A tale of perfect fit and phantom optima: how data-driven models can fail in real-time optimization

The paper examines the reliability of data‑driven models for real‑time optimization (RTO) using a vinyl acetate monomer benchmark. Two models—a structured hybrid model and a fully data‑driven neural ODE—accurately reproduce plant measurements but yield economic optima that differ markedly from the plant’s true optimum, producing multiple phantom optima. The study shows that even with noise‑free data and correct initialization, stochastic gradient training can drift to weights that degrade RTO performance, indicating that predictive accuracy alone does not ensure reliable economic outcomes.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• benchmarks