发表机构
Liveline Technologies（Liveline Technologies）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对制造AI需适应分布漂移且受安全信任约束的问题，提出闭环CPS自主管理模型生命周期，通过模型竞争与信任门机制，实现过程稳定性提升28-45%且零事故。
AI 中文摘要
制造业人工智能系统必须在严格的安全保障和操作员信任要求下，自主适应来自原材料变化、环境变化和设备老化带来的持续分布漂移，在这些场景中模型故障可能导致物理损坏。本文提出了一种闭环信息物理系统（CPS），用于汽车制造业中自主模型生命周期管理，该系统自2023年起已部署。该系统管理产品专用模型对：一个作为数字孪生的序列到序列物理模型（LPP），以及一个针对该模型训练的深度强化学习（RL）控制策略（LCP）。每个再训练周期中，涵盖架构家族和RL算法的多个模型变体进行竞争；只有得分最高的候选者才能晋级。一个指挥者（Conductor）编排器自主管理工厂范围内的模型清单，具有依赖感知的再训练和比例-积分-微分（PID）回退功能。体现以人为本智能的原则，LCP综合得分包含一个操作员信任门，惩罚偏离既定实践的策略；如果没有该门，23%的策略尽管通过准确性阈值仍会被操作员拒绝。在多个工厂中，LCP控制的过程相比未控制的基线实现了28-45%的过程稳定性提升，且零安全事故。
英文摘要
Manufacturing AI systems must autonomously adapt to continuous distributional shift from raw-material variability, ambient changes, and equipment aging, under strict safeguard and operator-trust requirements where model failures risk physical damage. This paper presents a closed-loop Cyber-Physical System (CPS) for autonomous model lifecycle management in automotive manufacturing, deployed since 2023. The system manages product-specialized model pairs: a sequence-to-sequence physics model (LPP) serving as a digital twin, and a deep Reinforcement Learning (RL) control policy (LCP) trained against it. Per retraining cycle, multiple model variants spanning architecture families and RL algorithms compete; only the best-scoring candidate advances. A Conductor orchestrator autonomously manages plant-wide model inventories with dependency-aware retraining and Proportional-Integral-Derivative (PID) fallback. Reflecting the principle of Human-Centric Intelligence, the LCP composite score embeds an operator-trust gate penalizing policies deviating from established practice; without it, 23% of policies are rejected by operators despite passing accuracy thresholds. Across multiple facilities, LCP-controlled processes achieve process stability improvements of 28-45% over uncontrolled baselines with zero safety incidents.
CommentsThe paper has been accepted for publication in the 2026 IEEE International Conference on Systems, Man, and Cybernetics (SMC 2026). The final published version will be made available on IEEE Xplore
