Stochastic Formulation of Causal Digital Twin: Kalman Filter Algorithm
This work addresses the challenge of causal inference in industrial IoT applications, such as predictive maintenance for machine bearings, but is incremental as it builds on prior digital twin research.
The authors tackled the problem of estimating causal factors in industrial systems by reformulating a Structural Vector Autoregressive Model as a state-space model and applying Kalman filter/smoother algorithms to noisy IoT data from machine bearings, achieving results similar to a previous neural network method with potential improvements in noisy conditions.
We provide some basic and sensible definitions of different types of digital twins and recommendations on when and how to use them. Following up on our recent publication of the Learning Causal Digital Twin, this article reports on a stochastic formulation and solution of the problem. Structural Vector Autoregressive Model (SVAR) for Causal estimation is recast as a state-space model. Kalman filter (and smoother) is then employed to estimate causal factors in a system of connected machine bearings. The previous neural network algorithm and Kalman Smoother produced very similar results; however, Kalman Filter/Smoother may show better performance for noisy data from industrial IoT sources.