Indoor environment model creation device
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for predicting air-conditioning loads in indoor environments require numerous parameters, including the number of people and physical properties of building materials, which are difficult to obtain accurately, and suffer from low accuracy due to reliance on CO2 concentration measurements.
Innovation Solution
An indoor environment model creation device that uses a combination of air-conditioning equipment, CO2 sensors, and humidity sensors to learn and predict indoor conditions through comprehensive physics models, including heat, moisture, and CO2 concentration parameters, without the need for setting numerous parameters.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If physics-based models are used to predict air-conditioning loads, then the physical phenomena can be accurately reconstructed, but numerous parameters including building material properties and shape are required which are difficult to obtain
Solution Approach 1:
The patent creates a virtual indoor environment model that copies and simulates the actual indoor space, allowing prediction of air-conditioning loads without physically measuring numerous building parameters. The learned model replicates the thermal behavior of the target building using data from a reference building, eliminating the need for detailed physical measurements.
Solution Approach 2:
The patent transforms the prediction approach by changing from direct physical parameter measurement to learning-based parameter inference. Instead of requiring direct measurement of building material properties and geometric parameters, the system learns equivalent parameters from operational data, effectively changing the parameter representation from physical to statistical.
2Ease of operation
If CO2 concentration measurement is used to estimate the number of people, then the parameter acquisition is simplified, but the prediction accuracy becomes low
Solution Approach 1:
The patent merges multiple data sources including CO2 concentration, humidity, air-conditioning operation data, and weather information into a comprehensive learning model. By combining these diverse parameters, the system achieves accurate prediction of the number of people and heat generation without relying solely on CO2 measurements.
Solution Approach 2:
The patent introduces a learned indoor environment model as an intermediary between sensor measurements and air-conditioning load prediction. This model translates easily obtainable sensor data into accurate predictions of thermal load by learning the complex relationships between environmental parameters and heat generation.
3Measurement precision
If multiple sensors and comprehensive physics models are used, then prediction accuracy is improved, but the system complexity and data processing requirements increase
Solution Approach 1:
The patent performs preliminary learning of the indoor environment model using historical data before actual prediction operations. This pre-learning phase establishes the relationship between sensor inputs and thermal conditions, so that during operation, only straightforward data collection and model application are needed, reducing operational complexity.
Data Source
AI summary
An indoor environment model creation device is configured to create an indoor environment model of an indoor space in which air-conditioning equipment configured to condition air, an indoor humidity sensor configured to measure an indoor humidity of the indoor space, and a CO2 sensor configured to measure a CO2 concentration in the indoor space are installed. The indoor environment model includes a plurality of physics models in which heat, moisture, and CO2 concentration parameters are included. The indoor environment model creation device includes: a data storage unit configured to store operation data of the air-conditioning equipment in a learning target period as learning-use input data, and store measurement data measured by the CO2 sensor and the humidity sensor; and a model parameter learning unit configured to comprehensively learn the plurality of physics models with use of the learning-use input data and the measurement data, which are stored in the data storage unit.