Predicting performance indicators with ANNs for AI-based online scheduling in dynamically interconnected assembly systems

Mass customization demands shorter manufacturing system response times due to frequent product changes. This increase in system dynamics imposes additional flexibility requirements especially on assembly processes, as complexity accumulates in this last step of value creation. Flexible and dynamically interconnected assembly systems can meet the increased requirements as opposed to traditional dedicated assembly line approaches. The high complexity and dynamical environment in these kinds of systems lead to the demand for real-time online control and scheduling solutions. Within the decision-making of online scheduling, the capability of predicting the consequences of available actions is crucial. In real-time environments, running extensive discrete-event simulations to evaluate how actions unfold requires too much computing time. Artificial neural networks (ANN) are a viable alternative to quickly evaluate the potential future performance value of a production state for online production planning and control. They can predict performance indicators such as the expected makespan given the current production status. Leveraging recent advances in artificial intelligence (AI) game algorithms, an assembly control system based on Google DeepMind’s AlphaZero was created. Specifically, an ANN is incorporated into the approach that suggests favorable job routing decisions and predicts the value of actions. The results show that the trained network can predict favorable actions with an accuracy of over 95% and estimate the makespan with an error smaller than 3%.

[1]  Robert Schmitt,et al.  Dynamically Interconnected Assembly Systems , 2017 .

[2]  Lukas Hollenstein,et al.  SimLack: simulation-based optimization and scheduling of generic powder coating lines , 2018 .

[3]  Thomas Bauernhansl,et al.  Changing Requirements of Competence Building Due to an Increase of Personalized Products , 2017 .

[4]  Abid Ali Khan,et al.  A research survey: review of flexible job shop scheduling techniques , 2016, Int. Trans. Oper. Res..

[5]  Sanja Petrovic,et al.  SURVEY OF DYNAMIC SCHEDULING IN MANUFACTURING SYSTEMS , 2006 .

[6]  George Chryssolouris,et al.  Assembly system design and operations for product variety , 2011 .

[7]  Haruhiko Suwa,et al.  Online scheduling in manufacturing , 2013 .

[8]  Jeffrey W. Herrmann,et al.  Rescheduling Manufacturing Systems: A Framework of Strategies, Policies, and Methods , 2003, J. Sched..

[9]  Robert Harrison,et al.  Convertibility Evaluation of Automated Assembly System Designs for High Variety Production , 2017 .

[10]  Jongpil Jeong,et al.  Demand Forecasting Based on Machine Learning for Mass Customization in Smart Manufacturing , 2019, Proceedings of the 2019 International Conference on Data Mining and Machine Learning.

[11]  Lenz Belzner,et al.  Deep reinforcement learning for semiconductor production scheduling , 2018, 2018 29th Annual SEMI Advanced Semiconductor Manufacturing Conference (ASMC).

[12]  Demis Hassabis,et al.  Mastering the game of Go without human knowledge , 2017, Nature.

[13]  Lars Hvam,et al.  Product complexity and operational performance: A systematic literature review , 2019, CIRP Journal of Manufacturing Science and Technology.

[14]  Botond Kádár,et al.  Manufacturing Lead Time Estimation with the Combination of Simulation and Statistical Learning Methods , 2016 .

[15]  Jongpil Jeong,et al.  A CPS-Based IIoT Architecture Using Level Diagnostics Model for Smart Factory , 2020, ICCSA.

[16]  Hans-Peter Wiendahl,et al.  Variantenbeherrschung in der Montage , 2004 .

[17]  Enzo Morosini Frazzon,et al.  Hybrid approach for the integrated scheduling of production and transport processes along supply chains , 2018, Int. J. Prod. Res..

[18]  Jun Ota,et al.  Big data in automation: Towards generalized makespan estimation in shop scheduling problems , 2017, 2017 13th IEEE Conference on Automation Science and Engineering (CASE).

[19]  Alain Bernard,et al.  Product Variety Management , 1998 .

[20]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[21]  Carina Mieth,et al.  Sheet-Metal Production Scheduling Using AlphaGo Zero , 2020 .

[22]  Kathryn E. Stecke,et al.  Classification of flexible manufacturing systems , 2011 .

[23]  Amos H. C. Ng,et al.  A simulation-based scheduling system for real-time optimization and decision making support , 2011 .

[24]  Enzo Morosini Frazzon,et al.  Evaluating the Robustness of Production Schedules using Discrete-Event Simulation , 2017 .

[25]  Vincent Hargaden,et al.  Machine learning technologies for order flowtime estimation in manufacturing systems , 2019 .

[26]  Erez Karpas,et al.  Temporal Planning while the Clock Ticks , 2018, ICAPS.

[27]  Erwin Rauch,et al.  An agile scheduling and control approach in ETO construction supply chains , 2019, Comput. Ind..

[28]  Jatoth Mohan,et al.  A Review of Dynamic Job Shop Scheduling Techniques , 2019, Procedia Manufacturing.

[29]  C. M. Harmonosky,et al.  Real-time scheduling in computer integrated manufacturing: a review of recent research , 1991 .

[30]  Demis Hassabis,et al.  Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm , 2017, ArXiv.

[31]  Samir Lamouri,et al.  Machine learning applied in production planning and control: a state-of-the-art in the era of industry 4.0 , 2020, Journal of Intelligent Manufacturing.

[32]  Yaoguang Hu,et al.  Joint Optimization of Production Planning and Capacity Adjustment for Assembly System , 2017 .

[33]  R. Pellerin,et al.  The industrial management of SMEs in the era of Industry 4.0 , 2018, Int. J. Prod. Res..

[34]  Jin Xie,et al.  Review for Flexible Job Shop Scheduling , 2019, Engineering Applications of Computational Methods.

[35]  J. R. Tony Arnold,et al.  Introduction to Materials Management , 1991 .