文章背景与核心概要
随着汽车电子电气（E/E）系统复杂性的不断增加，传统的鲁棒性验证（Robustness Validation, RV）过程往往高度依赖人工，不仅容易出错，而且效率难以满足现代开发周期的需求。本文介绍了一种由本体论（Ontology）支持的框架，旨在优化汽车E/E部件的鲁棒性验证流程。
该研究的核心技术在于利用网络本体语言（OWL）对部件特性和任务剖面（Mission Profiles, MPs）进行形式化建模，从而将原本易错的手动流程转化为基于语义查询的自动化决策支持系统。通过在汽车电力电子领域的工业用例验证，该方法展现出在显著提升设计效率的同时，确保验证过程全面性的强大能力。
Reasoning-supported Robustness Validation of Automotive E/E Components
Authors: Jan Novacek, Alexander Viehl, Oliver Bringmann, Wolfgang Rosenstiel
Published: 2017 IEEE 11th International Conference on Semantic Computing (ICSC)
arXiv ID: 2608.16421
Date: August 17, 2026
Reasoning-supported Robustness Validation of Automotive E/E Components
Authors: Jan Novacek, Alexander Viehl, Oliver Bringmann, Wolfgang Rosenstiel
Published: 2017 IEEE 11th International Conference on Semantic Computing (ICSC)
arXiv ID: 2608.16421
Date: August 17, 2026
Summary
This paper introduces an ontology-supported framework designed to optimize the Robustness Validation (RV) process for automotive electrical/electronic (E/E) components. By formalizing component characteristics and Mission Profiles (MPs) using OWL (Web Ontology Language), the authors replace error-prone manual procedures with an automated, semantic-query-based decision support system. The approach, validated through an industrial use-case in automotive power electronics, demonstrates significant improvements in design efficiency and process exhaustiveness.
Summary
This paper introduces an ontology-supported framework designed to optimize the Robustness Validation (RV) process for automotive electrical/electronic (E/E) components. By formalizing component characteristics and Mission Profiles (MPs) using OWL (Web Ontology Language), the authors replace error-prone manual procedures with an automated, semantic-query-based decision support system. The approach, validated through an industrial use-case in automotive power electronics, demonstrates significant improvements in design efficiency and process exhaustiveness.
Key Contributions
- Formalized Knowledge Representation: Utilizes OWL to structure RV process data, stress profiles, and load profiles, creating a machine-readable foundation for analysis.
- Automated Decision Support: Enables semantic queries against Mission Profile data, allowing for the automated selection of relevant analysis steps.
- Industrial Validation: The framework was successfully applied to real-world automotive power electronics, proving its capability to reduce design time while increasing the thoroughness of the validation process.
- Integration: Provides a systematic method for integrating complex load profiles into the broader E/E component development lifecycle.
Key Contributions
- Formalized Knowledge Representation: Utilizes OWL to structure RV process data, stress profiles, and load profiles, creating a machine-readable foundation for analysis.
- Automated Decision Support: Enables semantic queries against Mission Profile data, allowing for the automated selection of relevant analysis steps.
- Industrial Validation: The framework was successfully applied to real-world automotive power electronics, proving its capability to reduce design time while increasing the thoroughness of the validation process.
- Integration: Provides a systematic method for integrating complex load profiles into the broader E/E component development lifecycle.
Metadata & Citations
| Attribute | Details |
|---|---|
| Journal Reference | 2017 IEEE 11th International Conference on Semantic Computing (ICSC), pp. 220-226 |
| DOI | 10.1109/icsc.2017.28 |
| Primary Subject | Artificial Intelligence (cs.AI) |
Metadata & Citations
Attribute Details Journal Reference 2017 IEEE 11th International Conference on Semantic Computing (ICSC), pp. 220-226 DOI 10.1109/icsc.2017.28 Primary Subject Artificial Intelligence (cs.AI)
Accessing the Paper
Accessing the Paper