Classification and knowledge extraction method for unstructured equipment fault knowledge

Abstract

The invention discloses an unstructured equipment fault knowledge classification and knowledge extraction method. The method comprises the following steps: acquiring fault diagnosis knowledge of to-be-diagnosed equipment and classifying the fault diagnosis knowledge; based on classification of fault diagnosis knowledge, establishing a corresponding knowledge extraction method, performing first knowledge extraction, and extracting concepts, attributes and association relationships among different concept attributes to form local knowledge; and performing second knowledge extraction on the local knowledge, integrating the obtained shallow knowledge and deep knowledge into composite knowledge, forming a global knowledge base, and realizing integration and fusion of multi-source information. The method effectively solves the problem that the experience and resource reuse rate is low in the field of current equipment fault diagnosis, a large amount of unstructured fault data and experience knowledge are converted into diagnosis maintenance knowledge capable of being processed by a machine, implicit knowledge dominance and dominant knowledge standardization in fault diagnosis are achieved, and the fault diagnosis efficiency is improved. The method has the advantages of completeness, good consistency and accuracy, so that the subsequent diagnosis accuracy and the maintenance decision efficiency are improved.

Description

technical field [0001] The invention belongs to the technical field of equipment fault diagnosis, and in particular relates to a classification of unstructured equipment fault knowledge and a knowledge extraction method. Background technique [0002] With the characteristics of large-scale equipment, complex structure, prominent operation automation and intelligence, the increase of equipment-related data, and the rapid development of artificial intelligence technology, equipment fault diagnosis has entered the era of "big data" and intelligent management. [0003] Knowledge extraction is the creation of knowledge from structured and unstructured sources. The resulting knowledge needs to be in a machine-readable and machine-interpretable format, and needs to be expressed in a way that is also easy for humans to understand and logically infer. Knowledge extraction is applied in the field of equipment fault diagnosis, which can effectively shorten the response time of fault di...

AI Technical Summary

Problems solved by technology

[0008] 2) Non-normative nature of accessible knowledge

However, the current research on knowledge acquisition in the field of equipment fault diagnosis is mostly focused on knowledge acquisition based on data mining, which still has the characteristics of low reuse rate of experience and resources, and fault diagnosis knowledge is non-standard, that is, incomplete and inconsistent. and imprecision

Images