Structural integrity is a crucial aspect of engineering components, particularly in the field of additive manufacturing (AM). Surface roughness is a vital parameter that significantly influences the structural integrity of additively manufactured parts. This research work focuses on the prediction of the surface roughness of additive-manufactured polylactic acid (PLA) specimens using eight different supervised machine learning regression-based algorithms. For the first time, explainable AI techniques are employed to enhance the interpretability of the machine learning models. The nine algorithms used in this study are Support Vector Regression, Random Forest, XGBoost, AdaBoost, CatBoost, Decision Tree, the Extra Tree Regressor, the Explainable Boosting Model (EBM), and the Gradient Boosting Regressor. This study analyzes the performance of these algorithms to predict the surface roughness of PLA specimens, while also investigating the impacts of individual input parameters through explainable AI methods. The experimental results indicate that the XGBoost algorithm outperforms the other algorithms with the highest coefficient of determination value of 0.9634. This value demonstrates that the XGBoost algorithm provides the most accurate predictions for surface roughness compared with other algorithms. This study also provides a comparative analysis of the performance of all the algorithms used in this study, along with insights derived from explainable AI techniques.
31 January 2022 in Progress in Additive Manufacturing
The use of aluminum alloys, nowadays, is swiftly growing from the prerequisite of producing higher strength to weight ratio. Lightweight components are crucial interest in most manufacturing sectors, especially in transportation, aviation, maritime, automotive, and others. Traditional available joining methods have an adverse effect on joining these lightweight engineering materials, increasing needs for new environmentally friendly joining methods. Hence, friction stir welding (FSW) is introduced. Friction stir welding is a relatively new welding process that can produce high-quality weld joints with a lightweight and low joining cost with no waste. This paper endeavors to deals with optimizing process parameters for quality criteria on tensile and hardness strengths. Samples were taken from a 5 mm 6061-T6 aluminum alloy sheet with butt joint configuration. Controlled process parameters tool profile, rotational speed and transverse speed were utilized. The process parameters are optimized making use of the combination of Grey relation analysis method and L9 orthogonal array. Mechanical properties of the weld joints are examined through tensile, hardness, and liquid penetrant tests at room temperature. From this research, rotational speed and traverse speed become significant parameters at a 99% confidence interval, and the joint efficiency reached 91.3%.
5 October 2024 in Journal of Manufacturing Processes
Bioactive glasses (BAG) are one type of biomaterial that is used in dentistry and orthopedics to repair or replace damaged bone. The spray pyrolysis process is low-cost and one of the most common ways for producing porous films and films with high-density packing and particle homogeneity.