This paper proposes a novel evolutionary computation (EC) algorithm, fuzzy scaled mutation evolutionary computation (FSMEC), for solving nonlinear numerical optimization problems. Although EC has been typically used for obtaining nonlinear optimal solutions for several years, users are required to determine the parameters of the algorithm. In this study, a fuzzy inference system (FIS) was used to determine the mutation factor of the FSMEC algorithm according to the change in the solution and the distance between the whole best and each individual. The experimental results revealed that the FIS operates effectively. CEC2013 numerical optimization problems without rotation and shift were used as test functions. The FSMEC algorithm determined optimal solutions in 10, 30, and 50 dimensions for all unimodal functions. The convergence generations were less than 100 in 10 dimensions. The FSMEC algorithm obtains 16, 11, and 10 optimal values for 28 functions in 10, 30, and 50 dimensions, respectively. Moreover, statistical hypothesis tests demonstrated that the performance of the FSMEC algorithm in deriving optimal solutions was 68 %, which was higher than those of the FADE and SMEC algorithms for 28 test functions.