Physics-informed neural networks to solve lumped kinetic model for chromatography process

Tang, Si-Yuan; Yuan, Yun-Hao; Chen, Yu-Cheng; Yao, Shan-Jing; Wang, Ying; Lin, Dong-Qiang

doi:10.1016/j.chroma.2023.464346

Cited by 12 publications

(3 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In such scenarios, the introduction of fast PAT techniques such as infrared spectroscopy (Capito et al, 2015;Großhans et al, 2018;Thakur et al, 2021), Raman spectroscopy (Wang et al, 2023), and mass spectrometry (Haberger et al, 2021), can be used to obtain the key properties promptly, However, the increasing system complexity should be carefully evaluated. For the model calculation, cloud computing (Chen et al, 2020), hybrid modeling (Chen et al, 2020;Lin et al, 2022), or some AI approaches (Tang et al, 2023) can significantly reduce computation time, enabling real-time feedback control. Finally, considerations should be given to the industrial application of DT (O'Connor et al, 2016), including verification and validation of mathematical model and control strategies (Food, 2016) as well as life-cycle management (Bideault et al, 2021).…”

Section: Future Outlook For Iec Dtmentioning

confidence: 99%

Realization of digital twin for dynamic control toward sample variation of ion exchange chromatography in antibody separation

Shi,

Chen,

Zhong

et al. 2024

Biotech & Bioengineering

Self Cite

View full text Add to dashboard Cite

Digital twin (DT) is a virtual and digital representation of physical objects or processes. In this paper, this concept is applied to dynamic control of the collection window in the ion exchange chromatography (IEC) toward sample variations. A possible structure of a feedforward model‐based control DT system was proposed. Initially, a precise IEC mechanistic model was established through experiments, model fitting, and validation. The average root mean square error (RMSE) of fitting and validation was 8.1% and 7.4%, respectively. Then a model‐based gradient optimization was performed, resulting in a 70.0% yield with a remarkable 11.2% increase. Subsequently, the DT was established by systematically integrating the model, chromatography system, online high‐performance liquid chromatography, and a server computer. The DT was validated under varying load conditions. The results demonstrated that the DT could offer an accurate control with acidic variants proportion and yield difference of less than 2% compared to the offline analysis. The embedding mechanistic model also showed a positive predictive performance with an average RMSE of 11.7% during the DT test under >10% sample variation. Practical scenario tests indicated that tightening the control target could further enhance the DT robustness, achieving over 98% success rate with an average yield of 72.7%. The results demonstrated that the constructed DT could accurately mimic real‐world situations and perform an automated and flexible pooling in IEC. Additionally, a detailed methodology for applying DT was summarized.

show abstract

Section: Future Outlook For Iec Dtmentioning

confidence: 99%

Realization of digital twin for dynamic control toward sample variation of ion exchange chromatography in antibody separation

Shi,

Chen,

Zhong

et al. 2024

Biotech & Bioengineering

Self Cite

View full text Add to dashboard Cite

show abstract

“…More complex processes need more sophisticated mathematical models, and analytical solutions are not always available. These models offer greater extrapolation capabilities compared to data‐driven or statistical models (Dürauer et al, 2023; Tang et al, 2023). Establishing robust and efficient models require proper model calibration and suitable calibration experiments (Chen et al, 2022; Chen, Chen, et al, 2023; Chen, Yao, et al, 2023; Yang et al, 2024).…”

Section: Introductionmentioning

confidence: 99%

Residence time distribution in continuous virus filtration

Chen,

Recanati,

De Mathia

et al. 2024

Biotech & Bioengineering

Self Cite

View full text Add to dashboard Cite

Regulatory authorities recommend using residence time distribution (RTD) to address material traceability in continuous manufacturing. Continuous virus filtration is an essential but poorly understood step in biologics manufacturing in respect to fluid dynamics and scale‐up. Here we describe a model that considers nonideal mixing and film resistance for RTD prediction in continuous virus filtration, and its experimental validation using the inert tracer NaNO3. The model was successfully calibrated through pulse injection experiments, yielding good agreement between model prediction and experiment ( 0.90). The model enabled the prediction of RTD with variations—for example, in injection volumes, flow rates, tracer concentrations, and filter surface areas—and was validated using stepwise experiments and combined stepwise and pulse injection experiments. All validation experiments achieved 0.97. Notably, if the process includes a porous material—such as a porous chromatography material, ultrafilter, or virus filter—it must be considered whether the molecule size affects the RTD, as tracers with different sizes may penetrate the pore space differently. Calibration of the model with NaNO3 enabled extrapolation to RTD of recombinant antibodies, which will promote significant savings in antibody consumption. This RTD model is ready for further application in end‐to‐end integrated continuous downstream processes, such as addressing material traceability during continuous virus filtration processes.

show abstract

“…Process simulation stands as one of the important cores of chemical engineering, offering users a virtual playground to explore and comprehend the complexities of real-world industrial processes. − In recent years, much attention has been paid to practical and hands-on learning experiences with these process simulation tools. − However, traditional chemical education has predominantly relied on theoretical instruction, often lacking a tangible connection to the practical applications of their studies. Process simulation can bridge this gap by immersing students in a virtual environment that mirrors the challenges and decision-making processes they will encounter in their professional careers. − This not only enhances their grasp of theoretical principles but also cultivates problem-solving skills essential for success.…”

mentioning

confidence: 99%

Exploration and Practice of Online–Offline Blended Teaching in Process Simulation Courses

Lin,

Chen,

Chen

et al. 2024

J. Chem. Educ.

Self Cite

View full text Add to dashboard Cite

While process simulation tools offer immense potential in chemical engineering, effectively integrating them into the educational curriculum poses challenges. This work explored and practiced online−offline blended teaching in process simulation courses. The design of this blended course was based on a comparison of students' performances in fully online courses, Massive Open Online Courses (MOOCs) and Small Private Online Course (SPOCs). Approximately 2000 students from academic institutions or industries have participated in these online courses since 2021. The comparison between MOOCs and SPOCs encompassed participation rates and scores, revealing a preference among participants for hands-on software lectures over theoretical ones in the process simulation course. Based on the outcomes of online learning, we redesigned the online−offline blended course to optimize course arrangements, leveraging the complementary advantages of both online and offline instruction. This blended approach manifested in two key aspects: first, the online segment served as a precursor to the offline component, with the offline component acting as an evaluative measure of the online segment; second, the two-unit project-based online learning led to the redesigned five-unit offline instruction, which served as both a supplement and expansion to the two-unit online teaching. Furthermore, offline activities, such as error-correction exercises and case studies conducted through group learning, enhanced students' ability for open-ended and independent thinking and reinforced their understanding of innovation on process simulation, which was lacking in online learning.

show abstract

Physics-informed neural networks to solve lumped kinetic model for chromatography process

Cited by 12 publications

References 28 publications

Realization of digital twin for dynamic control toward sample variation of ion exchange chromatography in antibody separation

Realization of digital twin for dynamic control toward sample variation of ion exchange chromatography in antibody separation

Residence time distribution in continuous virus filtration

Exploration and Practice of Online–Offline Blended Teaching in Process Simulation Courses

Contact Info

Product

Resources

About