AI-Driven Automated Test Generation Framework for VCU: A Multidimensional Coupling Approach Integrating Requirements, Variables and Logic
Open Access
- 24 July 2025
- journal article
- research article
- Published by MDPI AG in World Electric Vehicle Journal
- Vol. 16 (8) , 417
Abstract
This paper proposes an AI-driven automated test generation framework for vehicle control units (VCUs), integrating natural language processing (NLP) and dynamic variable binding. To address the critical limitation of traditional AI-generated test cases lacking executable variables, the framework establishes a closed-loop transformation from requirements to executable code through a five-layer architecture: (1) structured parsing of PDF requirements using domain-adaptive prompt engineering; (2) construction of a multidimensional variable knowledge graph; (3) semantic atomic decomposition of requirements and logic expression generation; (4) dynamic visualization of cause–effect graphs; (5) path-sensitization-driven optimization of test sequences. Validated on VCU software from a leading OEM, the method achieves 97.3% variable matching accuracy and 100% test case executability, reducing invalid cases by 63% compared to conventional NLP approaches. This framework provides an explainable and traceable automated solution for intelligent vehicle software validation, significantly enhancing efficiency and reliability in automotive testing.Keywords
Funding Information
- Shanxi Province Major Science and Technology Project (202301150401011)
This publication has 12 references indexed in Scilit:
- Aspects of complexity in automotive software systems and their relation to maintainability effort. A case study2025
- TESTEVAL: Benchmarking Large Language Models for Test Case Generation2025
- Test Case Automation: Transforming Software Testing in the Digital EraInternational Journal of Computing and Engineering, 2024
- Extracting goal models from natural language requirement specificationsJournal of Systems and Software, 2024
- Applying declarative analysis to industrial automotive software product line modelsEmpirical Software Engineering, 2023
- A Review of Intelligent Connected Vehicle Cooperative Driving DevelopmentMathematics, 2022
- Intelligent algorithms and control strategies for battery management system in electric vehicles: Progress, challenges and future outlookJournal of Cleaner Production, 2021
- Model-based test case generation from UML sequence diagrams using extended finite state machinesSoftware Quality Journal, 2021
- Automotive Software in Connected and Autonomous Electric Vehicles: A ReviewIEEE Access, 2019
- Object analysis patterns for embedded systemsIEEE Transactions on Software Engineering, 2004