Abstract
Recently, artificial neural networks have proven their potential in manifold production related tasks. At this, the learning ability is both their greatest strength and greatest weakness. The performance in the application is highly related to the learning process. Only sufficient training data in combination with a suitable configuration of the learning parameters leads on to useful results. Nevertheless, due to the general structure of artificial neural networks, the learning behaviour not necessarily correlates with the later functional behaviour. This paper considers the learning process and the application performance of four common network architectures in two production related applications; control and prediction. The evaluation of the network performance takes place by means of a generic shop floor model.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Catelani M, Fort A (2002) Soft fault detection and isolation in analog circuits: some results and a comparison between a fuzzy approach and radial basis function networks. IEEE Trans Instrum Meas 51(2):196–202
Chaturvedi D (2008) Artificial neural networks and supervised learning. In: Chaturvedi D (ed) Soft computing: techniques and its applications in electrical engineering. Springer, Berlin, pp 23–50
Dreyfus G (2005) Neural networks methodology and application. Springer, Berlin
Elman J (1990) Finding structure in time. Cognitive Sci 14(2):179–211
Er M, Wu S, Lu J, Toh H (2002) Face recognition with radial basis function (RBF) neural networks. IEEE Trans Neural Networks 13(3):697–710
España-Boquera S, Zamora-Martínez F, Castro-Bleda M, Gorbe-Moya, J (2007) Efficient BP algorithms for general feedforward neural networks. In: Mira J, Álvarez JR (eds) Lecture notes in computer science—bio-inspired modeling of cognitive tasks. Springer, Berlin, pp 327–336
Fahlman S, Lebiere C (1990) The cascade-correlation learning architecture. In: Touretzky DS (ed) Advances in neural information processing II, Morgan Kauffman Publishers Inc., San Francisco, pp 524–532
Hamann T (2008) Lernfähige intelligente Produktionsregelung. Gito Verlag, Berlin
Harjes F, Scholz-Reiter B, Kaviani Mehr A (2011) Elman networks for the prediction of inventory levels and capacity utilization. Int J Appl Math Inf 10 5(4) pp 283–290
Haykin S (2008) Neural networks and learning machines, 3rd edn. Prentice Hall, New Jersey
Lawrence S, Giles C (2000) Overfitting and neural networks: conjugate gradient and backpropagation. Como, Italy, pp 114–119
Lee C, Chung P, Tsai J, Chang C (1999) Robust radial basis function neural networks. IEEE Trans Syst Man Cybern B Cybern 29(6):674–685
Mandic D, Chambers J (2001) Recurrent neural networks for prediction: learning algorithms, architectures and stability (adaptive and learning systems for signal processing, communications and control series). Wiley, Hoboken
Pawlus W, Robbersmyr K, Reza Karimi H (2011) Performance evaluation of feed forward neural networks for modeling a vehicle to pole central collision. In: Mastorakis N et al (eds) Recent researches in geography, geology, energy, environment and biomedicine. WSEAS Press, Corfu Island, pp 467–472
Rivest F, Shultz T (2002) Application of knowledge-based cascade-correlation to vowel recognition. Hawaii, USA, pp 53–58
Scholz-Reiter B, Hamann T (2008) The behaviour of learning production control. CIRP Ann Manuf Technol 7(1):459–462
Scholz-Reiter B, Hamann T, Höhns H, Middelberg G (2004) Decentral closed loop control of production systems by means of artificial neural networks. Budapest, Hungary, pp 199–203
Vamplev P, Ollington R (2005) On-line reinforcement learning using cascade constructive neural networks. In: Khosla R, Howlett RJ, Jain LC (eds) Lecture notes in computer science—knowledge-based intelligent information and engineering systems. Springer, Berlin, pp 562–568
Acknowledgments
This research is funded by the German Research Foundation (DFG) as part of the project Automation of continuous learning and examination of the long-run behaviour of artificial neural networks for production control, index SCHO 540/16-1.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Scholz-Reiter, B., Harjes, F. (2013). Towards the Learning Behaviour and Performance of Artificial Neural Networks in Production Control. In: Kreowski, HJ., Scholz-Reiter, B., Thoben, KD. (eds) Dynamics in Logistics. Lecture Notes in Logistics. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-35966-8_39
Download citation
DOI: https://doi.org/10.1007/978-3-642-35966-8_39
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-35965-1
Online ISBN: 978-3-642-35966-8
eBook Packages: EngineeringEngineering (R0)