Lecturer in Engineering Simulation and Data Science
University of Manchester
Dr. Ajay B Harish’s research focuses on the development of advanced computational mechanics methods, including classical computing methods (finite element techniques, machine learning, and uncertainty quantification) and, more recently, new paradigms in quantum computational mechanics. His work bridges fundamental method development with real-world applications, particularly in materials modelling. Recent efforts have been directed towards biomedical engineering, with projects in mathematical ophthalmology, neurovascular and cardiovascular flow modelling, and tendon mechanics.
Supervised learning of nonlinear superposition principle for hydrodynamic loading on structures
Structures like offshore wind turbines, marine renewable energy structures, bridge piers, and floating vessels, are routinely exposed to harsh environmental conditions. This is even more frequent during hazard events. These frequently drive the design. The physics and statistics of wave-structure interaction are complex and still not fully understood for strongly non-linear loads as experienced in the most severe conditions. In this work we aim to demostrate the possibility of a neural-network-based-surrogate model capable of probabilistically predicting the drag coefficients on the structures. In this regard, a building array subjected to wave loading as a demonstration for the more complex city configuration to be considered in future studies.Summary of Project Results
The project did not completely finish the outlined goals due to a conflict of architecture of the software and the GPU on the Bede system. However, this gave proof of concept of what could be achieved. It formed the basis for a larger allocation application to the WSI interaction community (HEC-WSI) (http://hec-wsi.ac.uk) for resources on Archer2.The work on Archer2 led to the publication of:
- Framework for uncertainty quantification of wave-structure interaction in a flume. Xiaoyuan Luo, Vijay Nandurdikar, Sangri-Yi, Alistair Revell, Georgios Fourtakas, Ajay B. Harish https://doi.org/10.1007/s40571-025-00967-4, which was recently accepted at the Journal of Computational Particle Mechanics.