Abstract
This paper reports the biopolymerization of ε-caprolactone, using lipase Novozyme 435 catalyst at varied impeller speeds and reactor temperatures. A multilayer feedforward neural network (FFNN) model with 11 different training algorithms is developed for the multivariable nonlinear biopolymerization of polycaprolactone (PCL). In previous works, biopolymerization carried out in scaled-up bioreactors is modeled through FFNN. No review discussed the role of different training algorithms in artificial neural network on the estimation of biopolymerization performance. This paper compares mean absolute error, mean square error, and mean absolute percentage error (MAPE) in the PCL biopolymerization process for 11 different training algorithms that belong to six classes, namely (1) additive momentum, (2) self-adaptive learning rate, (3) resilient backpropagation, (4) conjugate gradient backpropagation, (5) quasi-Newton, and (6) Bayesian regulation propagation. This paper aims to identify the most effective training method for biopolymerization. Results show that the quasi-Newton-based and Levenberg–Marquardt algorithms have the best performance with MAPE values of 4.512, 5.31, and 3.21% for the number of average molecular weight, weight average molecular weight, and polydispersity index, respectively.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Ajay K, Gross RA (2000) Candida antartica lipase B catalyzed polycaprolactone synthesis: effects of organic media and temperature. Biomacromology 1:133–138. https://doi.org/10.1021/cr990121l
Arumugasamy SK, Ahmad Z (2010) Candida antarctica as catalyst for polycaprolactone synthesis: effect of temperature and solvents. Asia-Pac J Chem Eng 6:398–405. https://doi.org/10.1002/apj.583
Arumugasamy SK, Uzir MH, Ahmad Z (2012) Modeling of polycaprolactone production from ε-caprolactone using neural network. In: Neural information processing: 19th international conference, ICONIP 2012, Doha, Qatar, November 12–15, 2012, proceedings, part II. Huang T, Zeng Z, Li C, Leung CS. Springer, Berlin, Heidelberg, pp 444–451. https://doi.org/10.1007/978-3-642-34481-7_54
Bassi AK, Gough JE, Zakikhani M, Downes S (2011) The chemical and physical properties of poly(ε-caprolactone) Scaffolds functionalised with poly(vinyl phosphonic acid-co-acrylic acid). J Tissue Eng 2011:615328. https://doi.org/10.4061/2011/615328
Chaibakhsh N, Abdul Rahman MB, Basri M, Salleh AB, Abdul Rahman RNZ (2012) Response surface modeling and optimization of immobilized Candida antarctica lipase-catalyzed production of dicarboxylic acid ester. Chem Prod Process Model 7:1–13. https://doi.org/10.1515/1934-2659.1483
Forouzanfar M, Dajani HR, Groza VZ, Bolic M, Rajan S (2010) Comparison of Feed-Forward Neural Network training algorithms for oscillometric blood pressure estimation. 4th International workshop on soft computing applications. https://doi.org/10.1109/sofa.2010.5565614
Ghaffari A, Abdollahi H, Khoshayand MR, Bozchalooi IS, Dadgar A, Rafiee-Tehrani M (2006) Performance comparison of neural network training algorithms in modeling of bimodal drug delivery. Int J Pharm 327:126–138. https://doi.org/10.1016/j.ijpharm.2006.07.056
Heaton J (2008). Introduction to neural networks with Java, Heaton Research
Hornik K, Stinchcombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural Netw 2(5):359–366
Hunsen M, Azim A, Mang H, Wallner SR, Ronkvist A, Xie W, Gross RA (2007) A cutinase with polyester synthesis activity. Macromolecules 40:148–150. https://doi.org/10.1021/ma062095g
Karsoliya S (2012) Approximating number of hidden layer neurons in multiple hidden layer BPNN architecture. Int J Eng Trends Technol 3(6):4
Khatti T, Naderi H, Kalantar SM (2017) Application of ANN and RSM techniques for modeling electrospinning process of polycaprolactone. Neural Comput Appl. https://doi.org/10.1007/s00521-017-2996-6
Kobayashi S, Makino A (2009) Enzymatic polymer synthesis: an opportunity for green polymer chemistry. Chem Rev 109:5288–5353. https://doi.org/10.1021/cr900165z
Labet M, Thielemans W (2009) Synthesis of polycaprolactone: a review. Chem Soc Rev 38:3484–3504. https://doi.org/10.1039/b820162p
Lee-Cosio BM, Delgado-Mata C, Ibanez J (2012) ANN for gesture recognition using accelerometer data. Procedia Technol 3:109–120. https://doi.org/10.1016/j.protcy.2012.03.012
Patricia M, Janusz K, Witold P (2010) Soft computing for recognition based biometrics. Springer, Berlin
Sulaiman J, Wahab SH (2018) Heavy rainfall forecasting model using artificial neural network for flood prone area. In: Kim K, Kim H, Baek N (eds) IT convergence and security 2017. Lecture notes in electrical engineering, vol 449. Springer, Singapore
Torres DPM, Gonçalves MDPF, Teixeira JA, Rodrigues LR (2010) Galacto-oligosaccharides: production, properties, applications, and significance as prebiotics. Comp Rev Food Sci Food Saf 9(5):438–454. https://doi.org/10.1111/j.1541-4337.2010.00119.x
Uyama H, Kikuchi H, Takeya K, Kobayashi S (1996) Lipase-catalyzed ring-opening polymerization and copolymerization of 15-pentadecanolide. Acta Polym 47(8):357–360. https://doi.org/10.1002/actp.1996.010470807
Varma IK, Albertsson AC, Rajkhowa R, Srivastava RK (2005) Enzyme catalyzed synthesis of polyesters. Prog Polym Sci 30(10):949–981. https://doi.org/10.1016/j.progpolymsci.2005.06.010
Xinxing P, Lee B, Chunrong Z (2013) A comparison of neural network backpropagation algorithms for electricity load forecasting. 2013 IEEE international workshop on intelligent energy systems (IWIES). https://doi.org/10.1109/iwies.2013.6698556
Acknowledgements
This work was supported by RU Geran-Faculti Program Grant RF008A-2018 by University of Malaya.
Author information
Authors and Affiliations
Corresponding authors
Rights and permissions
About this article
Cite this article
Wong, Y.J., Arumugasamy, S.K. & Jewaratnam, J. Performance comparison of feedforward neural network training algorithms in modeling for synthesis of polycaprolactone via biopolymerization. Clean Techn Environ Policy 20, 1971–1986 (2018). https://doi.org/10.1007/s10098-018-1577-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10098-018-1577-4