This work concerns the problem of gradually time-varying nonlinear systems parameter estimation using batch scheme recursive Hartley modulating functions (HMF) method. Clearly, most technical processes are nonlinear, continuous in time and contain time-varying parameters. The representative model and parameters for these processes need to be tracked on-line, for instance, for model-reference adaptive control, self-tuning, predictive control and for fault detection and diagnosis schemes. In this contribution, a batch scheme recursive approach for gradually time-varying parameters of nonlinear continuous-time systems identification is proposed using HMF by moving a fixed window size of time series data forward at each sampling time and by updating recursively the sequential Hartley transforms and spectra for each coming sampling-time of the I/O-signals. Illustrative simulation studies are included to examine the performance and potential of the proposed approach in the presence of output measurement disturbance.