Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
MODEL PREDICTION CONTROL DEVICE, MODEL PREDICTION CONTROL PROGRAM, MODEL PREDICTION CONTROL SYSTEM, AND MODEL PREDICTION CONTROL METHOD
Document Type and Number:
WIPO Patent Application WO/2020/202316
Kind Code:
A1
Abstract:
An operation path generation unit (210) generates an operation amount time series for an actuator (111) on the basis of a measured state quantity output from a state sensor (101). A prediction model unit (220) calculates a prediction model using the measured state quantity and the operation amount time series as inputs and thereby generates a predicted state quantity time series. A neural network unit (230) calculates a neural network using a measured environmental quantity output from an environmental sensor (102) and the predicted state quantity time series as inputs and thereby corrects the predicted state quantity time series. A state quantity evaluation unit (240) generates an evaluation result of the corrected state quantity time series. If the evaluation result satisfies appropriate criteria, the operation path generation unit outputs the first operation amount of the operation amount time series to the actuator.

Inventors:
SEGAWA HIDEKAZU (JP)
SETTSU ATSUSHI (JP)
TOYAMA MASAKATSU (JP)
KONAKA HIROKI (JP)
Application Number:
PCT/JP2019/014180
Publication Date:
October 08, 2020
Filing Date:
March 29, 2019
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
MITSUBISHI ELECTRIC CORP (JP)
International Classes:
G05B13/04; G05B13/02; G05D1/02; G06N3/08
Foreign References:
US20170139423A12017-05-18
JPH09504129A1997-04-22
JP2005044337A2005-02-17
JPH08211903A1996-08-20
JP2002157003A2002-05-31
CN107561942A2018-01-09
CN104238366A2014-12-24
JP2000099107A2000-04-07
Other References:
SHINDO, TOMONORI ET AL.: "Deep Learning for Control Engineering", APPLIED BY HITACHI TO MODEL PREDICTION CONTROL, 10 August 2017 (2017-08-10), Tokyo, pages 5 - 9, ISSN: 2189-5783
Attorney, Agent or Firm:
MIZOI INTERNATIONAL PATENT FIRM (JP)
Download PDF: