SEN54-SDN (Wireless Environmental Sensors)
General Description
For air quality monitoring, we implemented a sensorization system using high-precision particulate matter sensors. Specifically, we utilized the Sensirion SEN54, a laser-based sensor designed for accurate and long-term stable detection of airborne particles. This sensor operates on an optical scattering principle, enabling real-time measurement of PM1, PM2.5, PM4, and PM10 concentrations with minimal drift over time. Its advanced self-cleaning mechanism ensures reliability, making it well-suited for industrial applications such as monitoring air conditions in painting booths.
| Resource | Link |
|---|---|
| Source code | Link to source code |
| Demo Video | Link to video |
Contact
The following table includes contact information of the main developers in charge of the component:
| Name | Organisation | |
|---|---|---|
| Federico Orozco | forozco@iti.es |  |
License
GNU General Public License v3.0
Technical Foundations
Sensorization Testing and Key Insights
Secondly, we conducted tests on the sensorization system. One of the most relevant aspects is the size of airborne particles to which operators are exposed. Measurements were taken for four different particle sizes:
- PM1: Represents the concentration of particles smaller than 1 micrometer, measured in micrograms per cubic meter.
- PM2.5: Particles with a diameter of 2.5 micrometers or less.
- PM4 and PM10: Larger particulate matter categories, representing particles up to 4 and 10 micrometers in diameter, respectively.
Particle Behavior and System Implications
The first graph presents data for PM1, showing the concentration of sub-micrometer particles. Sharp peaks that quickly return to baseline values are observed, which correspond to data from the paint booth. These fluctuations provide a basis for extrapolating operational insights, such as estimating active painting time—at least while the spray gun is in use. If the extraction systems were to fail or prove insufficient, the particle concentration would not decrease rapidly, maintaining elevated levels for extended periods. In such cases, the system should generate alerts to notify personnel in the facility, prompting adjustments to the extraction airflow.
For larger particles, the behavior follows a similar trend. Since PM2.5 includes all particles smaller than 2.5 micrometers, it inherently encompasses the PM1 data. However, in this case, the upper measurement values appear relatively "flat," indicating that the sensor has reached its detection limit. This limitation led us to replace it with a higher-range sensor. Similar patterns were observed for PM4 and PM10 measurements, confirming the consistency of results across different particle size ranges.
Volatile Organic Compounds (VOC) and Air Quality
The first graph presents data for PM1, showing the concentration of sub-micrometer particles. Sharp peaks that quickly return to baseline values are observed, which correspond to data from the paint booth. These fluctuations provide a basis for extrapolating operational insights, such as estimating active painting time—at least while the spray gun is in use. If the extraction systems were to fail or prove insufficient, the particle concentration would not decrease rapidly, maintaining elevated levels for extended periods. In such cases, the system should generate alerts to notify personnel in the facility, prompting adjustments to the extraction airflow.
For larger particles, the behavior follows a similar trend. Since PM2.5 includes all particles smaller than 2.5 micrometers, it inherently encompasses the PM1 data. However, in this case, the upper measurement values appear relatively "flat," indicating that the sensor has reached its detection limit. This limitation led us to replace it with a higher-range sensor. Similar patterns were observed for PM4 and PM10 measurements, confirming the consistency of results across different particle size ranges.
Environmental Parameters: Humidity Considerations
In terms of humidity, no significant impact was observed on particle behavior or air quality. The only notable trend was a gradual increase in humidity throughout the day, which aligns with expected environmental fluctuations.
Potential Applications and Operational Benefits
These measurements and insights can be leveraged in two key areas:
1. Error Detection and Process Monitoring
- Identifying inefficiencies in the paint booth’s extraction system, allowing for early intervention to optimize airflow.
- Verifying that the cobot (collaborative robot) is effectively executing the painting process. Since the spray gun operates autonomously, it lacks an intrinsic mechanism to confirm actual paint dispersion. Sensor-based monitoring could detect issues such as nozzle clogging or paint depletion, ensuring process reliability.
2. Workplace Safety and Operator Protection
- Providing real-time feedback on air quality conditions to determine whether additional protective equipment is required.
- Enhancing workplace safety protocols by alerting personnel to hazardous conditions when particulate matter or VOC levels exceed recommended thresholds. Although not the primary focus of our system, this added functionality significantly contributes to a safer work environment.
Integrated and Open Source Components
This section outlines both pre-existing technologies and open-source components that have been integrated into the component. It provides details on their sources, purposes, modifications, and compliance with licensing terms.
Overview
✔️ Provide a high-level overview of the integrated and open-source components. Provide a high-level description of the funding received in previous projects and what is the progress in AI-PRISM.
Pre-existing Components
[Repeat for each sub-component] Sub-component Name
Source
✔️ For previous background, provide the project name or origin of the sub-component. Provide a link to project or origin. ✔️ For open source, provide a link to the open source repository.
Description
✔️ Provide a high-level description of the sub-component.
Modifications
✔️ Describe the modifications made to the sub-component to adapt it to the AI-PRISM project. Describe enhancements, or additional features that have been generated thanks to AI-PRISM.
Purpose in AI-PRISM
✔️ Describe how the sub-component is used in AI-PRISM. Describe the role of the component in the project.
License
✔️ Describe the license of the sub-component. Provide a link to the license if available.
How to install
✔️ Every AI-PRISM component is installed using the Cluster management service. During the installation process, the user needs to configure a set of high-level parameters. Provide here a description of the parameters that the user needs to fill in.
How to use
Add usage guidelines describing how to use your component.