{"title":"纺织废水:通过 Box-Behnken 设计、Fenton 方法和机器学习整合去除 COD,实现可持续发展","authors":"Selman Turkes, Hakan Güney, Serin Mezarciöz, Bülent Sari, Selami Seçkin Tetik","doi":"10.1108/ijcst-02-2024-0045","DOIUrl":null,"url":null,"abstract":"<h3>Purpose</h3>\n<p>The widespread use of washing machines in textile dyeing and finishing boosts product quality while leading to significant wastewater production. This wastewater poses environmental risks due to the textile industry's high pollution levels and water consumption. Sustainability hinges on minimizing water usage and treating wastewater for reuse. This study employs Matlab R2020a and Python 2023 to model experimental designs for treating textile production wastewater using the Fenton oxidation method, aiming to address sustainability concerns in the industry.</p><!--/ Abstract__block -->\n<h3>Design/methodology/approach</h3>\n<p>The Fenton oxidation process's efficacy and optimal operating conditions were determined through experimental sets employing the Box–Behnken design. Assessing machine learning algorithms on the data, Matlab R2020a utilized an artificial neural network (ANN), while Python 2023 employed support vector regression (SVR), decision trees (DT), and random forest (RF) models. Evaluation of model performance relied on regression coefficient (R2) and mean square error (MSE) outcomes. This methodology aimed to refine the Fenton oxidation process and identify the most efficient parameters, leveraging a combination of experimental design and advanced computational techniques across different programming platforms.</p><!--/ Abstract__block -->\n<h3>Findings</h3>\n<p>The study identified optimal conditions: pH 3, Fe+2 concentration of 0.75 g/L, and H2O2 concentration of 5 mM, yielding 87% COD removal. The Box–Behnken design achieved a high R2 of 0.9372, indicating precise predictions. Artificial neural networks (ANN) and support vector regression (SVR) exhibited successful applications, notably achieving an R2 of 0.99936 and low MSE of 0.00416 in the ANN (LOGSIG) model. However, decision trees (DT) and random forests (RF) proved less effective with limited datasets. The findings underscore technology integration in treatment modeling and the environmental imperative of wastewater purification and reuse.</p><!--/ Abstract__block -->\n<h3>Originality/value</h3>\n<p>This study, in which water use and wastewater treatment are evaluated with technological integration such as machine learning and data management, reveals how to contribute to targets 6, 9, 12, and 14 within the scope of UNEP 2030 sustainable development goals.</p><!--/ Abstract__block -->","PeriodicalId":50330,"journal":{"name":"International Journal of Clothing Science and Technology","volume":"24 1","pages":""},"PeriodicalIF":1.0000,"publicationDate":"2024-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Textile wastewater: COD removal via Box–Behnken design, Fenton method, and machine learning integration for sustainability\",\"authors\":\"Selman Turkes, Hakan Güney, Serin Mezarciöz, Bülent Sari, Selami Seçkin Tetik\",\"doi\":\"10.1108/ijcst-02-2024-0045\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<h3>Purpose</h3>\\n<p>The widespread use of washing machines in textile dyeing and finishing boosts product quality while leading to significant wastewater production. This wastewater poses environmental risks due to the textile industry's high pollution levels and water consumption. Sustainability hinges on minimizing water usage and treating wastewater for reuse. This study employs Matlab R2020a and Python 2023 to model experimental designs for treating textile production wastewater using the Fenton oxidation method, aiming to address sustainability concerns in the industry.</p><!--/ Abstract__block -->\\n<h3>Design/methodology/approach</h3>\\n<p>The Fenton oxidation process's efficacy and optimal operating conditions were determined through experimental sets employing the Box–Behnken design. Assessing machine learning algorithms on the data, Matlab R2020a utilized an artificial neural network (ANN), while Python 2023 employed support vector regression (SVR), decision trees (DT), and random forest (RF) models. Evaluation of model performance relied on regression coefficient (R2) and mean square error (MSE) outcomes. This methodology aimed to refine the Fenton oxidation process and identify the most efficient parameters, leveraging a combination of experimental design and advanced computational techniques across different programming platforms.</p><!--/ Abstract__block -->\\n<h3>Findings</h3>\\n<p>The study identified optimal conditions: pH 3, Fe+2 concentration of 0.75 g/L, and H2O2 concentration of 5 mM, yielding 87% COD removal. The Box–Behnken design achieved a high R2 of 0.9372, indicating precise predictions. Artificial neural networks (ANN) and support vector regression (SVR) exhibited successful applications, notably achieving an R2 of 0.99936 and low MSE of 0.00416 in the ANN (LOGSIG) model. However, decision trees (DT) and random forests (RF) proved less effective with limited datasets. The findings underscore technology integration in treatment modeling and the environmental imperative of wastewater purification and reuse.</p><!--/ Abstract__block -->\\n<h3>Originality/value</h3>\\n<p>This study, in which water use and wastewater treatment are evaluated with technological integration such as machine learning and data management, reveals how to contribute to targets 6, 9, 12, and 14 within the scope of UNEP 2030 sustainable development goals.</p><!--/ Abstract__block -->\",\"PeriodicalId\":50330,\"journal\":{\"name\":\"International Journal of Clothing Science and Technology\",\"volume\":\"24 1\",\"pages\":\"\"},\"PeriodicalIF\":1.0000,\"publicationDate\":\"2024-06-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Journal of Clothing Science and Technology\",\"FirstCategoryId\":\"88\",\"ListUrlMain\":\"https://doi.org/10.1108/ijcst-02-2024-0045\",\"RegionNum\":4,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"MATERIALS SCIENCE, TEXTILES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Clothing Science and Technology","FirstCategoryId":"88","ListUrlMain":"https://doi.org/10.1108/ijcst-02-2024-0045","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"MATERIALS SCIENCE, TEXTILES","Score":null,"Total":0}
Textile wastewater: COD removal via Box–Behnken design, Fenton method, and machine learning integration for sustainability
Purpose
The widespread use of washing machines in textile dyeing and finishing boosts product quality while leading to significant wastewater production. This wastewater poses environmental risks due to the textile industry's high pollution levels and water consumption. Sustainability hinges on minimizing water usage and treating wastewater for reuse. This study employs Matlab R2020a and Python 2023 to model experimental designs for treating textile production wastewater using the Fenton oxidation method, aiming to address sustainability concerns in the industry.
Design/methodology/approach
The Fenton oxidation process's efficacy and optimal operating conditions were determined through experimental sets employing the Box–Behnken design. Assessing machine learning algorithms on the data, Matlab R2020a utilized an artificial neural network (ANN), while Python 2023 employed support vector regression (SVR), decision trees (DT), and random forest (RF) models. Evaluation of model performance relied on regression coefficient (R2) and mean square error (MSE) outcomes. This methodology aimed to refine the Fenton oxidation process and identify the most efficient parameters, leveraging a combination of experimental design and advanced computational techniques across different programming platforms.
Findings
The study identified optimal conditions: pH 3, Fe+2 concentration of 0.75 g/L, and H2O2 concentration of 5 mM, yielding 87% COD removal. The Box–Behnken design achieved a high R2 of 0.9372, indicating precise predictions. Artificial neural networks (ANN) and support vector regression (SVR) exhibited successful applications, notably achieving an R2 of 0.99936 and low MSE of 0.00416 in the ANN (LOGSIG) model. However, decision trees (DT) and random forests (RF) proved less effective with limited datasets. The findings underscore technology integration in treatment modeling and the environmental imperative of wastewater purification and reuse.
Originality/value
This study, in which water use and wastewater treatment are evaluated with technological integration such as machine learning and data management, reveals how to contribute to targets 6, 9, 12, and 14 within the scope of UNEP 2030 sustainable development goals.
期刊介绍:
Addresses all aspects of the science and technology of clothing-objective measurement techniques, control of fibre and fabric, CAD systems, product testing, sewing, weaving and knitting, inspection systems, drape and finishing, etc. Academic and industrial research findings are published after a stringent review has taken place.