Time series forecasting for multidimensional telemetry data using GAN and BiLSTM in a Digital Twin

TL;DR

This work targets forecasting for multidimensional telemetry in Digital Twins by coupling a Predictive GAN with a BiLSTM to capture both data distributions and temporal dynamics. The method generates multivariate forecasts by first learning the data distribution with a GAN and then leveraging BiLSTM to model temporal evolution, augmented with Predictive GAN steps for long-horizon prediction. Case-study results on a four-feature telemetry dataset show that the PredGAN ➝ BiLSTM pipeline can achieve competitive RMSE and better multivariate consistency than BiLSTM alone, while still benefiting from ARIMA in some aggregate metrics. The approach enables more accurate, extended forecasting for Digital Twins and lays groundwork for downstream tasks like anomaly detection and Remaining Useful Life estimation.

Abstract

The research related to digital twins has been increasing in recent years. Besides the mirroring of the physical word into the digital, there is the need of providing services related to the data collected and transferred to the virtual world. One of these services is the forecasting of physical part future behavior, that could lead to applications, like preventing harmful events or designing improvements to get better performance. One strategy used to predict any system operation it is the use of time series models like ARIMA or LSTM, and improvements were implemented using these algorithms. Recently, deep learning techniques based on generative models such as Generative Adversarial Networks (GANs) have been proposed to create time series and the use of LSTM has gained more relevance in time series forecasting, but both have limitations that restrict the forecasting results. Another issue found in the literature is the challenge of handling multivariate environments/applications in time series generation. Therefore, new methods need to be studied in order to fill these gaps and, consequently, provide better resources for creating useful digital twins. In this proposal, it is going to be studied the integration of a BiLSTM layer with a time series obtained by GAN in order to improve the forecasting of all the features provided by the dataset in terms of accuracy and, consequently, improving behaviour prediction.

Figures (13)

• Figure 1: Digital Twin in Five Parts. Source tao2018digital
• Figure 2: LSTM Architecture. Source huang2022time.
• Figure 3: BiLSTM Architecture. Source huang2022time.
• Figure 4: Predictive GAN iteration for a sequence of three time levels. Source silva2021data.
• Figure 5: Proposed Architecture involving Predictive GAN and BiLSTM.