Adaptive data reduction method based on piecewise transient recognition

Abstract

The invention discloses an adaptive data reduction method based on piecewise transient recognition, which comprises the following steps of: A, determining the number of segments and the length of eachsegment of reduced data according to the total data length and the reduced target length; b, establishing proportionality coefficients of a segmentation method and a transient method; c, according tothe proportionality coefficient, adopting a segmentation method for each segment of signals, and obtaining screened data and corresponding timestamps; d, according to the proportionality coefficient,adopting a transient method for each section of signal to obtain screened data and a corresponding timestamp, wherein the step D and C are not sequential; and E, integrating the data obtained by thesegmentation method and the transient method of each section of signal to obtain reduced data. According to the method, the trend information in the signal is extracted by adopting a segmentation method, the mutation information in the signal is extracted by adopting a transient method, and the data length is shortened on the basis that the information of the overall trend in the signal and the information of the key mutation signal are reserved by matching the two modes according to the proportionality coefficient.

Description

technical field [0001] The invention relates to signal and information processing technology, in particular to an adaptive data reduction method based on subsection transient recognition. Background technique [0002] With the rapid development of computer technology, the amount of global data is increasing exponentially, and a large amount of data has been accumulated in various fields, which brings certain challenges to data display and data storage. In the industrial field, working condition data is often stored in units of seconds. Taking flow data as an example, one data point is collected every second, and the total number of data points in five years is 158 million. If you need to pull historical data, it takes too long and affects the user experience. If the equipment continues to be in a stable working condition, the data samples are distributed smoothly, and the data contains a large amount of redundant data and useless data. Therefore, it is increasingly importa...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the problem that the down-sampling method in the prior art cannot retain the duration of key data while retaining trend information, the present invention proposes an adaptive data reduction method based on segmental transient recognition, which can extract large data samples The key information of the key information, select representative information points to save, and keep the overall trend and key mutation signal information in the signal, shorten the data length, and finally realize data downsampling and reduce the amount of data storage

Images