Metal additive manufacturing (AM), particularly Laser Powder Bed Fusion (LPBF), has emerged as a promising technology for rapidly producing intricate parts while minimizing material waste. However, the widespread adoption of AM has been hindered by the lack of adequate quality control measures. To address this challenge, a large number of machine learning (ML) applications have been proposed to improve the quality and productivity of AM processes. This study proposes the Lean concept as a guiding framework for classifying ML applications according to the Lean principles they support. Through a comprehensive review of literature studies, the research demonstrates the efficacy of this holistic approach, emphasizing ML's contributions to the Lean principles and the derived benefits to refine metal AM practices, improve efficiency, foster continuous improvement in LPBF, and finally bring value to the customer. The obtained results are particularly important for manufacturing engineers, quality control specialists, and decision-makers in the AM industry, as they provide actionable insights for enhancing process reliability, reducing waste, and achieving higher productivity.
1 October 2021 in The International Journal of Advanced Manufacturing Technology
This research focuses on analyzing the impact of longitudinal and cross feed on the grinding quality, with particular emphasis on the parameters of surface roughness and flatness of the machined surfaces. The main objective is to examine how different combinations of these parameters affect the surface roughness and flatness. The experimental study is conducted using a surface grinding machine, where roughness (Ra) and flatness are measured under various longitudinal and cross feed settings. A full-factorial experimental design is implemented to systematically analyze the interaction between these factors. Statistical methods, including regression analysis, are used to determine the significance of the variables and their effect on surface characteristics. The results indicate that both longitudinal and cross feed affect the roughness and flatness of the machined surfaces. These findings highlight the need to optimize process parameters to balance surface roughness and flatness for improved machining performance. The insights gained from this research provide valuable guidelines for optimizing grinding operations in industrial applications, ultimately enhancing efficiency and product quality.
Engineering polymers like PMMA have increasingly replaced traditional materials where feasible, with CO 2 laser cutting gaining attention for its high quality and speed in processing these materials. Precise cuts are essential for product accuracy, with kerf width being a key quality attribute for ensuring the final product's quality. This study focuses on the impact of three process variables: stand-off distance, laser power, and cutting speed, on the kerf width in CO 2 laser cutting of PMMA. A full-factorial experiment systematically varies process parameters to understand their individual and interaction effects on the cutting process. The kerf width is measured as an indicator of precision to evaluate the quality of the laser cuts. In order to address the non-linear relationships between these process parameters and kerf width, several machine learning models were utilized. Performance comparisons indicated that the Artificial Neural Network (ANN) model provided the highest accuracy, with R² values of 0.98 for the validation dataset and 0.95 for the testing dataset. The optimized ANN model is a robust tool for parameter optimization, determining optimal settings to achieve the desired kerf width and ensure productivity.