Fri, 12 April, 2024
We are happy to announce the publication of our recent research article from the FORGE project, ‘Machine Learning-Based Predictions of Porosity during Cold Spray Deposition of High Entropy Alloy Coatings’; led by Dr Deepak Sharma, Research Associate at Materials Innovation Centre, University of Leicester.
This work presents a machine learning-based approach to predict porosity based on the feedstock powder characteristics and the cold spray process parameters. The work also presents the hierarchical impact of the above-mentioned parameters on the formation of porosity. The paper is co-authored by Dr Dibakor Boruah from TWI, and Ali Alperen Bakir, Ahamed Ameen, and Dr Shiladitya Paul from the University of Leicester.
Cold spray is a solid-state materials deposition process that has attracted attention due to its relatively low operating temperatures. In the process of deposition, porosity may form due to geometrical effects at the particle/particle interfaces, called interface porosities, and due to variations in the number density of particles in the gas flow, called stack porosities. These porosities are detrimental to the mechanical properties and corrosion mitigation behaviour of the deposited coating. The formation of porosity is affected by powder characteristics (powder morphology and size), and CS process parameters (gas temperature, gas pressure, stand-off distance, etc.). Hence, we used nine different machine learning models based on linear regression (LR), decision trees (DT), random forests (RF), gradient boosting (GBOOST), support vector machine (SVM), and neural networks (ANN) to predict the formation of porosity based on the above-mentioned input parameters. Considering the excellent properties of high entropy alloys, Cantor alloy was taken as the consumable.
Our dataset, derived from the literature and experiments, identified SVM with a linear kernel and LR as the top-performing models based on the Pearson correlation coefficient (PCC) and root mean square error, where the PCC values exceeded 0.8 (Figure 1). The SHapley Additive exPlanations (SHAP; Figure 2) method helped in identifying that the type of gas and powder morphology are the top two factors in pore formation.
You can see the paper, in full, here.
Figure 1. The Pearson correlation coefficient (PCC), mean absolute error (MAE), and root mean square error (RMSE) values for all the employed ML models: LR, DT, RF, GBOOST, XGBOOST, SVR_lin, SVR_poly, SVR_rbf, and ANN.
Figure 2. The figure showcases the hierarchical importance of the input features obtained from the SHAP method for the top five models: LR, DT, RF, XGBOOST, and SVR_lin. The hierarchical importance indicates which factor contributes the most to the formation of porosity during cold spray deposition of the Cantor alloy. Here, 'G' refers to gas type (He or N2), 'Pdr' refers to powder morphology, 'D' stands for stand-off distance, 'P' represents process gas pressure, and 'T' denotes process gas temperature.
The FORGE project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No. 958457.