



















Abstract:Accurate time-series forecasting for complex physical systems is the backbone of modern industrial monitoring and control, yet deep learning models often lack the physical consistency required in regulated this http URL bridge this gap, we introduce Process-Informed Forecasting (PIF) models for temperature in pharmaceutical lyophilization, embedding deterministic production recipes as macro-structural priors. We investigate classical methods (e.g., Autoregressive Integrated Moving Average (ARIMA) model) and modern deep learning architectures, including Kolmogorov-Arnold Networks (KANs). We compare three different loss function formulations that integrate a process-informed trajectory prior: a fixed-weight loss, a dynamic uncertainty-based loss, and a Residual-Based Attention (RBA) mechanism. We evaluate all models not only for accuracy and physical consistency but also for robustness to sensor noise. Furthermore, we test the practical generalizability of the best model in a transfer-learning scenario to a new process. Our results show that PIF models outperform their data-driven counterparts in terms of accuracy, physical plausibility and noise resilience, offering a scalable framework for reliable and generalizable forecasting solutions in critical manufacturing.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2509.20349 [cs.LG] |
| (or arXiv:2509.20349v3 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2509.20349 arXiv-issued DOI via DataCite |
From: Ramona Rubini [view email]
[v1]
Wed, 24 Sep 2025 17:42:00 UTC (7,547 KB)
[v2]
Sat, 4 Apr 2026 17:53:03 UTC (8,312 KB)
[v3]
Fri, 15 May 2026 15:59:06 UTC (8,269 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理,仅供阅读参考。 原文来自 — 版权归原作者所有。