Using Neural Networks in Mathematical Modeling for Engineering Systems
American Journal Of Engineering Mathematics · 2022-12-31 · 3 (6) · 1-6
DOI: 10.71465/ajem734 ↗At a glance
Journal article in American Journal Of Engineering Mathematics, published online on 2022-12-31. Written by Dr. Emily R. Thompson.
Abstract (original language)
Neural networks (NNs), a subset of artificial intelligence, have gained significant traction in the field of mathematical modeling for engineering systems. Their ability to approximate complex nonlinear relationships, learn from data, and generalize well to unseen scenarios makes them ideal for tackling engineering problems that are difficult to model analytically. This paper reviews the theoretical foundations and practical applications of neural networks in engineering system modeling, highlighting key architectures, training algorithms, and their integration with traditional mathematical approaches. Case studies from structural dynamics, control systems, and thermal modeling are discussed to illustrate the effectiveness of neural networks. Challenges such as overfitting, interpretability, and computational cost are also addressed. Finally, the paper outlines future research directions for enhancing the reliability and applicability of neural network-based models in engineering.
Cite
APA
Thompson, D. E. R. (2022). Using Neural Networks in Mathematical Modeling for Engineering Systems. American Journal Of Engineering Mathematics, 3(6), 1-6. https://doi.org/10.71465/ajem734
Vancouver
Thompson DER. Using Neural Networks in Mathematical Modeling for Engineering Systems. American Journal Of Engineering Mathematics. 2022;3(6):1-6. doi:10.71465/ajem734
BibTeX
@article{Thompson2022,
author = {Thompson, Dr. Emily R.},
title = {Using Neural Networks in Mathematical Modeling for Engineering Systems},
journal = {American Journal Of Engineering Mathematics},
year = {2022},
volume = {3},
number = {6},
pages = {1--6},
doi = {10.71465/ajem734}
}
EUVIMED