Surrogate Models for Online Monitoring and Process Troubleshooting of NBR Emulsion Copolymerization

Madhuranthakam, Chandra Mouli R.; Penlidis, Alexander

doi:10.3390/pr4010006

Cited by 3 publications

(1 citation statement)

References 21 publications

(30 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These models can detect process deviations, anomalies, and potential equipment failures before they lead to product quality issues or downtime. Predictive process monitoring with ML can improve process control and decision-making, leading to higher product yields and reduced waste [13][14][15][16]. Moreover, ML-based optimization techniques can identify optimal process conditions to achieve desired product properties while minimizing energy consumption and raw material usage.…”

Section: Machine Learning and Polymerizationmentioning

confidence: 99%

Artificial Neural Network Modeling in the Presence of Uncertainty for Predicting Hydrogenation Degree in Continuous Nitrile Butadiene Rubber Processing

Madhuranthakam,

Hourfar,

Elkamel

2024

Processes

View full text Add to dashboard Cite

The transition from batch to continuous production in the catalytic hydrogenation of nitrile butadiene rubber (NBR) into hydrogenated NBR (HNBR) marks a significant advance for applications under demanding conditions. This study introduces a continuous process utilizing a static mixer (SM) reactor, which notably achieves a hydrogenation conversion rate exceeding 97%. We thoroughly review a mechanistic model of the SM reactor to elucidate the internal dynamics governing the hydrogenation process and address the inherent uncertainties in key parameters such as the Peclet number (Pe), dimensionless time (θτ), reaction coefficient (R), and flow rate coefficient (q). A comprehensive dataset generated from varied parameter values serves as the basis for training an artificial neural network (ANN), which is then compared against traditional models including linear regression, decision tree, and random forest in terms of efficacy. Our results clearly demonstrate the ANN’s superiority in predicting the degree of hydrogenation, achieving the lowest root mean squared error (RMSE) of 3.69 compared to 21.90 for linear regression, 4.94 for decision tree, and 7.51 for random forest. The ANN’s robust capability for modeling complex nonlinear relationships and dynamics significantly enhances decision-making, planning, and optimization of the reactor, reducing computational demands and operational costs. In other words, this approach allows users to rely on a single ML-based model instead of multiple mechanistic models for reflecting the effects of possible uncertainties. Additionally, a feature importance study validates the critical impact of time and element number on the hydrogenation process, further supporting the ANN’s predictive accuracy. These findings underscore the potential of ML-based models in streamlining and enhancing the efficiency of chemical production processes.

show abstract

Section: Machine Learning and Polymerizationmentioning

confidence: 99%