The current study performed modeling, analysis, and optimization of electrical discharge machining (EDM) under nano graphene mixed dielectric machining of Inconel 718 using ANFIS and a newly developed multi-objective seagull optimization algorithm. The influence of three major EDM controlling parametersnamely peak current (Ip), pulse on time (Ton), and pulse off time (Toff) have been studied on the output machining characteristics viz. material removal rate (MRR) and cylindricity (CY) deviation for each of the experiments. In this work, EDM performance was enhanced by dispersing nano-graphene powder into EDM Oil as a dielectric medium and improvement from conventional EDM was analysed. The Taguchi L27 orthogonal array was utilized for planning and conducting EDM experiments, while analysis of variance (ANOVA) testsand regression analysis were conducted for examining the influence of input process variables on machining response variables. From results, it was realized that nano graphene mixed dielectric EDM improved the machining performance in comparison to traditional EDM performance. The modeling of response variables in terms of input process variables and optimal process conditions were determined using efficient intelligent methods namely ANFIS model and the newly developed multi-objective seagull optimization algorithm (MOSOA), respectively. It was found that nanographene mixed EDM improved MRR and cylindricity deviation by 13.88% and 25.76% respectively in comparison to conventional EDM without nanographene mixed dielectric. The MOSOA algorithm provides a number of non-dominated pareto solutions and best machining conditions among 32 optimal sets for nanographene mixed EDM was selected as a pulse on time of 12 μs, pulse off time as 7 μs, and peak current at 9 A. Finally, the scanning electron microscopy image also shows the improvement in surface finish of nano graphene mixed dielectric EDM in comparison to traditional EDM.