Title:
【発明の名称】工業設備での神経回路網の作動方法および付属の神経回路網
Document Type and Number:
Japanese Patent JPH10509825
Kind Code:
A
Abstract:
A network has to be adapted to changing boundary conditions of a production process in particular when structured fuzzy neural networks are used therein. The knowledge which the network contains in each case should not be overlearned during this adaptation. According to the invention, in order to adapt the network to changing boundary conditions of the production process, the neural network used is divided into individual regions which reproduce the influence of the individual input and output variables. Each region can be subject to a partial learning process when the system is operating, i.e. is online. The associated neural network has a unit for monitoring the partial learning process (the so-called supervisor).
Inventors:
Hulmoto, Herbert
Wolf, Thomas
Wolf, Thomas
Application Number:
JP51725196A
Publication Date:
September 22, 1998
Filing Date:
December 05, 1995
Export Citation:
Assignee:
Siemens Aktiengesellschaft
International Classes:
G05B13/02; G06F15/80; G06N3/00; G06F15/18; G06N3/04; (IPC1-7): G05B13/02; G05B13/02; G06F15/18
Attorney, Agent or Firm:
Tomimura Kiyoshi