Coal mining equipment predictive maintenance method based on two-dimensional projection

Abstract

The invention discloses a coal mining equipment predictive maintenance method through regression analysis combined with two-dimensional projection, and relates to a coal main fan and an elevator. The diagnosis method includes the steps of extracting a vibration signal from an equipment monitoring system to obtain 24 characteristic indexes used for describing equipment operating states through data analysis and calculation, respectively extracting a time sequence for each of the 24 characteristic indexes, carrying out regression analysis to obtain predictive factors corresponding to the 24 characteristic indexes respectively, projecting the predictive factors on a two-dimensional space by means of two-dimensional projection, building a fitting function of predictive factor projection values and corresponding characteristic index values, calculating future values of the 24 characteristic indexes, projecting the future values of the 24 characteristic indexes in a best projection image direction matrix, judging the trend of the equipment future operating state according to the distribution situation of the projection values, and accordingly achieving predictive maintenance of coal mine equipment.

Description

technical field [0001] The invention belongs to the technical field of fault diagnosis of coal mine equipment, and specifically relates to a method of calculating 24 characteristic indicators by using equipment vibration data, extracting a time series for each of the 24 characteristic indicators and performing auto-regression analysis respectively to obtain respective corresponding predictive factors; Utilize two-dimensional projection to project the predictors into two-dimensional space, respectively establish the fitting functions of predictor projection values ​​and corresponding characteristic index values, respectively calculate the future values ​​of 24 characteristic indexes; The future value of each characteristic index is projected under the optimal projected image direction matrix, and the trend of the future operation status of the equipment is judged according to the distribution of the projected value, so as to realize the predictive maintenance of coal mine equipm...

AI Technical Summary

Problems solved by technology

However, in terms of fault alarm processing for monitoring data, fault alarms are all carried out through a given threshold. Threshold alarms have serious disadvantages: fault identification lags behind, and early warning of fault latency cannot be realized, resulting in very passive equipment maintenance and management.

[0004] Equipment failure is a gradual deterioration process from abnormality to failure. The most sensitive signal in this process is the frequency domain signal. At present, there are also equipment fault diagnosis with the help of frequency domain signals, but the judgment is mainly based on typical frequency components, but typical Frequency components often fluctuate or deviate, and the correspondence with different fault types is difficult to determine

At the same time, coupled with the harsh working conditions and complex working conditions of coal mines, it is impossible to achieve fast state judgment and accurate fault identification only by typical frequency components

Images