By Topic

Reduced gradient computation in prediction error identification

Sign In

Full text access may be available.

To access full text, please use your member or institutional sign in.

The purchase and pricing options are temporarily unavailable. Please try again later.
1 Author(s)
Hill, S. ; Johns Hopkins University, Laurel, MD, USA

One way to design practical identification algorithms using the prediction error method is to find a computationally efficient expression for the gradient of the prediction error cost function. Here, results on adjoint equations are used to derive an efficient gradient expression which reduces the computational burden of evaluating it.

Published in:

Automatic Control, IEEE Transactions on  (Volume:30 ,  Issue: 8 )