As the core component of aero engines, compressor blades in turbine engines have complex surface geometry requirements. With the rapid iteration of the turbine power system, the compressor blades used are constantly updated. An accurate prediction model that can quickly adapt to new blade production on manufacturing processes is urgently needed. However, most of the existing technologies cannot meet the high precision requirements of blade manufacturing, and the lack of data for newer blades makes training a predictive model in a new machining task a high time and economic cost. In this paper, we propose a domain generalization-based quality prediction framework for high-precision compressor blade manufacturing processes. The framework can make full use of the relevant manufacturing process data of historical blades to build a domain generalization model for adapting to the prediction of processing accuracy of new blades that have not been processed before. In particular, this study proposes a non-invasive generalization solution that meets accuracy requirements. Coordinate measuring machine (CMM) data is used as input features for prediction, rather than retrofitting sensors onto machinery after installation. To evaluate the effectiveness of the proposed framework, experiments were conducted on four series of aerospace compressor blades from Wuxi Turbine Blade Co., Ltd., China. CMM data from key stages such as blade root milling and integrated precision milling are used as input to predict final geometric errors. Comparison results verify that the proposed framework achieves the smallest prediction error at 0.037 mm, 0.013 mm, 0.021 mm, and 0.016 mm for four blades respectively. Note to Practitioners—This study is motivated by the necessity to develop a high-precision quality prediction model for compressor blade manufacturing, aiming to enhance production efficiency and mitigate economic and temporal costs associated with manufacturing losses. The rapid advancement of turbine engine power systems necessitates continuous dimensional modifications of compressor blades, which are high-precision components with complex curved surfaces. However, when blades with dimensional changes are introduced into production, existing quality prediction models often fail to align with the new specifications, necessitating model retraining. This model retraining process not only incurs significant time delays, adversely affecting production efficiency, but also results in economic losses due to the consumption of test-cut products. To address this issue, we propose a domain generalization-based quality prediction model that leverages historical machining data from similar blades. This approach enables the direct application of the model to blades with dimensional adjustments, ensuring high precision, improving processing efficiency, and reducing costs.
