Statistical modelling and optimization of clad characteristics in laser metal deposition of austenitic stainless steel

The study aims to design and develop an integrated system to model and optimize the direct metal deposition process. Direct metal deposition is an emerging metal additive manufacturing technology, in which powder particles are melted using a high-energy laser source to consolidate a solid layer. With the aim to work with a variety of materials, process economy is an important consideration. Keeping this in mind, the present work shows application of statistical methods and evolutionary algorithms in laser-based manufacturing. A regression model using response surface method has been developed considering laser power, scan speed and powder flow rate as the process parameters, while capture efficiency and clad layer height are considered as the clad characteristics response. The developed regression model provides useful information to control responses and ensure building a desired clad layer height as per prototyping requirements. A robust correlation between the experimentally obtained values and model-predicted values for responses is achieved, and the error percentage is 5% and 10% for capture efficiency and clad layer height, respectively. Genetic algorithm-based approach for optimization yields improvement of 30.93% and 71.02% for capture efficiency and clad layer height, respectively.