Mechanical fault diagnosis method based on LOF-Kurtogram

Abstract

The invention discloses a rotating machine fault diagnosis method based on LOF-Kurtogram. The method comprises the following steps: firstly, segmenting a mechanical monitoring signal into a pluralityof data sections by utilizing a sliding time window with a fixed length; extracting feature index vectors such as a time domain and a time-frequency domain of each data sections; setting an initial value of a parameter k in an LOF algorithm, calculating a local abnormal factor value of each data section, screening out abnormal sections based on a 3 sigma criterion, and removing and cleaning the abnormal sections; and then inputting the cleaned data into the Kurtogram to obtain a filtered data section, solving an envelope spectrum of the filtered data section, and searching a fault characteristic frequency to complete fault diagnosis. According to the method, a traditional Kurtogram algorithm is improved on the basis of local abnormal factors, data diagnosis under large impact noise causedby environmental interference is achieved, the anti-noise processing capacity of mechanical fault data is improved, and the method has a more ideal effect on diagnosis of mechanical faults.

Description

technical field [0001] The invention belongs to the field of mechanical monitoring and fault diagnosis, and in particular relates to a mechanical fault diagnosis method based on LOF-Kurtogram. Background technique [0002] Industrial equipment contains a large number of rotating machinery parts such as bearings, gears, etc. They play a role in supporting and transmitting torque in rotating machinery, which is very important for the safe and reliable operation of equipment. However, these rotating parts also frequently fail. Once a failure occurs, the equipment will not operate normally, shutdown and production will be stopped, and the unit will be damaged, causing heavy casualties. It can be seen that the timely and accurate diagnosis of rotating machinery faults is of great significance for preventing major accidents and improving the economic benefits of equipment production. Obtaining vibration signals based on vibration sensors, analyzing the signals, and judging whethe...

AI Technical Summary

Problems solved by technology

However, Kurtogram is only suitable for the extraction of impact signals that do not contain obvious noise points. In real environments, for example, due to human testing, environmental interference, etc., the collected signals often contain one or several obvious noise points, which have greater kurtosis. The value makes the target signal finally extracted by Kurtogram not contain periodic shocks, and the fault cannot be accurately diagnosed

Images