Swarm optimization kernel extreme learning and sparse representation mechanical fault identification method

Abstract

The invention discloses a swarm optimization kernel extreme learning and sparse representation mechanical fault identification method, which is used for improving the efficiency and precision of mechanical fault identification. The invention provides a kernel extreme learning and sparse representation mechanical fault recognition method capable of effectively improving the fault recognition precision by combining the advantage of high efficiency of a kernel extreme learning machine and the advantage that sparse representation captures intrinsic characteristics of signals through dictionary redundancy. The bee colony optimization algorithm is integrated into the kernel extreme learning machine method, and the optimal model parameters of the kernel extreme learning machine are obtained through the optimization algorithm to further improve the performance of the recognition model. An input mechanical signal sample is firstly subjected to fault identification by utilizing a swarm-optimizedkernel extreme learning machine, and an input sample which cannot reach an expected identification result is subjected to secondary identification by adopting a sparse representation method, so thatrapid and accurate fault identification is realized. The method is suitable for mechanical fault identification.

Description

technical field [0001] The invention relates to the field of mechanical fault identification, in particular to a method for identifying mechanical faults using bee colony optimization kernel extreme learning and sparse representation. Background technique [0002] Industrial machinery and equipment usually operate in complex and harsh environments, resulting in frequent failures of mechanical components and economic losses. Mechanical equipment faults are characterized by gradualness and concealment at the initial stage. In the non-disassembled state, the time-frequency domain analysis method can solve the fault identification problem of mechanical equipment, but the diagnosis often depends on the experience and judgment of experts. However, due to the randomness of the development of fatigue damage, the uncertainty of the load and the complexity and diversity of the failure modes of the mechanical equipment, the sudden failure of the mechanical equipment is caused by the sm...

AI Technical Summary

Problems solved by technology

However, sparse representation classification is a linear representation model based on data. This linear representation is often based on the over-completeness of the dictionary, resulting in high computational complexity and low classification efficiency.

At present, the efficiency of fault identification based on sparse representation method is low, and it is difficult to meet the actual requirements.

[0005] In summary, one of the mechanical fault identification methods based solely on the kernel extreme learning machine method or the sparse representation method is difficult to meet the requirements of actual production

Images