Method for quickly screening steady-state condition data in large-scale process data
A technology of process data and steady-state working conditions, applied in other database retrieval, electronic digital data processing, other database retrieval based on metadata, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0069] A method for quickly screening steady-state operating condition data in large-scale process data, comprising the following steps:
[0070] A. Initialization processing of steady-state data screening,
[0071] Perform data filtering on the data segment that needs to be filtered for steady-state working condition data,
[0072] According to the purpose of selecting data, the storage space with a length of n is selected as the sliding window, and the storage space is the minimum unit for judging the stability of the process data segment, wherein n represents the number of data contained in the sliding window,
[0073] According to the allowable deviation value α of a single data in a sliding window containing n data, calculate the threshold δ of the standard deviation of n data in the sliding window y ;
[0074] Calculate the mean value of n data at the starting position of the data segment as the initial value of the sliding window mean value
[0075] Calculate the s...
Embodiment 2
[0129] This embodiment is improved on the basis of Embodiment 1.
[0130] In step B, calculate the standard deviation σ of the data within the sliding window at time k+1 k+1 When the variance diff k+1 Make corrections. use diff k to diff k-n+1 The n variance data are fitted (k / 2k The rate of change of the slope at the diff k+1 The predicted value of diff′ k+1 , using diff k+1 with diff' k+1 Calculate the weighted average of σ k+1 . where diff' k+1 The weighting rate of is inversely proportional to the linearity of the fitted curve. by diff k+1 Correction can effectively reduce the interference of interference signals to the data screening process.
Embodiment 3
[0132] This embodiment is improved on the basis of Embodiment 2.
[0133]The system traverses the selected steady-state data segment ste, clusters the traversed data according to the density, and determines the abnormal data through the clustered local abnormal factors. According to the proportion of abnormal data detected, use diff k to diff k-n+1 The n variance data are fitted to the fitting curve for feedback correction. Through feedback correction, it is possible to improve the diff in Example 2 k+1 The accuracy with which the correction is made.
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 
PatSnap Eureka turns technology decisions into work you can execute. Powered by our Innovation Knowledge Graph, it runs expert workflows across engineering, life sciences, materials and intellectual property. Get your review-ready output in minutes.
