Abstract The morphological structure and dynamic characteristics of power distribution systems are rapidly evolving due to the widespread application of distributed renewable energy and the rapid advancement of power electronics technology. The stability analysis of these complex new distribution systems depends on electromagnetic transient (EMT) simulation. However, the intellectual property rights protection by manufacturers leads to many distribution network devices that can only use black-box models with missing parameters, which challenges the simulation. This reduces the accuracy of the dynamic analysis of these new distribution systems. To address this problem, this paper proposes a black-box modelling method based on neural Ordinary Differential Equation (ODE) for active distribution equipment. The method uses port measurement data to construct a data-driven model that accurately captures the black-box device characteristics, transforming the uncertainties in the user-side black-box devices into observable, controllable, and analysable models. The paper also builds an IEEE-33 node system that includes the energy storage black-box model for validation, and the results confirm the accuracy of the model.