Explore physics informed machine learning simulation through a published research reference related to Artificial Intelligence & Machine Learning. This M.Tech resource summarizes the available source and suggests questions to validate before choosing an implementation.
Physics informed machine learning simulation: source and project details
| Research overview |
This reviewβbased project looks at how artificial intelligence and machine learning are being used in major mechanicalβengineering areas: structural simulation, computational fluid dynamics, design automation, additive manufacturing, and prognostics. We only had access to the indexed abstract of the 2026 review by Kherdekar and Kherdekar, so the full paper was not examined; our analysis relies on the published metadata. The abstract notes that surrogate models and physicsβinformed learning architectures can cut the computational cost of highβfidelity simulations dramatically, but they also bring challenges in generalizability and physical validation. Deep generative models are moving topology optimization from slow iterative searches to learned mappings.
Hybrid digital twins that blend physicsβbased solvers with dataβdriven corrections enable realβtime decisionβmaking. In prognostics, deep sequence models improve estimates of remaining useful life, and reinforcement learning is becoming more mature for robotic control. To help M.Tech researchers, this resource offers a structured way to design evaluation frameworks that compare these dataβdriven surrogates with traditional finiteβelement analysis and CFD solvers. Using the guidance, researchers can model the tradeβoffs between computational speedups and physical consistency.
|
| Reference Paper |
Impact of Artificial Intelligence and Machine Learning on Applications and Simulation Tools of Mechanical Engineering: A Comprehensive Review |
| Publication year (source record) |
2026 |
| Source document classification |
Research reference (type not independently verified) |
| Discovered via |
HAL metadata |
| Authors (source metadata) |
Vaishali Kherdekar, Shravani Kherdekar |
| Publication type (source metadata) |
journal-article |
| Journal / conference (source metadata) |
Asian Journal of Research in Computer Science |
| Publisher (source metadata) |
Sciencedomain International |
| DOI (from source metadata) |
10.9734/ajrcos/2026/v19i7887 |
| Metadata consistency check |
DOI registration metadata compared with indexed record; original PDF text not independently verified. |
| Evidence reviewed by generator |
Indexed abstract/description only; original full text, author names in PDF and methods require editorial verification. |
| Domain |
Computer Science & Engineering |
| Sub-Domain |
Artificial Intelligence & Machine Learning |
| Research source |
View Source |
| Get Help |
Get Help on WhatsApp
Message: Hi FE, I need help with “Impact of Artificial Intelligence and Machine Learning on Applications and Simulation Tools of Mechanical Engineering: A Comprehensive Review” in “Computer Science & Engineering”
|
Project or research direction
This is a source-backed research starting point, not a tested, ready-made student project. Any implementation requires independent feasibility, safety and results verification.
Possible tools or components to evaluate
Python, PyTorch, TensorFlow, DeepXDE, ANSYS, OpenFOAM, MATLAB
Methods or operating principles to examine
Comparative evaluation framework for physics-informed neural networks (PINNs) versus traditional numerical solvers; Surrogate model architecture design for structural or fluid dynamics simulation; Implementation guidance for deep sequence models in remaining useful life (RUL) estimation; Structuring of hybrid digital twin workflows integrating real-time data-driven correction terms.
Outputs to plan and verify
A structured methodology for evaluating surrogate model generalizability and physical validation; Comparative performance metrics (MSE, computational speedup, physical boundary condition adherence) between ML surrogates and FEA/CFD baselines; A research framework detailing the integration of deep generative models for topology optimization.
Techniques already mentioned by the source to verify
Development of active learning loops to mitigate data scarcity in high-value manufacturing contexts.
Further study ideas to evaluate
Integration of uncertainty quantification (UQ) methods to address the generalizability and interpretability challenges of deep learning surrogates
Check the complete source before describing any of these as new or absent from the original work.
Suggested verification steps
- Read the cited paper and check which methods, parameters and results it actually reports.
- Define a measurable project objective and list equipment or software you can access.
- Validate the proposed approach independently before claiming results, working code or experimental success.
Implementation ideas above are planning suggestions, not claims that the cited researchers built or tested those exact extensions.
Explore related M.Tech project topics or browse the engineering resource library for different methods and reference papers.