Scholarlink

<p>This study investigates the photocatalytic degradation of oil-produced water (OPW) using solar irradiation, the application of response surface methodology, and deep learning models. A total of 70 experimental batch reactor trials were conducted by varying pH from 6 to 9, Titanium dioxide (TiO<sub>2</sub>) catalyst dosage from 1 to 4&#xa0;g/L, and reaction time from 180&#xa0;min, along with chemical oxygen demand (COD) removal efficiency. Using the RSM, the effects of inputs on COD were quantified to determine the optimal conditions. Subsequently, Support Vector Machine (SVM), Artificial Neural Network (ANN), Long Short-Term Memory (LSTM), and Extreme Learning Machine (ELM) were employed to further predict COD based on the RSM study, and the results were evaluated. According to RSM, the optimum value for COD removal efficiency was 95% at pH 8.993, TiO<sub>2</sub> photocatalyst dosage 3.998&#xa0;g/L, and reaction time 180&#xa0;min with R<sup>2</sup> = 0.9675. The R<sup>2</sup> scores of ANN and SVMs were limited to 0.84 and 0.88 for all data. LSTM achieved an R<sup>2</sup> score of 0.93 training and 0.99 testing dataset whereas, ELM showed the best performance, with R²=0.95 and 0.94. RSM is suitable for process optimization, and an ELM energy-efficient model is used to treat OPW using natural sunlight sustainably.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

TiO2 Photocatalysis for Sustainable Treatment of Oil Produced Water: A Computational Approach

  • 期刊论文

  • 发表日期：

    2026年5月5日

查看全文
  • Nayeemuddin Mohammed,
  • Faizan Ahmed,
  • Feroz Shaik,
  • Hiren Mewada

摘要

This study investigates the photocatalytic degradation of oil-produced water (OPW) using solar irradiation, the application of response surface methodology, and deep learning models. A total of 70 experimental batch reactor trials were conducted by varying pH from 6 to 9, Titanium dioxide (TiO2) catalyst dosage from 1 to 4 g/L, and reaction time from 180 min, along with chemical oxygen demand (COD) removal efficiency. Using the RSM, the effects of inputs on COD were quantified to determine the optimal conditions. Subsequently, Support Vector Machine (SVM), Artificial Neural Network (ANN), Long Short-Term Memory (LSTM), and Extreme Learning Machine (ELM) were employed to further predict COD based on the RSM study, and the results were evaluated. According to RSM, the optimum value for COD removal efficiency was 95% at pH 8.993, TiO2 photocatalyst dosage 3.998 g/L, and reaction time 180 min with R2 = 0.9675. The R2 scores of ANN and SVMs were limited to 0.84 and 0.88 for all data. LSTM achieved an R2 score of 0.93 training and 0.99 testing dataset whereas, ELM showed the best performance, with R²=0.95 and 0.94. RSM is suitable for process optimization, and an ELM energy-efficient model is used to treat OPW using natural sunlight sustainably.