Toward a framework of extracting typical machining process routines based on knowledge representation learning

Abstract

With the application of CAPP systems, manufacturing enterprises have accumulated a large volume of process data of parts, which are important strategic resources. Deeply mining the value hidden in these process data to improve the reuse rate of process knowledge is the key to realize the intellectualization of process planning. This paper builds a novel framework of extracting typical machining process routines (TMPRs) based on knowledge representation learning. First, two graph models, which describe machining processes including the relationships among “part-material-process-machine tool-cutting tool”, are established to present the semantic meaning of process data through the connectivity of graph structures in a direct way. One model conforms to the standard process routes, while the other makes some modifications to make the node “parts” have more in-links and out-links. Then, TransD algorithm is used to map the entities and relations based on the two models into dense low-dimensional real-valued spaces, and the better model is determined. After that, the vectors representing the parts of the better model are clustered, and the results show that the parts with a similar operation sequence and processed by the same cutting tools and machine tools can be clustered into the same cluster. This method breaks through the singleness and limitation of the traditional classification depending on the features of parts. Furthermore, TMPRs are extracted from the cluster results to verify the expression ability of semantic meaning of these vectors. Finally, we package the main functions of the research results into corresponding software modules. Compared with the existing process reuse methods, the proposed framework is much more efficient and extensible.