Method for preprocessing vibration signal of mechanical component with missing value

Abstract

The invention provides a method for preprocessing a vibration signal of a mechanical component with a missing value. The method comprises the following steps: the step 1, calculating a root-mean-square of an original vibration signal by using a feature extraction method; the step 2, establishing an exponential stochastic regression model, and estimating model parameters; the step 3, interpolating a root mean square missing value of the vibration signal based on Monte Carlo simulation; the step 4, interpolating the missing value of the original vibration signal; and the step 5, carrying out quality analysis on the vibration data of the mechanical component. According to the method, the integrity and authenticity of original data are guaranteed, the process fo the method has low calculation requirements on model parameters, iterative calculation is not needed, parameter estimation has an analytical expression, the calculation efficiency is high, the method is scientific, the manufacturability is good, and the method has wide popularization and application value.

Description

technical field [0001] The invention provides a method for preprocessing vibration signals of mechanical components with missing values, which relates to a method for interpolating missing values ​​of vibration signals of mechanical components based on exponential random regression model, which is a method based on exponential random regression model theory and vibration signal Missing value imputation methods for time-domain analysis theory. For mechanical component vibration signals with missing values ​​and exponential degradation trends, by extracting the root mean square statistics in the signal, the missing values ​​in the original vibration signal are converted into missing values ​​of the vibration signal root mean square statistics, and the index is established. The random regression model predicts the missing value of the root mean square of the vibration signal, and then interpolates the missing value of the original vibration signal. By introducing the time series ...

AI Technical Summary

Problems solved by technology

Usually, due to the lack of vibration signals of mechanical components caused by improper data collection, data storage, and data organization, the reliability of mechanical component fault feature extraction results is reduced.

In particular, the on-site vibration signal monitoring data of mechanical components are often affected by the replacement of data acquisition equipment, sensor failures, communication failures, and extreme environments, and there are a large number of continuous missing data, which makes it impossible to extract monotonic and trendy data directly from the original data. Degradation characteristics of mechanical components

Images