A multi-innovation stochastic gradient parameter estimation algorithm for controlled autoregressive ARMA systems based on the data filtering

This paper decomposes a controlled autoregressive autoregressive moving average (CARARMA) system into two subsystems, uses the data filtering technique to drive a multi-innovation stochastic gradient algorithm for identifying the parameters of each subsystems. The basic idea is to replace the unknown variables in the information vectors with their corresponding estimates. The simulation example shows that the proposed algorithms can work well.