1. Proceedings
  2. I3M
  3. 2022
  4. MAS
  5. 10.46354/i3m.2022.mas.003

Sheet metal assortment optimization with k-Means

  • a Markus Witthaut ,
  • b Nils Kalbe
  • a,b, 1Fraunhofer Institute of Material Flow and Logistics IML, Joseph-von-Fraunhofer-Str. 2-4, Dortmund, 44227, Germany
Cite as
Kalbe N.,and Witthaut M. (2022).,Assortment optimization in sheet metal procurement with k-means. Proceedings of the 21st International Conference on Modelling and Applied Simulation MAS 2022). , 003 . DOI: https://doi.org/10.46354/i3m.2022.mas.003

Abstract

This paper deals with inventory optimization in the procurement of sheet metal for small series and contract manufacturers. An AI-based algorithm was developed and tested for a real-world application. The underlying use case is a variant of the cutting stock problem. The objective is to optimize the number of metal sheet variants to be source to reduce inventory and handling costs. Therefore, demand for metal sheets with different dimensions are combined so that large sheets are sourced from which the sheets required for production are cut. Here we have a trade-off between the savings in inventory management versus the additional costs due to scrapping of cut losses. Decision models for this application case which take all these factors into account have not been developed so far. This paper presents a first approach by modelling parts of the problem as a linear integer problem which is heuristically solved with a k-Means clustering algorithm. With this model different scenarios can be simulated for making better inventory decisions. This approach was implemented in a software application based on Power BI and the Python library scikit-learn and tested in practice by a company. The test showed considerable savings potential for the use case and provided important stimuli for further research, especially regarding further modelling approaches and search algorithms.

References

  1. Arthur, D., & Vassilvitskii, S. (2006).k-means++: Theadvantages of careful seeding. Stanford.
  2. Becker, L. T., & Gould, E. M. (2019). Microsoft power BI:extending excel to manipulate, analyze, andvisualize diverse data. Serials Review, 45(3), 184-188.
  3. Benabdellah, A. C., Benghabrit, A., & Bouhaddou, I.(2019). A survey of clustering algorithms for anindustrial context. Procedia computer science, 148,291-302.
  4. Chauhan, S. S., Martel, A., & D’Amour, S. (2008).Rollassortment optimization in a paper mill: An integerprogramming approach. Computers & operationsresearch, 35(2), 614-627.
  5. Chen, Y., Li, K. W., & Liu, S. F. (2008, October). Acomparative study on multicriteria ABC analysis ininventory management. In 2008 IEEE InternationalConference on Systems, Man and Cybernetics.3280-3285.
  6. García, J., Crawford, B., Soto, R., Castro, C., & Paredes,F. (2018). A k-means binarization frameworkapplied to multidimensional knapsack problem.Applied Intelligence, 48(2), 357-380.
  7. García, J., Crawford, B., Soto, R., Castro, C., & Paredes,F. (2018). A k-means binarization frameworkapplied to multidimensional knapsack problem.Applied Intelligence, 48(2), 357-380.
  8. Horowitz, E., & Sahni, S. (1974). Computing partitionswith applicationsto the knapsack problem. Journalof the ACM (JACM), 21(2), 277-292.
  9. Iori, M., de Lima, V. L., Martello, S., Miyazawa, F. K., &Monaci, M. (2021). Exact solution techniques fortwo-dimensional cutting and packing. EuropeanJournal of Operational Research, 289(2), 399-415.
  10. Iori, M., de Lima, V. L., Martello, S., & Monaci, M.(2022). 2DPackLib: a two-dimensional cutting andpacking library. Optimization Letters, 16(2), 471-480.
  11. Karp, R. M. (1972). Reducibility among combinatorialproblems. InComplexity of computer computations(pp. 85-103). Springer, Boston, MA.
  12. Mehdi, M. R. A. D., Balma, A.,Gharbi, A.,Samhan, A., &ouly, M. (2021). The Two-Dimensional Strip CuttingProblem: Improved Results on Real-WorldInstances. The Eurasia Proceedings of Educationaland Social Sciences, 22, 1-10.
  13. Mostafa, N., & Eltawil, A. (2017). Solving theheterogeneous capacitated vehicle routing problemusing K-means clustering and valid inequalities. InProceedings of the international conference onindustrial engineering and operationsmanagement.
  14. Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V.,Thirion, B., Grisel, O., ... & Duchesnay, E. (2011).Scikit-learn: Machine learning in Python. theJournal of machine Learning research, 12, 2825-2830.
  15. Pentico, D.W. (2008). The assortment problem: Asurvey. European Journal of Operational Research,190(2), 295-309.
  16. Prestwich, S. D., Fajemisin, A. O., Climent, L., &O’Sullivan, B. (2015, September). Solving a hardcutting stock problem by machine learning andoptimisation. In Joint European Conference onMachine Learning and Knowledge Discovery inDatabases,Springer, Cham,335-347.
  17. Sachs, A. L. (2015). Retail analytics. Lecture Notes inEconomics and Mathematical Systems.Schrijver, A.(1998).Theory of linear and integer programming.John Wiley & Sons.
  18. Teter, S.;Craparo, E.,&Salmerón, J. (2019).Simulatedoperating concepts for wholesale inventoryoptimization at Naval Supply Systems Command.In18th International Conference on Modeling andAppliedSimulation,101-108.
  19. Vahrenkamp, R. (1996). Random search in the one-dimensional cutting stock problem. EuropeanJournal of Operational Research, 95(1), 191-200.
  20. Wäscher, G., Haußner, H., & Schumann, H. (2007). Animproved typology of cutting and packing problems.European journal of operational research, 183(3),1109-1130.