Development of a Machine Learning Model for Predicting Hardness in the Water Treatment Pharmaceutical Industry
The pharmaceutical industry has a water treatment process for production needs, and the softener process reduces the content of Ca2, Mg2. Few studies have been conducted to predict hardness in water. Some related studies have been undertaken to indicate lake water quality, water sulfur content, and...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
University of Novi Sad, Faculty of Technical Sciences
2023-06-01
|
| Series: | International Journal of Industrial Engineering and Management |
| Subjects: | |
| Online Access: | http://www.ijiemjournal.uns.ac.rs/images/journal/volume14/IJIEM_329.pdf |
| _version_ | 1797821442756182016 |
|---|---|
| author | Al Ansor Siahaan Muhammad Asrol |
| author_facet | Al Ansor Siahaan Muhammad Asrol |
| author_sort | Al Ansor Siahaan |
| collection | DOAJ |
| description | The pharmaceutical industry has a water treatment process for production needs, and the
softener process reduces the content of Ca2, Mg2. Few studies have been conducted to
predict hardness in water. Some related studies have been undertaken to indicate lake water
quality, water sulfur content, and water content in reverse osmosis output in factory water
systems. This study aims to determine the prediction of hardness in water treatment systems
using machine learning random forest regression and long short-term memory. The dataset is
from Programmable Logic Controller records and daily sampling data from pharmaceutical
factory laboratories. Machine learning models developed hyperparameter tuning processes
to get the most optimal results. The best machine learning model is RFR with R2 Train 0.990
and R2 Test 0.960, while LSTM with R2 Train 0.946 and R2 Test 0.917. |
| first_indexed | 2024-03-13T09:52:45Z |
| format | Article |
| id | doaj.art-a169ba630b4a494796a2639549470efa |
| institution | Directory Open Access Journal |
| issn | 2217-2661 2683-345X |
| language | English |
| last_indexed | 2024-03-13T09:52:45Z |
| publishDate | 2023-06-01 |
| publisher | University of Novi Sad, Faculty of Technical Sciences |
| record_format | Article |
| series | International Journal of Industrial Engineering and Management |
| spelling | doaj.art-a169ba630b4a494796a2639549470efa2023-05-24T06:58:53ZengUniversity of Novi Sad, Faculty of Technical SciencesInternational Journal of Industrial Engineering and Management2217-26612683-345X2023-06-011424150http://doi.org/10.24867/IJIEM-2023-2-329329Development of a Machine Learning Model for Predicting Hardness in the Water Treatment Pharmaceutical IndustryAl Ansor Siahaan0Muhammad Asrol1Industrial Engineering Department, BINUS Graduate Program - Master of Industrial Engineering, Bina Nusantara University, Jakarta, 11480, IndonesiaIndustrial Engineering Department, BINUS Graduate Program - Master of Industrial Engineering, Bina Nusantara University, Jakarta, 11480, IndonesiaThe pharmaceutical industry has a water treatment process for production needs, and the softener process reduces the content of Ca2, Mg2. Few studies have been conducted to predict hardness in water. Some related studies have been undertaken to indicate lake water quality, water sulfur content, and water content in reverse osmosis output in factory water systems. This study aims to determine the prediction of hardness in water treatment systems using machine learning random forest regression and long short-term memory. The dataset is from Programmable Logic Controller records and daily sampling data from pharmaceutical factory laboratories. Machine learning models developed hyperparameter tuning processes to get the most optimal results. The best machine learning model is RFR with R2 Train 0.990 and R2 Test 0.960, while LSTM with R2 Train 0.946 and R2 Test 0.917.http://www.ijiemjournal.uns.ac.rs/images/journal/volume14/IJIEM_329.pdfhardnesslong short-term memory (lstm)pharmaceuticalrandom forrest regression (rfr)water system |
| spellingShingle | Al Ansor Siahaan Muhammad Asrol Development of a Machine Learning Model for Predicting Hardness in the Water Treatment Pharmaceutical Industry International Journal of Industrial Engineering and Management hardness long short-term memory (lstm) pharmaceutical random forrest regression (rfr) water system |
| title | Development of a Machine Learning Model for Predicting Hardness in the Water Treatment Pharmaceutical Industry |
| title_full | Development of a Machine Learning Model for Predicting Hardness in the Water Treatment Pharmaceutical Industry |
| title_fullStr | Development of a Machine Learning Model for Predicting Hardness in the Water Treatment Pharmaceutical Industry |
| title_full_unstemmed | Development of a Machine Learning Model for Predicting Hardness in the Water Treatment Pharmaceutical Industry |
| title_short | Development of a Machine Learning Model for Predicting Hardness in the Water Treatment Pharmaceutical Industry |
| title_sort | development of a machine learning model for predicting hardness in the water treatment pharmaceutical industry |
| topic | hardness long short-term memory (lstm) pharmaceutical random forrest regression (rfr) water system |
| url | http://www.ijiemjournal.uns.ac.rs/images/journal/volume14/IJIEM_329.pdf |
| work_keys_str_mv | AT alansorsiahaan developmentofamachinelearningmodelforpredictinghardnessinthewatertreatmentpharmaceuticalindustry AT muhammadasrol developmentofamachinelearningmodelforpredictinghardnessinthewatertreatmentpharmaceuticalindustry |