The design configuration of the nozzle has a vital role in the performance measures of the machining processes. However, parameter optimizations are primary considerations of published works. This study optimizes nozzle design parameters to minimize environmental impacts and enhance the surface quality for the diamond burnishing (DB) operation. The performance measures considered are energy efficiency (ED), noise emission (NE), and the total height of profile roughness (Rt). The variables are the inner diameter (D), spraying distance (S), and pitch angle (P). The optimal Taguchi-based Bayesian regularized feed-forward neural network (TBRFFNN) was applied to propose performance models. The CRITIC approach is utilized to compute the weight values of responses, while the desirability approach (DA) is employed to select optimality. The observed results of the D, S, and P were 3.0 mm, 15 mm, and 45 deg., respectively. The ED was enhanced by 12.7%, while the RT and NE were decreased by 24.4% and 9.1%, respectively, as compared to the original design parameters. The obtained outcomes could be utilized in the practice to boost technical characteristics. The developed optimizing approach could be employed to deal with optimization problems for different machining processes