Developing adaptive neuro-fuzzy inference system-based models to predict the bending strength of polyurethane foam-cored sandwich panels

Abstract

The aim of this paper was to improve the performance of the adaptive neuro-fuzzy inference system (ANFIS) and to predict the flexural strength of the sandwich panels made with thin medium density fiberboard as surface layers, and polyurethane foam as a core layer, by applying metaheuristic optimization methods. For this purpose, various models, namely ant colony optimization for the continuous domain (ACOR), differential evolution (DE), genetic algorithm (GA), and particle swarm optimization (PSO) were applied and compared, as different efficient bio-inspired paradigms, to assess their suitability for training the adaptive neuro-fuzzy inference system model. The predicted values of the flexural strength resulting from applying adaptive neuro-fuzzy inference system trained by ACOR, DE, GA, and PSO, were compared with the values derived from adaptive neuro-fuzzy inference system classical model. The molar ratio of formaldehyde to melamine and urea, sandwich panel thickness, and the weight ratio of the modified starch to MUF resin (OS/MUF weight ratio) were used as an input variables and the modulus of rupture was used as an output one. The developed hybrid models were used to predict the values of the modulus of rupture obtained from experimental tests. In order to evaluate and compare the performance of the models, three performance criteria were employed namely, determination coefficient (R²), root mean square error, and mean absolute percentage error. It was found that ANFIS–ACOR, ANFIS–DE, ANFIS–GA, and ANFIS–PSO showed different performance ratios compared to the predicting model. In addition, the ANFIS–GA model is found to be by far more accurate than the other hybrid models.

Keywords

Sandwich panel bending strength polyurethane foam modified protein MUF resin adaptive neuro-fuzzy inference system

Get full access to this article

View all access options for this article.

References

Katunin

and Chuda-Kowalska

Assessment of internal damages in sandwich panels via active thermography. Eng Trans 2015; 63: 171–180.

Davies

JM.

Design criteria for structural sandwich panels. J Struct Eng 1987; 65A: 435–441.

Shen

, et al. Mechanical resistance properties of FRP/polyol-isocyanate foam sandwich panels. Compos Struct 2013; 99: 419–432.

Garg

, et al. A review of the analysis of sandwich FGM structures Compos Struct 2021. DOI: 10.1016/j.compstruct.2020.113427.

Belingardi

Cavatorta

and Duella

Material characterization of a composite-foam sandwich for the front structure of a high speed train. Compos Struct 2003; 61: 13–25.

Manalo

AC.

Behaviour of fiber composite sandwich structures under short and asymmetrical beam shear tests. Compos Struct 2013; 99: 339–349.

Sayyad

and Ghugal

YM.

A unified five-degree-of-freedom theory for the bending analysis of softcore and hardcore functionally graded sandwich beams and plates. J Sandw Struct Mater 2021. DOI: 10.1177/1099636219840980.

Garg

and Chalak

HD.

Analysis of non-skew and skew laminated composite and sandwich plates under hygro-thermo-mechanical conditions including transverse stress variations. J Sandw Struct Mater 2021. DOI: 10.1177/1099636220932782.

Belkacemi

and Bezzazi

Sandwich panels from cork and polyester in presence of epoxy resin as interfacial adhesive. Int J Phys Sci 2016; 11: 336–346.

10.

Hirane

, et al. On the layerwise finite element formulation for static and free vibration analysis of functionally graded sandwich plates. Eng Comput 2021. DOI: 10.1007/s00366-020-01250-1.

11.

Krzyzak

Sandwich structured composites for aeronautics: methods of manufacturing affecting some mechanical properties. Int J Aerosp Eng 2016.

12.

Campbell

FC.

Structural composite materials. Materials Park, OH: ASM international, 2010.

13.

Vnucec

Kutnar

and Gorsek

Soy-based adhesives for wood-bonding – a review. J Adhes Sci Technol 2017; 31: 910–931.

14.

Ghahri

and Pizzi

Improving soy-based adhesives for wood particleboard by tannins addition. Wood Sci Technol 2018; 52: 261–279.

15.

Wang

and Chen

Carbohydrate elimination of alkaline-extracted lignin liquor by steam explosion and its methylolation for substitution of phenolic adhesive. Ind Crop Prod 2014; 53: 93–101.

16.

, et al. Effects of typical soybean meal type on the properties of soybean-based adhesive. Int J Adhes Adhes 2019; 90: 15–21

17.

, et al. Effect of ambient aging during soybean meal storage on the performance of a soybean-based adhesive. Ind Crop Prod 2019; 140: 111725.

18.

Chen

, et al. Water resistances and bonding strengths of soybased adhesives containing different carbohydrates. Ind Crop Prod 2013; 50: 44–49.

19.

Jang

, et al. A new formaldehyde-free wood adhesive from renewable materials. Int J Adhes Adhes 2011; 31: 754–759.

20.

Jain

Mao

and Mohiuddin

KM.

Artificial neural networks: a tutorial. IEEE Comput Soc 1996; 29: 31–44.

21.

Iman

, et al. Experimental and ANFIS modeling for fouling analysis of oily waste water treatment using ultrafiltration. Asia Pacific J Chem Eng 2013; 8: 527–538.

22.

Peyghami

and Khanduzi

Novel MLP neural network with hybrid Tabu Search algorithm. Neural Netw World 2013; 3: 255–270.

23.

Pousinho

HMI

Mendes

VMF

and Catalao

JPS.

Hybrid PSO-ANFIS approach for short-term electricity prices prediction. In: Proceedings of the 2010 PES general meeting, Michigan, USA, 2010, pp. 1–6.

24.

Sheikhan

and Mohammadi

Time series prediction using PSO-optimized neural network and hybrid feature selection algorithm for IEEE load data. Neural Comput Appl 2013; 23: 1185–1194.

25.

Mercy

, et al. Neurofuzzy modelling of moisture absorption kinetics and its effect on the mechanical properties of pineapple fiber-reinforced polypropylene composite. J Compos Mater 2020; 54: 867–882.

26.

Nasir

, et al. Stress wave evaluation for predicting the properties of thermally modified wood using neuro-fuzzy and neural network modeling. Holzforschung 2019; 73: 827–838.

27.

Tas

and Cetisli

Estimation of physical and mechanical properties of composite board via adaptive neural networks, polynomial curve fitting, and the adaptive neuro-fuzzy inference system. Bioresources 2016; 11: 2334–2348.

28.

Armaghani

and Asteris

PG.

A comparative study of ANN and ANFIS models for the prediction of cement-based mortar materials compressive strength. Neural Comput Appl 2020; 20: 1–32.

29.

Wong

Senthil

and Mustapha

KB.

Development of a computational predictive model for the nonlinear in-plane compressive response of sandwich panels with bio-foam. Compos Struct 2019; 212: 423–433.

30.

Dehghani

Payandeh

and Mazloum

Minimizing the peak force and maximizing the internal energy of the corrugated core sandwich panel filled with foam using imperialist competitive algorithm (ICA). MMSEJ 2018; 17.

31.

Nouri Damghani

and Mohammadzadeh Gonabadi

Experimental investigation of energy absorption in aluminum sandwich panels by drop hammer test. MMSEJ 2016; 7: 123–141.

32.

ASTM D790-10. Standard test methods for flexural properties of unreinforced and reinforced plastics and electrical insulating materials. Philadelphia, PA: American Society for Testing and Materials, 2010.

33.

Ostad Shabani

, et al. Performance of ANFIS coupled with PSO in manufacturing superior wear resistant aluminum matrix nano composites. Trans Indian Inst Met 2017; 71: 2095–2103.

34.

Zhi

, et al. Viscosity prediction for six pure refrigerants using different artificial neural networks. Int J Refrig 2018; 88: 432–440.

35.

Jang

JSR.

ANFIS: adaptive-network-based fuzzy inference system. Systems, man and cybernetics. IEEE Trans 1993; 23: 665–685.

36.

Yalcin

, et al. Prediction of effect of natural antioxidant compounds on hazelnut oil oxidation by adaptive neuro-fuzzy inference system and artificial neural network. J Food Sci 2011; 76: 112–120.

37.

Yaseen

, et al. RBFNN versus FFNN for daily river flow forecasting at Johor River, Malaysia. Neural Comput Appl 2016; 27: 1533–1542.

38.

Afan

, et al. Harmonize input selection for sediment transport prediction. J Hydrol 2017; 552: 366–375.

39.

Shenk

and Westerhaus

MO.

Calibration the ISI way. In: Davies

AMC

and Williams

(eds), Near infrared spectroscopy. Chichester: NIR Publications, 1996.

40.

Kecebas

Yabanova

and Yumurtaci

Artificial neural network modeling of geothermal district heating system thought exergy analysis. Energy Convers Manage 2012; 64: 206–212.

41.

Hazir

Ozcan

and Kucuk Koc

KH.

Prediction of adhesion strength using extreme learning machine and support vector regression optimized with genetic algorithm. Arab J Sci Eng 2020; 45: 6985–7004.

42.

Yapici

Senyer

and Esen

Comparison of the multiple regression, ANN, and ANFIS models for prediction of MOE value of OSB panels. Wood Res 2016; 61: 741–754.

43.

Fernandez

, et al. Prediction of MOR and MOE of structural plywood board using an artificial neural network and comparison with a multivariate regression model. Compos B Eng 2012; 43: 3528–3533.

44.

Frihart

and Wescott

JM.

Improved water resistance of bio-based adhesives for wood bonding. In: Proceedings of the 1st international conference on environmentally compatible forest products, Porto, Portugal, 22–24 September 2004, pp. 293–302.

45.

Lorenz

Frihart

and Wescott

JM.

Chromatographic analysis of the reaction of soy flour with formaldehyde and phenol for wood adhesives. J Amer Oil Chem Soc 2007; 84:769–776.

46.

Nordqvist

, et al. Plant proteins as wood adhesives: bonding performance at the macro- and nanoscale. Ind Crop Prod 2013; 44: 246–252.

47.

, et al. Study on alfalfa protein-based adhesive modified by sodium hydroxide. Adv Mater Res 2013; 726–731: 9–12.

48.

Lei

and Du

Disruption of soy-based adhesive treated by Ca(OH)₂ and NaOH.

J Adhes Sci Technol 2013; 27: 2226–2232.

49.

Hettiarachchy

Kalapathy

and Myers

DJ.

Alkali-modified soy protein with improved adhesive and hydrophobic properties. J Am Oil Chem Soc 1995; 72: 1461–1464.

50.

, et al. The effect of hydrolyzed soy protein isolate on the structure and biodegradability of urea–formaldehyde adhesives. J Adhes Sci Technol 2015; 29: 502–517.

51.

Nakanshi

and Solomon

PH.

Infrared absorption spectroscopy. San Francisco, CA: Holden-Day, Inc., 1977.

52.

Silverstein

and Webster

FX.

Infrared spectrometry. Spectrometric identification of organic compounds. 6th ed. NewYork: JohnWiley & Sons, Inc., 1997.

53.

, et al. Improve performance of soy protein adhesives with a low molar ratio melamine-urea-formaldehyde resin. J Phys Conf Ser 2020; 1549: 1–6.

54.

Vinson

JR.

The behavior of sandwich structures of isotropic and composite materials. Lancaster: Technomic, 1999.

55.

Kielmann

, et al. Strength changes in ash, beech and maple wood modified with a n-methylol melamine compound and a metal-complex dye. Wood Res 2013; 53: 343–350.

56.

Gren

Szatkowski

and Cholpak

Characteristics of failure mechanism and shear strength of sandwich composites.

Compos Theory Pract 2016; 16: 255–259.