Comparison of central composite design and artificial neural network approaches for modeling and optimization of 2-methylpropane-2-thiol removal from contaminated soil by ultrasound

Document Type: Original Article

Authors

1 Ph.D. Student of Chemical engineering, Environmental Engineering Research Center (EERC), Sahand University of Technology, Sahand New Town, Tabriz, Iran

2 Professor of Chemical engineering, Environmental Engineering Research Center (EERC), Sahand University of Technology, Sahand New Town, Tabriz, Iran

3 Associate Professor of Chemical Engineering, Environmental Engineering Research Center (EERC), Sahand University of Technology, Sahand New Town, Tabriz, Iran

Abstract

In this article a comparative study for modeling and optimization of 2-methylpropane-2-thiol removal from contaminated soil by ultrasound is investigated. Central Composite Design (CCD) and artificial neural network (ANN) were utilized and compared to each other in order to obtain appropriate predicting model with respect to sonication power (w), sonication time (min) and water/reactor volume ratio (ml/ml). CCD was used based on Response Surface Model (RSM) and the ANN model was developed by the Levenberg−Marquardt feed forward back-propagation training algorithm and topology (3:8:1). Analysis of variance and Pareto analysis resulted from CCD demonstrate that sonication power is the most influential parameter on 2-methylpropane-2-thiol removal efficiency (sonication time and amount of added water in the next order respectively). This is confirmed by ANN model. Also interaction between water content and power, sonication time and power are effective interaction (P-values=0.025 and 0.007 respectively). Comparison between CCD and ANN methods demonstrate that ANN model has excellent predicting power compared to CCD model and both of them show good agreement with experimental values with high correlation coefficients (R2ANN=98.39%, R2CCD=96.34%). Optimized condition suggests that for maximum removal efficiency (82.83%), power and sonication time must be in highest level and water/reactor volume ratio must be in lowest level in the studied interval.
 
Highlights

Soil polluted with 2-methylpropane-2-thiol is remediated with sonication process.
The effects of the sonication power (w), sonication time (min) and water/reactor volume ratio (ml/ml) are added to the batch reactor as the main factor and interaction between them are investigated.
For preparing the best experimental model CCD and ANN methods are used and compared to each other. 

Keywords


Article Title [Persian]

Comparison of central composite design and artificial neural network approaches for modeling and optimization of 2-methylpropane-2-thiol removal from contaminated soil by ultrasound

Authors [Persian]

  • پژمان روحی 1
  • اسماعیل فاتحی فر 2
  • رضا علیزاده 3
1 دانشگاه صنعتی سهند تبریز، ایران
2 دانشگاه صنعتی سهند تبریز، ایران
3 دانشگاه صنعتی سهند تبریز، ایران
Abstract [Persian]

In this article a comparative study for modeling and optimization of 2-methylpropane-2-thiol removal from contaminated soil by ultrasound is investigated. Central Composite Design (CCD) and artificial neural network (ANN) were utilized and compared to each other in order to obtain appropriate predicting model with respect to sonication power (w), sonication time (min) and water/reactor volume ratio (ml/ml). CCD was used based on Response Surface Model (RSM) and the ANN model was developed by the Levenberg−Marquardt feed forward back-propagation training algorithm and topology (3:8:1). Analysis of variance and Pareto analysis resulted from CCD demonstrate that sonication power is the most influential parameter on 2-methylpropane-2-thiol removal efficiency (sonication time and amount of added water in the next order respectively). This is confirmed by ANN model. Also interaction between water content and power, sonication time and power are effective interaction (P-values=0.025 and 0.007 respectively). Comparison between CCD and ANN methods demonstrate that ANN model has excellent predicting power compared to CCD model and both of them show good agreement with experimental values with high correlation coefficients (R2ANN=98.39%, R2CCD=96.34%). Optimized condition suggests that for maximum removal efficiency (82.83%), power and sonication time must be in highest level and water/reactor volume ratio must be in lowest level in the studied interval.
 
Highlights

Soil polluted with 2-methylpropane-2-thiol is remediated with sonication process.
The effects of the sonication power (w), sonication time (min) and water/reactor volume ratio (ml/ml) are added to the batch reactor as the main factor and interaction between them are investigated.
For preparing the best experimental model CCD and ANN methods are used and compared to each other. 

Keywords [Persian]

  • Central composite design
  • artificial neural network
  • Ultrasound
  • 2-methylpropane-2-thiol
  • Modeling
  • Optimization
(1)  Kalainesan, S., Erickson, L., Hutchinson, S., Urban J., Karthikeyan R. Transformation of tertiary butyl mercaptan in aerobic environments. Environmental Progress 2006, pp 25: 189- 200.

(2)  Darban, A., Ganjdoust, H., Salehian, E., Khodadadi, A. Factors Affecting Site Remediation of diesel contaminated soils using surfactants. OIDA International Journal of Sustainable Development 2013; 6, pp 39- 46.

(3)  Salehian, E., Khodadadi, A., Hosseini, B. Remediation of diesel contaminated soils using surfactants: Column study. American Journal of Environmental Science 2012, 8, pp 352- 359.

(4)  Basturk, E., Karatas, M. Advanced oxidation of Reactive Blue 181 solution: A comparison between Fenton and Sono-Fenton Process. Ultrason sonochem 2014, 21, pp 1881- 1885.

(5)  Wang, C., Shih, Y. Degradation and detoxification of diazinon by sono-Fenton and sono-Fenton-like processes. Separation and Purification Technology 2015, 140, pp 6- 12.

(6)  Cailean, D., Teodosiu, C., Friedl, A. Integrated Sono-Fenton ultrafiltration process for 4-chlorophenol removal from aqueous effluents: assessment of operational parameters (Part 1). Clean Technology and Environmental policy 2014, 16, pp 1145-1160.

(7)  Cailean, D., Wukovits, W., Teodosiu, C., Ungureanu, F., Friedl, A. Integrated Sono-Fenton ultrafiltration process for 4-chlorophenol removal from aqueous effluents: process modeling and simulation Part 2. Clean Technology and Environmental policy 2014, 16, pp 1161- 1177.

(8)  Wang, C., Liu, C. Decontamination of alachlor herbicide wastewater by a continuous dosing mode ultrasound/Fe 2+/H2O2 process. Journal of Environmental Science 2014, 26, pp 1332- 1339.

(9)  Park, J-S., Her, N-G., Yoon, Y. Sonochemical degradation of chlorinated phenolic compounds in water: effects of physicochemical properties of the compounds on degradation. Water, Air and Soil Pollution 2011, 215, pp 585- 593.

(10)             Nejumal, K., Manoj, P., Aravind, UK., Aravindakumar, C. Sonochemical degradation of a pharmaceutical waste, atenolol, in aqueous medium. Environmental Science and Pollution Research 2014, 21, pp 4297- 4308.

(11)             Song, W., Li J., Zhang, W., Hu, X., Wang, L. An experimental study on the remediation of phenanthrene in soil using ultrasound and soil washing. Environmental Earth Sciences 2012, 66, pp 1487-1496.

(12)             Teo, KC., Xu, Y., Yang, C. Sonochemical degradation for toxic halogenated organic compounds. Ultrasonic Sonochemistry 2001, 8, pp 241- 246.

(13)             Pang, YL., Abdullah, AZ., Bhatia, S. Review on sonochemical methods in the presence of catalysts and chemical additives for treatment of organic pollutants in wastewater. Desalination 2011, 277, pp 1-14.

(14)             Chowdhury, P., Viraraghavan, T. Sonochemical degradation of chlorinated organic compounds, phenolic compounds and organic dyes–a review. Scince of Total Environment 2009, 407, pp 2474-2492.

(15)             Little, C., El-Sharif, M., Hepher, M. The effect of solution level on calorific and dosimetric results in a 70kHz tower type sonochemical reactor. Ultrasonic Sonochemistry 2007, 14, pp 375-379.

(16)             Suravajala, A., Erickson, LE., Bhandari, A. Sorption of Tertiary Butyl Mercaptan to Indoor Materials in Contact with Air or Water. Journal of Environmental Engineering 2008, 134, pp 161-168.

(17)             Karthikeyan, R., Hutchinson, SLL., Erickson, LE. Biodegradation of tertiary butyl mercaptan in water. Journal of Bioremediation & Biodegradation 2012, 3, pp 2-7.

(18)             Smidt, M., Kusic, H., Juretic, D. D., Resulev, B., Bozic, A. L., Modeling of photooxidative degradation of aromatics in water; optimization study using response surface and structural-relationship approaches. Chemical Engineering Journal 2015, 257, pp 229-241.

(19)             Prabhakaran, D., Kannadasan, T., Thirumarimurugan, M., Chellamboli, C. Experimental Studies on Electrochemical and Photo Oxidation of Effluent Containing Ethyl Benzene and Optimization Using RSM. International Journal of Bioscience, Biochemistry and Bioinformatics 2012, 2, pp 369.

(20)             Mokhtarani, N., Yasrobi, SY., Ganjidoust, H. Optimization of Ozonation Process for a Composting Leachate Contaminated Soils Treatment Using RSM. Ozone: Science & Engineering 2015, 37(3), pp 279-286.

(21)             Hazime, R., Nguyen, Q., Ferronato, C., Huynh, T., Jaber, F., Chovelon, J-M. Optimization of imazalil removal in the system UV/TiO2/K2S2O8 using a response surface methodology (RSM). Applied Catalysis B: Environmental 2013; 132, pp 519-526.

(22)             Long, A., Zhang, H., Lei, Y. Surfactant flushing remediation of toluene contaminated soil: Optimization with response surface methodology and surfactant recovery by selective oxidation with sulfate radicals. Separation and Purification Technology 2013, 118, pp 612-619.

(23)             Khataee, A., Zarei, M., Dehghan, G., Ebadi, E., Pourhassan M. Biotreatment of a triphenylmethane dye solution using a Xanthophyta alga: Modeling of key factors by neural network. Journal of the Taiwan Institute of Chemical Engineers2011, 42, pp 380-386.

(24)             Rahmanian, B., Majid, P., Mansoori, S.A.A., Esfandyari, M., Jafari, D., Heidar Maddah, H., et al., Prediction of MEUF process performance using artificial neural networks and ANFIS approaches. Journal of the Taiwan Institute of Chemical Engineers2012, 43, pp 558-565.

(25)             Chang C-W., Yu W-C., Chen W-J., Chang R-F., Kao W-S. A study on the enzymatic hydrolysis of steam exploded napiergrass with alkaline treatment using artificial neural networks and regression analysis. Journal of the Taiwan Institute of Chemical Engineers2011, 42, pp 889-894.

(26)             Frontistis, Z., Hapeshi, E., Fatta-Kassinos, D., Mantzavinos, D. Ultraviolet-activated persulfate oxidation of methyl orange: a comparison between artificial neural networks and factorial design for process modelling. Photochemical & Photobiological Sciences2015, 14, pp 528-535.

(27)             Mustafa, YA., Jaid, GM., Alwared, AI., Ebrahim, M. The use of artificial neural network (ANN) for the prediction and simulation of oil degradation in wastewater by AOP. Environmental Science and Pollution Research 2014, 21, pp 7530-7537.

(28)             Elmolla, ES., Chaudhuri, M., Eltoukhy, MM. The use of artificial neural network (ANN) for modeling of COD removal from antibiotic aqueous solution by the Fenton process. Journal of Hazardous Materials 2010, 179, pp 127-134.

(29)             Antonopoulou, M., Papadopoulos, V., Konstantinou, I. Photocatalytic oxidation of treated municipal wastewaters for the removal of phenolic compounds: optimization and modeling using response surface methodology (RSM) and artificial neural networks (ANNs). Journal of Chemical Technology and Biotechnology2012, 87, pp 1385-1395.

(30)             Kasiri, M., Aleboyeh, H., Aleboyeh, A. Modeling and optimization of heterogeneous photo-fenton process with response surface methodology and artificial neural networks. Environmental Science & Technology 2008, 42, pp 7970-7975.

(31)             Karimi, F., Rafiee, S., Taheri-Garavand, A., Karimi, M. Optimization of an air drying process for Artemisia absinthium leaves using response surface and artificial neural network models. Journal of the Taiwan Institute of Chemical Engineers 2012, 43, pp 29-39.

(32)             Aghaeinejad-Meybodi, A., Ebadi, A., Shafiei, S., Khataee, AR., Rostampour, M. Modeling and optimization of antidepressant drug Fluoxetine removal in aqueous media by ozone/H2O2 process: Comparison of central composite design and artificial neural network approaches. Journal of the Taiwan Institute of Chemical Engineers2015; 48, pp 40- 48.

(33)             Wei, TK., Manickam, S. Response Surface Methodology., an effective strategy in the optimization of the generation of curcumin‐loaded micelles. Asia-Pacific Journal of Chemical Engineering 2012, 7, pp 125-133.

(34)             Aghaeinejad-Meybodi, A., Ebadi, A., Shafiei, S., Khataee, A., Rostampour, M. Degradation of antidepressant drug fluoxetine in aqueous media by ozone/H2O2 system: process optimization using central composite design. Environmental Technology 2015, 36, pp 1477-1488.

(35)             Ahmadi, R., Khodadadi Darban, A. Modeling and optimization of nano-bubble generation process using Response Surface Methodology. International Journal of Nanoscience and Nanotechnology 2013, 9, pp 151-162.

(36)             Kahforoushan, D., Bezaatpour, J., Fatehifar, E. Effect of various parameters on emission factors of gas flares. Iranian Journal of Chemical Engineering 2014, 11, pp 59-66.

(37)             Hosseini, M., Khoshfetrat, AB., Sahraei, E., Ebrahimi, S. Continuous nitrifying granular sludge bioreactor: Influence of aeration and ammonium loading rate. Process Safety and Environmental Protection 2014; 92, pp 869-878.

(38)             Hadavifar, M., Zinatizadeh, AA., Younesi, H., Galehdar, M. Fenton and photo-Fenton treatment of distillery effluent and optimization of treatment conditions with response surface methodology. Asia-Pacific Journal of Chemical Engineering 2010; 5, pp 454-464.

(39)             Karimi A., Mahdizadeh F., Salari D., Vahabzadeh F., Khataee A. Enzymatic scavenging of oxygen dissolved in water: Application of response surface methodology in optimization of conditions. Chemical Industry and Chemical Engineering Quarterly/CICEQ 2012, 18, pp 431-439.

(40)             Thangavadivel, K., Megharaj, M., Smart, RSC., Lesniewski, PJ., Naidu, R. Application of high frequency ultrasound in the destruction of DDT in contaminated sand and water. Journal of Hazardous Materials 2009, 168, pp 1380-1386.

(41)             Her, N-G., Park, J-S., Oh, J., Yoon, Y. New design approaches for ultrasonic reactors: degradation of naphthalene and phenol in water. Water, Air and Soil Pollution 2011, 220, pp 173-180.

Thangavadivel, K., Megharaj, M., Mudhoo, A., Naidu, R. 18 The Degradation of Organic Pollutants Using Ultrasound. Handbook on Applications:Sonochemistry for Sustainability; CRC Press: Teylor & Francis Group,2012, pp 447-474