A dynamic construction method of knowledge graph for cnc machine tool fault diagnosis

Abstract

The example of the present invention provides a method for dynamically constructing a knowledge map for fault diagnosis of CNC machine tools, including: extracting entities from structured data and non-structural data and establishing relationships between entities, and establishing a case-specific part of the knowledge map; The similarity information between users is obtained from the user's evaluation of the case, and the relationship attributes between users in the knowledge graph are established. Because machine tool failures mainly occur in the production process and rely more on experience, a layer of relationship information between users is added to the original case information, and the corresponding cases are better recommended through the similarity between users. Improve the accuracy of diagnosis. According to the technical solution provided by the patent of the present invention, the reliability when using the knowledge map can be improved.

Description

technical field [0001] The invention relates to the field of fault diagnosis, and mainly relates to a method for dynamically constructing a knowledge graph for fault diagnosis of CNC machine tools. Background technique [0002] The CNC system integrates advanced computer technology, microelectronics technology, servo control technology and automatic control technology, so that the CNC machine tool shows the characteristics of electromechanical and hydraulic integration. While the operation ability of the CNC machine tool is improved, its failure rate is higher than that of ordinary machine tools. more, the difficulty of maintenance also increases. In the actual production and processing process, various faults may occur in the CNC system. Generally, the relevant maintenance engineers need a lot of case experience, accumulation of relevant knowledge, and the ability to quickly find and solve problems and practical experience , which virtually increases the difficulty of the ...

AI Technical Summary

Problems solved by technology

[0003] In the field of mechanical fault diagnosis, there are still great deficiencies in the representation and acquisition of knowledge. There is also a lot of room for improvement in the reasoning strategy of fault diagnosis. Most of the current research still lacks an effective learning mechanism. A practical In addition to the perfect fault identification method, the fault diagnosis system should also contain enough rich, accurate and effective knowledge in the knowledge base, so this requires our system to also need a certain learning ability

Images