Intelligent Identification of Simultaneous Faults of Automotive Software Systems Under Noisy and Imbalanced Data Using Ensemble LSTM and Random Forest

Abstract

According to ISO 26262 standard, functional validation of the developed Automotive Software Systems (ASSs) is crucial to ensure the safety and reliability aspects. Hardware-in-the-loop (HIL) has been introduced as a reliable, safe and flexible test platform to enable the validation process in real-time. However, the traditional failure analysis process of HIL tests is time-consuming, extremely difficult and requires considerable effort. Therefore, an intelligent solution that can overcome the above challenges is required. Following a data-driven approach, the development of deep learning methods for fault detection and classification has gradually become a hot topic. However, despite the fruitful results, most of the previous studies were conducted for single faults without considering the simultaneous occurrence of multiple faults and ignoring the noisy conditions. In this study, based on multi-label ensemble long short term memory (LSTM) and random forest (RF) techniques, a novel method for simultaneous fault classification under noisy conditions is developed. To improve the robustness of the model against noise, a GRU-based denoising autoencoder (DAE) was implemented. Furthermore, to overcome the challenge of imbalanced data, a random undersampling algorithm was employed. By doing so, the single and simultaneous sensor faults occurring during HIL testing of ASSs can be efficiently and automatically detected and identified. To evaluate the capabilities and robustness of the proposed method, a high-fidelity gasoline engine with a dynamic vehicle system and driving environment was used as a case study. The analysis results demonstrate that the proposed model can achieve a high degree of accuracy under noise with an average detection accuracy of 99.43%. Moreover, compared to the individual methods, the proposed ensemble learning architecture with DAE provides more promising fault identification performance with improved accuracy and robustness. Specifically, the test results show that the proposed model is superior to other state-of-the-art models in identifying simultaneous faults with 92.65% F1-Score. INDEX TERMSAutomotive software systems, fault detection and diagnosis, deep learning, denoising autoencoder, LSTM, random forest, real-time simulation, fault injection; Hardware-in-the-Loop (HIL).

Representative Real-Time Dataset Generation Based on Automated Fault Injection and HIL Simulation for ML-Assisted Validation of Automotive Software Systems

“…To put it in another way, two or more factors have contributed to creating a novel pattern in the signals as a result of the simultaneous FI. Detailed information regarding the setup of the simultaneous FI can be found at [45]. Figure 8c illustrates the effect of the simultaneous faults on the vehicle system behaviour, i.e., vehicle speed, between 170-330 s. The vehicle speed closely follows the desired behaviour up to 170 s, the time at which the faults are activated.…”

Automating Fault Test Cases Generation and Execution for Automotive Safety Validation via NLP and HIL Simulation

“…The motivation for exploring the evolution of vehicles with advanced driver-assistance systems (ADAS), autonomous driving capabilities, and Internet of Things (IoT) integrations lies in the increasing complexity of their operating systems [5]. Fault injection tests the reliability of these interconnected systems to ensure that a fault in one component does not lead to a comprehensive system breakdown [6].…”

Identification of combined sensor faults in structural health monitoring systems

“…Luca et al (2023) have presented a methodology for fault identification of dissolved oxygen sensors in wastewater treatment plants using the Fisher discriminant analysis to identify six sensor fault types, bias, drift, gain, precision degradation, fixed value, and complete failure. In automotive software systems, Abboush et al (2023) have reported a methodology to identify combined sensor faults using ensemble LSTM and random forest networks. In the field of mechatronic systems, Sergiyenko et al (2022) have introduced an approach for sensor fault identification via linear and nonlinear dynamic models using sliding mode observers.…”