Advanced

On the Maximum Likelihood Method of Identification

Bohlin, Torsten (1970) In IBM Journal of Research and Development 14(1). p.41-51
Abstract
The maximum likelihood principle of estimation applied to the linear black-box identification problem gives models with theoretically attractive properties. Also, the method has been applied to industrial data (various processes in paper production) and proved able to work in practice.

This paper presents further developments of the method in the case of a single output. The reliability and speed of the identification algorithm have been improved, and the method has been made easier to use. A rather sophisticated computer program, however, was needed. It employs a generalized model structure, an improved hill-climbing algorithm, and an automatic procedure for determining model orders and transport delays. Some statistics from... (More)
The maximum likelihood principle of estimation applied to the linear black-box identification problem gives models with theoretically attractive properties. Also, the method has been applied to industrial data (various processes in paper production) and proved able to work in practice.

This paper presents further developments of the method in the case of a single output. The reliability and speed of the identification algorithm have been improved, and the method has been made easier to use. A rather sophisticated computer program, however, was needed. It employs a generalized model structure, an improved hill-climbing algorithm, and an automatic procedure for determining model orders and transport delays. Some statistics from performance tests of the program are presented.
(Less)
Please use this url to cite or link to this publication:
author
publishing date
type
Contribution to journal
publication status
published
subject
in
IBM Journal of Research and Development
volume
14
issue
1
pages
41 - 51
publisher
IBM Corp
external identifiers
  • scopus:0014705263
ISSN
0018-8646
DOI
10.1147/rd.141.0041
language
English
LU publication?
no
id
25728f25-e3ed-485f-8894-df24f46b6574
date added to LUP
2018-12-16 14:43:13
date last changed
2019-07-07 05:04:38
@article{25728f25-e3ed-485f-8894-df24f46b6574,
  abstract     = {The maximum likelihood principle of estimation applied to the linear black-box identification problem gives models with theoretically attractive properties. Also, the method has been applied to industrial data (various processes in paper production) and proved able to work in practice.<br/><br/>This paper presents further developments of the method in the case of a single output. The reliability and speed of the identification algorithm have been improved, and the method has been made easier to use. A rather sophisticated computer program, however, was needed. It employs a generalized model structure, an improved hill-climbing algorithm, and an automatic procedure for determining model orders and transport delays. Some statistics from performance tests of the program are presented.<br/>},
  author       = {Bohlin, Torsten},
  issn         = {0018-8646},
  language     = {eng},
  number       = {1},
  pages        = {41--51},
  publisher    = {IBM Corp},
  series       = {IBM Journal of Research and Development},
  title        = {On the Maximum Likelihood Method of Identification},
  url          = {http://dx.doi.org/10.1147/rd.141.0041},
  volume       = {14},
  year         = {1970},
}