Hybrid mechanism and data driven approach for high-precision modeling of gas flow regulation systems of VFDR

The variable flow ducted rocket (VFDR) poses significant challenges for high-precision modeling due to its complex nonlinear dynamics, harsh operational conditions, and integration of multiple physical fields. To address this challenge, this paper introduces a hybrid mechanism and data-driven modeling approach. Initially, the parameter perturbation method was employed to elucidate the interdependencies between system parameters and the VFDR's dynamic and steady-state responses. Entropy weight method (EWM) and technique for order preference by similarity to ideal solution (TOPSIS) were utilized for ranking the compensation parameters of the dynamic-state and steady-state models of the VFDR. Additionally, the throat area of the regulation valve was chosen as a compensatory parameter for the steady-state model. A data-driven residual compensation model was developed using the nonlinear autoregressive neural networks with external inputs (NARX) algorithm to enhance the steady-state mechanistic VFDR model, addressing its time-varying and high uncertainty characteristics. To mitigate dynamic response errors in the mechanistic model, a compensation strategy integrating error and similarity evolution with extreme learning machine (ELM) was implemented to generate compensation value. Simulation and ground experiment results validate the efficacy of the proposed algorithm, the experimental results indicate that, after compensation using the proposed strategy, the maximum error in a single test is reduced by 24.19%, and the average error is decreased by 17.81%.