Multi-Domain Airflow Modeling and Ventilation Characterization Using Mobile Robots, Stationary Sensors and Machine Learning

Sensors (Basel). 2019 Mar 5;19(5):1119. doi: 10.3390/s19051119.

Abstract

Ventilation systems are critically important components of many public buildings and workspaces. Proper ventilation is often crucial for preventing accidents, such as explosions in mines and avoiding health issues, for example, through long-term exposure to harmful respirable matter. Validation and maintenance of ventilation systems is thus of key interest for plant operators and authorities. However, methods for ventilation characterization, which allow us to monitor whether the ventilation system in place works as desired, hardly exist. This article addresses the critical challenge of ventilation characterization-measuring and modelling air flow at micro-scales-that is, creating a high-resolution model of wind speed and direction from airflow measurements. Models of the near-surface micro-scale flow fields are not only useful for ventilation characterization, but they also provide critical information for planning energy-efficient paths for aerial robots and many applications in mobile robot olfaction. In this article we propose a heterogeneous measurement system composed of static, continuously sampling sensing nodes, complemented by localized measurements, collected during occasional sensing missions with a mobile robot. We introduce a novel, data-driven, multi-domain airflow modelling algorithm that estimates (1) fields of posterior distributions over wind direction and speed ("ventilation maps", spatial domain); (2) sets of ventilation calendars that capture the evolution of important airflow characteristics at measurement positions (temporal domain); and (3) a frequency domain analysis that can reveal periodic changes of airflow in the environment. The ventilation map and the ventilation calendars make use of an improved estimation pipeline that incorporates a wind sensor model and a transition model to better filter out sporadic, noisy airflow changes. These sudden changes may originate from turbulence or irregular activity in the surveyed environment and can, therefore, disturb modelling of the relevant airflow patterns. We tested the proposed multi-domain airflow modelling approach with simulated data and with experiments in a semi-controlled environment and present results that verify the accuracy of our approach and its sensitivity to different turbulence levels and other disturbances. Finally, we deployed the proposed system in two different real-world industrial environments (foundry halls) with different ventilation regimes for three weeks during full operation. Since airflow ground truth cannot be obtained, we present a qualitative discussion of the generated airflow models with plant operators, who concluded that the computed models accurately depicted the expected airflow patterns and are useful to understand how pollutants spread in the work environment. This analysis may then provide the basis for decisions about corrective actions to avoid long-term exposure of workers to harmful respirable matter.

Keywords: airflow modeling; environmental monitoring; machine learning; mobile robotics; static sensor networks; ventilation.