Machine Learning Algorithms for Engineering Design Optimization
PDF

Keywords

Machine Learning
Engineering Design
Optimization Algorithms
Neural Networks
Genetic Algorithms
Surrogate Modeling
Reinforcement Learning
Support Vector Machines

Abstract

Engineering design optimization is a complex, multidimensional problem that requires efficient computational methods to explore vast design spaces and identify optimal solutions. Machine learning (ML) algorithms have recently emerged as powerful tools to enhance the design optimization process by providing predictive models, surrogate modeling, and intelligent search capabilities. This paper reviews the application of several prominent machine learning algorithms—including neural networks, support vector machines, genetic algorithms, and reinforcement learning—in the context of engineering design optimization. Their strengths, limitations, and integration with traditional optimization techniques are discussed. A comparative analysis is provided, alongside a demonstration graph illustrating convergence performance of different ML-augmented optimization approaches. The study highlights the potential of ML to revolutionize engineering design workflows by reducing computational cost and improving solution quality.

PDF

All articles published in the American Journal of Engineering Mathematics (AJEM) are licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0). This license allows users to:

  • Share — copy and redistribute the material in any medium or format

  • Adapt — remix, transform, and build upon the material for any purpose, even commercially

Terms of use:

  • Appropriate credit must be given to the original author(s) and source.

  • A link to the license must be provided.

  • Any changes made must be indicated.

By submitting to AJEM, authors agree to make their work openly accessible under these terms.