In the background of Industry 4.0, sustainable advanced manufacturing has become a pivotal challenge, necessitating the development of technologies that minimize resource consumption and environmental impact while maintaining high-quality production. Grinding technology plays a crucial role in this domain, providing solutions for processing hard and brittle materials with microscale accuracy, particularly when the grinding process is classified as precision machining. This study addresses the gaps in sustainable grinding by presenting a comprehensive review of lubrication strategies using an improved latent Dirichlet allocation (LDA) model integrated with Principal component analysis (PCA). The proposed model systematically identifies keyword distributions and topic clusters related to lubricant selection, providing insights into the evolving trends and practices in sustainable grinding. The findings enhance understanding of the main themes and future perspectives of sustainable grinding, bridging the gap between theoretical research and practical implementation in sustainable manufacturing.

Knowledge graphs (KGs) consisting of a large number of triples have become widespread recently, and many knowledge graph embedding (KGE) methods are proposed to embed entities and relations of a KG into continuous vector spaces. Such embedding methods simplify the operations of conducting various in-KG tasks (e.g., link prediction) and out-of-KG tasks (e.g., question answering). They can be viewed as general solutions for representing KGs. However, existing KGE methods are not applicable to inductive settings, where a model trained on source KGs will be tested on target KGs with entities unseen during model training. Existing works focusing on KGs in inductive settings can only solve the inductive relation prediction task. They can not handle other out-of-KG tasks as general as KGE methods since they don't produce embeddings for entities. In this paper, to achieve inductive knowledge graph embedding, we propose a model MorsE, which does not learn embeddings for entities but learns transferable meta-knowledge that can be used to produce entity embeddings. Such meta-knowledge is modeled by entity-independent modules and learned by meta-learning. Experimental results show that our model significantly outperforms corresponding baselines for in-KG and out-of-KG tasks in inductive settings.