Abstract
A classical algorithm Tabu Search was compared with Q Learning (named learning) with regards to the scheduling problems in the Austempered Ductile Iron (ADI) manufacturing process. The first part comprised of a review of the literature concerning scheduling problems, machine learning and the ADI manufacturing process. Based on this, a simplified scheme of ADI production line was created, which a scheduling problem was described for. Moreover, a classic and training algorithm that is best suited to solve this scheduling problem was selected. In the second part, was made an implementation of chosen algorithms in Python programming language and the results were discussed. The most optimal algorithm to solve this problem was identified. In the end, all tests and their results for this project were presented.
Go to article
Bibliography
[1] Yang, L., Jiang, G., Chen, X., Li, G., Li, T. & Chen, X. (2019). Design of integrated steel production scheduling knowledge network system. Claster Comput. 10197-10206.
[2] Żurada, J. Barski, M., Jędruch, W. (1996). Artificial Neural Networks. Fundamentals of theory and application. Warszawa: PWN. (in Polish).
[3] Janiak, A. (2006). Scheduling in computer and manufacturing systems. Warszawa: Wydawnictwa Komunikacji i Łączności.
[4] Smutnicki, C. (2002). Scheduling algorithms. Warszawa: Akademicka Oficyna Wydawnicza EXIT. (in Polish).
[5] Coffman, E.G. (1980). Task scheduling theory. Warszawa: Wydawnictwa Naukowo-Techniczne. (in Polish).
[6] Janczarek, M. (2011). Managing production processes in the enterprise. Lublin: Lubelskie Towarzystwo Naukowe. (in Polish).
[7] Szeliga, M. (2019) Practical machine learning. Warszawa: PWN. (in Polish).
[8] Raschka, S. (2018) Python machine learning. Gliwice: Helion. (in Polish).
[9] Choi, H-S, Kim, J-S. & Lee, D-H. (2011). Real-time scheduling for reentrant hybrid flow shops: A decision tree based mechanism and its application to a TFT-LCD line. Expert System with Application. 38, 3514-3521.
[10] Agarwal, A., Pirkul, H. & Jacob, V.S. (2003). Augmented neutral network for task scheduling. European Journal of Operational Research. 151, 481-502.
[11] Jain, A.S. & Meeran, S. (1998). Jop-shop scheduling using neutral networks. International Journal of Production Research. 36(5), 1249-1272
[12] Fonseca-Reyna, Y.C., Martinez-Jimenez, Y. & Nowe, A. (2017). Q-Learning algorithm performance for m-machine, n-jobs flow shop scheduling problems to minimize makespan, Revista Investigacion Operacional. 38(3), 281-290.
[13] Dewi, Andriansyah, & Syahriza, (2019). Optimization of flow shop scheduling problem using classic algorithm: case study, IOP Conf. Series: Materials Science and Engineering 506.
[14] Putatunda, K. (2001) Development of austempered ductile cast iron (ADI) with simultaneous high yield strength and fracture toughness by a novel two-step austempering process. Material Science and Engineering A. 315, 70-80.
[15] Dayong Han, Hubei Key, Qiuhua Tang; Zikai Zhang; Jun Cao, (2020). Energy-efficient integration optimization of production scheduling and ladle dispatching in steelmaking plants. IEEE Access. 8, 176170-176187.
[16] Perzyk, M. (2017). The use of production data mining methods in the diagnosis of the causes of product defects and disruptions in the production process. Utrzymanie Ruchu. 4, 45-47. (in Polish).
[17] Perzyk, M., Dybowski, B. & Kozłowski, J. (2019). Introducing advanced data analytics in perspective of industry 4.0 in a die casting foundry. Archives of Foundry Engineering. 19(1), 53-57.
[18] Yescas, M. (2003). Prediction of the Vickers hardness in austempered ductile irons using neural networks. International Journal of Cast Metals Research. 15(5), 513-521.
[19] Report on the contract no. U / 227/2014 implemented at the Foundry Research Institute. (in Polish).
Go to article
en
pl
