Online Identification of Regulator Model Based on Adaptive Forgetting Factor RLS Algorithm

In order to improve the accuracy of the time-varying system model identification of the voltage regulator and the rapidity and robustness of the on-line identification of the parameters, and to study the effect of forgetting factor on the performance of forgetting factor recursive least squares algorithm, an adaptive forgetting factor recursive least squares algorithm based on fuzzy algorithm is proposed in this paper. The average value of time series of the residual and its change rate between the dynamic characteristic value of the system and the identified model value are taken as the input of the fuzzy algorithm, and the correction of the forgetting factor is taken as the output to realize the adaptive adjustment of the forgetting factor. The simulation results of a regulator pressure reduction system of a nuclear power plant show that the algorithm can adjust the forgetting factor in real time, and effectively solve the time-varying problem of the parameters of the regulator model. Thus it can obtain a more accurate time-varying model, and can effectively solve the contradiction between the stability and the convergence speed of parameters identification results. Therefore, the algorithm is feasible and superior.