用少量数据学出可解释的工业过程模型，实现精准调控
Learning Actionable World Models for Industrial Process Control
- 通过对比学习解耦潜空间中的工艺参数，实现细粒度控制
- 在注塑成型场景中验证，能提出具体可行的调控动作
- 适合需要低数据依赖与高可解释性的工业控制场景
从被动监控转向主动控制，AI系统需在极有限训练数据下学习复杂系统的动态行为，构建针对工艺输入输出的临时数字孪生，以捕捉操作对工艺世界的影响。本文提出一种基于世界模型的新方法，通过联合嵌入预测架构中的对比学习，解耦潜空间中的工艺参数，使表征变化可由输入变化预测，反之亦然，从而提升关键影响因素的可解释性，为维持工艺在运行边界内提供有效控制策略。该方法在注塑成型这一典型不稳定的工艺中得到验证，展示了实际应用价值。
原文摘要 · Abstract (English)
To go from (passive) process monitoring to active process control, an effective AI system must learn about the behavior of the complex system from very limited training data, forming an ad-hoc digital twin with respect to process inputs and outputs that captures the consequences of actions on the process's world. We propose a novel methodology based on learning world models that disentangles process parameters in the learned latent representation, allowing for fine-grained control. Representation learning is driven by the latent factors influencing the processes through contrastive learning within a joint embedding predictive architecture. This makes changes in representations predictable from changes in inputs and vice versa, facilitating interpretability of key factors responsible for process variations, paving the way for effective control actions to keep the process within operational bounds. The effectiveness of our method is validated on the example of plastic injection molding, demonstrating practical relevance in proposing specific control actions for a notoriously unstable process.
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。