Performance evaluation of whey flux in dead-end and cross-flow modes via convolutional neural networks
Effluent originating from cheese production puts pressure onto environment due to its high organic load. Therefore, the main objective of this work was to compare the influence of different process variables (transmembrane pressure (TMP), Reynolds number and feed pH) on whey protein recovery from sy...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Academic Press
2022
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/103197/1/AhmadFauziIsmail2022_PerformanceEvaluationofWheyFluxInDead_compressed.pdf |
| _version_ | 1796867413689499648 |
|---|---|
| author | Yogarathinam, Lukka Thuyavan Velswamy, Kirubakaran Gangasalam, Arthanareeswaran Ismail, Ahmad Fauzi Goh, Pei Sean Narayanan, Anantharaman Abdullah, Mohd. Sohaimi |
| author_facet | Yogarathinam, Lukka Thuyavan Velswamy, Kirubakaran Gangasalam, Arthanareeswaran Ismail, Ahmad Fauzi Goh, Pei Sean Narayanan, Anantharaman Abdullah, Mohd. Sohaimi |
| author_sort | Yogarathinam, Lukka Thuyavan |
| collection | ePrints |
| description | Effluent originating from cheese production puts pressure onto environment due to its high organic load. Therefore, the main objective of this work was to compare the influence of different process variables (transmembrane pressure (TMP), Reynolds number and feed pH) on whey protein recovery from synthetic and industrial cheese whey using polyethersulfone (PES 30 kDa) membrane in dead-end and cross-flow modes. Analysis on the fouling mechanistic model indicates that cake layer formation is dominant as compared to other pore blocking phenomena evaluated. Among the input variables, pH of whey protein solution has the biggest influence towards membrane flux and protein rejection performances. At pH 4, electrostatic attraction experienced by whey protein molecules prompted a decline in flux. Cross-flow filtration system exhibited a whey rejection value of 0.97 with an average flux of 69.40 L/m2h and at an experimental condition of 250 kPa and 8 for TMP and pH, respectively. The dynamic behavior of whey effluent flux was modeled using machine learning (ML) tool convolutional neural networks (CNN) and recursive one-step prediction scheme was utilized. Linear and non-linear correlation indicated that CNN model (R2 – 0.99) correlated well with the dynamic flux experimental data. PES 30 kDa membrane displayed a total protein rejection coefficient of 0.96 with 55% of water recovery for the industrial cheese whey effluent. Overall, these filtration studies revealed that this dynamic whey flux data studies using the CNN modeling also has a wider scope as it can be applied in sensor tuning to monitor flux online by means of enhancing whey recovery efficiency. |
| first_indexed | 2024-03-05T21:26:53Z |
| format | Article |
| id | utm.eprints-103197 |
| institution | Universiti Teknologi Malaysia - ePrints |
| language | English |
| last_indexed | 2024-03-05T21:26:53Z |
| publishDate | 2022 |
| publisher | Academic Press |
| record_format | dspace |
| spelling | utm.eprints-1031972023-10-20T02:35:13Z http://eprints.utm.my/103197/ Performance evaluation of whey flux in dead-end and cross-flow modes via convolutional neural networks Yogarathinam, Lukka Thuyavan Velswamy, Kirubakaran Gangasalam, Arthanareeswaran Ismail, Ahmad Fauzi Goh, Pei Sean Narayanan, Anantharaman Abdullah, Mohd. Sohaimi TP Chemical technology Effluent originating from cheese production puts pressure onto environment due to its high organic load. Therefore, the main objective of this work was to compare the influence of different process variables (transmembrane pressure (TMP), Reynolds number and feed pH) on whey protein recovery from synthetic and industrial cheese whey using polyethersulfone (PES 30 kDa) membrane in dead-end and cross-flow modes. Analysis on the fouling mechanistic model indicates that cake layer formation is dominant as compared to other pore blocking phenomena evaluated. Among the input variables, pH of whey protein solution has the biggest influence towards membrane flux and protein rejection performances. At pH 4, electrostatic attraction experienced by whey protein molecules prompted a decline in flux. Cross-flow filtration system exhibited a whey rejection value of 0.97 with an average flux of 69.40 L/m2h and at an experimental condition of 250 kPa and 8 for TMP and pH, respectively. The dynamic behavior of whey effluent flux was modeled using machine learning (ML) tool convolutional neural networks (CNN) and recursive one-step prediction scheme was utilized. Linear and non-linear correlation indicated that CNN model (R2 – 0.99) correlated well with the dynamic flux experimental data. PES 30 kDa membrane displayed a total protein rejection coefficient of 0.96 with 55% of water recovery for the industrial cheese whey effluent. Overall, these filtration studies revealed that this dynamic whey flux data studies using the CNN modeling also has a wider scope as it can be applied in sensor tuning to monitor flux online by means of enhancing whey recovery efficiency. Academic Press 2022 Article PeerReviewed application/pdf en http://eprints.utm.my/103197/1/AhmadFauziIsmail2022_PerformanceEvaluationofWheyFluxInDead_compressed.pdf Yogarathinam, Lukka Thuyavan and Velswamy, Kirubakaran and Gangasalam, Arthanareeswaran and Ismail, Ahmad Fauzi and Goh, Pei Sean and Narayanan, Anantharaman and Abdullah, Mohd. Sohaimi (2022) Performance evaluation of whey flux in dead-end and cross-flow modes via convolutional neural networks. Journal of Environmental Management, 301 (113872). pp. 1-13. ISSN 0301-4797 http://dx.doi.org/10.1016/j.jenvman.2021.113872 DOI: 10.1016/j.jenvman.2021.113872 |
| spellingShingle | TP Chemical technology Yogarathinam, Lukka Thuyavan Velswamy, Kirubakaran Gangasalam, Arthanareeswaran Ismail, Ahmad Fauzi Goh, Pei Sean Narayanan, Anantharaman Abdullah, Mohd. Sohaimi Performance evaluation of whey flux in dead-end and cross-flow modes via convolutional neural networks |
| title | Performance evaluation of whey flux in dead-end and cross-flow modes via convolutional neural networks |
| title_full | Performance evaluation of whey flux in dead-end and cross-flow modes via convolutional neural networks |
| title_fullStr | Performance evaluation of whey flux in dead-end and cross-flow modes via convolutional neural networks |
| title_full_unstemmed | Performance evaluation of whey flux in dead-end and cross-flow modes via convolutional neural networks |
| title_short | Performance evaluation of whey flux in dead-end and cross-flow modes via convolutional neural networks |
| title_sort | performance evaluation of whey flux in dead end and cross flow modes via convolutional neural networks |
| topic | TP Chemical technology |
| url | http://eprints.utm.my/103197/1/AhmadFauziIsmail2022_PerformanceEvaluationofWheyFluxInDead_compressed.pdf |
| work_keys_str_mv | AT yogarathinamlukkathuyavan performanceevaluationofwheyfluxindeadendandcrossflowmodesviaconvolutionalneuralnetworks AT velswamykirubakaran performanceevaluationofwheyfluxindeadendandcrossflowmodesviaconvolutionalneuralnetworks AT gangasalamarthanareeswaran performanceevaluationofwheyfluxindeadendandcrossflowmodesviaconvolutionalneuralnetworks AT ismailahmadfauzi performanceevaluationofwheyfluxindeadendandcrossflowmodesviaconvolutionalneuralnetworks AT gohpeisean performanceevaluationofwheyfluxindeadendandcrossflowmodesviaconvolutionalneuralnetworks AT narayanananantharaman performanceevaluationofwheyfluxindeadendandcrossflowmodesviaconvolutionalneuralnetworks AT abdullahmohdsohaimi performanceevaluationofwheyfluxindeadendandcrossflowmodesviaconvolutionalneuralnetworks |