Optimization of Process Parameters for Green Composites in Abrasive Water Jet Machining Process Using Neuro-Regression Analysis

Authors : Serap TANRIVERDİ, Levent AYDIN

Pages : 71-79

View : 14 | Download : 8

Publication Date : 2021-08-30

Article Type : Research Paper

Abstract :This study aims to develop a design procedure for optimizing the abrasive water jet machining insert ignore into journalissuearticles values(AWJM); process in green composites. Multiple non-linear neuro-regression analysis has been performed methodically to overcome insufficient approaches to modeling-design-optimizing green composites in AWJM. First, the model generation process is carried out according to three criteria: linearity, order, and functions used in the model. Next, R^2_training, R^2_testing, and R^2_validation values have been checked for the validity of the models. Then, the machining parameters have been optimized by applying a numerical non-linear global optimization algorithm, Simulated Annealing. Pressure within the pumping system insert ignore into journalissuearticles values(PwPS);, stand-off distance insert ignore into journalissuearticles values(SoD);, and nozzle speed insert ignore into journalissuearticles values(NS); are design variables; surface roughness insert ignore into journalissuearticles values(Ra); and process time insert ignore into journalissuearticles values(PT); are objective functions of introduced mathematical optimization problems. The numerical result shows that the optimum process parameters obtained are PwPS insert ignore into journalissuearticles values(150 MPa);, SoD insert ignore into journalissuearticles values(3.5 mm);, and NS insert ignore into journalissuearticles values(125 mm/min);. This novel optimization approach is also feasible for another modeling design optimization problem. The proposed design can be used as a systematic framework for parameter optimization in environmentally conscious manufacturing processes.
Keywords : Abrasive water jet machining, green composite, neuro regression, optimization