Representative Dataset Generation Framework for AI-based Failure Analysis during real-time Validation of Automotive Software Systems
2026-08-10 • Software Engineering
Software Engineering
AI summaryⓘ
The authors explain that using data from past events helps improve how systems are tested and fixed. They point out that getting good examples of system problems to learn from is hard. To solve this, they created a new method that uses hardware testing combined with intentional fault creation to produce realistic problem data. This data can then train machine learning models to detect or understand faults better. Their method produces different kinds of data, including logs, showing it works well for fault simulation.
Hardware-in-the-Loop (HIL) simulationFault Injection (FI)Machine Learning (ML)system validationfaulty data generationreal-time system testingfault logsdata-driven approachsignal-based methodsmodel-based methods
Authors
Mohammad Abboush, Christoph Knieke, Andreas Rausch
Abstract
Recently, thanks to its ability to extract knowledge from historical datasets, the data-driven approach has been widely used in various phases of the system development life cycle. During real-time system validation, remarkable achievements have been accomplished in developing an intelligent failure analysis based on historical data. However, despite its superiority over other conventional approaches, e.g., model-based and signal-based, the availability of representative datasets persists as a major challenge. Thus, for different engineering applications, new solutions to generate representative faulty data in different forms should be explored. Therefore, in this study, a novel approach based on Hardware-in-the-Loop (HIL) simulation and real-time Fault Injection (FI) method is proposed to generate and collect data samples under single and simultaneous faults for Machine Learning (ML) applications during system validation phases. The developed framework can generate not only sequential data, but also textual data including fault logs. The results show the applicability of the proposed framework in simulating and capturing the system behaviour under faults within the system components.