Expert system for prediction of changes to local environment

• US 9,406,028 B2
• Filed: 03/12/2013
• Issued: 08/02/2016
• Est. Priority Date: 08/31/2012
• Status: Active Grant

• Current Assignee: Halio Incorporated
• Original Assignee: Christian Humann
• Inventors: Humann, Christian
• Primary Examiner(s): Starks, Wilbert L
• Application Number:
  US13/798,050
• Publication Number:
  US 20140067733A1
• Time in Patent Office: 1,239 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: F24F 11/30 for purposes related to the operation of the system, e.g. for safety or monitoring
• CPC Class Codes: F24F 11/46 Improving electric energy efficiency or saving
• CPC Class Codes: F24F 11/62 characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
• CPC Class Codes: F24F 11/63 Electronic processing
• CPC Class Codes: F24F 11/65 for selecting an operating mode
• CPC Class Codes: F24F 2110/00 Control inputs relating to air properties
• CPC Class Codes: F24F 2130/00 Control inputs relating to environmental factors not covered by group F24F2110/00
• CPC Class Codes: F24F 2130/10 Weather information or forecasts
• CPC Class Codes: F24F 2130/20 Sunlight
• CPC Class Codes: G05B 13/02 electric
• CPC Class Codes: G05B 13/028 using expert systems only
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06N 5/046 Forward inferencing; Production systems

Abstract

Disclosed is a photometer that employs high dynamic range (HDR) image processing and manipulation algorithms for capturing and measuring real-time sky conditions for processing into control input signals to a building'"'"'s automated fenestration (AF) system, daylight harvesting (DH) system and HVAC system. The photometer comprises a color camera and a fitted fish-eye lens to capture 360-degree, hemispherical, low dynamic range (LDR) color images of the sky. Both camera and lens are housed in a sealed enclosure protecting them from environmental elements and conditions. In some embodiments the camera and processes are controlled and implemented by a back-end computer.

Claims

1. An apparatus comprising:

an HDR (high dynamic range) capturer configured to obtain an image of a local environment;

a mapper processing said image and extracting a plurality of metrics and performance data of said local environment; and

an expert learning system, responsive to said plurality of metrics and performance data generating a near real-time prediction of a local change in said local environment and initiating a change in a local-environment-influencing system to counter said local change.

2. The apparatus of claim 1 wherein said local environment includes a sky view from a building exterior, said sky view including a near real-time characterization of a sun, a sun location, and a path of said sun in said sky view, and a position, a velocity, an acceleration, and an opacity of a sun-occluding object that influences said near real-time prediction by said expert system.

3. The apparatus of claim 2 wherein said sun-occluding object includes a cloud disposed in said sky view along said path of said sun.

4. The apparatus of claim 2 wherein said HDR capturer includes an HDR photometer.

5. The apparatus of claim 4 wherein said HDR photometer includes a camera configured to capture a plurality of sequences of low dynamic range (LDR) color images, each image of a particular sequence having one of a different aperture or a different shutter speed as compared to other images of said particular sequence, said camera capturing said sequence of images through a field of view accessed by a fish-eye lens of said camera, said field-of-view configured to provide a 360-degree azimuthal view and a 180-degree or more horizon-to-horizon view of said sky view.

6. The apparatus of claim 5 wherein each said sequence includes five LDR color images and each said sequence is captured approximately every two minutes.

7. A computer-implemented method, comprising:

a) producing an HDR (high dynamic range) image for a local environment;

b) extracting, using a computing system, a plurality of metrics and performance data of said local environment from said HDR image; and

c) predicting, using said computing system, a predicted local change in said local environment responsive to said plurality of metrics and performance data of said local environment from said HDR image, wherein said predicted local change is in advance of an actual local change in said local environment wherein said steps a)-c) are included in a control system for a building, wherein said building includes an automated climate control responsive to said control system, and wherein said predicted local change is processed into control signals for said control system which operates said automated climate control to reduce a magnitude of said actual local change or a rate of change of said actual local change.

8. The computer-implemented method of claim 7 wherein said automated climate control includes an automated fenestration system for one or more portals of said building.

9. The computer-implemented method of claim 7 wherein said automated climate control includes a heating, ventilation, and air conditioning (HVAC) system for one or more occupancy zones within said building.

10. The computer-implemented method of claim 7 wherein said automated climate control includes a daylight harvesting system for one or more occupancy zones within said building.

11. A computer-implemented method, comprising:

a) producing an HDR (high dynamic range) image for a local environment;

b) extracting, using a computing system, a plurality of metrics and performance data of said local environment from said HDR image; and

c) predicting, using said computing system, a predicted local change in said local environment responsive to said plurality of metrics and performance data of said local environment from said HDR image, wherein said predicted local change is in advance of an actual local change in said local environment wherein said steps a)-c) are included in a distributed meteorological system having a plurality of data gathering locations distributed over a geographical region having a plurality of microclimates greater in number than a number of said data gathering locations, wherein each said data gathering location performs steps a)-c), and wherein a statistical processing of said predicted local changes for one or more of said microclimates.

12. A computer-implemented method, comprising:

a) producing an HDR (high dynamic range) image for a local environment;

b) extracting, using a computing system, a plurality of metrics and performance data of said local environment from said HDR image; and

c) predicting, using said computing system, a predicted local change in said local environment responsive to said plurality of metrics and performance data of said local environment from said HDR image, wherein said predicted local change is in advance of an actual local change in said local environment wherein said steps a)-c) produce a predicted local change for a first building connected to a power grid operated by a utility company, wherein said predicted local change for said first building is accompanied by a change in an energy demand by said first building through said power grid wherein said change in said energy demand determines whether said utility changes an energy production for said power grid, and wherein said predicted local change is provided to said utility allowing said utility to modify said energy production consistent with said actual local change.