Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Multidimensional telemetry data intelligent interpretation method based on corrected ELM prediction model

A prediction model and intelligent interpretation technology, applied in prediction, data processing application, calculation, etc., can solve the problems of inability to track the slow changing trend of data, abnormal missed detection of satellite components, and inability to change, etc., to achieve strong applicability and scalability. , Reduce the dependence of expert experience, and automatically extract the effect of interpretation rules

Active Publication Date: 2018-11-02
HARBIN INST OF TECH
View PDF3 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] The purpose of the present invention is to solve the missing detection of abnormal satellite components caused by the existing abnormal data that does not exceed the threshold; a large number of criteria rules in the satellite operating environment need to be manually input in advance based on expert experience, but complex telemetry data types and unknown abnormal patterns make It is difficult for technicians to form a complete satellite telemetry data rule base; and in the traditional method, once the criterion rules are entered, they cannot be changed, the flexibility is poor, and the slow-changing trend of the data cannot be tracked. Once the data exceeds the preset threshold, a large number of In view of the problem of false alarms, an intelligent interpretation method of multi-dimensional telemetry data based on the modified ELM prediction model is proposed

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Multidimensional telemetry data intelligent interpretation method based on corrected ELM prediction model
  • Multidimensional telemetry data intelligent interpretation method based on corrected ELM prediction model
  • Multidimensional telemetry data intelligent interpretation method based on corrected ELM prediction model

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0045] Specific implementation mode 1: The specific process of the multi-dimensional telemetry data intelligent interpretation method based on the modified ELM prediction model in this implementation mode is as follows:

[0046] The present invention is directed to satellite telemetry data;

[0047]Step 1. Construct A ELM single-step prediction models, and input the prediction factors (such as the state of charge of the battery pack of the satellite power supply subsystem) into the A ELM single-step prediction models, and the A ELM single-step prediction models output A at the current time point. A target parameter (such as satellite power subsystem solar array output power, battery pack pressure, battery pack output voltage, battery pack charging current and other parameters); A usually takes the value of A∈[5,50];

[0048] Step 2. Predict the predicted value of the target parameter at the current time point based on the historical real target parameter;

[0049] Step 3, usi...

specific Embodiment approach 2

[0066] Specific embodiment two, the difference between this embodiment and specific embodiment one is: construct A ELM single-step forecasting models in the described step one, input predictive factor respectively into A ELM single-step forecasting models, A ELM single-step forecasting The model outputs A target parameters at the current time point; the specific process is:

[0067] Based on the ELM forecasting model, the present invention carries out the interpretation of abnormal parameters and the interpretation of the operation mode on the multi-dimensional telemetry data respectively. The historical telemetry data is used to construct the model input phase space to realize the offline training and real-time prediction of the ELM prediction model. Aiming at the characteristics of the time dimension of the data, a method for correcting the prediction results based on the exponential smoothing method is proposed. Finally, based on the ensemble learning method, the interpreta...

specific Embodiment approach 3

[0083] Specific embodiment 3. The difference between this embodiment and specific embodiment 1 or 2 is that in the step 1 or 2, the predictors are reduced according to the correlation between the predictors, and the predictors after parameter normalization are obtained; the specific process For: the specific process is as follows figure 2 shown.

[0084] Step 121, calculate the correlation between any two predictors, and judge whether the correlation coefficient is greater than 0.9, if yes, execute step 122, if no, execute step 125;

[0085] Step 122, calculate the correlation between the predictive factor and the historical real target parameter, and execute step 123;

[0086] Steps one, two and three, select the parameter with the strongest correlation between the predictor and the historical real target parameter;

[0087] Step 124, reducing the predictor corresponding to the parameter whose correlation degree between the predictor and the historical real target paramete...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to a multidimensional telemetry data intelligent interpretation method based on a corrected ELM prediction model, and aims to solve the problems that satellite parts are abnormaland miss being detected due to existing abnormal data which does not exceed a threshold value, criterion rules in a traditional method cannot be changed once being input, the flexibility is poor, a slow change trend of the data cannot be tracked, and a large amount of false alarms are generated once the data exceeds the preset threshold value. The specific process comprises the steps of 1, building A ELM single-step prediction models, and outputting A target parameters of a current time point by the A ELM single-step prediction models; 2, predicting target parameter prediction values of the current time point on the basis of historical real target parameters; 3, obtaining A corrected target parameter values of the current time point; and 4, judging whether a sample is normal or not. The method is used in the field of multidimensional telemetry data intelligent interpretation methods.

Description

technical field [0001] The invention relates to an intelligent interpretation method of multi-dimensional telemetry data based on a modified ELM prediction model. Background technique [0002] During the satellite's in-orbit operation, the sensor monitoring data of its operation status monitoring system is transmitted to the ground through the telemetry system. This telemetry data is the only basis for the ground control center to judge the operation status and health status of the satellite in orbit. Analyzing the potential laws of telemetry data and establishing the corresponding relationship between satellite telemetry data and satellite operating status has very important practical significance for satellite measurement and control management and decision-making activities, such as improving satellite design, enhancing its operational reliability, and improving testing and monitoring automation. . [0003] Interpretation of satellite telemetry data refers to the process...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06Q10/04
CPCG06Q10/04
Inventor 刘大同彭宇史欣田庞景月彭喜元
Owner HARBIN INST OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com