AI-Controlled Indoor Air Mitigation System
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for mitigating airborne contamination in indoor environments are inefficient in reducing aerosol concentrations without excessive energy expenditure, and they often compromise comfort conditions, leading to increased carbon emissions.
Innovation Solution
A system comprising multiple sensing modules and a control module using artificial intelligence and machine learning to selectively activate mitigation modules, such as ventilation, scrubbers, and filtration systems, to reduce aerosol concentrations based on real-time particle detection and environmental conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Object-affected harmful factors
If large amounts of fresh air are introduced to reduce aerosol concentration, then airborne contamination is mitigated, but energy consumption increases and comfort conditions deteriorate
Solution Approach 1:
The system performs preliminary detection of aerosol concentrations using sensing modules before contamination becomes severe. The AI algorithm predicts when mitigation will be needed and pre-activates appropriate modules, avoiding the need for continuous high-energy ventilation and enabling timely, energy-efficient intervention.
Solution Approach 2:
The system dynamically adjusts mitigation strategies based on real-time sensor data and AI analysis. Instead of continuous high-energy ventilation, the system varies the intensity and type of mitigation (ventilation, scrubbing, filtration) according to actual aerosol levels, occupancy patterns, and environmental conditions, optimizing energy usage while maintaining effectiveness.
2Object-affected harmful factors
If large amounts of fresh air are introduced to reduce aerosol concentration, then airborne contamination is mitigated, but comfort conditions (temperature, humidity) deteriorate
Solution Approach 1:
The system monitors temperature and humidity conditions in advance alongside aerosol levels. The AI algorithm predicts comfort deterioration before it occurs and adjusts mitigation strategies proactively, selecting approaches that address contamination while preserving comfort, or pre-conditioning the environment to withstand necessary ventilation.
Solution Approach 2:
The system changes operational parameters of mitigation modules based on real-time conditions. When comfort conditions approach unacceptable levels, the AI algorithm adjusts ventilation rates, activates conditioning systems, or switches to alternative mitigation methods that maintain both air quality and comfort, dynamically optimizing the balance between these competing requirements.
3Object-affected harmful factors
If continuous mitigation is applied to maintain low aerosol concentration, then airborne contamination is reduced, but energy consumption increases carbon emissions
Solution Approach 1:
The system implements periodic monitoring and intermittent mitigation rather than continuous operation. Sensing modules continuously detect aerosol levels, and the AI algorithm determines optimal timing for mitigation activation, creating periodic cycles of monitoring and intervention that maintain effectiveness while minimizing energy consumption and associated carbon emissions.
Solution Approach 2:
The system employs feedback loops where sensor data on aerosol concentrations continuously informs AI algorithm decisions about mitigation activation. This closed-loop control ensures mitigation is applied only when and where needed, optimizing the balance between contamination reduction and energy consumption, thereby reducing unnecessary carbon emissions from continuous operation.
Data Source
AI summary
A system and method for mitigating airborne contamination in a conditioned indoor environment utilizes one or more sensing modules configured to detect presence and/or concentration of particles and/or aerosols at different locations. A control module employs an artificial intelligence algorithm to selectively activate at least one mitigation module utilizing machine learning programmed rules and output signals from the sensing module(s). The mitigation module(s) are configured to take one or more actions to reduce presence and/or concentration of particles and/or aerosols in the conditioned indoor environment.