Sequence-Based Evolutionary and Neural Strategies for Reducing Zone Crossings in Toolpaths

Yasamin Aali, Ansh Shah, Mohammad Istiaq Uddin, Kazi Nishat Anwar, Sheridan Houghten, Rahnuma Islam Nishat
Proceedings of the The 39th Canadian Conference on Artificial Intelligence, PMLR 318:932-939, 2026.

Abstract

Excessive transitions between material zones in 3D printing reduce both efficiency and integrity. We introduce a hybrid optimization framework to minimize these zone cross- ings in Hamiltonian toolpaths. Our approach combines the local search capabilities of Simulated Annealing (SA) with the global exploration of a sequence-based Genetic Algo- rithm (GA). Furthermore, we propose a hybrid neural network that models the learned optimization behavior and predicts efficient sequences of operations. Experiments show thatourmethodsignificantlyreduceszonecrossingsacrossvariouscomplexpatterns, and provesitseffectivenessandscalabilityforefficientmulti-materialadditivemanufacturing.

Cite this Paper

BibTeX
@InProceedings{pmlr-v318-aali26a, title = {Sequence-Based Evolutionary and Neural Strategies for Reducing Zone Crossings in Toolpaths}, author = {Aali, Yasamin and Shah, Ansh and Uddin, Mohammad Istiaq and Anwar, Kazi Nishat and Houghten, Sheridan and Nishat, Rahnuma Islam}, booktitle = {Proceedings of the The 39th Canadian Conference on Artificial Intelligence}, pages = {932--939}, year = {2026}, editor = {Bouzar-Benlabiod, Lydia and Leung, Carson}, volume = {318}, series = {Proceedings of Machine Learning Research}, month = {25--29 May}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v318/main/assets/aali26a/aali26a.pdf}, url = {https://proceedings.mlr.press/v318/aali26a.html}, abstract = {Excessive transitions between material zones in 3D printing reduce both efficiency and integrity. We introduce a hybrid optimization framework to minimize these zone cross- ings in Hamiltonian toolpaths. Our approach combines the local search capabilities of Simulated Annealing (SA) with the global exploration of a sequence-based Genetic Algo- rithm (GA). Furthermore, we propose a hybrid neural network that models the learned optimization behavior and predicts efficient sequences of operations. Experiments show thatourmethodsignificantlyreduceszonecrossingsacrossvariouscomplexpatterns, and provesitseffectivenessandscalabilityforefficientmulti-materialadditivemanufacturing.} }
Endnote
%0 Conference Paper %T Sequence-Based Evolutionary and Neural Strategies for Reducing Zone Crossings in Toolpaths %A Yasamin Aali %A Ansh Shah %A Mohammad Istiaq Uddin %A Kazi Nishat Anwar %A Sheridan Houghten %A Rahnuma Islam Nishat %B Proceedings of the The 39th Canadian Conference on Artificial Intelligence %C Proceedings of Machine Learning Research %D 2026 %E Lydia Bouzar-Benlabiod %E Carson Leung %F pmlr-v318-aali26a %I PMLR %P 932--939 %U https://proceedings.mlr.press/v318/aali26a.html %V 318 %X Excessive transitions between material zones in 3D printing reduce both efficiency and integrity. We introduce a hybrid optimization framework to minimize these zone cross- ings in Hamiltonian toolpaths. Our approach combines the local search capabilities of Simulated Annealing (SA) with the global exploration of a sequence-based Genetic Algo- rithm (GA). Furthermore, we propose a hybrid neural network that models the learned optimization behavior and predicts efficient sequences of operations. Experiments show thatourmethodsignificantlyreduceszonecrossingsacrossvariouscomplexpatterns, and provesitseffectivenessandscalabilityforefficientmulti-materialadditivemanufacturing.
APA
Aali, Y., Shah, A., Uddin, M.I., Anwar, K.N., Houghten, S. & Nishat, R.I.. (2026). Sequence-Based Evolutionary and Neural Strategies for Reducing Zone Crossings in Toolpaths. Proceedings of the The 39th Canadian Conference on Artificial Intelligence, in Proceedings of Machine Learning Research 318:932-939 Available from https://proceedings.mlr.press/v318/aali26a.html.

Related Material