Carbon dioxide concentration prediction system, carbon dioxide concentration prediction method, and computer readable medium
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current carbon dioxide concentration prediction systems in power generation equipment lack effective methods to accurately predict and manage CO2 levels, especially in enclosed spaces where infectious agents like SARS-CoV-2 may be present, leading to potential health risks and inefficient ventilation strategies.
Innovation Solution
A carbon dioxide concentration prediction system that includes a CO2 sensor, image capturing unit, LIDAR, and audio acquisition unit, coupled with a prediction unit and provision unit, which uses environmental information and machine learning models to predict CO2 concentrations and provide real-time alerts and ventilation recommendations to maintain safe levels and reduce infection risks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If CO2 sensing devices are arranged in power generation equipment, then CO2 concentration can be detected, but the prediction accuracy and real-time monitoring capability are insufficient
Solution Approach 1:
The system performs preliminary actions by collecting environmental information (temperature, humidity, atmospheric pressure) and motion information in advance, then uses machine learning models to predict future CO2 concentrations before actual changes occur. This allows the system to proactively alert users about potential CO2 accumulation rather than merely reacting to current levels.
Solution Approach 2:
The system implements feedback mechanisms by continuously monitoring CO2 concentrations, comparing predicted values with actual sensor readings, and using this feedback to refine predictions and provide real-time alerts. The provision unit delivers feedback to users about ventilation needs based on the correlation between CO2 levels and infectious agent presence.
2Object-affected harmful factors
If ventilation is increased to maintain low CO2 levels, then air quality improves and infection risk reduces, but ventilation costs increase
Solution Approach 1:
The system changes parameters by using machine learning models to predict CO2 concentration trends based on environmental conditions (temperature, humidity, pressure) and motion information. This allows dynamic adjustment of ventilation strategies - increasing ventilation only when predictions indicate CO2 levels will rise to harmful thresholds, rather than maintaining constant high ventilation rates.
Solution Approach 2:
The system provides self-service by automatically analyzing environmental data, predicting CO2 concentrations, and generating ventilation recommendations without requiring manual intervention. The provision unit autonomously communicates prediction results and ventilation advice to users, enabling them to make informed decisions about air quality management.
3Measurement precision
If multiple sensing devices are deployed to improve monitoring coverage, then detection capability increases, but device complexity and cost increase
Solution Approach 1:
The system achieves universality by using a single CO2 sensing device that integrates multiple detection capabilities through machine learning. Instead of deploying multiple specialized sensors, the system processes environmental information (temperature, humidity, pressure) and motion data through ML models to predict CO2 concentrations, making one device perform the work of multiple sensors.
Solution Approach 2:
The system replaces mechanical sensor arrays with an information processing approach. Rather than using multiple physical CO2 sensors to achieve coverage, the system uses machine learning algorithms that process environmental parameters and motion information to predict CO2 distribution, substituting computational complexity for physical sensor complexity.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The system effectively predicts CO2 concentrations and provides timely alerts and ventilation adjustments, enhancing indoor air quality, reducing the risk of infection, and optimizing ventilation costs by accurately managing CO2 levels in enclosed spaces.
Implementation Method 1
LIDAR configured to measure at least one of a distance between a plurality of living subjects, a location of the living subject, or a size of the prediction target
Data Source
AI summary
Provided is a carbon dioxide concentration prediction system including a prediction unit configured to predict, based on a current carbon dioxide concentration of an internal space in a prediction target and environment information in the prediction target, a carbon dioxide concentration of the internal space, and a provision unit configured to provide the carbon dioxide concentration predicted by the prediction unit. The prediction unit may further predict a change over time of the carbon dioxide concentration in the prediction target from the current carbon dioxide concentration to the carbon dioxide concentration predicted based on the current carbon dioxide concentration and the environment information, and the provision unit may further provide the change over time of the carbon dioxide concentration.