Physics-Informed Neural Networks and Sequence Encoder: Application to heating and early cooling of thermo-stamping process

📰 ArXiv cs.AI

Physics-Informed Neural Networks (PINNs) combined with Sequence Encoder are applied to model heating and cooling in thermo-stamping processes

advanced Published 30 Mar 2026

Action Steps

Implement PINNs to encode physical laws into neural networks
Utilize Sequence Encoder to transform time series data into feature vectors
Combine PINNs with Sequence Encoder (PINN-SE) for improved prediction of system response
Apply PINN-SE to real-world scenarios such as thermo-stamping process modeling

Who Needs to Know This

Data scientists and AI engineers on a team can benefit from this research as it provides a novel approach to modeling complex dynamical systems, while product managers can explore potential applications in manufacturing and process control

Key Insight

💡 The combination of Physics-Informed Neural Networks and Sequence Encoder can effectively predict system response under changing parameters and initial conditions

Key Takeaways

Physics-Informed Neural Networks (PINNs) combined with Sequence Encoder are applied to model heating and cooling in thermo-stamping processes

Full Article

Title: Physics-Informed Neural Networks and Sequence Encoder: Application to heating and early cooling of thermo-stamping process

Abstract:
arXiv:2603.26245v1 Announce Type: cross Abstract: In a previous work (Elaarabi et al., 2025b), the Sequence Encoder for online dynamical system identification (Elaarabi et al., 2025a) and its combination with PINN (PINN-SE) were introduced and tested on both synthetic and real data case scenarios. The sequence encoder is able to effectively encode time series into feature vectors, which the PINN then uses to map to dynamical behavior, predicting system response under changes in parameters, ICs a

Read full paper → ← Back to Reads