Key points are not available for this paper at this time.
Data and knowledge fusion-driven predictive model (DKF-DPM) has garnered significant attention for their ability to achieve high accuracy and robustness in complex manufacturing scenarios. By integrating data-driven learning with physical and domain knowledge, DKF-DPM is capable of more reliable modeling and prediction of nonlinear, multi-source and highly uncertain processes. This review systematically surveys recent advances of DKF-DPM in intelligent manufacturing, focusing on their modeling frameworks, representative applications in failure and fatigue life, cutting force and residual stress, machining quality and optimal processing parameters. In addition, current limitations and future research directions are discussed to highlight key challenges and opportunities. Overall, this study concludes that the integration of data-driven methods with domain knowledge is a critical pathway toward developing more reliable, interpretable, and adaptive predictive systems for intelligent manufacturing.
Ren et al. (Wed,) studied this question.