Video: Deep dive into IAQ data using data analytics and machine learning
Interest in indoor air quality (IAQ) has increased substantially with COVID-19. Improved air cleaning techniques have been installed and their efficacy evaluated using IoT sensors.
Learning objectives
- Understand modern particulate matter sensors and the impact on the quality of the data.
- Identify the significance of CO2 data from outside air, supply air, and return air monitoring points.
- How machine learning can be applied to outside air intake and used to detect anomalies in filtration efficacy.
- Understand the use of capturing real-time IAQ data and how to leverage it for managing key HVAC system infrastructures in buildings.
Interest in indoor air quality (IAQ) has increased substantially with COVID-19. Improved air cleaning techniques have been installed and their efficacy evaluated using IoT sensors. HVAC system design can be further evaluated using practical application of machine learning (ML) to detect anomalies. For example: ML can be applied to ensure outside air intake is adequate based on occupancy, and detect anomalies in filtration efficacy that would indicate filter issue events.
The concerns about, and the importance of, indoor air quality (IAQ) has increased substantially. COVID-19 has sensitized the general public about what may be in the air that they are breathing. Building owners and operators are rightfully responding to these concerns in leveraging technology such as the Internet of Things (IoT) to bring assurance to building occupants. As it is well known that expiratory human activities generate sub-micron airborne droplets, which can also carry viruses (e.g., COVID-19), enhanced air filtration strategies have been introduced using pre-filters or filters with different MERV ratings for different particle sizes. The efficacy of those advanced air filtration systems can only be determined using particulate matter (PM) sensors having sufficient quality and accuracy. This session will include an in-depth discussion of the different design choices of modern PM sensors to enable understanding of the impact on the quality of the PM data.
Additionally, an analysis of current outside-air intake strategies is provided in leveraging CO2 data from outside air, supply air, and return air monitoring points to calculate the percentage of outside air particles coming in vs the percentage of recirculated particles. HVAC system design can be further evaluated using practical application of Machine Learning (ML) to detect different system anomalies. For example, ML can be applied to (1) ensure outside air intake is adequate based on occupancy, and (2) detect anomalies in filtration efficacy that would indicate filter issue events that would generate more particles than the HVAC system can handle. These case studies and others will highlight the utility of capturing real-time IAQ data from the physical environment. Illuminating the hidden reality of real-time airborne conditions will provide key decision makers with the data needed to not only numerically assess levels of airborne pollutants, but also leverage such real-time data in managing key HVAC system infrastructures within buildings.
CxEnergy is the premier conference & expo in commissioning, building technology, and energy management. CSE subscribers receive a 10% discount to the CxEnergy 2024 with promo code CSE10 (April 29 – May 2, San Diego, CA). Learn more and register at www.CxEnergy.com.
Do you have experience and expertise with the topics mentioned in this content? You should consider contributing to our CFE Media editorial team and getting the recognition you and your company deserve. Click here to start this process.
