In this paper, we introduce an efficient method for identifying fractional dynamic systems using extended sparse regression and cross-validation techniques. The former identifies equations that fit the data with varying candidate functions, while the latter determines the optimal equation with the fewest terms yet ensuring accuracy. The identified optimal equation is expected to share the same dynamic properties as the original fractional system. Unlike previous studies focusing on efficiently computing fractional terms, this strategy addresses dynamic analysis from a data perspective. Importantly, in the proposed method, we treat the fractional order as a variable to account for its impact on the dynamic properties of the identified equation. This treatment enables the identified equation to successfully capture dynamic behaviors when the fractional order changes. We validate the effectiveness of the method using three classical fractional-order systems as well as an energy harvesting system. Interestingly, we find that, although the identified equations do not contain non-local terms like the original fractional-order systems, they exhibit the same stochastic P-bifurcation phenomena. In other words, we construct an equivalent equation without memory properties, sharing the dynamic properties with the original system.