An adaptive recursive filter for autoregressive inputs

✍ Scribed by R. López-Valcarce; F. Pérez-González

• Publisher: John Wiley and Sons
• Year: 1998
• Tongue: English
• Weight: 261 KB
• Volume: 12
• Category: Article
• ISSN: 0890-6327
• DOI: 10.1002/(sici)1099-1115(199809)12:6<467::aid-acs506>3.0.co;2-z

✦ Synopsis

A novel o -line procedure for IIR system identiÿcation problems has been recently proposed and analysed under the assumption of a white input signal. The method happens to have a single, unbiased stationary point under this condition. This approach is based in interpolation theory and tries to overcome the drawbacks of equation-and output-error strategies. Here it is shown that the unicity of the stationary point is still preserved for a wider class of input signals, namely autoregressive processes of a certain order. With coloured input signals, an SPR condition arises for the convergence of the original on-line algorithm. A modiÿcation is proposed that eliminates this SPR condition, while leaving the stationary point untouched. Two di erent structures that implement the on-line algorithm are presented; the use of a lattice structure for the implementation of the recursive part of the ÿlter is considered as well.