Online parameter estimation and model maintenance using parameter-aware physics-informed neural network
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Machine learning-based (ML) digital twins for chemical processes are gaining popularity with the advent of Industry 4.0. These digital twins are often developed under the assumption of constant process parameters. However, in most chemical engineering processes, parameters often change during operations. To ensure optimal performance under such evolving conditions, there is a need for models that can adapt to these changes. In this work, we propose a framework for developing a PINN-based (Physics-Informed Neural Network) digital twin that is sensitive to parameter variations. The proposed framework also monitors the process in real-time using physics-based residual equations, identifies the parameters undergoing changes using sensitivity matrices, and re-estimates them to maintain the performance of the PINN model. We demonstrate the utility of the framework through a case study involving a continuous stirred tank reactor experiencing changes in activation energy and the overall heat transfer coefficient. The results show that the proposed framework improves the predictive accuracy of the PINN by approximately 84% for ramp changes and 12% for step changes in parameters. The framework is further applied to more realistic case studies, including a polymethyl methacrylate polymerization reactor and a pressure swing adsorption process, highlighting its applicability to high-dimensional nonlinear systems and cyclic separation processes. These findings indicate that the performance of digital twins can be significantly enhanced in the presence of varying process parameters by employing a PINN architecture that incorporates parameters as inputs and solves real-time inverse problems to estimate parameter values.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it