High-dimension index structure technique of equipment failure cases based on distance measurement

Abstract

The invention discloses a high-dimensional indexing structure technology of an equipment failure case based on the distance measurement. A novel high-dimensional data indexing structure is provided. The indexing structure divides a space dynamic state into a grid structure according to the aggregating properties of an equipment state case, so that two spatially-adjacent cases are put together. Atthe same time, the relation between a threshold to be inquired and the distance from a vector to be inquired to two reference points is utilized, thereby excluding impossible data in a large range, greatly improving the efficiency of inquiry and reducing the CPU consumption, and meanwhile the indexing structure is insensitive to the data distribution, so as to lay the foundation for the engineering intellectualization of the equipment fault diagnosis.

Description

technical field [0001] The invention belongs to the fields of data mining and cluster analysis of mechanical equipment information, and relates to similar case retrieval technology of equipment failure cases, in particular to a high-dimensional index structure of equipment failure cases based on distance measurement. Background technique [0002] With the wide application of equipment monitoring and diagnosis technology in enterprises, especially the application of remote monitoring and diagnosis technology in large equipment manufacturing enterprises, cases of equipment failures have been fully accumulated. In this context, how to make full use of these cases to guide the judgment of unknown faults has aroused great interest. In essence, equipment failure cases can be regarded as a high-dimensional data formed by various features, and the set of equipment failure cases forms a high-dimensional database. Therefore, the problem of utilizing equipment failure cases can be tran...

AI Technical Summary

Problems solved by technology

It is reflected in the following two aspects: 1) As the number of dimensions increases, the query efficiency decreases

For example, the current mainstream multi-dimensional index structure has relatively high efficiency when dealing with low-dimensional situations, but once the high-dimensionality is high, it will appear powerless, even if the dimensionality reduction technology is used, it may not be able to achieve ideal results.

This is because the use of this technique may lead to the loss of effective information, especially not suitable for dealing with the case where the correlation of eigenvectors in special spaces is small

2) High calculation cost

Images