Machine-learning method for conditioning individual or shared areas

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current HVAC systems for maintaining thermal comfort in indoor locations are inefficient and costly, relying on manual controls and basic temperature sensors, which fail to accurately adjust to the comfort needs of occupants, leading to high energy consumption.

Innovation Solution

A computer-implemented method and system that retrieves environmental and outdoor conditions, calculates thermal comfort using user-specific data and feedback, and adjusts HVAC operations based on predicted mean vote and user satisfaction, incorporating machine-learning techniques and thermal profiling to optimize energy use.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If HVAC systems are manually controlled or controlled by basic temperature sensors, then the system operation is simple, but the thermal comfort accuracy and energy efficiency deteriorate

Engineering Contradiction:
Improvethermal comfort accuracyVSAvoidcontrol system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent implements feedback mechanisms by collecting user comfort feedback and environmental sensor data, then using this information to continuously adjust HVAC operations. The system monitors thermal comfort conditions and uses this feedback to optimize heating and cooling operations, improving accuracy while managing complexity through automated control loops.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The patent replaces manual mechanical control systems with automated computer-implemented control systems that use algorithms to calculate thermal comfort and control HVAC operations. This substitution of mechanical/manual systems with automated computational systems improves measurement precision and control accuracy.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If HVAC systems operate continuously to maintain thermal comfort, then user comfort is improved, but energy consumption increases

Engineering Contradiction:
Improvethermal comfort maintenanceVSAvoidenergy consumption
Core Design Contradiction:
ReliabilityVSUse of energy by moving object

Solution Approach 1:

The patent applies partial action by adjusting HVAC operations based on actual thermal comfort needs rather than continuous full-capacity operation. The system calculates the precise heating or cooling required to achieve thermal comfort, avoiding excessive energy consumption while maintaining reliability through on-demand adjustments.

Inventive Principle:
Principle #16Partial or excessive action

Solution Approach 2:

The patent changes operational parameters dynamically by adjusting temperature setpoints, airflow rates, and equipment operation schedules based on calculated thermal comfort conditions. This allows the system to maintain thermal comfort reliability while optimizing energy consumption through parameter optimization rather than continuous full-operation.

Inventive Principle:
Principle #35Parameter changes

3Adaptability or versatility

If basic temperature sensing is used for HVAC control, then the system complexity is low, but the adaptability to individual user comfort needs deteriorates

Engineering Contradiction:
Improveuser-specific comfort adaptationVSAvoidsystem complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent segments the control system into multiple independent components: environmental sensing, user feedback collection, thermal comfort calculation, and HVAC control. This segmentation allows the system to achieve high adaptability to individual user needs while managing complexity through modular, independent functional blocks that can operate and be adjusted separately.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP3769014B1Machine-learning method for conditioning individual or shared areas
Publication Date: 2023.08.16 CARRIER CORP
  • EP3769014B1 patent drawingFigure 1
  • EP3769014B1 patent drawingFigure 2
  • EP3769014B1 patent drawingFigure 3

AI summary

A method and system for conditioning an interior area is disclosed. A method includes retrieving environmental conditions regarding the interior area, wherein the environmental conditions include temperature, humidity, and air speed; retrieving outdoor environmental conditions; generating a field of environmental conditions at a plurality of points within the interior area; estimating clothing insulation of a user based on the outdoor environmental conditions; calculating a thermal comfort of the user to determine a predicted mean vote; and operating a heating, ventilation, and air conditioning system based on the calculated thermal comfort.