Physics-Informed Machine Learning for Specific Cutting Energy in Abrasive Waterjet Cutting: A Simulation-Based Feasibility and Sustainable Process-Planning Study

Main Article Content

Ketan D. Panchal

Abstract

Background: Abrasive waterjet (AWJ) cutting combines erosion-based material removal with substantial hydraulic and electrical energy demands. Physics-informed learning could potentially improve data efficiency, but this proposition needs careful evaluation before experimental claims are made. Objective: This simulation-based methodological study examines a physics-guided modelling framework for abrasive specific cutting energy, material removal rate (MRR) and kerf taper in 6-mm austenitic stainless-steel cutting. Methods: A proposed 44-setting design comprises 30 face-centred central composite design (CCD) settings for fitting and 14 interior Latin-hypercube settings for testing. Analytical abrasive power is coupled with neural-network prediction through feature, residual and energy-balance formulations and compared with response-surface regression (RSM), a conventional artificial neural network, Gaussian process regression and gradient boosting. Results: In the supplied simulation, residual physics-informed learning (PIML-R) achieved a test MAPE of 2.84% (R² = 0.979) for abrasive specific energy, compared with 2.99% (R² = 0.978) for quadratic RSM and 3.26% (R² = 0.970) for the conventional ANN. Confidence intervals overlapped. A simulated process-planning example indicated approximately 12% lower modelled electricity demand per 100-mm cut relative to a centre-point setting; this estimate depends on assumed pump efficiency and grid-emission intensity. Conclusion: The computational example illustrates a feasible workflow, not experimentally demonstrated superiority or energy savings. Measured AWJ cutting data and independently verified power consumption are required before engineering deployment.

Article Details

How to Cite
Ketan D. Panchal. (2026). Physics-Informed Machine Learning for Specific Cutting Energy in Abrasive Waterjet Cutting: A Simulation-Based Feasibility and Sustainable Process-Planning Study. International Journal of Advanced Research and Multidisciplinary Trends (IJARMT), 3(04), 353–360. Retrieved from https://ijarmt.com/index.php/j/article/view/1415
Section
Articles

References

Chithirai Pon Selvan, M., et al. 2020. A mathematical modelling of abrasive waterjet machining on Ti–6Al–4V using artificial neural network. Materials Today: Proceedings. doi:10.1016/j.matpr.2019.12.215

Finnie, I. 1960. Erosion of surfaces by solid particles. Wear 3(2): 87–103.

Hashish, M. 1989. A model for abrasive waterjet (AWJ) machining. Journal of Engineering

Materials and Technology 111(2): 154–162.

Himmelreich, U. 1992. Fluiddynamische Modelluntersuchungen an Wasserabrasivstrahlen. VDI-Fortschritt-Berichte, Reihe 7, Nr. 219.

Janković, P. L., Madić, M. J., Petković, D. L., and Radovanović, M. R. 2018. Analysis and modeling of the effects of process parameters on specific cutting energy in abrasive water jet cutting. Thermal Science 22: S1459–S1470.

Nambiath, P., Galecki, G., and Summers, D. A. 2007. Energy based modelling of abrasive slurry jet. WJTA American Waterjet Conference, Houston.

Narayanan, C., Balz, R., Weiss, D. A., and Heiniger, K. C. 2013. Modelling of abrasive particle energy in water jet machining. Journal of Materials Processing Technology 213(12): 2201–2210.

Panchal, K. D., and Shaikh, A. H. 2021. Performance analysis and process parameters optimisation on specific cutting energy in the abrasive waterjet cutting. International Journal of Ambient Energy. doi:10.1080/01430750.2021.1873851

Panchal, K. D., and Shaikh, A. H. 2022. Depth of penetration model in AWJ cutting process considering the effect of frictional drag of kerf wall on the water-jet velocity. Smart and Sustainable Manufacturing Systems 6(1): 1–10. doi:10.1520/SSMS20210018

Shukla, M., and Tambe, P. B. 2010. Predictive modelling of surface roughness and kerf widths in abrasive water jet cutting of Kevlar composites using neural network. International Journal of Machining and Machinability of Materials 8(1–2): 226–246.

Srinath Reddy, N., Tirumala, D., Gajjela, R., and Das, R. 2018. ANN and RSM approach for modelling and multi objective optimization of abrasive water jet machining process. Decision Science Letters 7(4): 535–548.

Uhlmann, E., and Männel, C. 2019. Modelling of the kerf formation through primary and secondary jet energy for the abrasive waterjet. WJTA American Waterjet Conference.

Wang, J. 2007. Predictive depth of jet penetration model for abrasive water jet cutting of alumina ceramics. International Journal of Mechanical Sciences 49(3): 306–316.

Zhang, P., and Nambiath, S. 2005. Accurate hole drilling using an abrasive water jet in titanium. WJTA American Waterjet Conference, Houston