Industrial AI Robustness Card: Evaluating and Monitoring Time Series Models
This addresses the need for concrete robustness protocols for industrial AI practitioners, especially under regulations like the EU AI Act, but is incremental as it builds on existing methods like drift monitoring and stress tests.
The paper tackles the problem of vague robustness requirements in industrial AI by introducing the Industrial AI Robustness Card (IARC), a lightweight protocol for documenting and evaluating AI models on industrial time series, demonstrated in a biopharmaceutical case study.
Industrial AI practitioners face vague robustness requirements in emerging regulations and standards but lack concrete, implementation ready protocols. This paper introduces the Industrial AI Robustness Card (IARC), a lightweight, task agnostic protocol for documenting and evaluating the robustness of AI models on industrial time series. The IARC specifies required fields and an empirical measurement and reporting protocol that combines drift monitoring, uncertainty quantification, and stress tests, and it maps these to relevant EU AI Act obligations. A soft sensor case study on a biopharmaceutical fermentation process illustrates how the IARC supports reproducible robustness evidence and continuous monitoring.