Physics-Informed Deep Neural Operator for Estimation of kinetic parameters in distributed activation energy model for parallel reaction systems
Abstract
Abstract Kinetic parameter estimation is essential in thermogravimetric analysis and pyrolysis modeling. We apply the physics-informed deep neural operator (PI-DeepONet) to estimate kinetic parameters of the discrete distributed activation energy model (DAEM), a multi-step parallel reaction system whose activation energy distribution is approximated by discrete values with weights. The kinetic laws are embedded in the architecture: the branch net encodes the conversion curve and the trunk net relates the heating rate to the kinetic parameters, the loss combining parameter prediction and conversion reconstruction errors. Tests on one- and two-step reaction models show high accuracy, and validation on experimental TGA data of calcium oxalate monohydrate confirms that reconstructed conversion and mass loss curves agree well with measurements. The method requires no a priori assumptions and enables direct parameter prediction after a single training, providing an efficient and reliable solution for online kinetic analysis of complex multi-step pyrolysis.
Read the paper
Related studies
- Preliminary Toxicity Analysis of 3DCRT versus IMRT on the High Dose Arm of the RTOG 0126 Prostate Cancer Trial
- Adaptive Radiotherapy for Head and Neck Cancer: Initial Clinical Outcomes from a Prospective Trial
- American Association of Physicists in Medicine Task Group 263: Standardizing Nomenclatures in Radiation Oncology
- Motion Management Strategies and Technical Issues Associated with Stereotactic Body Radiotherapy of Thoracic and Upper Abdominal Tumors: A Review from NRG Oncology
- High-dose-rate interstitial brachytherapy as a monotherapy for localized prostate cancer: treatment description and preliminary results of a phase I/II clinical trial
- Highly efficient training, refinement, and validation of a knowledge-based plan quality control system for radiotherapy clinical trials
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.