Development of an automated assembly process supported with an artificial neural network

• Autorzy: Bobka P. , Heyn J. , Henningson J.-O. , Römer M. , Engbers T. , Dietrich F. , Dröder K.

Identyfikatory

DOI

10.5604/01.3001.0012.4605

• Języki publikacji: EN

Abstrakty

EN

A central problem in automated assembly is the ramp-up phase. In order to achieve the required tolerances and cycle times, assembly parameters must be determined by extensive manual parameter variations. Therefore, the duration of the ramp-up phase represents a planning uncertainty and a financial risk, especially when high demands are placed on dynamics and precision. To complete this phase as efficiently as possible, comprehensive planning and experienced personnel are necessary. In this paper, we examine the use of machine learning techniques for the ramp-up of an automated assembly process. Specifically we use a deep artificial neural network to learn process parameters for pick-and-place operations of planar objects. We describe how the handling parameters of an industrial robot can be adjusted and optimized automatically by artificial neural networks and examine this approach in laboratory experiments. Furthermore, we test whether an artificial neural network can be used to optimize assembly parameters in process as an adaptive process controller. Finally, we discuss the advantages and disadvantages of the described approach for the determination of optimal assembly parameters in the ramp-up phase and during the utilization phase.

Słowa kluczowe

EN

assembly; machine learning; neural network; industrial robot

• Wydawca: Wydawnictwo Wrocławskiej Rady FSNT NOT
• Czasopismo: Journal of Machine Engineering
• Rocznik: 2018
• Tom: Vol. 18, No. 3
• Strony: 28--41
• Opis fizyczny: Bibliogr. 17 poz., rys., tab.

Twórcy

autor

Bobka P.

• Technische Universität Braunschweig, Institut für Werkzeugmaschinen und Fertigungstechnik (IWF), Braunschweig Germany

autor

Heyn J.

• Technische Universität Braunschweig, Institut für Werkzeugmaschinen und Fertigungstechnik (IWF), Braunschweig Germany

autor

Henningson J.-O.

• Technische Universität Braunschweig, Institut für Werkzeugmaschinen und Fertigungstechnik (IWF), Braunschweig Germany

autor

Römer M.

• Technische Universität Braunschweig, Institut für Werkzeugmaschinen und Fertigungstechnik (IWF), Braunschweig Germany

autor

Engbers T.

• Technische Universität Braunschweig, Institut für Werkzeugmaschinen und Fertigungstechnik (IWF), Braunschweig Germany

autor

Dietrich F.

• Technische Universität Braunschweig, Institut für Werkzeugmaschinen und Fertigungstechnik (IWF), Braunschweig Germany

autor

Dröder K.

• Technische Universität Braunschweig, Institut für Werkzeugmaschinen und Fertigungstechnik (IWF), Braunschweig Germany

Bibliografia

• [1] BOLMSJO G., 2014, Reconfigurable and Flexible Industrial Robot Systems, Adv. Robot. Autom., 3/117, DOI: 10.4172/2168-9695.1000117.
• [2] SCHERF, H., 2010, Modellbildung und Simulation dynamischer Systeme, Eine Sammlung von Simulink-Beispielen, l, Oldenbourg Wissenschaftsverlag, Available online at http://lib.myilibrary.com/detail.asp?id=609459.
• [3] SCRIMIERI D., OATES R.F., RATCHEV S.M., 2015, Learning and reuse of engineering ramp-up strategies for modular assembly systems, J. Intell. Manuf., 26/6, 1063-1076, DOI: 10.1007/s10845-013-0839-6.
• [4] GRAVEL D., ZHANG G., BELL A., ZHANG B., 2009, Objective metric study for DOE-based parameter optimization in robotic torque converter assembly, IEEE/RSJ International Conference on Intelligent Robots and Systems, St. Louis, MO, USA, 10.10.2009 - 15.10.2009, 3832-3837.
• [5] SU Ch.T., CHIANG T.L., 2003, Optimizing the IC wire bonding process using a neural networks/genetic algorithms approach, Journal of Intelligent Manufacturing,14/2, 229-238, DOI: 10.1023/A:1022959631926.
• [6] MONKMAN Gareth J., 2007, Robot grippers, Weinheim, Chichester, Wiley-VCH, http://search.ebscohost.com/ login.aspx?direct=true&scope=site&db=nlebk&db=nlabk&AN=190005
• [7] ARAI F., RONG L., FUKUDA T., 1993, Trajectory control of flexible plate using neural network, Proceedings IEEE International Conference on Robotics and Automation, Atlanta, GA, USA, 2-6 May 1993, IEEE Comput. Soc. Press., 155-160.
• [8] KOBER J., PETERS J., 2014, Learning Motor Skills. From Algorithms to Robot Experiments, Springer Tracts in Advanced Robotics, 97, http://dx.doi.org/10.1007/978-3-319-03194-1.
• [9] ZHONG X., LEWIS J.N.N., FRANCIS L., 1996, Inverse robot calibration using artificial neural networks, Engineering Applications of Artificial Intelligence, 9/1, 83-93, DOI: 10.1016/0952-1976(95)00069-0.
• [10] WEI Z.P., FANG G., 1999, Model Predictive Control for Robot Manipulators Using a Neural Network Model, Australian Conference on Robotics and Automation, 62-67, http://www.araa.asn.au/acra/acra1999/papers/ paper13.pdf.
• [11] CYBENKO G., 1989, Approximation by superpositions of a sigmoidal function, Math. Control Signal Systems, 2/4, 303-314. DOI: 10.1007/BF02551274.
• [12] KUSIAK A., 1994, Artificial Neural Networks for Intelligent Manufacturing, Dordrecht, Springer Netherlands. https://ebookcentral.proquest.com/lib/gbv/detail.action?docID=3109078.
• [13] WANG D., BAI Y., 2005, Improving Position Accuracy of Robot Manipulators Using Neural Networks, IEEE, Instrumentation and Measurement Technology Conference Proceedings, Ottawa, ON, Canada, 16-19 May 2005, 1524-1526.
• [14] MAREŠ T., JANOUCHOVÁ E., KUČEROVÁ A., 2016, Artificial neural networks in the calibration of nonlinear mechanical models, Advances in Engineering Software 95, 68-81, DOI: 10.1016/j.advengsoft.2016.01.01.
• [15] DAS A., 2015, Introduction to Digital Image, Guide to Signals and Patterns in Image Processing, Foundations, Methods and Applications, Springer International Publishing, 1-42, https://doi.org/10.1007/978-3-319-14172-5_1.
• [16] GÉRON A., 2017, Hands-On machine learning with Scikit-learn and TensorFlow, Concepts, tools, and techniques to build intelligent systems, O'Reilly, http://proquest.safaribooksonline.com/9781491962282.
• [17] CLEVERT D.A., UNTERTHINER T., HOCHREITER S., 2015, Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs), Published as a conference paper at ICLR 2016, arXiv:1511.07289.