Characteristic extracting method for prediction of rotating mechanical failure trend

Abstract

The invention relates to a characteristic extracting method for prediction of rotating mechanical failure trend. The method includes the steps: (1) utilizing the remote online monitoring diagnostic center to conduct industrial onsite data collection and collecting vibration signals xj (t) of a plurality of channels through a plurality of sensors arranged on a rotating mechanical device; (2) conducting blind source separation on the vibration signals xj (t) according to FastICA algorithm and obtaining similar signal source yj (t) of the original independent vibration source sj (t); and (3) conducting characteristic frequency band decomposition of time frequency domain based on small wavelet packet on vector signals Y of the similar signal source yj (t) and extracting fault sensitive characteristic band. The characteristic extracting method is capable of recognizing the original independent signal source which shows as collecting signals in aliasing mode by adopting independent component analysis (ICA) processing, conducts characteristic frequency band acquisition based on the small wavelet packet on the independent signal source to judge whether one source signal has the development trend to fault and achieve the aim of preventing the fault in advance. The characteristic extracting method can be widely applied to prediction of the rotating mechanical failure trend.

Description

technical field [0001] The invention relates to a method for predicting the trend of mechanical faults, in particular to a feature extraction method for predicting the fault trend of rotating machinery. Background technique [0002] Rotating machinery is a complex nonlinear dynamic system. The working conditions of the equipment often change. The load, noise, and ambient temperature are all factors in dynamic changes. These non-fault factors will cause changes in the vibration signal energy collected by the sensor. Traditional theories generally linearize the nonlinear factors of the system, so when the vibration signal is analyzed to determine whether the equipment is faulty, the real equipment fault information is often ignored. At the same time, the process of most faults of complex rotating machinery from occurrence, development to final manifestation in a macroscopic form has the characteristics of a long history. The signal-to-noise ratio is very low, and the traditio...

AI Technical Summary

Problems solved by technology

Traditional theories generally linearize the nonlinear factors of the system, so when analyzing the vibration signal to determine whether the equipment is faulty, the real equipment fault information is often ignored

At the same time, the process of most faults of complex rotating machinery from occurrence, development to final manifestation in a macroscopic form has the characteristics of a long history. The signal-to-noise ratio is very low. The traditional method of fault prediction based on energy amplitude has great limitations when dealing with equipment signals with variable working conditions, and it is difficult to make effective predictions for equipment status.

Images