TwinExplainer: Explaining Predictions of an Automotive Digital Twin
This addresses trust and decision-making issues for automotive stakeholders by providing explanations, but it is incremental as it applies existing explainability methods to a specific domain.
The paper tackles the problem of opaque deep learning predictions in automotive digital twin systems by introducing TwinExplainer, a three-layered pipeline that explains predictions globally and locally, resulting in visualizations for normal and abnormal sensor channel behaviors.
Vehicles are complex Cyber Physical Systems (CPS) that operate in a variety of environments, and the likelihood of failure of one or more subsystems, such as the engine, transmission, brakes, and fuel, can result in unscheduled downtime and incur high maintenance or repair costs. In order to prevent these issues, it is crucial to continuously monitor the health of various subsystems and identify abnormal sensor channel behavior. Data-driven Digital Twin (DT) systems are capable of such a task. Current DT technologies utilize various Deep Learning (DL) techniques that are constrained by the lack of justification or explanation for their predictions. This inability of these opaque systems can influence decision-making and raises user trust concerns. This paper presents a solution to this issue, where the TwinExplainer system, with its three-layered architectural pipeline, explains the predictions of an automotive DT. Such a system can assist automotive stakeholders in understanding the global scale of the sensor channels and how they contribute towards generic DT predictions. TwinExplainer can also visualize explanations for both normal and abnormal local predictions computed by the DT.