Rotor Stress Prediction Using Convolutional Neural Network
Bibliographic record
Abstract
Abstract Application of AI/ML in creating predictive surrogate models in engineering domain is still in very initial stages. Several deep learning architectures such as Physics Informed Neural Network (PINN), and Kolmogorov Arnold Network are being developed. PINN requires explicit use of governing PDEs in the network and may not be straightforward for some industry problems. KAN is still in the initial development stage. Limited data and demand of higher quantitative accuracy mean that while using more conventional ML models, identification-cum-transformation of input features and model selection can be a challenge that requires deeper understanding of physics of the problem being solved. In this study, we present an innovative AI-ML based stress prediction model specifically designed for gas turbine rotor disks. The model leverages CNN (Convolutional Neural Network) architecture of AlexNet to create a deep learning regression model that identifies critical geometric features from the 2D cross-sectional images of the rotor disk and predicts the stress distribution at key locations under centrifugal loading conditions. To train and validate our model, the data is generated from ANSYS based FEA simulations using auto-generated rotor disk geometries. Our model demonstrates high accuracy with a margin of error within 5%, making it a valuable tool for rapid iterations during the preliminary design phase. This capability significantly enhances the efficiency of the design process, allowing for quicker optimization and validation of rotor disk designs. Looking ahead, we aim to extend the application of our AI-ML model to other gas turbine components and analysis, enabling the creation of a true digital twin of a gas turbine. This expansion will further streamline the design and analysis process, contributing to the development of more robust and efficient gas turbine systems.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".