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

Area of Science:

• Automotive Engineering
• Software Engineering
• Functional Safety

Background:

• Automotive electronic systems are increasingly complex and critical.
• ISO 26262 mandates safety development processes, including fault injection.
• Current manual fault injection is time-consuming, expert-dependent, and limits test case coverage.

Purpose of the Study:

• To develop an automated approach for fault injection test case generation and execution.
• To address the limitations of manual fault injection in complex automotive systems.
• To improve the efficiency and scalability of safety verification processes.

Main Methods:

• Utilizing Natural Language Processing (NLP) to derive fault test cases from Functional Safety Requirements (FSRs).
• Implementing automated fault injection execution using Hardware-in-the-Loop (HIL) in real-time.
• Adhering to the black-box concept and ISO 26262 standards.

Main Results:

• Effectively identifies fault injection locations and conditions automatically.
• Significantly simplifies the complex automotive testing process.
• Provides a scalable solution for diverse safety-critical systems.

Conclusions:

• The proposed NLP-driven approach automates fault injection, enhancing automotive safety.
• This method improves efficiency, reduces expert dependency, and increases test coverage.
• It offers a robust solution for verifying safety-critical automotive electronic systems.