An explainable hybrid deep learning-enabled intelligent fault detection and diagnosis approach for automotive software systems validation

• Proposing an intelligent test recordings analysis approach of automotive software systems (ASSs) based on explainable deep learning methods. • Developing a hybrid 1dCNN-GRU-based DL model architecture for fault detection, identification, and localization, considering single and concurrent faults with imbalanced data. • Providing an improved interpretability DL model version with identification of significant variables based on interpretation of prediction results, improving performance and efficiency along with reducing complexity. • Investigating and analyzing four explainable AI techniques, highlighting their different computational costs and performance results. • Employing HIL real-time simulation dataset to validate the proposed approach as an industrial application, considering user behaviour and the high-fidelity ASSs models. Advancements in data-driven machine learning have emerged as a pivotal element in supporting automotive software systems (ASSs) engineering across various levels of the V-development process. During system verification and validation, the integration of an intelligent fault detection and diagnosis (FDD) model with test recordings analysis process serves as a powerful tool for efficiency, ensuring functional safety. However, the lack of interpretability of the black-box FDD models developed not only hinders understanding of the cause underlying the prediction but also prevents the model from being adapted based on the prediction result. This, in turn, increases the computational cost required for developing a complex FDD model and limits confidence in real-time safety-critical applications. To address this challenge, a novel explainable method for fault detection, identification, and localization is proposed in this article with the aim of providing a clear understanding of the logic behind the prediction outcome. To this end, a hybrid 1dCNN-GRU-based intelligent model was developed to analyze the recordings from the real-time validation process of ASSs. The employment of explainable AI techniques, i.e., IGs, DeepLIFT, Gradient SHAP, and DeepLIFT SHAP, was instrumental in enabling model adaptation and facilitating the root cause analysis (RCA). The proposed approach is applied to the real-time dataset collected during a virtual test drive performed by the user on hardware-in-the-loop (HIL) system. A thorough evaluation of the model’s performance revealed its superiority in diagnosing the fault type and location compared to state-of-the-art models. By integrating XAI techniques, the proposed approach offers a high-performance, low-computational-cost DL model with improved interpretability, which not only supports safety engineers but also contributes to the optimisation of the real-time validation process of ASSs.