Method and System for Uncertainty Prediction of Monitoring Quantities Based on Variational Autoencoder

Abstract

The method and system for predicting the uncertainty of monitoring quantities based on variational autoencoders uses the environmental sample data as an independent variable to change the physical quantity of the monitoring object itself, and takes the physical quantity of the monitoring object itself as the dependent variable; establishes a correspondence based on the acquisition time of the environmental sample data Based on the time index of the physical quantity of the monitoring object itself, the acquisition time corresponding to the time index is used as the time index point of the data set; the probability distribution model of the hidden variable that causes the change of the physical quantity of the monitoring object itself is constructed, and the probability distribution model of the hidden variable is obtained by using the prior distribution function. Prior probability, build a deep neural network model and build a recognition model for the generation process of the prior probability, predict the missing value of the missing physical quantity according to the recognition model and obtain the probability distribution of the physical quantity of the monitoring object itself, and obtain the probability distribution of the physical quantity of the monitoring object itself Uncertainty estimates for missing values. The invention makes the prediction result of the monitoring object have better uncertainty estimation, and better grasps the performance of the monitoring object.

Description

technical field [0001] The invention relates to the technical field of object monitoring, in particular to a method and system for predicting uncertainty of monitoring quantities based on variational autoencoders. Background technique [0002] At present, many objects in the real world need to be monitored continuously, so as to ensure that the monitored objects have the accuracy to meet specific performance. During the continuous monitoring of the monitoring object, a series of monitoring data with time attributes will be obtained, and people can judge whether the monitoring object meets the ideal state through the monitoring data. Since there is uncertainty in the monitoring data of the monitoring object, predicting this uncertainty will make the monitoring of the monitoring object more accurate and reliable. [0003] Time series is the numerical sequence formed by arranging the values ​​of certain statistical indicators in chronological order. By compiling and analyzing...

AI Technical Summary

Problems solved by technology

However, these models have high model assumptions, and the model's ability to model data is not strong

[0006] On the whole, although some methods in the existing technical schemes have high accuracy, they lack the estimation of uncertainty, and some technical schemes can obtain the uncertainty of monitoring data, but the accuracy is low

Images