network used is with backpropagation algorithm. The study focused on cases concerning overcrowding forecasting based District in Simalungun in Indonesia in 2010-2015. The data source comes from the Central Bureau of Statistics of Simalungun Regency. The population density forecasting its future will be processed using backpropagation algorithm focused on binary sigmoid function (logsig) and a linear function of identity (purelin) with 5 network architecture model used the 3-5-1, 3-10-1, 3-5 -10-1, 3-5-15-1 and 3-10-15-1. Results from 5 to architectural models using Neural Networks Backpropagation with binary sigmoid function and identity functions vary greatly, but the best is 3-5-1 models with an accuracy of 94%, MSE, and the epoch 0.0025448 6843 iterations. Thus, the use of binary sigmoid activation function (logsig) and the identity function (purelin) on Backpropagation Neural Networks for forecasting the population density is very good, as evidenced by the high accuracy results achieved.

A Hybrid Connectionist/ Substitution Approach for Data Encryption

2020 ◽  
pp. 23-42
Author(s):  
Raed Abu Zitar ◽  
Muhammed Jassem Al-Muhammed
Keyword(s):  
Neural Network ◽  
Hybrid Model ◽  
Network Architecture ◽  
Real Life ◽  
Data Encryption ◽  
Substitution Method ◽  
Neural Network Approach ◽  
The Neural Network ◽  
Encryption Method ◽  
Symbolic Approach

The authors believe that the hybridization of two different approaches results in more complex encryption outcomes. The proposed method combines a symbolic approach, which is a table substitution method, with another paradigm that models real-life neurons (connectionist approach). This hybrid model is compact, nonlinear, and parallel. The neural network approach focuses on generating keys (weights) based on a feedforward neural network architecture that works as a mirror. The weights are used as an input for the substitution method. The hybrid model is verified and validated as a successful encryption method.

scholarly journals Artificial Neural Network Approach to Mobile Location Estimation in GSM Network

2017 ◽  
Vol 63 (1) ◽  
pp. 39-44 ◽  
Author(s):  
Longinus S. Ezema ◽  
Cosmas I. Ani
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Performance Metrics ◽  
Federal Communication Commission ◽  
Location Estimation ◽  
Location Based Services ◽  
Estimation Accuracy ◽  
Neural Network Approach ◽  
Mobile Location ◽  
Gsm Network

AbstractThe increase in utilisation of mobile location-based services for commercial, safety and security purposes among others are the key drivers for improving location estimation accuracy to better serve those purposes. This paper proposes the application of Levenberg Marquardt training algorithm on new robust multilayered perceptron neural network architecture for mobile positioning fitting for the urban area in the considered GSM network using received signal strength (RSS). The key performance metrics such as accuracy, cost, reliability and coverage are the major points considered in this paper. The technique was evaluated using real data from field measurement and the results obtained proved the proposed model provides a practical positioning that meet Federal Communication Commission (FCC) accuracy requirement.

Sign in / Sign up

Export Citation Format

Share Document