Application of Artificial Neural Network as a Near-Real Time Technique for Solving Non-Linear Inverse Heat Conduction Problems in a One-Dimensional Medium With Moving Boundary

2021 ◽  
Author(s):  
Jian Zhang ◽  
Obinna Uyanna ◽  
Hamidreza Najafi
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Heat Conduction ◽  
Real Time ◽  
Moving Boundary ◽  
Inverse Heat Conduction ◽  
One Dimensional ◽  
Non Linear ◽  
Artificial Neural ◽  
Inverse Heat Conduction Problems

A Near Real-Time Solution Approach for Surface Heat Flux Estimation in One Dimensional Inverse Heat Conduction Problems With Moving Boundary

2019 ◽  
Author(s):  
Obinna Uyanna ◽  
Hamidreza Najafi
Keyword(s):  
Heat Flux ◽  
Heat Conduction ◽  
Real Time ◽  
Surface Heat Flux ◽  
Moving Boundary ◽  
Surface Heat ◽  
Inverse Heat Conduction ◽  
Heat Flux Estimation ◽  
Flux Estimation ◽  
Inverse Heat Conduction Problems

Abstract Developing accurate and efficient solutions for inverse heat conduction problems allows advancements in the heat flux measurement techniques for many applications. In the present paper, a one-dimensional medium with a moving boundary is considered. It is assumed that two thermocouples are used to measure temperature at two locations within the medium while the front boundary is moving towards the back surface. Determining surface heat flux using measured temperature data is an inverse heat conduction problem. A filter based Tikhonov regularization method is used to develop a solution for this problem. Filter coefficients are calculated for various thicknesses of the medium. It is demonstrated that the filter coefficients can be interpolated to calculate the appropriate values for each thickness while it is continuously moving at a known rate. The use of filter method allows near real-time heat flux estimation. The developed solution is validated through several numerical test cases including a test case for a moving boundary in a medium modeled in COMSOL. It is shown that the proposed solution can effectively estimate the surface heat flux on the moving boundary in a near real-time fashion.

scholarly journals Improved non-linear transfer function and neural network methods of flow routing for real-time forecasting

2001 ◽  
Vol 3 (3) ◽  
pp. 153-164 ◽  
Author(s):  
D. F. Lekkas ◽  
C. E. Imrie ◽  
M. J. Lees
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Transfer Function ◽  
Real Time ◽  
State Of The Art ◽  
Comparison Results ◽  
Network Methods ◽  
Forecasting Performance ◽  
Non Linear ◽  
Artificial Neural

Data-based methods of flow forecasting are becoming increasingly popular due to their rapid development times, minimum information requirements, and ease of real-time implementation, with transfer function and artificial neural network methods the most commonly applied methods in practice. There is much antagonism between advocates of these two approaches that is fuelled by comparison studies where a state-of-the-art example of one method is unfairly compared with an out-of-date variant of the other technique. This paper presents state-of-the-art variants of these competing methods, non-linear transfer functions and modified recurrent cascade-correlation artificial neural networks, and objectively compares their forecasting performance using a case study based on the UK River Trent. Two methods of real-time error-based updating applicable to both the transfer function and artificial neural network methods are also presented. Comparison results reveal that both methods perform equally well in this case, and that the use of an updating technique can improve forecasting performance considerably, particularly if the forecast model is poor.

Inverse Estimation of Surface Temperature in Nanoscale Using the Artificial Neural Network

2005 ◽  
Author(s):  
Bup Sung Jung ◽  
Sun K. Kim ◽  
Woo Il Lee
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Heat Conduction ◽  
Heat Conduction Problem ◽  
Inverse Heat Conduction Problem ◽  
Inverse Heat Conduction ◽  
Nanoscale Structures ◽  
Temperature Observation ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

An inverse heat conduction problem (IHCP) for nanoscale structures was studied. The conduction phenomenon is modeled using the Boltzmann transfer equation. Phonon-mediated heat conduction in one dimension is considered. One boundary, where temperature observation takes place, is subjected to a known boundary condition and the other boundary is exposed to an unknown temperature. The artificial neural network (ANN) is employed to solve the described inverse problem. Sample results are presented and discussed.

Sign in / Sign up

Export Citation Format

Share Document