Skip to main content
Erschienen in: Wood Science and Technology 3/2020

07.05.2020 | Original

Prediction of mechanical properties of wood fiber insulation boards as a function of machine and process parameters by random forest

verfasst von: M. Schubert, M. Luković, H. Christen

Erschienen in: Wood Science and Technology | Ausgabe 3/2020

Einloggen

Aktivieren Sie unsere intelligente Suche um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

In this case study, machine and process variables were extracted from the process control system (Prod-IQ) and combined with tested mechanical properties of wood fiber insulation boards according to product type and time of manufacture. The boards were taken from the production line (dry process), and the internal bond strength (σmt) and the compressive strength at 10% deformation (σ10) were determined according to the European Standard EN 826 and 1607. The complete data set was preprocessed and split into training and test sets using k-fold cross-validation. The performance of the random forest algorithm (RF) was evaluated with the correlation coefficient (R), the coefficient of determination (R2), root-mean-square error (RMSE) and mean absolute percentage error (MAPE) and compared with artificial neural networks (ANN) and support vector machines (SVM). Forward feature selection was used to reduce input dimensionality and improve the generalizability of the algorithms. All machine learning algorithms predicted the mechanical properties with high accuracy, but the RF algorithm revealed the best generalization performance (σmt: R = 0.960, R2= 0.916, RMSE = 4.05, MAPE = 12.11; σ10: R = 0.981, R2= 0.963, RMSE = 17.19, MAPE = 5.64). This work demonstrates that machine learning can be applied to predict relevant properties of wood fiber boards for an improved quality control in real time.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Literatur
Zurück zum Zitat André N, Cho H-W, Baek SH, Jeong M-K, Young TM (2008) Prediction of internal bond strength in a medium density fiberboard process using multivariate statistical methods and variable selection. Wood Sci Technol 42:521–534CrossRef André N, Cho H-W, Baek SH, Jeong M-K, Young TM (2008) Prediction of internal bond strength in a medium density fiberboard process using multivariate statistical methods and variable selection. Wood Sci Technol 42:521–534CrossRef
Zurück zum Zitat Barnes D (2001) A model of the effect of strand length and strand thickness on the strength properties of oriented wood composites. Forest Prod J. 51:36–45 Barnes D (2001) A model of the effect of strand length and strand thickness on the strength properties of oriented wood composites. Forest Prod J. 51:36–45
Zurück zum Zitat Bishop CM (2006) Pattern Recognition and Machine Learning (Information Science and Statistics). Springer, Berlin Bishop CM (2006) Pattern Recognition and Machine Learning (Information Science and Statistics). Springer, Berlin
Zurück zum Zitat Burden F, Winkler D (2009) Bayesian regularization of neural networks. In: Livingstone DJ (ed) Artificial neural networks: methods and applications. Humana Press, Totowa, NJ, pp 23–42 Burden F, Winkler D (2009) Bayesian regularization of neural networks. In: Livingstone DJ (ed) Artificial neural networks: methods and applications. Humana Press, Totowa, NJ, pp 23–42
Zurück zum Zitat Cai J, Luo J, Wang S, Yang S (2018) Feature selection in machine learning: a new perspective. Neurocomputing. 300:70–79CrossRef Cai J, Luo J, Wang S, Yang S (2018) Feature selection in machine learning: a new perspective. Neurocomputing. 300:70–79CrossRef
Zurück zum Zitat Cook DF, Chin-Chou C (1997) Predicting the internal bond strength of particleboard, utilizing a radial basis function neural network. Eng Appl Artif Intell 10:171–177CrossRef Cook DF, Chin-Chou C (1997) Predicting the internal bond strength of particleboard, utilizing a radial basis function neural network. Eng Appl Artif Intell 10:171–177CrossRef
Zurück zum Zitat Cook DF, Ragsdale CT, Major RL (2000) Combining a neural network with a genetic algorithm for process parameter optimization. Eng Appl Artif Intell 13:391–396CrossRef Cook DF, Ragsdale CT, Major RL (2000) Combining a neural network with a genetic algorithm for process parameter optimization. Eng Appl Artif Intell 13:391–396CrossRef
Zurück zum Zitat Devaney M, Ram A (1997) Efficient Feature Selection in Conceptual Clustering, in Proceedings of the Fourteenth International Conference on Machine Learning 1997, Morgan Kaufmann Publishers Inc. p. 92-97 Devaney M, Ram A (1997) Efficient Feature Selection in Conceptual Clustering, in Proceedings of the Fourteenth International Conference on Machine Learning 1997, Morgan Kaufmann Publishers Inc. p. 92-97
Zurück zum Zitat Dunky M, Niemz P (2002) Holzwerkstoffe und Leime (Wood-based products and glue). Springer, Berlin (In German) CrossRef Dunky M, Niemz P (2002) Holzwerkstoffe und Leime (Wood-based products and glue). Springer, Berlin (In German) CrossRef
Zurück zum Zitat Escobar CA, Morales-Menendez R (2018) Machine learning techniques for quality control in high conformance manufacturing environment. Adv Mech Eng 10:1–16CrossRef Escobar CA, Morales-Menendez R (2018) Machine learning techniques for quality control in high conformance manufacturing environment. Adv Mech Eng 10:1–16CrossRef
Zurück zum Zitat Esteban LG, Fernández FG, de Palacios P (2009a) MOE prediction in Abies pinsapo Boiss. timber: application of an artificial neural network using non-destructive testing. Comput Struct 87:1360–1365CrossRef Esteban LG, Fernández FG, de Palacios P (2009a) MOE prediction in Abies pinsapo Boiss. timber: application of an artificial neural network using non-destructive testing. Comput Struct 87:1360–1365CrossRef
Zurück zum Zitat Esteban LG, García Fernández F, Palacios Pd, Conde M (2009b) Artificial neural networks in variable process control: application in particleboard manufacture. For Syst 18:92–100 Esteban LG, García Fernández F, Palacios Pd, Conde M (2009b) Artificial neural networks in variable process control: application in particleboard manufacture. For Syst 18:92–100
Zurück zum Zitat Esteban LG, Fernández FG, de Palacios P (2011) Prediction of plywood bonding quality using an artificial neural network. Holzforschung 65:209–214CrossRef Esteban LG, Fernández FG, de Palacios P (2011) Prediction of plywood bonding quality using an artificial neural network. Holzforschung 65:209–214CrossRef
Zurück zum Zitat European Standard EN 13171 (2012). Thermal insulating products for buildings—factory made wood fibre (WF) products—specification. European Committee for Standardization (CEN), Brussels, Belgium European Standard EN 13171 (2012). Thermal insulating products for buildings—factory made wood fibre (WF) products—specification. European Committee for Standardization (CEN), Brussels, Belgium
Zurück zum Zitat European Standard EN 1607 (1996a) Thermal insulation products for building applications—Determination of compression behaviour. European Commitee for Standardization (CEN), Brussels, Belgium European Standard EN 1607 (1996a) Thermal insulation products for building applications—Determination of compression behaviour. European Commitee for Standardization (CEN), Brussels, Belgium
Zurück zum Zitat European Standard EN 826 (1996b) Thermal insulating products for building applications—Determination of tensile strenght perpendicular to faces. European Commitee for Standardization (CEN), Brussels, Belgium European Standard EN 826 (1996b) Thermal insulating products for building applications—Determination of tensile strenght perpendicular to faces. European Commitee for Standardization (CEN), Brussels, Belgium
Zurück zum Zitat Gupta A, Jordan P, Pang S (2007) Modelling of the Development of the Vertical Density Profile of MDF during Hot Pressing. In: Chemical Product and Process Modeling 2007 Gupta A, Jordan P, Pang S (2007) Modelling of the Development of the Vertical Density Profile of MDF during Hot Pressing. In: Chemical Product and Process Modeling 2007
Zurück zum Zitat Kira K, Rendell LA (1992) A practical approach to feature selection. In: Proceedings of the ninth international workshop on Machine learning 1992, Morgan Kaufmann Publishers Inc.: Aberdeen, Scotland, United Kingdom. pp 249–256CrossRef Kira K, Rendell LA (1992) A practical approach to feature selection. In: Proceedings of the ninth international workshop on Machine learning 1992, Morgan Kaufmann Publishers Inc.: Aberdeen, Scotland, United Kingdom. pp 249–256CrossRef
Zurück zum Zitat Kohavi R (1995) A study of cross-validation and bootstrap for accuracy estimation and model selection. In: Proceedings of the 14th international joint conference on Artificial intelligence—Volume 2 1995, Morgan Kaufmann Publishers Inc.: Montreal, Quebec, Canada. pp. 1137–1143 Kohavi R (1995) A study of cross-validation and bootstrap for accuracy estimation and model selection. In: Proceedings of the 14th international joint conference on Artificial intelligence—Volume 2 1995, Morgan Kaufmann Publishers Inc.: Montreal, Quebec, Canada. pp. 1137–1143
Zurück zum Zitat Kruse K, Thömen H, Maurer H, Steffen A, Leon-Mendez R (1997) Optimierung der Spanplattenproduktionsprozesses mit Hilfe der Prozessmodelierung. (Optimisation of particleboard production by means of process modelling). Holz Roh- Werkst. 55:17–24CrossRef Kruse K, Thömen H, Maurer H, Steffen A, Leon-Mendez R (1997) Optimierung der Spanplattenproduktionsprozesses mit Hilfe der Prozessmodelierung. (Optimisation of particleboard production by means of process modelling). Holz Roh- Werkst. 55:17–24CrossRef
Zurück zum Zitat Kusiak A (2017) Smart manufacturing must embrace big data. Nature 544:23–25CrossRef Kusiak A (2017) Smart manufacturing must embrace big data. Nature 544:23–25CrossRef
Zurück zum Zitat Kwak D-S, Kim K-J (2012) A data mining approach considering missing values for the optimization of semiconductor-manufacturing processes. Exp Sys Appl 39:2590–2596CrossRef Kwak D-S, Kim K-J (2012) A data mining approach considering missing values for the optimization of semiconductor-manufacturing processes. Exp Sys Appl 39:2590–2596CrossRef
Zurück zum Zitat Lobenhoffer H (1982) Auswertung von Prozessdaten mittels statistischer Methoden. (Evaluation of Process Data by Means of Statistical Methods). Holz Roh- Werkst. 40:395–401CrossRef Lobenhoffer H (1982) Auswertung von Prozessdaten mittels statistischer Methoden. (Evaluation of Process Data by Means of Statistical Methods). Holz Roh- Werkst. 40:395–401CrossRef
Zurück zum Zitat Lobenhoffer H (1986) Überprüfung eines Optimierungsverfahrens für einen Spanplattenformstrang durch Simulation mit Betriebs-Datensätzen. (Testing an optimization method for particleboard forming lines by simulation using real process data). Holz Roh- Werkst. 44:55–56CrossRef Lobenhoffer H (1986) Überprüfung eines Optimierungsverfahrens für einen Spanplattenformstrang durch Simulation mit Betriebs-Datensätzen. (Testing an optimization method for particleboard forming lines by simulation using real process data). Holz Roh- Werkst. 44:55–56CrossRef
Zurück zum Zitat Lobenhoffer H (1987) Verfahren zur optimalen Regelung eines Formstrangs zur Herstellung von Spanplatten. (Procedure for the optimal control of a mat forming line in particleboard production). Holz Roh- Werkst 45:429-337CrossRef Lobenhoffer H (1987) Verfahren zur optimalen Regelung eines Formstrangs zur Herstellung von Spanplatten. (Procedure for the optimal control of a mat forming line in particleboard production). Holz Roh- Werkst 45:429-337CrossRef
Zurück zum Zitat Lu SCY (1990) Machine learning approaches to knowledge synthesis and integration tasks for advanced engineering automation. Comput Ind 15:105–120CrossRef Lu SCY (1990) Machine learning approaches to knowledge synthesis and integration tasks for advanced engineering automation. Comput Ind 15:105–120CrossRef
Zurück zum Zitat Mansfield Shawn D, Iliadis L, Avramidis S (2007) Neural network prediction of bending strength and stiffness in western hemlock (Tsuga heterophylla Raf.). Holzforschung 61:707–716CrossRef Mansfield Shawn D, Iliadis L, Avramidis S (2007) Neural network prediction of bending strength and stiffness in western hemlock (Tsuga heterophylla Raf.). Holzforschung 61:707–716CrossRef
Zurück zum Zitat Niemz P, Schweitzer F (1990) Einfluss ausgewählter Strukturparameter auf die Zug- und Druckfestigkeit von Spanplatten. (Influence of some selected structural parameters on tensile and compression strength of particle boards). Holz Roh- Werkst. 48:361–364CrossRef Niemz P, Schweitzer F (1990) Einfluss ausgewählter Strukturparameter auf die Zug- und Druckfestigkeit von Spanplatten. (Influence of some selected structural parameters on tensile and compression strength of particle boards). Holz Roh- Werkst. 48:361–364CrossRef
Zurück zum Zitat Refaeilzadeh P, Tang L, Liu H (2009) Cross-validation. In: Liu, L., ÖZsu, M.T. (eds) Encyclopedia of database systems. Springer, Boston, pp 532–538 Refaeilzadeh P, Tang L, Liu H (2009) Cross-validation. In: Liu, L., ÖZsu, M.T. (eds) Encyclopedia of database systems. Springer, Boston, pp 532–538
Zurück zum Zitat Riegler M, Spangl B, Weigl M, Wimmer R, Müller U (2013) Simulation of a real-time process adaptation in the manufacture of high-density fibreboards using multivariate regression analysis and feedforward control. Wood Sci Technol 47:1243–1259CrossRef Riegler M, Spangl B, Weigl M, Wimmer R, Müller U (2013) Simulation of a real-time process adaptation in the manufacture of high-density fibreboards using multivariate regression analysis and feedforward control. Wood Sci Technol 47:1243–1259CrossRef
Zurück zum Zitat Ritter C, Landmesser W, Niemz P, Hänsel A (1990) Vergleichende Untersuchungen zur Anwendbarkeit verschiedener Methoden für die Modellierung der Spanplattenfertigung. (Comparative studies on the applicability of different methods for modelling particleboard production). Holztechnologie 30:23–25 Ritter C, Landmesser W, Niemz P, Hänsel A (1990) Vergleichende Untersuchungen zur Anwendbarkeit verschiedener Methoden für die Modellierung der Spanplattenfertigung. (Comparative studies on the applicability of different methods for modelling particleboard production). Holztechnologie 30:23–25
Zurück zum Zitat Snoek J, Larochelle H, Adams RP (2012) Practical Bayesian optimization of machine learning algorithms. In: Proceedings of the 25th international conference on neural information processing systems—volume 2 2012, Curran Associates Inc.: Lake Tahoe, Nevada, pp 2951–2959 Snoek J, Larochelle H, Adams RP (2012) Practical Bayesian optimization of machine learning algorithms. In: Proceedings of the 25th international conference on neural information processing systems—volume 2 2012, Curran Associates Inc.: Lake Tahoe, Nevada, pp 2951–2959
Zurück zum Zitat Vapnik VN (1995) The nature of statistical learning theory. Springer, BerlinCrossRef Vapnik VN (1995) The nature of statistical learning theory. Springer, BerlinCrossRef
Zurück zum Zitat Wang J, Ma Y, Zhang L, Gao RX, Wu D (2018) Deep learning for smart manufacturing: methods and applications. J Manuf Syst 48(C):144–156CrossRef Wang J, Ma Y, Zhang L, Gao RX, Wu D (2018) Deep learning for smart manufacturing: methods and applications. J Manuf Syst 48(C):144–156CrossRef
Zurück zum Zitat Wu D, Jennings C, Terpenny J, Gao RX, Kumara S (2017) A comparative study on machine learning algorithms for smart manufacturing: tool wear prediction using random forests. J Manuf Sci Eng 139:1–9 Wu D, Jennings C, Terpenny J, Gao RX, Kumara S (2017) A comparative study on machine learning algorithms for smart manufacturing: tool wear prediction using random forests. J Manuf Sci Eng 139:1–9
Zurück zum Zitat Wuest T, Weimer D, Irgens C, Thoben K-D (2016) Machine learning in manufacturing: advantages, challenges, and applications. Prod Manuf Res 4:23–45 Wuest T, Weimer D, Irgens C, Thoben K-D (2016) Machine learning in manufacturing: advantages, challenges, and applications. Prod Manuf Res 4:23–45
Metadaten
Titel
Prediction of mechanical properties of wood fiber insulation boards as a function of machine and process parameters by random forest
verfasst von
M. Schubert
M. Luković
H. Christen
Publikationsdatum
07.05.2020
Verlag
Springer Berlin Heidelberg
Erschienen in
Wood Science and Technology / Ausgabe 3/2020
Print ISSN: 0043-7719
Elektronische ISSN: 1432-5225
DOI
https://doi.org/10.1007/s00226-020-01184-3

Weitere Artikel der Ausgabe 3/2020

Wood Science and Technology 3/2020 Zur Ausgabe