Performance of Radial Basis Function and Group Method of Data Handling-type Neural-Networks in Flammability Characteristics Prediction of PMMA
Performance of Radial Basis Function and Group Method of Data Handling-type Neural-Networks in Flammability Characteristics Prediction of PMMA |
||
 |
 |
|
| © 2023 by IJETT Journal | ||
| Volume-71 Issue-5 |
||
| Year of Publication : 2023 | ||
| Author : Mohammed Okoe Alhassan, Stephen Eduku, Doreen Ama Amoah, Joseph Sekyi-Ansah, Felix Uba |
||
| DOI : 10.14445/22315381/IJETT-V71I5P233 | ||
How to Cite?
Mohammed Okoe Alhassan, Stephen Eduku, Doreen Ama Amoah, Joseph Sekyi-Ansah, Felix Uba, "Performance of Radial Basis Function and Group Method of Data Handling-type Neural-Networks in Flammability Characteristics Prediction of PMMA," International Journal of Engineering Trends and Technology, vol. 71, no. 5, pp. 313-327, 2023. Crossref, https://doi.org/10.14445/22315381/IJETT-V71I5P233
Abstract
In this paper, the characterization of polymers fire behavior is studied for predicting the thermophysical flammability characteristics from developed supervised machine learning (SML) models. In the first stage, polymethyl methacrylate (PMMA) flammability properties, total heat release (THR) and heat release capacity (HRC) were examined and measured based on conducted micro-scale combustion calorimetry (MCC) experiments at varying heating rates (β) of milli-gram masses (m) ranging (0.1-3.5 Ks-1) and (1-3.5 mg) respectively. Normalized experimental data was then used to develop SML models, radial basis function (RBF) and group method of data handling (GMDH-type) neural networks (NN) using m and β as input variables for performance prediction of HRC and THR. GMDHNN model performed remarkably well, attaining nominal errors in predicting HRC. Also, in estimating THR, RBFNN attained values with improved outcomes as compared to GMDHNN; hence, RBFNN performed relatively better in predicting THR. Overall, both ML algorithms performed well; nonetheless, GMDHNN outperformed RBFNN for prediction. Moreover, the GMDHNN and RBFNN models provided the lowest mean errors compared with HRC outcomes for PMMA from other HRC estimation models in the literature. As a result, both GMDHNN and RBFNN serve as applicable tools for PMMA flammability properties estimation based on the MCC fire test.
Keywords
Flammability, Group method of data handling-type neural-network, Microscale combustion calorimetry, Polymethyl Methacrylate (PMMA), Radial basis function neural-network.
References
[1] Mohammad Hossein Keshavarz et al., “A Simple Model for Reliable Prediction of the Specific Heat Release Capacity of Polymers as an Important Characteristic of their Flammability,” Journal of Thermal Analysis and Calorimetry, vol. 128, no. 1, pp. 417–426, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[2] N. Saba et al., “A Review on Flammability of Epoxy Polymer, Cellulosic and Non-Cellulosic Fiber Reinforced Epoxy Composites,” Polymers Advanced Technologies, vol. 27, no. 5, pp. 577–590, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[3] H. E. Yang, “Quantitative Microscale Assessment of Polymer Flammability," Plastics Research, 2015.
[Google Scholar]
[4] Richard Norman Walters, “Development of Instrumental and Computational Tools for Investigation of Polymer Flammability,” Universities of Central Lancashire, p. 267, 2013.
[Google Scholar] [Publisher Link]
[5] Qiang Xu et al., “A Critical Review of the Methods and Applications of Microscale Combustion Calorimetry for Material Flammability Assessment,” Journal of Thermal Analysis and Calorimetry, vol. 147, no. 11, pp. 6001–6013, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[6] R. E. Lyon et al., “Principles and Practice of Microscale Combustion Calorimetry,” Fed. Aviat. Adm. Atl. City Airport, NJ 8405, pp. 1–80, 2013.
[7] “Standard Test Method for Determining Flammability Characteristics of Plastics and Other Solid Materials Using Microscale Combustion Calorimetry,” ASTM D7309, American Society for Testing and Materials, West Conshohocken, PA, pp. 1–11, 2013.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Richard E. Lyon et al., “A Molecular Basis for Polymer Flammability,” Polymer (Guildf), vol. 50, no. 12, pp. 2608-2617, 2009.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Fariborz Atabaki, and Mohammad Hossein Keshavarz, “The Simplest Model for Reliable Prediction of the Total Heat Release of Polymers for Assessment of their Combustion Properties,” Journal of Thermal Analysis and Calorimetry, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Priya V. Parandekar, Andrea R. Browning, and Om Prakash, “Modeling the Flammability Characteristics of Polymers using Quantitative Structure – Property Relationships (QSPR),” Polymer Engineering and Science, vol. 55, no. 2, pp. 1553-1559, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Richard N. Walters, and Richard E. Lyon, “Molar Group Contributions to Polymer Flammability,” Journal of Applied Polymer Science, vol. 87, no. 3, pp. 548–563, 2003.
[CrossRef] [Google Scholar] [Publisher Link]
[12] R. Sonnier et al., “Relationships between the Molecular Structure and the Flammability of Polymers : Study of Phosphonate Functions using Microscale Combustion Calorimeter,” Polymer (Guildf), vol. 53, no. 6, pp. 1258–1266, 2012.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Rodolphe Sonnier et al., “Prediction of Thermosets Flammability using a Model based on Group Contributions,” Polymer (Guildf), vol. 127, pp. 203–213, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Rhoda Afriyie Mensah et al., “Correlation Analysis of Cone Calorimetry and Microscale Combustion Calorimetry Experiments Correlation Analysis of Cone Calorimetry and Microscale Combustion Calorimetry Experiments,” Journal of Thermal Analysis and Calorimetry, vol. 136, pp. 589-599, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[15] R.Swarnalatha et al., "Synthesis, Characterization, and Dielectric Studies of (1-x) PMMA: x PC: 10PVP: 5LiClO4 Plasticized Blend Polymer Solid Electrolyte Systems," SSRG International Journal of Material Science and Engineering, vol. 6, no. 3, pp. 1-4, 2020.
[CrossRef] [Publisher Link]
[16] Rhoda Afriyie Mensah et al., “Application of Adaptive Neuro-Fuzzy Inference System in Flammability Parameter Prediction,” Polymers (Basel)., vol. 12, no. 1, p. 122, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Solomon Asante-Okyere et al., “Generalized Regression and Feed Forward Back Propagation Neural Networks in Modelling Flammability Characteristics of Polymethyl Methacrylate (PMMA),” Thermochimica Acta, vol. 667, pp. 79–92, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Mohammed Okoe Alhassan et al., “Novel Approaches to Modelling Flammability Characteristics of Polymethyl Methacrylate (PMMA) via Multivariate Adaptive Regression Splines and Random Forest Methods,” Asian Journal of Research in Computer Science, vol. 4, no. 4, pp. 1–14, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Rhoda Afriyie Mensah et al., “Comparative Evaluation of the Predictability of Neural Network Methods on the Flammability Characteristics of Extruded Polystyrene from Microscale Combustion Calorimetry,” Journal of Thermal Analysis and Calorimetry, vol. 138, pp. 3055-3064, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Jitesh J. Shewale, and Kiran S. Bhole, "Fabrication and Analysis of Three Dimensional Polymer Microneedle Array Potentially for Transdermal Drug Delivery," SSRG International Journal of Mechanical Engineering, vol. 2, no. 2, pp. 22-27, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[21] A. G. Ivakhnenko, “Polynomial Theory of Complex Systems,” IEEE Transactions on Systems, Man, and Cybernetics,, vol. 1, no. 4, pp. 364–378, 1971.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Saeb M. Besarati et al., “Modeling Friction Factor in Pipeline Flow Using a GMDH-Type Neural Network,” Cogent Engineering, vol. 2, no. 1, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Yao Yevenyo Ziggah et al., “Capability` of Artificial Neural Network for Forward Conversion of Geodetic Coordinates (ϕ, λ, h) to Cartesian Coordinates (X, Y, Z),” Mathematical Geosciences, vol. 48, no. 6, pp. 687–721, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Khaled Assaleh, Tamer Shanableh, and Yasmin Abu Kheil, “Group Method of Data Handling for Modeling Magnetorheological Dampers,” Intelligent Control and Automation, vol. 4, no. 1, pp. 70–79, 2013.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Farzad Rayegani, and Godfrey C. Onwubolu, “Fused Deposition Modelling (FDM) Process Parameter Prediction and Optimization using Group Method for Data Handling (Gmdh) and Differential Evolution (DE),” The International Journal of Advanced Manufacturing Technology, vol. 73, no. 1–4, pp. 509–519, 2014.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Mohammad Hossein Ahmadi et al., “Using GMDH Neural Networks to Model the Power and Torque of a Stirling Engine,” Sustainability, vol. 7, no. 2, pp. 2243–2255, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[27] Isa Ebtehaj et al., “GMDH-Type Neural Network Approach for Modeling the Discharge Coefficient of Rectangular Sharp-Crested Side Weirs,” Engineering Science and Technology, An International Journal, vol. 18, no. 4, pp. 746-757, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[28] Tiantian Xie, Hao Yu, and Bogdan Wilamowski, “Comparison between Traditional Neural Networks and Radial Basis Function Networks,” IEEE International Symposium on Industrial Electronics, pp. 1194–1199, 2011.
[CrossRef] [Google Scholar] [Publisher Link]
[29] Qiang Xu et al., “Wood Dust Flammability Analysis by Microscale Combustion Calorimetry,” Polymers (Basel)., vol. 14, no. 1, p. 45, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[30] Sarah A. Elawam et al., "Structural Configuration and Thermal Analyses of Composite Films of Poly (methyl methacrylate)/Lead Oxide Nanoparticles," SSRG International Journal of Applied Physics, vol. 3, no. 3, pp. 6-14, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[31] Govmark Datasheet of Micro-Scale Combustion Calorimeter (MCC-2), Govmark Organ. Inc.
[32] Qiang Xu et al., “A PMMA Flammability Analysis Using the MCC: Effect of Specimen Mass,” Journal of Thermal Analysis and Calorimetry, vol. 126, no. 3, pp. 1831–1840, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[33] Umar Ali et al., “A Review of the Properties and Applications of Poly (Methyl Methacrylate) (PMMA),” Polymer Reviews, vol. 55, no. 4, pp. 678–705, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[34] N.Hamid-Zadeh et al., “A Polynomial Model for Concrete Compressive Strength Prediction using GMDH-type Neural Networks and Genetic Algorithm," Proceedings of the 5th WSEAS International Conference on System Science and Simulation in Engineering, pp. 13–18, 2006.
[Google Scholar] [Publisher Link]
[35] Godfrey C Onwubolu, “Chapter 1,” GMDH: Methodology and Implementation in Matlab, pp. 1–24, 2016.
[Google Scholar] [Publisher Link]
[36] Rita Yi Man Li, Simon Fong, and Kyle Weng Sang Chong, “Forecasting the REITs and Stock Indices: Group Method of Data Handling Neural Network Approach,” Pacific Rim Property Research Journal, vol. 23, no. 2, pp. 123–160, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[37] Ahmed Amara Konaté et al., “Generalized Regression and Feed-Forward Back Propagation Neural Networks in Modelling Porosity from Geophysical Well Logs,” Journal of Petroleum Exploration and Production Technology, vol. 5, no. 2, pp. 157–166, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[38] Kevin Gurney, An Introduction to Neural Networks, 2005.
[Google Scholar] [Publisher Link]
[39] M.T. Hagan, and M.B. Menhaj, “Training Feedforward Networks with the Marquardt Algorithm,” IEEE Transactions on Neural Networks, vol. 5, no. 6, pp. 989–993, 1994.
[CrossRef] [Google Scholar] [Publisher Link]
[40] T. Chai and R. R. Draxler, “Root Mean Square Error (RMSE) or Mean Absolute Error (MAE)? -Arguments Against Avoiding RMSE in the Literature,” Geoscientific Model Development, vol. 7, no. 3, pp. 1247–1250, 2014.
[CrossRef] [Google Scholar] [Publisher Link]
[41] Qiang Xu et al., “Correlation Analysis of Cone Calorimetry Test Data Assessment of the Procedure with Tests of Different Polymers,” Journal of Thermal Analysis and Calorimetry, vol. 110, no. 1, pp. 65–70, 2012.
[CrossRef] [Google Scholar] [Publisher Link]
[42] Mohammad Sepehr et al., “Modeling Dynamic Viscosity of N-Alkanes Using LSSVM Technique,” Energy Sources, Part A: Recovery, Utilization, and Environmental Effects, vol. 40, no. 16, pp. 1966–1973, 2018.
[CrossRef] [Google Scholar] [Publisher Link]