Smart solutions for dissolved oxygen control in semi-batch fermenters: A machine learning approach
The monitoring and measurement of dissolved oxygen (DO), plays a significant role in industrial effluent, and disposal of effluents has been a serious challenge to researchers. Aeration is the primary step in effluent treatment. The basic method for determining DO is direct measurement. This study h...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-01-01
|
| Series: | Desalination and Water Treatment |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1944398624000043 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849721977565085696 |
|---|---|
| author | J. Sumathi P. Aravind G. Gandhimathi |
| author_facet | J. Sumathi P. Aravind G. Gandhimathi |
| author_sort | J. Sumathi |
| collection | DOAJ |
| description | The monitoring and measurement of dissolved oxygen (DO), plays a significant role in industrial effluent, and disposal of effluents has been a serious challenge to researchers. Aeration is the primary step in effluent treatment. The basic method for determining DO is direct measurement. This study has been carried out in effluent from the paper industry to estimate the performance of dissolved oxygen in a semi-batch lark hygiene fermenter and was oxygenated till saturation at 25 °C under real-time study. This study has been carried out using Multi-Layered Feed Forward Back Propagation Artificial Neural Network (ML-FFBPANN) and the experimental results were optimized with fourteen different machine learning algorithms such as Polak-Ribiere Conjugate Gradient (CGP), Conjugate Gradient with Powell/Beale Restarts (CGB), Bayesian Regularization (BR), Gradient Descent (GD), BFGS Quasi-Newton (BFG), GD with Momentum (GDM), Gaussian Discriminate Analysis(GDA), Fletcher-Powell Conjugate Gradient (CGF), Resilient Backpropagation (RP), Variable Learning Rate Gradient Descent (GDX), One Step Secant (OSS), Regression (R), Levenberg-Marquardt (LM), Scaled Conjugate Gradient(SCG). Parameters Root Mean Squared Error (RMSE) and the correlation coefficient (R-square) were used to evaluate the performance of each model and mathematical modeling for correlation co-efficient of all algorithms are also presented. LM and R are the best algorithms but the ML-FFBPANN-LM algorithm provided the best optimization results of maximum correlation co-efficient. LM algorithm produced a maximum correlation coefficient under training (0.99818), testing (0.99351), valediction (1.0), and an overall correlation coefficient be 0.9568. From the study, it can be concluded that the ML-FFBPANN with LM algorithm can be used in the aeration process in effluent treatment for analysis and prediction of process parameters. |
| format | Article |
| id | doaj-art-8c752d253fcc4da499cc330700f9646e |
| institution | DOAJ |
| issn | 1944-3986 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Desalination and Water Treatment |
| spelling | doaj-art-8c752d253fcc4da499cc330700f9646e2025-08-20T03:11:30ZengElsevierDesalination and Water Treatment1944-39862024-01-0131710000410.1016/j.dwt.2024.100004Smart solutions for dissolved oxygen control in semi-batch fermenters: A machine learning approachJ. Sumathi0P. Aravind1G. Gandhimathi2The Institution of Engineers (India) [IEI], Thanjavur Zone, Tamil Nadu, IndiaDepartment of Electrical and Computer Engineering, Mattu University, Mattu, Ethiopia.; corresponding author.Department of Electronics and Communication Engineering, SRM TRP Engineering College, Tiruchirappalli, Tamil Nadu, IndiaThe monitoring and measurement of dissolved oxygen (DO), plays a significant role in industrial effluent, and disposal of effluents has been a serious challenge to researchers. Aeration is the primary step in effluent treatment. The basic method for determining DO is direct measurement. This study has been carried out in effluent from the paper industry to estimate the performance of dissolved oxygen in a semi-batch lark hygiene fermenter and was oxygenated till saturation at 25 °C under real-time study. This study has been carried out using Multi-Layered Feed Forward Back Propagation Artificial Neural Network (ML-FFBPANN) and the experimental results were optimized with fourteen different machine learning algorithms such as Polak-Ribiere Conjugate Gradient (CGP), Conjugate Gradient with Powell/Beale Restarts (CGB), Bayesian Regularization (BR), Gradient Descent (GD), BFGS Quasi-Newton (BFG), GD with Momentum (GDM), Gaussian Discriminate Analysis(GDA), Fletcher-Powell Conjugate Gradient (CGF), Resilient Backpropagation (RP), Variable Learning Rate Gradient Descent (GDX), One Step Secant (OSS), Regression (R), Levenberg-Marquardt (LM), Scaled Conjugate Gradient(SCG). Parameters Root Mean Squared Error (RMSE) and the correlation coefficient (R-square) were used to evaluate the performance of each model and mathematical modeling for correlation co-efficient of all algorithms are also presented. LM and R are the best algorithms but the ML-FFBPANN-LM algorithm provided the best optimization results of maximum correlation co-efficient. LM algorithm produced a maximum correlation coefficient under training (0.99818), testing (0.99351), valediction (1.0), and an overall correlation coefficient be 0.9568. From the study, it can be concluded that the ML-FFBPANN with LM algorithm can be used in the aeration process in effluent treatment for analysis and prediction of process parameters.http://www.sciencedirect.com/science/article/pii/S1944398624000043Artificial neural networkMachine learning algorithmsDissolved oxygenPaper industry effluentRegression analysisDissolved oxygen parameter |
| spellingShingle | J. Sumathi P. Aravind G. Gandhimathi Smart solutions for dissolved oxygen control in semi-batch fermenters: A machine learning approach Desalination and Water Treatment Artificial neural network Machine learning algorithms Dissolved oxygen Paper industry effluent Regression analysis Dissolved oxygen parameter |
| title | Smart solutions for dissolved oxygen control in semi-batch fermenters: A machine learning approach |
| title_full | Smart solutions for dissolved oxygen control in semi-batch fermenters: A machine learning approach |
| title_fullStr | Smart solutions for dissolved oxygen control in semi-batch fermenters: A machine learning approach |
| title_full_unstemmed | Smart solutions for dissolved oxygen control in semi-batch fermenters: A machine learning approach |
| title_short | Smart solutions for dissolved oxygen control in semi-batch fermenters: A machine learning approach |
| title_sort | smart solutions for dissolved oxygen control in semi batch fermenters a machine learning approach |
| topic | Artificial neural network Machine learning algorithms Dissolved oxygen Paper industry effluent Regression analysis Dissolved oxygen parameter |
| url | http://www.sciencedirect.com/science/article/pii/S1944398624000043 |
| work_keys_str_mv | AT jsumathi smartsolutionsfordissolvedoxygencontrolinsemibatchfermentersamachinelearningapproach AT paravind smartsolutionsfordissolvedoxygencontrolinsemibatchfermentersamachinelearningapproach AT ggandhimathi smartsolutionsfordissolvedoxygencontrolinsemibatchfermentersamachinelearningapproach |