Title:
HVAC CONTROL SYSTEM WITH MODEL-DRIVEN DEEP LAYER LEARNING
Document Type and Number:
Japanese Patent JP2023162185
Kind Code:
A
Abstract:
To provide an HVAC control system with model-driven deep layer learning.SOLUTION: A method includes operating equipment to affect a variable state or a condition of a space, and determining a set of learned weights for a neural network by modeling estimated cost of operating the equipment over a plurality of simulated scenarios. Each simulated scenario includes simulated measurements relating to the space. The neural network is configured to generate simulated control dispatches for the equipment on the basis of the simulated measurements. The method also includes configuring the neural network for online control by applying the set of learned weights, applying actual measurements relating to the space to the neural network to generate a control dispatch for the equipment, and controlling the equipment in accordance with the control dispatch.SELECTED DRAWING: Figure 13
Inventors:
ROBERT D TURNEY
HENRY O MARCY V
HENRY O MARCY V
Application Number:
JP2023125392A
Publication Date:
November 08, 2023
Filing Date:
August 01, 2023
Export Citation:
Assignee:
JOHNSON CONTROLS TECH CO
International Classes:
F24F11/62; F24F11/47
Attorney, Agent or Firm:
Hidekazu Miyoshi
Hiroko Hara
Kazushi Obuchi
Hiroko Hara
Kazushi Obuchi
Previous Patent: Phosphor plate and light emitting device using it
Next Patent: Colored film and colored adhesive tape
Next Patent: Colored film and colored adhesive tape