Small manufacturing imperfections can have a surprisingly large impact on how efficiently modern turbine blades operate. While engineers have relied on complex computer simulations to understand these effects, evaluating every possible variation is often expensive and time-consuming. Researchers Xiaojing Wang, Hao Chen, Qifeng Jiang, Yifei Wu, Lichao Yao, Yifan Wang, and Zhengping Zou explore this challenge using a different approach. In their paper, “Bayesian Transfer Learning–Based Aerodynamic Robust Optimization of Ultrahigh-Lift Turbine Blades,” they make use of existing knowledge and limited new data to predict performance more efficiently.
At the heart of the study is a Bayesian framework that blends information from previous projects, engineering experience, and lower-cost analyses with a smaller number of new simulations. The goal is to help engineers make reliable design decisions without the huge computational effort traditionally required. The research demonstrates how this approach can identify more robust turbine blade designs while reducing the time and resources needed for optimization.
Although the study focuses on turbine blades, the methodology has potential applications across many engineering fields where performance can be affected by manufacturing tolerances and uncertainty. Learn more about how data-driven tools and engineering expertise can work together to create smarter, more resilient designs in the Journal of Aerospace Engineering at https://ascelibrary.org/doi/10.1061/JAEEEZ.ASENG-6769. The abstract is below.
Abstract
Geometric deviations can significantly degrade the aerodynamic performance of ultrahigh-lift (UHL) low-pressure turbine (LPT) blades. Conventional uncertainty quantification and robust optimization require extensive computational fluid dynamics (CFD) evaluations and are seldom practical. For efficient analysis and optimization based on limited data, we propose a Bayesian framework that integrates priors and external knowledge, as well as uncertainty modeling, to evaluate and enhance the aerodynamic robustness of UHL LPT blades. The Bayesian neural network (BNN) surrogate predicts deviation-induced performance variations while simultaneously quantifies its own predictive uncertainty, providing interpretability and facilitating transfer learning. Further, by integrating Bayesian inference and active learning, the active transfer learning scheme utilizes regularization from pretrained posterior information and adaptively selects high-value samples, lowering the BNN’s training cost by 80%–90% relative to training from scratch. Building on this efficient surrogate model, a biobjective Bayesian optimization approach balances aerodynamic robustness against blade area reduction. By leveraging external knowledge from low-cost nominal optimization and sensitivity analysis, this optimization method further halves the cost and yields a diverse Pareto front. When applied to the reference T106D-EIZ profile, the method increases the loading margin by 20%, lowers sensitivity to geometric deviations, and decreases blade area by 14.8%, demonstrating significantly enhanced robustness. Strategies to mitigate the detrimental effects of ultrahigh loading and geometric deviations are consistent: the key is to mitigate excessive adverse pressure gradients and improve the flow conditions in sensitive regions, thereby enhancing resistance to high loading and random perturbations. This Bayesian framework can be deployed to other turbomachinery blades with modest retraining, providing a data-efficient route for aerodynamic robust design in turbomachinery.
Get the details on how to apply this Bayesian framework to turbine blade analysis or to other forms of tolerance testing in the ASCE Library: https://ascelibrary.org/doi/10.1061/JAEEEZ.ASENG-6769.
