Artificial Intelligence in Steam Cracking Modeling: A Deep Learning Algorithm for Detailed Effluent Prediction
Chemical processes can benefit tremendously from fast and accurate effluent composition prediction for plant design, control, and optimization. The Industry 4.0 revolution claims that by introducing machine learning into these fields, substantial economic and environmental gains can be achieved. The...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2019-12-01
|
| Series: | Engineering |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2095809918310324 |
| _version_ | 1811269860548673536 |
|---|---|
| author | Pieter P. Plehiers Steffen H. Symoens Ismaël Amghizar Guy B. Marin Christian V. Stevens Kevin M. Van Geem |
| author_facet | Pieter P. Plehiers Steffen H. Symoens Ismaël Amghizar Guy B. Marin Christian V. Stevens Kevin M. Van Geem |
| author_sort | Pieter P. Plehiers |
| collection | DOAJ |
| description | Chemical processes can benefit tremendously from fast and accurate effluent composition prediction for plant design, control, and optimization. The Industry 4.0 revolution claims that by introducing machine learning into these fields, substantial economic and environmental gains can be achieved. The bottleneck for high-frequency optimization and process control is often the time necessary to perform the required detailed analyses of, for example, feed and product. To resolve these issues, a framework of four deep learning artificial neural networks (DL ANNs) has been developed for the largest chemicals production process—steam cracking. The proposed methodology allows both a detailed characterization of a naphtha feedstock and a detailed composition of the steam cracker effluent to be determined, based on a limited number of commercial naphtha indices and rapidly accessible process characteristics. The detailed characterization of a naphtha is predicted from three points on the boiling curve and paraffins, iso-paraffins, olefins, naphthenes, and aronatics (PIONA) characterization. If unavailable, the boiling points are also estimated. Even with estimated boiling points, the developed DL ANN outperforms several established methods such as maximization of Shannon entropy and traditional ANNs. For feedstock reconstruction, a mean absolute error (MAE) of 0.3 wt% is achieved on the test set, while the MAE of the effluent prediction is 0.1 wt%. When combining all networks—using the output of the previous as input to the next—the effluent MAE increases to 0.19 wt%. In addition to the high accuracy of the networks, a major benefit is the negligible computational cost required to obtain the predictions. On a standard Intel i7 processor, predictions are made in the order of milliseconds. Commercial software such as COILSIM1D performs slightly better in terms of accuracy, but the required central processing unit time per reaction is in the order of seconds. This tremendous speed-up and minimal accuracy loss make the presented framework highly suitable for the continuous monitoring of difficult-to-access process parameters and for the envisioned, high-frequency real-time optimization (RTO) strategy or process control. Nevertheless, the lack of a fundamental basis implies that fundamental understanding is almost completely lost, which is not always well-accepted by the engineering community. In addition, the performance of the developed networks drops significantly for naphthas that are highly dissimilar to those in the training set. Keywords: Artificial intelligence, Deep learning, Steam cracking, Artificial neural networks |
| first_indexed | 2024-04-12T21:50:37Z |
| format | Article |
| id | doaj.art-3d0b3869d22e4c71986cf3eceb30ad65 |
| institution | Directory Open Access Journal |
| issn | 2095-8099 |
| language | English |
| last_indexed | 2024-04-12T21:50:37Z |
| publishDate | 2019-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Engineering |
| spelling | doaj.art-3d0b3869d22e4c71986cf3eceb30ad652022-12-22T03:15:30ZengElsevierEngineering2095-80992019-12-015610271040Artificial Intelligence in Steam Cracking Modeling: A Deep Learning Algorithm for Detailed Effluent PredictionPieter P. Plehiers0Steffen H. Symoens1Ismaël Amghizar2Guy B. Marin3Christian V. Stevens4Kevin M. Van Geem5Laboratory for Chemical Technology, Department of Materials, Textiles and Chemical Engineering, Ghent University, Gent 9052, BelgiumLaboratory for Chemical Technology, Department of Materials, Textiles and Chemical Engineering, Ghent University, Gent 9052, BelgiumLaboratory for Chemical Technology, Department of Materials, Textiles and Chemical Engineering, Ghent University, Gent 9052, BelgiumLaboratory for Chemical Technology, Department of Materials, Textiles and Chemical Engineering, Ghent University, Gent 9052, BelgiumSynBioC Research Group, Department of Green Chemistry and Technology, Faculty of Bioscience Engineering, Ghent University, Gent 9000, BelgiumLaboratory for Chemical Technology, Department of Materials, Textiles and Chemical Engineering, Ghent University, Gent 9052, Belgium; Corresponding author.Chemical processes can benefit tremendously from fast and accurate effluent composition prediction for plant design, control, and optimization. The Industry 4.0 revolution claims that by introducing machine learning into these fields, substantial economic and environmental gains can be achieved. The bottleneck for high-frequency optimization and process control is often the time necessary to perform the required detailed analyses of, for example, feed and product. To resolve these issues, a framework of four deep learning artificial neural networks (DL ANNs) has been developed for the largest chemicals production process—steam cracking. The proposed methodology allows both a detailed characterization of a naphtha feedstock and a detailed composition of the steam cracker effluent to be determined, based on a limited number of commercial naphtha indices and rapidly accessible process characteristics. The detailed characterization of a naphtha is predicted from three points on the boiling curve and paraffins, iso-paraffins, olefins, naphthenes, and aronatics (PIONA) characterization. If unavailable, the boiling points are also estimated. Even with estimated boiling points, the developed DL ANN outperforms several established methods such as maximization of Shannon entropy and traditional ANNs. For feedstock reconstruction, a mean absolute error (MAE) of 0.3 wt% is achieved on the test set, while the MAE of the effluent prediction is 0.1 wt%. When combining all networks—using the output of the previous as input to the next—the effluent MAE increases to 0.19 wt%. In addition to the high accuracy of the networks, a major benefit is the negligible computational cost required to obtain the predictions. On a standard Intel i7 processor, predictions are made in the order of milliseconds. Commercial software such as COILSIM1D performs slightly better in terms of accuracy, but the required central processing unit time per reaction is in the order of seconds. This tremendous speed-up and minimal accuracy loss make the presented framework highly suitable for the continuous monitoring of difficult-to-access process parameters and for the envisioned, high-frequency real-time optimization (RTO) strategy or process control. Nevertheless, the lack of a fundamental basis implies that fundamental understanding is almost completely lost, which is not always well-accepted by the engineering community. In addition, the performance of the developed networks drops significantly for naphthas that are highly dissimilar to those in the training set. Keywords: Artificial intelligence, Deep learning, Steam cracking, Artificial neural networkshttp://www.sciencedirect.com/science/article/pii/S2095809918310324 |
| spellingShingle | Pieter P. Plehiers Steffen H. Symoens Ismaël Amghizar Guy B. Marin Christian V. Stevens Kevin M. Van Geem Artificial Intelligence in Steam Cracking Modeling: A Deep Learning Algorithm for Detailed Effluent Prediction Engineering |
| title | Artificial Intelligence in Steam Cracking Modeling: A Deep Learning Algorithm for Detailed Effluent Prediction |
| title_full | Artificial Intelligence in Steam Cracking Modeling: A Deep Learning Algorithm for Detailed Effluent Prediction |
| title_fullStr | Artificial Intelligence in Steam Cracking Modeling: A Deep Learning Algorithm for Detailed Effluent Prediction |
| title_full_unstemmed | Artificial Intelligence in Steam Cracking Modeling: A Deep Learning Algorithm for Detailed Effluent Prediction |
| title_short | Artificial Intelligence in Steam Cracking Modeling: A Deep Learning Algorithm for Detailed Effluent Prediction |
| title_sort | artificial intelligence in steam cracking modeling a deep learning algorithm for detailed effluent prediction |
| url | http://www.sciencedirect.com/science/article/pii/S2095809918310324 |
| work_keys_str_mv | AT pieterpplehiers artificialintelligenceinsteamcrackingmodelingadeeplearningalgorithmfordetailedeffluentprediction AT steffenhsymoens artificialintelligenceinsteamcrackingmodelingadeeplearningalgorithmfordetailedeffluentprediction AT ismaelamghizar artificialintelligenceinsteamcrackingmodelingadeeplearningalgorithmfordetailedeffluentprediction AT guybmarin artificialintelligenceinsteamcrackingmodelingadeeplearningalgorithmfordetailedeffluentprediction AT christianvstevens artificialintelligenceinsteamcrackingmodelingadeeplearningalgorithmfordetailedeffluentprediction AT kevinmvangeem artificialintelligenceinsteamcrackingmodelingadeeplearningalgorithmfordetailedeffluentprediction |