Method for predicting time sequence of multiple measuring points on gas turbine based on time-varying feature composition

Abstract

The invention discloses a time-varying feature composition-based time sequence prediction method for multiple measuring points on a gas turbine, which comprises the following steps of: extracting time-varying features of an input sample in an end-to-end manner, constructing an incidence relation network, and performing sequence prediction by using a space-time convolutional network. A space-time convolution feature fusion module; and a sequence prediction output feedback module. The time-varying association network construction module is used for extracting time-varying feature information in a sample and constructing a time-varying association network, the space-time convolution feature fusion module is used for inputting features of an output aggregation sample of the time-varying association network construction module, and the sequence prediction output feedback module is used for realizing iterative optimization of the network. And finally outputting a gas turbine multi-sensor time sequence prediction curve. According to the method, the time-varying information implied in the data is added into relation network construction, so that self-adaptive time-varying feature learning is realized, and the prediction effect of the time sequence is further improved.

Description

technical field [0001] The invention belongs to the design and application of a neural network model, in particular to the application of a space-time convolutional network model of a time-varying feature composition. Background technique [0002] The problem of multivariate time series forecasting has been a hot topic in statistics and deep learning research. Uncertainty is divided into model uncertainty and data uncertainty. The traditional ARIMA (Auto-regressive Integrated Moving Average model) model can handle non-stationary sequences. The main idea is to first differentiate the non-stationary sequence to make it a stationary sequence, and then use the ARMA model to fit the sequence after the difference. It is mainly used in single Linear models in variable, homoscedastic cases. ARIMA requires that the time series have univariate, homoscedasticity, and the series follow linear regression, but these assumptions are not true in many cases. In real life, there are more ti...

AI Technical Summary

Problems solved by technology

Although this part of the composition method gets rid of the limitations of the traditional composition method, it still does not take into account that in a complex system, the relationship between nodes exists statically, and the relationship between nodes is strong at different times and in different states. Weakness and interaction behavior patterns will undergo drastic changes

Images