Hybrid modelling for remote process monitoring and optimisation

Hamid, Anuar; Hasan, Anton Heryanto; Azhari, Siti Nurfaqihah; Harun, Zalina; Putra, Zulfan Adi

doi:10.1016/j.dche.2022.100044

Cited by 6 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The neural network model accurately modeled process dynamics and aided in discerning between process and measurement uncertainties and underlying biochemical phenomena . DNNs excel in managing nonlinearities and uncertainties compared to SNNs, but their efficacy encounters some challenges including needing a large dataset, the complexity of optimizing architecture and parameters, a lack of straightforward physical interpretation, and susceptibility to overfitting and underfitting risks, . The combination of physical phenomena in NNs, known as Physics-Informed Neural Networks (PINNs), presents an excellent opportunity to develop good NN models with limited data …”

Section: Introductionmentioning

confidence: 99%

“…20 DNNs excel in managing nonlinearities and uncertainties compared to SNNs, but their efficacy encounters some challenges including needing a large dataset, the complexity of optimizing architecture and parameters, a lack of straightforward physical interpretation, and susceptibility to overfitting and underfitting risks, 21 . 22 The combination of physical phenomena in NNs, known as Physics-Informed Neural Networks (PINNs), presents an excellent opportunity to develop good NN models with limited data. 23 PINNs have been used to solve differential equations such as PDEs, 24 fractional, and integro-differential equations (IDEs), 25 .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Physics-Informed Neural Networks for Process Systems: Handling Plant-Model Mismatch

Moayedi,

Chandrasekar,

Rasmussen

et al. 2024

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

This work addresses the problem of leveraging first-principles knowledge with data-driven techniques in the Physics-Informed/Inspired Neural Network (PINN) framework to handle plant−model mismatch. To this end, a PINN is developed utilizing the first-principles model of the system and plant data and demonstrated to handle plant−model mismatch. The PINN is compared with another dynamic modeling technique, a Recurrent Neural Network (RNN), and for the illustrative simulation example, is shown to improve the predictive capabilities of the model compared to the other techniques.In particular, purely datadriven approaches often encounter challenges when applied to complex systems. This can lead to compromised predictive performance in situations where the model fails to capture the actual relationships among system variables. In contrast, the PINN respects the physical characteristics of the problem, while yielding a good dynamic model, based on process data. These results indicate the benefit of utilizing hybrid modeling techniques and their potential application to more complex systems.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Physics-Informed Neural Networks for Process Systems: Handling Plant-Model Mismatch

Moayedi,

Chandrasekar,

Rasmussen

et al. 2024

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

show abstract

“…By doing so, the required data variety and volume are drastically reduced. This modeling approach has been used in several fields of chemical engineering, including reaction kinetics estimation [35,36], separations [29,37] and overall optimization [38]. Despite the wide application of hybrid modeling in process systems engineering for chemical applications, to our best knowledge, the literature lacks papers and methodologies where hybrid modeling is applied to estimate the interactions between molecules for systems with uncertainty over the interactions between the molecules and their nature.…”

Section: Introductionmentioning

confidence: 99%