Patent · US Expired

Learning process for a neural network

US6745169B1 · kind B1 · utility

10Cited by

11References

13Claims

0Family size

Assignee

Siemens Aktiengesellschaft · DE

Inventors

Martin Schlang · Munich, DE
Frank-Oliver Malisch · Neubiberg, DE
Einar Broese · Erlangen, DE
Otto Gramckow · Uttenreuth, DE

Key dates

Filing date	Jul 26, 1996
Grant date	Jun 1, 2004
Priority date	—
Expiry date	Aug 5, 2016

Classification

Technology area (CPC B)Performing Operations; Transporting
CPC primaryB21B2265/12
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

A learning process for a neural network for open-loop or closed-loop control of an industrial process with time-variable parameters. The neural network is configured either as an open-loop or closed-loop-control network with which the process is controlled. The neural network is trained with the current process data so that it builds a model of the current process. The neural network can also be configured as a background network which is trained during operation with representative process data so that it builds an averaged model of the process over a longer period of time. After a certain learning time or upon the occurrence of an external event, the open-loop or closed-control network is replaced by the background network.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.