Real-Time PM2.5 Monitoring in a Diesel Generator Workshop Using Low-Cost Sensors

Abstract

Particulates from diesel generator operation are a known air pollutant with adverse health effects. In this study, we used low-cost particulate matter (PM) sensors to monitor PM2.5 in a diesel generator plant. We compared the measurement results from a PM sensor and a reference instrument (DustTrak), and we found a high correlation between them. The data overestimation or underestimation of PM sensors implied the need for data calibration. Hence, we proposed a data calibration algorithm based on a nonlinear support vector machines (SVM) model, and we investigated the effect of three calibration factors on the model: humidity, temperature, and total volatile organic compounds (TVOC). It was found that the TVOC correction coefficient has great influence on the model, which should be considered when calibrating the low-cost PM sensor in diesel generator operation sites. A monitoring network with six low-cost sensors was installed in the diesel generator plant to monitor PM2.5 concentration. It was found that normal diesel generator work, diesel generator set handling work, and human activity are the most dominant ways of producing particulate matter at the site, and dispersion is the main cause of increased PM2.5 concentrations in nonworking areas. In this study, PM2.5 emissions from two different diesel generators were tested, and PM2.5 concentrations at monitoring points reached 220 μg/m3 and 120 μg/m3, respectively. This further confirms that diesel generators produce many respirable particles when working.

Evaluating Performance of Socio-Technical Systems for Improved Reliability: Evidence from Sensor and Human Networks

“…Calibrating these sensors can dramatically improve their accuracy. For instance, Feng et al (2022) reported a noticeable post-calibration improvement in R^2 from a range of 0.64-0.71 to 0.75-0.81 (Feng et al, 2022). Another study using a network of 19 sensors deployed over a period of 2 months in Sacramento, CA also observed a boost in post-calibration R^2 values from 0.6 to 0.73 (Mukherjee et al, 2019).…”