Self-adaptive stochastic resonance early fault diagnosis method based on grey wolf optimization algorithm

Abstract

The invention relates to the field of early fault diagnosis of rotating machineries, and discloses a self-adaptive stochastic resonance early fault diagnosis method based on a grey wolf optimization algorithm. The self-adaptive stochastic resonance early fault diagnosis method improves the weak signal detection ability of a stochastic resonance method, and realizes precise diagnosis of machinery early faults. The self-adaptive stochastic resonance early fault diagnosis method introduces the grey wolf optimization algorithm into a bistable state stochastic resonance method, optimizes stochastic resonance structure parameters, selects the optimal structure parameter adaptively according to input signal features, realizes the optimal stochastic resonance output, and further achieves precise extraction of weak faults and accurate fault recognition. The self-adaptive stochastic resonance early fault diagnosis method is suitable for early fault diagnosis of rotating machinery.

Description

technical field [0001] The invention relates to the field of early fault diagnosis of rotating machinery, in particular to a bistable self-adaptive stochastic resonance early fault diagnosis method based on gray wolf optimization algorithm. Background technique [0002] As the key large-scale modern rotating machinery equipment in the pillar enterprises of the national economy, its safe operation is not only related to the life safety of equipment operators, the economic interests of enterprises, but also to national security and rights and interests. A large number of scientific research and engineering examples show that if the fault characteristics can be effectively extracted in the early stage of the fault, and then effective targeted remedial measures can be formulated to ensure the safe and efficient operation of the equipment. [0003] However, large rotating machinery usually works in a low-speed, heavy-load, and strong-noise environment, resulting in the vibration ...

AI Technical Summary

Problems solved by technology

However, the stochastic resonance method is greatly affected by its structural parameters, and it is difficult to obtain ideal detection results in the actual signal processing process.

Most of the existing adaptive stochastic resonance methods select the values ​​of each parameter separately, and seldom consider the interaction between parameters, so it is difficult to realize the synchronous adaptive selection of multiple parameters, resulting in low accuracy of early weak fault diagnosis

Images