Abstract
Fixtures are used to locate and secure workpieces for further machining or measurement process. Design of these fixtures remains a costly process due to the significant technical know-how required. Automated fixture design can mitigate much of these costs by reducing the dependence on skilled labour, making it an attractive endeavour. Historical attempts in achieving automated fixture design solutions predominantly relied on case-based reasoning (CBR) to generate fixtures by extrapolating from previously proven designs. These approaches are limited by their dependence on a fixturing library. Attempts in using rule-based reasoning (RBR) has also shown to be difficult to implement comprehensively. Reinforcement learning, on the other hand, does not require a fixturing library and instead builds experience and learns through interacting with an environment. This paper discusses the use of reinforcement learning to generate optimized fixturing solutions. Through a proposed reinforcement learning driven fixture design (RL-FD) framework, reinforcement learning was used to generate optimized fixturing solutions. In response to the fixturing environment, adjustments to the reinforcement learning process in the exploration phase is studied. A case study is presented, comparing a conventional exploration method with an adjusted one. Both agents show improved average results over time, with the adjusted exploration model exhibiting faster performance.
Similar content being viewed by others
Notes
3 locators are typically the optimal result in most scenarios, but this goal can be user-adjusted for special cases.
A step counts as a single action performed by the agent. Five million steps was chosen as a basis of comparison between both agents as preliminary runs show stable results prior to this step count.
References
Nee AYC, Kumar AS (1991) A Framework for an Object/Rule-Based Automated Fixture Design System. CIRP Ann 40(1):147–151, 1991/01/01/
Kumar AS, Nee AYC (1995) A framework for a variant fixture design system using case-based reasoning technique. Manuf Sci Eng ASME 3:763–775
Sun SH, Chen JL (1996) A fixture design system using case-based reasoning. Eng Appl Artif Intell 9(5):533–540, 1996/10/01
Li W, Li P, Rong Y (2002) Case-based agile fixture design. J Mater Process Technol 128(1):7–18, 2002/10/06
Hashemi H, Shaharoun AM, Sudin I (2014) A case-based reasoning approach for design of machining fixture. Int J Adv Manuf Technol 74(1):113–124, 2014/09/01
McSherry D (2002) The Inseparability Problem in Interactive Case-Based Reasoning. In: Research and Development in Intelligent Systems XVIII. Springer London, London, pp 109–122
Szczepaniak PS, Duraj A (2018) case-based reasoning: the search for similar solutions and identification of outliers. Complexity 2018:12 Art. no. 9280787
Nee AYC, Kurnar AS, Prombanpong S, Puah KY (1992) A Feature-Based Classification Scheme for Fixtures. CIRP Ann 41(1):189–192, 1992/01/01
Dong X, DeVries WR, Wozny MJ (1991) Feature-Based Reasoning in Fixture Design. CIRP Ann 40(1):111–114, 1991/01/01
Kumar AS, Nee AYC, Prombanpong S (1992) Expert fixture-design system for an automated manufacturing environment. Comput Aided Des 24(6):316–326, 1992/06/01
Prentzas J, Hatzilygeroudis I (2007) Categorizing approaches combining rule-based and case-based reasoning. Expert Syst 24(2):97–122
Zhang FP, Wu D, Zhang TH, Yan Y, Butt SI (2018) Knowledge component-based intelligent method for fixture design. Int J Adv Manuf Technol 94(9):4139–4157, 2018/02/01
Kumar AS, Subramaniam V, Boon Teck T (2000) Conceptual design of fixtures using machine learning techniques. Int J Adv Manuf Technol 16(3):176–181
Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiller M, Fidjeland AK, Ostrovski G, Petersen S, Beattie C, Sadik A, Antonoglou I, King H, Kumaran D, Wierstra D, Legg S, Hassabis D (2015) Human-level control through deep reinforcement learning. Nature 518:529, 02/25/online
Arel I, Rose DC, Karnowski TP (2010) Deep machine learning - a new frontier in artificial intelligence research [research frontier]. IEEE Comput Intell Mag 5(4):13–18
V Mnih, K Kavukcuoglu, D Silver, A Graves, I Antonoglou, D Wierstra, and M Riedmiller (2013) "Playing atari with deep reinforcement learning," arXiv preprint arXiv:1312.5602
MD Pendrith (2000) "Distributed reinforcement learning for a traffic engineering application," in Proceedings of the fourth international conference on Autonomous agents, pp. 404–411: Citeseer
Chaharsooghi SK, Heydari J, Zegordi SH (2008) A reinforcement learning model for supply chain ordering management: an application to the beer game. Decis Support Syst 45(4):949–959
E Catto (2011) Box2D. Available: https://github.com/erincatto/Box2D. Accessed 01 Jan 2019
K Lauer (2011) pybox2d. Available: https://github.com/pybox2d/pybox2d. Accessed 01 Jan 2019
A. Muntean. (2017). Deep Q-Learning. Available: https://github.com/andreimuntean/Deep-Q-Learning. Accessed 01 Jan 2019
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Low, D.W.W., Neo, D.W.K. & Kumar, A.S. A study on automatic fixture design using reinforcement learning. Int J Adv Manuf Technol 107, 2303–2311 (2020). https://doi.org/10.1007/s00170-020-05156-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00170-020-05156-6