融合环境数据的车辆预测维护系统，在真实道路场景中实现100%故障预警，误差仅12.2天。
AI-Driven Predictive Maintenance with Environmental Context Integration for Connected Vehicles: Simulation, Benchmarking, and Field Validation
- 整合车内外数据，通过V2X与外部API获取路况、天气等环境信号
- 在三国家真实车队验证中，六类磨损事件检测率达100%，平均误差12.2天
- 边缘计算使推理延迟低于1秒，适合高实时性车载系统部署
面向联网汽车的预测性维护有望降低意外故障并提升车队可靠性，但现有系统多仅依赖内部诊断信号，且验证基于仿真或工业基准数据。本文提出一种上下文数据融合框架，将车辆内部传感器流与外部环境信号——道路质量、天气、交通密度和驾驶行为——通过V2X通信与第三方API集成，并在车辆边缘端进行推理。该框架在四个层面进行评估：在物理启发的合成数据集上进行特征组消融实验，结果显示引入上下文特征可使F1得分提升2.6点；去除所有上下文后，宏观F1从0.855降至0.807。在AI4I 2020基准数据集（10,000样本）上，轻量梯度提升机（LightGBM）在五折分层交叉验证中达到AUC-ROC 0.973，SMOTE仅限训练集使用。噪声敏感性分析显示，低噪声下宏观F1保持在0.88以上，高噪声时降至0.74。最关键是，该流程在来自印度、德国、巴西五辆汽车的真实遥测数据上完成验证，涵盖992次行程和11个可评估的服务事件（由行程日志中的部件磨损重置识别）。针对六种磨损驱动事件，模型实现100%检测率，平均绝对误差（MAE）为12.2天。微调消融实验表明，基础合成模型已实现6/6二分类检测；按车辆微调后，磨损相关事件的MAE由25.9天降至12.2天。SHAP分析确认上下文及交互特征位列前15预测因子。边缘推理将估计延迟从3.5秒降至1.0秒以下，相比纯云端处理。
原文摘要 · Abstract (English)
Predictive maintenance for connected vehicles offers the potential to reduce unexpected breakdowns and improve fleet reliability, but most existing systems rely exclusively on internal diagnostic signals and are validated on simulated or industrial benchmark data. This paper presents a contextual data fusion framework integrating vehicle-internal sensor streams with external environmental signals -- road quality, weather, traffic density, and driver behaviour -- acquired via V2X communication and third-party APIs, with inference at the vehicle edge. The framework is evaluated across four layers. A feature group ablation study on a physics-informed synthetic dataset shows contextual features contribute a 2.6-point F1 improvement; removing all context reduces macro F1 from 0.855 to 0.807. On the AI4I 2020 benchmark (10,000 samples), LightGBM achieves AUC-ROC 0.973 under 5-fold stratified cross-validation with SMOTE confined to training folds. A noise sensitivity analysis shows macro F1 remains above 0.88 at low noise and degrades to 0.74 at high noise. Most critically, the pipeline is validated on real-world telemetry from five vehicles across three countries (India, Germany, Brazil), comprising 992 trips and 11 evaluable service events identified from component wear resets in the trip logs. Across six wear-driven events spanning four vehicles, the model achieves 100% detection with mean MAE of 12.2 days. A fine-tuning ablation shows the base synthetic model already achieves 6/6 binary detection; per-vehicle adaptation reduces wear-driven MAE from 25.9 to 12.2 days. SHAP analysis confirms contextual and interaction features rank among the top 15 predictors. Edge-based inference reduces estimated latency from 3.5 seconds to under 1.0 second relative to cloud-only processing.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。