Air conditioning system, and machine learning method

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Optimizing the transfer of heat quantity in air conditioning systems is challenging due to varying operation conditions and loads, requiring extensive data collection and model building for each device combination, leading to high workload and inefficiency.

Innovation Solution

A machine learning method using reinforcement learning to optimize the transfer of heat quantity by learning from operation conditions, load data, and power consumption, associating state variables with target values for temperature and flowrate of the thermal medium, thereby reducing power consumption.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of energy

If simulation-based optimization is used to optimize heat quantity transfer, then energy consumption can be reduced, but extensive data collection and model building for each device combination is required, leading to high workload

Engineering Contradiction:
Improveenergy consumptionVSAvoidworkload
Core Design Contradiction:
Loss of energyVSDevice complexity

Solution Approach 1:

The system uses reinforcement learning to enable the air conditioning system to automatically optimize its own heat quantity transfer parameters. The learning apparatus autonomously learns optimal control strategies through interaction with the system, eliminating the need for manual simulation and model building for each device combination, thus reducing workload while maintaining energy optimization capabilities

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The invention changes the approach from static simulation-based optimization to dynamic reinforcement learning-based optimization. The system continuously adapts parameters such as thermal medium flowrate and temperature based on real-time operation conditions and load variations, allowing energy optimization without requiring extensive pre-collected data for each device combination

Inventive Principle:
Principle #35Parameter changes

2Loss of energy

If simulation-based optimization is used to optimize heat quantity transfer, then energy consumption can be reduced, but extensive data collection and model building for each device combination is required, leading to inefficiency

Engineering Contradiction:
Improveenergy consumptionVSAvoidefficiency
Core Design Contradiction:
Loss of energyVSProductivity

Solution Approach 1:

The reinforcement learning apparatus enables the system to autonomously optimize heat quantity transfer in real-time through continuous learning and adaptation. This self-service capability eliminates the inefficiency of manual simulation and model building, allowing the system to rapidly adapt to changing conditions while maintaining energy optimization

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The invention transitions from static simulation models to dynamic reinforcement learning that continuously adapts to changing operation conditions and load variations. The system dynamically adjusts thermal medium flowrate and temperature based on real-time feedback, improving both energy efficiency and system responsiveness without requiring extensive pre-collection of data for each device combination

Inventive Principle:
Principle #15Dynamics

Data Source

PatentEP3961114B1Air conditioning system, and machine learning method
Publication Date: 2024.01.03 DAIKIN INDUSTRIES LTD
  • EP3961114B1 patent drawingFigure 1
  • EP3961114B1 patent drawingFigure 2
  • EP3961114B1 patent drawingFigure 3

AI summary

A machine learning apparatus for optimizing transfer of heat quantity is provided. A machine learning apparatus for learning at least one of a temperature and a flowrate at which a thermal transfer apparatus transfers a thermal medium in an air conditioning system including a device on a heat-providing side, a device on a heat-using side, and the thermal transfer apparatus configured to transfer the thermal medium from the device on the heat-providing side to the device on the heat-using side, the machine learning apparatus including: a state variable obtaining unit configured to obtain state variables including an operation condition of the device on the heat-providing side, an operation condition of the device on the heat-using side, and a value correlated with a heat quantity required by the device on the heat-using side; a learning unit configured to perform learning by associating the state variables with the at least one of the temperature and the flowrate; and a reward calculating unit configured to calculate a reward, based on a total value of a power consumption of the device on the heat-providing side, a power consumption of the device on the heat-using side, and a power consumption of the thermal transfer apparatus, wherein the learning unit performs learning by using the reward.