Filling method of sensor missing value fused with spatio-temporal information

Abstract

The invention provides a filling method of a sensor missing value fused with spatio-temporal information. The method comprises the following steps of: inputting N pieces of historical data X and M pieces of missing data Xmissing, wherein M and N are greater than the input time sequence length T; filling a threshold eta, and inputting historical data into the trained LSTM-AES, then eta = std (X-X ') so as to obtain the trained model LSTM-AES and the repaired data Xrepaired; dividing the original data into a time series data set; initializing LSTM-AES; then, using the Tensorflow for carrying outnetwork initialization; updating the weight W of the LSTM-AES by using a common back propagation algorithm of the neural network; and carrying out missing value filling. Space-time information is considered at the same time, robustness can be achieved when a large number of sensors are missing at the same time, a single model can be trained to process different types of missing, and the real-timerequirement of sensor missing value filling can be met.

Description

technical field [0001] The invention belongs to the field of equipment health management, and more specifically relates to a filling method for sensor missing values ​​fused with spatio-temporal information. Background technique [0002] Previously, missing value filling methods only used the connection in the data space, but did not use the time series information. They do not perform well when the data has multidimensional misses, and cannot even be used in the presence of block misses. In addition, previous work has first modeled a single missing type assuming the location of the missing value is known. But the locations of missing values ​​are not known in real-time systems. In this case, in order to be able to deal with various types of missing in real time, the number of models required to be trained increases exponentially with the number of sensors, which is not conducive to the practical application of missing value filling methods. Contents of the invention ...

AI Technical Summary

Problems solved by technology

But the locations of missing values ​​are not known in real-time systems

In this case, in order to be able to deal with various types of missing in real time, the number of models required to be trained grows exponentially with the number of sensors, which is not conducive to the practical application of missing value filling methods.

Images