Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{195742,
        author = {Raksha B. Patel and Priyanka N. Thorat and Divyesh V. Chavda},
        title = {An Orthogonal Neural Network-Based Extreme Learning Machine Approach for Solving Linear Chemical Physics Differential Equations},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {no},
        pages = {179-181},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=195742},
        abstract = {Differential equations are fundamental in chemistry and physics, especially in areas such as chemical physics, governing processes including diffusion, heat trans- fer, electrostatics, and reaction-transport. Although some equations are linear, explicit analytical solutions do not exist due to complex geometries, varied mate- rial properties, and nontrivial boundary conditions, which frequently make data unavailable. This paper presents an Orthogonal neural network-based Extreme Learning Machine (ONN-ELM) numerical framework for approximating solutions to linear differential equations with boundary conditions. The hidden layers are re- placed by a single-layer functional expansion block, and to optimize weights, we use the ELM algorithm. The proposed approach provides a mesh-free, computationally efficient, and physically consistent alternative to traditional numerical methods},
        keywords = {Linear differential equations, orthogonal neural network-based extreme learn- ing machine, chemical physics, numerical approximation, physics-based learning},
        month = {March},
        }