Integrated supporting vector machine mixed intelligent diagnosing method for mechanical fault

Abstract

The present invention discloses an integrated support vector machine mixed intelligent diagnosis method of machine failure. Said method includes the following steps: respectively adopting and lifting small wave packet, utilizing frequency band and empirical mode decomposition process to decompose vibration signal according to the eigen mode component and extract time domain statistical character of decomposed signal to form total characteristic set; providing characteristic distance evaluation technique and characteristic evaluation index; utilizing said characteristic evaluation index to select most sensitive characteristic set from the total characteristic set; using said most sensitive characteristic set as diagnosis characteristics and creating integrated support vector machine mixed intelligent diagnosis model so as to implement intelligent diagnosis of machine failure state.

Description

technical field [0001] The invention belongs to the field of intelligent diagnosis of mechanical equipment faults, in particular to an integrated support vector machine hybrid intelligent diagnosis method for mechanical faults. Background technique [0002] In order to get rid of the problem of excessive reliance on professional technicians and diagnostic experts in the fault diagnosis of mechanical equipment, and realize efficient and reliable intelligent diagnosis online, in recent years, people have applied artificial intelligence technologies such as fuzzy theory, expert system, neural network and cluster analysis. The intelligent fault diagnosis of mechanical equipment has achieved certain results in practice. However, in practical applications, people find that these technologies are not perfect. For example, fuzzy fault diagnosis often needs to manually determine the membership function and fuzzy relationship matrix based on prior knowledge. There are many difficulti...

AI Technical Summary

Problems solved by technology

However, in practical applications, due to the high complexity of time and space, the execution of support vector machines is often an approximate calculation; at the same time, the selection of kernel function parameters makes support vector machines prone to over-learning or under-learning, which directly affects its performance. Promote performance

[0005] The integrated support vector machine can effectively improve the classification performance of a single support vector machine, however, when the early fault features are very weak or the fault samples are not typical, it may still produce wrong diagnostic results

Images