Improved turbine design optimization using mixed fidelity data
A Novel Multi-fidelity Surrogate for Turbomachinery Design Optimization
Computational Engineering, Finance, and Science
Summary
Optimizing the design of turbines is very costly because it relies on detailed computer simulations called high-fidelity models. The authors found that current methods using both cheap, rough models and expensive, accurate models sometimes fail to find the best design over time. They created a new method that combines global models using all data with local models using only the accurate data, detecting when the cheap data is not helpful. This new method works better and more reliably in tests, including real turbine design cases.
What this means in practice
- •For aerospace engineers: Optimize turbine aerodynamic profiles more efficiently by combining multiple simulation fidelities with adaptive local modeling strategies.
- •For mechanical design teams: Improve turbine endwall cooling layout designs using adaptive surrogate models that reduce costly high-fidelity simulation needs.
Authors
Qineng Wang, Liming Song, Zhendong Guo, Jun Li, Zhenping Feng
Abstract
Turbomachinery design optimization involves expensive black-box problems. Sample-efficient multi-fidelity optimization (MFO) offers an efficient solution. By utilizing multi-fidelity surrogates (MFS), the MFO algorithm can use fewer high-fidelity samples aided by low-fidelity samples to establish an accurate surrogate model. However, when MFS is used in sequential sampling optimization, it has been observed that the final optimal solution obtained by single-fidelity optimization (SFO) is better than that of MFO, even though MFO performs better at the early stages. This can be attributed to the assumption of an even and nested distribution of samples, which is incorrect when using a sequential adding strategy. To address these issues, we propose a novel algorithm called multi-single-fidelity optimization (MSFO) to overcome the limitations of the conventional MFO procedures. In the surrogate establishment of MSFO, we use the density-based spatial clustering of applications with noise (DBSCAN) method to detect local areas where low-fidelity samples are no longer effective. A combination of both global MFS and local single-fidelity surrogate model, built using high-fidelity samples alone, is used to establish an ensemble, which improves the anti-interference ability of the algorithm against misleading low-fidelity data. The effectiveness of the MSFO algorithm is verified first on numerical benchmark functions. Then, the algorithm is used to optimize the aerodynamic profile of a turbine and the film cooling layout design of a turbine endwall. Here, high-fidelity sample sources are obtained from fine-mesh CFD simulations, whereas low-fidelity sample sources are obtained from the same simulations run on a coarser mesh. The results demonstrate that our MSFO algorithm performs significantly better than the conventional SFO and MFO processes, with a higher level of robustness.