Hybrid modeling of first-principles and machine learning: A step-by-step tutorial review for practical implementation

Computers & Chemical Engineering, Год журнала: 2024, Номер unknown, С. 108926 - 108926

Опубликована: Ноя. 1, 2024

Язык: Английский

---

Machine learning-based input-augmented Koopman modeling and predictive control of nonlinear processes

Computers & Chemical Engineering, Год журнала: 2024, Номер 191, С. 108854 - 108854

Опубликована: Авг. 24, 2024

Язык: Английский

---

Multi-objective optimization for sustainable and economical polycarbonate production with reaction kinetics inference for real-world industrial process

Chemical Engineering Journal, Год журнала: 2024, Номер 490, С. 151484 - 151484

Опубликована: Апрель 25, 2024

Язык: Английский

---

Physics-informed neural networks for state reconstruction of hydrogen energy transportation systems

Computers & Chemical Engineering, Год журнала: 2024, Номер 192, С. 108898 - 108898

Опубликована: Ноя. 2, 2024

Язык: Английский

---

Advancing Kinetic Study of Catalytic Reaction: A Hybrid Modeling Approach for Predicting Effective Activation Energies

ACS Catalysis, Год журнала: 2025, Номер unknown, С. 9544 - 9554

Опубликована: Май 20, 2025

Язык: Английский

---

Data-driven plant-model mismatch detection for dynamic matrix control systems using sum-of-norms regularization

Computers & Chemical Engineering, Год журнала: 2024, Номер 190, С. 108823 - 108823

Опубликована: Авг. 13, 2024

Язык: Английский

---

Integrating Deep Neural Networks for Hybrid Modeling of Complex Chemical Processes: Estimation of Spatiotemporally Varying Parameters in Moving Boundary Problems

2022 American Control Conference (ACC), Год журнала: 2024, Номер 2, С. 5370 - 5375

Опубликована: Июль 10, 2024

Язык: Английский

---

Leveraging neural networks to estimate parameters with confidence intervals

The Canadian Journal of Chemical Engineering, Год журнала: 2024, Номер unknown

Опубликована: Авг. 7, 2024

Abstract This manuscript presents a proof of concept for the estimation parameters in bioprocess while providing reliable confidence intervals. Specifically, Bayesian inference is used to estimate uncertainty prediction parameter due presence measurement noise process. The resultant joint probability distribution utilized infer interval estimates. method numerically applied using technique known as nested sampling. algorithm iteratively samples from pre‐determined range values compare model predictions and obtain density function. One challenge typically associated with this determination error, especially when high‐fidelity dynamic being utilized. For motivating example present manuscript, where simulated considered, use provided by Sartorius AG part poses computational challenges. To overcome challenge, universal approximator such parameterized neural network used. designed simulate results first principles (while also capturing dependence on output), once trained can provide near instantaneous making sampling computationally tractable application. Simulation demonstrate feasibility capability proposed approach.

Язык: Английский

---

Empowering Hybrid Models with Attention-Based Time-series Transformers: A Case Study in Batch Crystallization

2022 American Control Conference (ACC), Год журнала: 2024, Номер 2004, С. 62 - 67

Опубликована: Июль 10, 2024

Язык: Английский

---

A Hybrid Modeling Framework for Catalytic Systems: Sensitivity Analysis and Estimation of Activation Energies

2022 American Control Conference (ACC), Год журнала: 2024, Номер 24, С. 5376 - 5381

Опубликована: Июль 10, 2024

Язык: Английский

---