Session: GT9.1 - Analytics & Digital Solutions and GT6.2 - Emerging Technologies (includes Wind Energy)

Paper Number: 161958

161958 - Rotor Stress Prediction Using Convolutional Neural Network 

Application of AI/ML in creating predictive surrogate models in engineering domain is still in very initial stages. Several deep learning architectures are such as Physics Informed Neural Network (PINN) and Kolmogorov Arnold Network are being developed. PINN requires explicit use of governing PDEs in the network may not be straightforward for some industry problems. KAN is still in 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 a 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 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.

Presenting Author: Saurabh Mangal Siemens energy

Presenting Author Biography: Gas turbine design and analysis engineer Siemens energy Gurgaon.