Invention Grant
- Patent Title: Controller, method and computer program product using a neural network for adaptively controlling an environmental condition in a building
-
Application No.: US15927342Application Date: 2018-03-21
-
Publication No.: US10598401B2Publication Date: 2020-03-24
- Inventor: Dominic Gagnon
- Applicant: Distech Controls Inc.
- Applicant Address: CA Brossard
- Assignee: DISTECH CONTROLS INC.
- Current Assignee: DISTECH CONTROLS INC.
- Current Assignee Address: CA Brossard
- Agency: RatnerPrestia
- Main IPC: F24F11/63
- IPC: F24F11/63 ; G05D23/19 ; G05B13/02 ; G05B13/04 ; G06N5/04 ; G06N3/02 ; F24F110/40 ; G05B17/02 ; F24F110/10 ; F24F110/20 ; F24F130/30

Abstract:
Environmental condition controller and method for controlling an environmental condition in an area of a building. The controller stores a predictive model generated by a neural network training engine, and a previously calculated environmental condition adjustment value (yn−1). The controller receives an environmental condition target value (xref), and an environmental condition measured value (x). The controller recursively calculates an environmental condition adjustment value (yn) by executing a neural network inference engine using the predictive model for inferring the environmental condition adjustment value (yn) based on the previously calculated environmental condition adjustment value (yn−1), the environmental condition target value (xref), the environmental condition measured value (x), and an adaptive proportionality value (k). The controller also generates and transmits a command based on the environmental condition adjustment value (yn). The controller further stores the calculated environmental condition adjustment value (yn) as the previously calculated environmental condition adjustment value (yn−1).
Public/Granted literature
Information query