Schema自适应动作条件JEPA用于部分传感器重叠下的跨机床CNC迁移
World Models for Cross-Machine CNC Transfer under Partial Sensor Overlap
浏览论文内容
中文总结 AI 辅助
本研究提出SAAC-JEPA架构，解决部分传感器重叠下的跨机床CNC动力学迁移问题，发现源域预测精度不足以评估工业表示，跨机床适应需作为独立评估维度。
中文摘要 AI 辅助
跨机床部署工业世界模型需要应对动力学、传感接口、采样机制和控制单元的变化。我们研究了一种用于CNC动力学的Schema自适应动作条件联合嵌入预测架构（SAAC-JEPA），其中源机床具有17个标准传感器通道，而目标机床仅共享10个。评估采用组不相交的源数据划分、仅源归一化、留出自监督验证、单元审计以及模型锁定后的密封目标测试。在五个随机种子下，JEPA预训练未带来干净的源预测增益：从头训练和预训练主体模型分别获得RMSE=0.811±0.022和0.813±0.022。对20个候选模型的仅源搜索在七种子稳定性检查后选择了一个Schema一致的动作条件JEPA。在确认性目标测试中，锁定模型达到零样本RMSE=0.546，R²=0.012，NLL=0.52，优于持久性基线，但未超过配备RevIN的PatchTST和iTransformer基线（分别为0.503和0.498）。一项预先声明的配对消融显示，在同一架构中引入RevIN可将RMSE改善至0.495±0.004（三种子），但在平稳上下文窗口上降低了目标校准性能（NLL=20.6）。一次锁定前的自适应扫描在有限目标支持下进一步将RMSE降低至0.520。这些结果表明，仅源域预测精度不足以评估工业预测表示，且部分传感器重叠下的跨机床适应是一个独立的评估维度。
英文摘要
Industrial world models must move between machines whose dynamics, sensing interfaces and command conventions differ. This study asks whether a command-conditioned latent world model, trained to predict future representations of the process rather than to reconstruct future samples, keeps its value on a machine it has never seen: a source CNC machine exposes 17 sensor channels, the target sharing 10 of those. All model selection uses source data only, and the locked configuration is evaluated on the target once. Two findings follow. First, latent-predictive pretraining brings no in-domain forecasting gain over matched training from scratch, so source accuracy alone cannot show what such a representation is worth. Second, the transferred model beats persistence on the unseen machine (with $R^2\approx0.01$ against the target mean) but trails official forecasters that normalize each input window by its own statistics; a post-lock ablation, declared before it ran, shows that this input normalization alone closes the gap, and closing it costs predictive calibration. Cross-machine transfer under partial sensor overlap is therefore a distinct evaluation axis for command-conditioned world models.
发表机构
- Université de Bretagne Occidentale（西布列塔尼大学）
- Mines Nancy, Université de Lorraine（洛林大学南锡国立高等矿业学校）
机构由 AI 辅助整理，请以论文原文为准。
