论文：用 Transformer、因果发现与 LLM 统一建模高基数汽车诊断事件序列
Learning to Predict, Discover, and Reason in High-Cardinality Event Sequences
AI 导读
这是一篇 141 页主内容（共 207 页）的博士论文，研究汽车诊断故障码（DTC）事件序列的自动化故障诊断。论文提出统一框架，将事件序列建模、因果发现与大语言模型（LLM）结合，把诊断序列当作语言来建模、预测与解释。工作包括用于预测性维护的多种 Transformer 架构、可扩展的样本级与总体级因果发现框架，以及自动合成布尔错误模式（EP）规则的多智能体系统。
正文 · 原文
Abstract:Electronic control units (ECUs) embedded within modern vehicles generate a large number of asynchronous events known as diagnostic trouble codes (DTCs). These discrete events form complex temporal sequences that reflect the evolving health of the vehicle's subsystems. In the automotive industry, domain experts manually group these codes into higher-level error patterns (EPs) using Boolean rules to characterize system faults and ensure safety. However, as vehicle complexity grows, this manual process becomes increasingly costly, error-prone, and difficult to scale. Notably, the number of unique DTCs in a modern vehicle is on the same order of magnitude as the vocabulary of a natural language, often numbering in the tens of thousands. This observation motivates a paradigm shift: treating diagnostic sequences as a language that can be modeled, predicted, and ultimately explained. Traditional statistical approaches fail to capture the rich dependencies and do not scale to high-cardinality datasets characterized by thousands of nodes, large sample sizes, and long sequence lengths. Specifically, the high cardinality of categorical event spaces in industrial logs poses a significant challenge, necessitating new machine learning architectures tailored to such event-driven systems. This thesis addresses automated fault diagnostics by unifying event sequence modeling, causal discovery, and large language models (LLMs) into a coherent framework for event streams. It is structured in three parts, reflecting a progressive transition from prediction to causal understanding and finally to reasoning for vehicle diagnostics. Consequently, we introduce several Transformer-based architectures for predictive maintenance, scalable sample- and population-level causal discovery frameworks and a multi-agent system that automates the synthesis of Boolean EP rules.
| Comments: | PhD dissertation, 141 pages of main content, 207 pages in total |
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2603.16313 [cs.AI] |
| (or arXiv:2603.16313v4 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2603.16313 arXiv-issued DOI via DataCite |
Submission history
From: Hugo Math [view email]
[v1]
Tue, 17 Mar 2026 09:45:01 UTC (3,887 KB)
[v2]
Thu, 19 Mar 2026 10:30:31 UTC (3,888 KB)
[v3]
Thu, 27 Aug 2026 08:24:54 UTC (3,902 KB)
[v4]
Fri, 23 Oct 2026 08:33:42 UTC (1,985 KB)
来源：arXiv cs.AI · arxiv.org