发表机构
Xuteli School, Beijing Institute of Technology; School of Integrated Circuits and Electronics, Beijing Institute of Technology（北京理工大学徐特立学院; 北京理工大学集成电路与电子学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对EV充电数据的三类问题，提出Note-Chord-Voice框架，在江门数据集验证后，发现稳定价格敏感语音支持因果推断，定向折扣可回收52.8%折扣支出。
AI 中文摘要
真实世界的电动汽车（EV）充电数据存在三类相互关联的问题：硬件碎片化（网络超时和计费重置会拆分会话）、物理违规（独立的能量/时长模型会产生不可能的状态，例如在7kW充电器上10分钟内充电50kWh）、碰撞偏差（对处理后结果进行聚类会为价格弹性打开后门路径）。我们提出Note-Chord-Voice框架，这是一种受音乐启发、由公理驱动的流程，将数据清洗（修复和弦）、结构模式发现（谐波和弦）、描述性源分离（NMF语音）和因果推断划分为不同的、可证伪的阶段。关键创新点包括：（i）证伪门（A1-A5、G3、G10），用于在建模前测试数据适用性；（ii）从STL分解得到的Gamma初始化NMF，结合输入缩放以保证收敛稳定性；（iii）基于标签的优惠券分级（A/B/C/D），用于从夜间混杂因素和定向促销中分离准随机处理；（iv）每个语音单独使用OLS，以避免单纯形共线性；（v）Foote novelty曲线用于结构状态检测。将该框架应用于江门数据集（495707个会话、20个站点，时间范围为2024年7月至2025年3月），除G3（无强168小时周期）外，所有核心公理均通过验证。NMF的R²达到0.9921；受物理约束的时长模型的总R²为0.5409。有两个语音对价格敏感（β=-11至-14分钟，p<0.001），其中一个稳定（语音3，β=-14.16），另一个由处理驱动（语音1，β=-11.10）；仅稳定语音支持因果主张。反事实模拟显示，针对价格敏感语音定向投放折扣可回收52.8%的折扣支出（约85万元人民币/年）；仅针对单一稳定价格敏感语音则会得到更保守的估计。
英文摘要
Real-world EV charging data exhibit three interlocking pathologies: hardware fragmentation (network timeouts and billing resets split sessions), physical violations (independent energy/duration models produce impossible states like 50 kWh in 10 min on a 7 kW charger), and collider bias (clustering on post-treatment outcomes opens backdoor paths for price elasticity). We propose the Note-Chord-Voice framework, a music-inspired, axiom-driven pipeline that separates data cleaning (Repair Chords), structural pattern discovery (Harmonic Chords), descriptive source separation (NMF Voices), and causal inference into distinct, falsifiable stages. Key innovations: (i) falsification gates (A1-A5, G3, G10) that test data suitability before modeling; (ii) Gamma-initialized NMF with input rescaling for convergence stability from STL decomposition; (iii) tag-based coupon grading (A/B/C/D) to isolate quasi-random treatment from night-time confounders and targeted promotions; (iv) separate per-voice OLS to avoid simplex collinearity; (v) Foote novelty curves for structural regime detection. Applied to the Jiangmen dataset (495,707 sessions, 20 stations, from July 2024 to March 2025), all core axioms pass except G3 (no strong 168 h cycle). NMF achieves R^2=0.9921; the physically constrained duration model yields aggregate R^2=0.5409. Two voices are price-sensitive (beta = -11 to -14 min, p<0.001), of which one is stable (Voice 3, beta=-14.16) and one treatment-driven (Voice 1, beta=-11.10); only the stable voice supports causal claims. Counterfactual simulation shows targeting discounts to price-sensitive voices recovers 52.8% of discount expenditures (~0.85M CNY/year); restricting to the single stable price-sensitive voice yields a more conservative estimate.
Comments30 pages, 10 figures
