Transfer Optimization in Accelerating the Design of Turbomachinery Cascades

Abstract This paper draws motivation from the fact that engineering optimizations were mostly carried out from scratch. In contrast, however, humans routinely take advantage of the knowledge from past experiences whenever a new task is met. Such a transfer learning process by leveraging knowledge from already completed tasks can be promising to significantly improve the performance of current state-of-the-art algorithms, particularly in solving expensive black-box problems. In light of the above, we propose a Cokriging based transfer optimization framework for the design of turbomachinery cascades, which is demonstrated by optimization to re-design the first-stage vane of GEE3. Specifically, when building Cokriging surrogate in such a transfer optimization context, the samples from already completed tasks are treated as low-fidelity (LF) data. The acquisition function of expected improvement is adopted to guide the search for high-fidelity (HF) data. In order to make full use of the “past experiences”, one of our efforts was drawn to designing selection strategies of initial HF samples. In addition, as the “past experiences” may do harm to the optimization of the target task, the correlation coefficients between source and target tasks in each optimization process were calculated to avoid “negative transfer”. The test results show that, by learning from the past, the transfer optimization framework can reduce the computational cost by much as 50%. More importantly, our proposed transfer learning strategy can effectively avoid “negative transfer” and thus always achieve better solutions than the compared state-of-the-art algorithms.