Advertisement

Neural Computing and Applications

, Volume 27, Issue 6, pp 1577–1592 | Cite as

A new approach for dynamic modelling of energy consumption in the grinding process using recurrent neural networks

  • A. Arriandiaga
  • E. Portillo
  • J. A. Sánchez
  • I. Cabanes
  • I. Pombo
Original Article

Abstract

Grinding is a critical machining process because it produces parts of high precision and high surface quality. Due to the semi-artisan production of the wheel, it is not possible to know in advance the performance of the wheel. One of the most useful parameters to characterize the grinding process is the specific grinding energy, which varies with the wear of the grinding wheel during its lifecycle. Thus, it would be useful to model the specific grinding energy in order to get information about the performance of the wheel before buying it. Unlike the typical applications of time series forecasting, in this work, a totally different issue is presented: the prediction of new and complete time series bounded in time without initial or historic values. In this context, an analysis of the effect of the time characteristics and the number of points of the time series on the prediction capabilities of the ANN is presented. The results of the analysis show that 200 points are enough to predict a complete time series up to 2000 mm3/mm of specific volume of material removed. Actually, it is shown that modelling the evolution of the grinding specific energy up to 2000 mm3/mm is possible. The net shows good capability to generalize to new grinding conditions, with errors below 23.65 %, and to new wheel characteristics, with errors below 20.01 %, which are satisfactory from the grinding process perspective.

Keywords

Specific grinding energy Dynamic modelling Complete time series Recurrent neural networks Static inputs Generalization 

Notes

Acknowledgments

The authors gratefully acknowledge the funding support received from the Spanish Ministry of Economy and Competitiveness and the FEDER operation program for funding the project DPI-2010-21652-C02-00 and DPI2012-32882. This work was also supported in part by the Regional Government of the Basque Country through the Departamento de Educación, Universidades e Investigación (Project IT719-13) and UPV/EHU under Grant UFI11/28.

References

  1. 1.
    Coit DW, Smith AE (1995) Using designed experiments to produce robust neural network models of manufacturing processes. In: 4th industrial engineering research conference proceedings, pp 229–238Google Scholar
  2. 2.
    Brinksmeier E, Tönshoff HK, Czenkusch C, Heinzel C (1998) Modelling and optimization of grinding processes. J Intell Manuf 9:303–314CrossRefGoogle Scholar
  3. 3.
    Fuh KH, Wang SB (1997) Force modeling and forecasting in creep feed grinding using improved BP neural network. Int J Mach Tools Manuf 37(8):1167–1178CrossRefGoogle Scholar
  4. 4.
    Yang Q, Jin J (2010) Study on machining prediction in plane grinding based on artificial neural network. In: 2010 international conference on intelligent systems and knowledge engineering (ISKE), pp 442–444Google Scholar
  5. 5.
    Sedighi M, Afshari D (2010) Creep feed grinding optimization by an integrated GA-NN system. J Intell Manuf 21:657–663CrossRefGoogle Scholar
  6. 6.
    Maksoud TMA, Atia MR, Koura MM (2003) Applications of artificial intelligence to grinding operations via neural networks. Mach Sci Technol 7(3):361–387CrossRefGoogle Scholar
  7. 7.
    Kruszyński BW, Lajmert P (2005) An intelligent supervision system for cylindrical traverse grinding. CIRP Ann Manuf Technol 54(1):305–308CrossRefGoogle Scholar
  8. 8.
    Liu HX, Chen T, Qu LS (1997) Predicting grinding burn using artificial neural networks. J Intell Manuf 8(3):235–237CrossRefGoogle Scholar
  9. 9.
    Karpuschewski B, Wehmeier M, Inasaki I (2000) Grinding monitoring system based on power and acoustic emission sensors. CIRP Ann Manuf Technol 49(1):235–240CrossRefGoogle Scholar
  10. 10.
    Hosokawa A, Mashimo K, Yamada K, Ueda T (2004) Evaluation of grinding wheel surface by means of grinding sound discrimination. JSME Int J Ser C 47(1):52–58CrossRefGoogle Scholar
  11. 11.
    Arriandiaga A, Portillo E, Sánchez JA, Cabanes I, Pombo I (2014) Virtual sensors for on-line wheel wear and part roughness measurement in the grinding process. Sensors 14:8756–8778CrossRefGoogle Scholar
  12. 12.
    Wu CL, Chau KW, Li YS (2009) Predicting monthly streamflow using data-driven models coupled with data-preprocessing techniques. Water Resour Res 45:W08432CrossRefGoogle Scholar
  13. 13.
    Cheng C, Chau K, Sun Y, Lin J (2005) Long-term prediction of discharges in Manwan Reservoir using artificial neural network models. Lect Notes Comput Sci 3498:1040–1045CrossRefzbMATHGoogle Scholar
  14. 14.
    Claveria O, Torra S (2013) Forecasting tourism demand in Catalonia: neural networks vs. time series models. Econ Model 36:220–228CrossRefGoogle Scholar
  15. 15.
    Ticknor JL (2013) A Bayesian regularized artificial neural network for stock market forecasting. Expert Syst Appl 40(14):5501–5506CrossRefGoogle Scholar
  16. 16.
    Sivapragasam C, Vanitha S, Muttil N, Suganya K, Suji S, Selvi MT, Selvi R, Sudha SJ (2014) Monthly flow forecast for Mississippi River basin using artificial neural networks. Neural Comput Appl 24:1785–1793CrossRefGoogle Scholar
  17. 17.
    Reyes J, Morales-Esteban A, Martínez-Álvarez F (2013) Neural networks to predict earthquakes in Chile. Appl Soft Comput 13(2):1314–1328CrossRefGoogle Scholar
  18. 18.
    Wu CL, Chau KW (2013) Prediction of rainfall time series using modular soft computing methods. Eng Appl Artif Intell 26(3):997–1007CrossRefGoogle Scholar
  19. 19.
    Taormina R, Chau KW, Sethi R (2012) Artificial neural network simulation of hourly groundwater levels in a coastal aquifer system of the Venice lagoon. Eng Appl Artif Intell 25(8):1670–1676CrossRefGoogle Scholar
  20. 20.
    Girish KJ, Sinha K (2014) Time-delay neural networks for time series prediction: an application to the monthly wholesale price of oilseeds in India. Neural Comput Appl 24:563–571CrossRefGoogle Scholar
  21. 21.
    Tian Z, Zuo MJ (2010) Health condition prediction of gears using a recurrent neural network approach. IEEE Trans Reliab 59(4):700–705CrossRefGoogle Scholar
  22. 22.
    Godarzi AA, Amiri RM, Talaei A, Jamasb T (2014) Predicting oil price movements: a dynamic artificial neural network approach. Energy Policy 68:371–382CrossRefGoogle Scholar
  23. 23.
    Zhang N (2011) Prediction of urban stormwater runoff in Chesapeake Bay using neural networks. Adv Neural Netw 6676:27–36Google Scholar
  24. 24.
    Zhou H, Su G, Li G (2011) Forecasting daily gas load with OIHF-Elman neural network. Procedia Comput Sci 5:754–758CrossRefGoogle Scholar
  25. 25.
    Park DC (2011) Prediction of sunspot series using a recurrent neural network. In: 2011 international conference on information science and applications (ICISA), pp 1–5Google Scholar
  26. 26.
    Pisoni E, Farina M, Carnevale C, Piroddi L (2009) Forecasting peak air pollution levels using NARX models. Eng Appl Artif Intell 22:593–602CrossRefGoogle Scholar
  27. 27.
    Teufel E, Kletting M, Teich WG, Pfleiderer HJ, Tarin-Sauer C (2003) Modeling the glucose metabolism with backpropagation through time trained Elman nets. In: Proceedings of the 13th IEEE workshop on neural network for signal processing, pp 789–798Google Scholar
  28. 28.
    Rowe WB (2009) Principles of modern grinding technology. Elsevier Inc, BurlingtonGoogle Scholar
  29. 29.
    Hagan MT, Menhaj M (1994) Training feed-forward networks with the Marquardt algorithm. IEEE Trans Neural Netw 5:989–993CrossRefGoogle Scholar
  30. 30.
    Yuce B, Li H, Rezgui Y, Petri I, Jayan B, Yang C (2014) Utilizing artificial neural network to predict energy consumption and thermal comfort level: an indoor swimming pool case study. Energy Build 80:45–56CrossRefGoogle Scholar
  31. 31.
    MacKay DJC (1992) A practical Bayesian framework for backpropagation networks. Neural Comput 4:448–472CrossRefGoogle Scholar
  32. 32.
    Werbos PJ (1990) Backpropagation through time: what it does and how to do it. Proc IEEE 78(10):1550–1560CrossRefGoogle Scholar
  33. 33.
    Nguyen D, Widrow B (1990) Improving the Learning speed of 2-layer neural networks by choosing initial values of the adaptive weights. In: 1990 international joint conference on neural networks (IJCNN), pp 21–26 (III)Google Scholar

Copyright information

© The Natural Computing Applications Forum 2015

Authors and Affiliations

  • A. Arriandiaga
    • 1
  • E. Portillo
    • 1
  • J. A. Sánchez
    • 2
  • I. Cabanes
    • 1
  • I. Pombo
    • 2
  1. 1.Department of Automatic Control and System EngineeringUniversity of the Basque CountryBilbaoSpain
  2. 2.Department of Mechanical EngineeringUniversity of the Basque CountryBilbaoSpain

Personalised recommendations