Smart sensors, smart calibration: Applications in machine learning for coal dust monitoring

Abstract

The recent resurgence of pneumoconiosis among coal miners in the United States has been linked to their exposure to excessive levels of coal dust. PDM3700 monitors are used in the mining industry to measure each miner’s coal dust exposure levels and control overexposure. However, the high cost of the PDM3700 hinders its use in measuring the exposure levels of all miners. Plantower PMS5003 low-cost particulate matter (PM) sensors can measure coal dust concentrations with high spatial resolution in real-time owing to their low cost and small size. However, these sensors require extensive calibration to ensure a high accuracy over long deployment periods. Because they have only been calibrated for mining-induced PM monitoring using linear regression models, the objective of this study was to leverage machine learning algorithms for calibration of coal-dust-monitoring sensors. Laboratory collocation tests were performed using the PDM3700 and aerodynamic particle sizer as reference monitors in a wind tunnel at a wide range of concentrations (0–3 mg/m³), temperatures (20–32°C), and relative humidities (23%–43%). The results revealed that nonlinear machine learning techniques significantly outperformed traditional linear regression models for low-cost sensor calibration. With the artificial neural network (ANN) being the strongest calibration model, Pearson’s correlation of the PMS5003 sensors reached 0.98 and 0.97, those of the Airtrek sensors reached of 0.89 and 0.91, and those of the GasLab sensors reached 0.93 and 0.92. This shows a 2%–11% improvement in model performance over the linear regression model using ANN calibration. The success of the machine learning algorithms used in this study demonstrates the feasibility of deploying low-cost PM sensors for coal dust monitoring in mines.

Keywords

Smart sensors / Smart calibration / Machine learning / Coal dust monitoring / Artificial neural network

References

[1] A.S. Laney, M.D. Attfield, Coal workers’ pneumoconiosis and progressive massive fibrosis are increasingly more prevalent among workers in small underground coal mines in the United States, Occup. Environ. Med. 67 (6) (2010) 428-431.

[2] H.B. Liu, Z.F. Tang, Y.L. Yang, D. Weng, G. Sun, Z.W. Duan, J. Chen, Identification and classification of high risk groups for coal Workers’ pneumoconiosis using an artificial neural network based on occupational histories: a retrospective cohort study, BMC Public Health 9 (2009) 366.

[3] R.A. Cohen, E.L. Petsonk, C. Rose, B. Young, M. Regier, A. Najmuddin, J.L. Abraham, A. Churg, F.H. Green, Lung pathology in U.S. Coal workers with rapidly progressive pneumoconiosis implicates silica and silicates, Am. J. Respir. Crit. Care Med. 193 (6) (2016) 673-680.

[4] D.J. Blackley, C.N. Halldin, A.S. Laney, Continued increase in prevalence of coal workers' pneumoconiosis in the United States, 1970-2017, Am. J. Public Health 108 (9) (2018) 1220-1222.

[5] B.C. Doney, D. Blackley, J.M. Hale, C. Halldin, L. Kurth, G. Syamlal, A.S. Laney, Respirable coal mine dust in underground mines, United States, 1982-2017, Am. J. Ind. Med. 62 (6) (2019) 478-485.

[6] M.M. Zaid, N. Amoah, A. Kakoria, Y. Wang, G. Xu, Advancing occupational health in mining: investigating low-cost sensors suitability for improved coal dust exposure monitoring, Meas. Sci. Technol. 35 (2) (2023) 025128.

[7] Mine Safety and Health Administration, Major provisions and effective dates MSHA’s final rule to lower miners’ exposure to respirable coal mine dust, MSHA, 2014.

[8] M.M. Zaid, G. Xu, N.A. Amoah, Accuracy of low-cost particulate matter sensor in measuring coal mine dust-A wind tunnel evaluation, in: Underground Ventilation, CRC Press, 2023, pp. 274-284.

[9] U.S. Environmental Protection Agency, Roadmap for Next-Generation Air Monitoring, EPA, 2013. 〈 https://www.epa.gov/sites/default/files/2014-09/documents/roadmap-20130308.pdf〉 (Accessed September 11, 2023).

[10] R. Williams, A. Kaufman, T. Hanley, S. Rice, J. Garvey, EPA Sensor Evaluation Report, U.S. Environmental Protection Agency, 2014. 〈 https://www.aqmd.gov/docs/default-source/aq-spec/resources-page/us-epa-sensor-evaluation-report.pdf〉 (Accessed September 11, 2023).

[11] M. Badura, P. Batog, A. Drzeniecka-Osiadacz, P. Modzel, Evaluation of low-cost sensors for ambient PM_2.5 monitoring , J. Sens. 2018 (1) (2018) 5096540.

[12] Z.Al Barakeh, P. Breuil, N. Redon, C. Pijolat, N. Locoge, J.P. Viricelle, Development of a normalized multi-sensors system for low cost on-line atmospheric pollution detection, Sens. Actuat. B Chem. 241 (2017) 1235-1243.

[13] J.C. Volkwein, R.P. Vinson, L.J. McWilliams, D.P. Tuchman, S.E. Mischler, Performance of a new personal respirable dust monitor for mine use, National Institute for Occupational Safety and Health, Cincinnati, OH, 2004.

[14] M.U. Khan, A.D.S. Gillies, Real-time monitoring of DPM, airborne dust and correlating elemental carbon measured by two methods in underground mines in USA, in: E. Sarver, S. Schafrik, E. Jong, K. Luxbacher (Eds.), 15th North American Mine Ventilation Symposium, 2015, pp. 1-7.

[15] N.A. Amoah, G. Xu, Y. Wang, J.Y. Li, Y.M. Zou, B.S. Nie, Application of low-cost particulate matter sensors for air quality monitoring and exposure assessment in underground mines: a review, Int. J. Miner. Metall. Mater. 29 (8) (2022) 1475-1490.

[16] K.E. Kelly, J. Whitaker, A. Petty, C. Widmer, A. Dybwad, D. Sleeth, R. Martin, A. Butterfield, Ambient and laboratory evaluation of a low-cost particulate matter sensor, Environ. Pollut. 221 (2017) 491-500.

[17] L. Spinelle, M. Aleixandre, M. Gerboles, Protocol of evaluation and calibration of Low-cost gas sensors for the monitoring of air pollution, Publications Office of the European Union, Luxembourg, 2013.

[18] D.M. Holstius, A. Pillarisetti, K.R. Smith, E. Seto, Field calibrations of a low-cost aerosol sensor at a regulatory monitoring site in california, Atmos. Meas. Tech. 7 (4) (2014) 1121-1131.

[19] S. Kelleher, C. Quinn, D. Miller-Lionberg, J. Volckens, A low-cost particulate matter (PM_2.5) monitor for wildland fire smoke , Atmos. Meas. Tech. 11 (2) (2018) 1087-1097.

[20] A. Polidori, V. Papapostolou, H. Zhang, Laboratory evaluation of low-cost air quality sensors: laboratory setup and testing protocol, South Coast Air Quality Management District, 2016. 〈 https://www.aqmd.gov/docs/default-source/aq-spec/protocols/sensors-lab-testing-protocol6087afefc2b66f27bf6fff00004a91a9.pdf〉 (Accessed September 9, 2023).

[21] T. Sayahi, A. Butterfield, K.E. Kelly, Long-term field evaluation of the plantower PMS low-cost particulate matter sensors, Environ. Pollut. 245 (2019) 932-940.

[22] Y. Wang, J. Li, H. Jing, Q. Zhang, J. Jiang, P. Biswas, Laboratory evaluation and calibration of three low-cost particle sensors for particulate matter measurement, Aerosol Sci. Technol. 49 (11) (2015) 1063-1077.

[23] T.S. Zheng, M.H. Bergin, K.K. Johnson, S.N. Tripathi, S. Shirodkar, M.S. Landis, R. Sutaria, D.E. Carlson, Field evaluation of low-cost particulate matter sensors in high- and low-concentration environments, Atmos. Meas. Tech. 11 (8) (2018) 4823-4846.

[24] B. Feenstra, V. Papapostolou, S. Hasheminassab, H. Zhang, B. Der Boghossian, D. Cocker, A. Polidori, Performance evaluation of twelve low-cost PM_2.5 sensors at an ambient air monitoring site , Atmos. Environ. 216 (2019) 116946.

[25] A. Polidori, V. Papapostolou, B. Feenstra, H. Zhang, Field evaluation of low-cost air quality sensors: field setup and testing protocol, South Coast AQMD, 2017. 〈 http://www.aqmd.gov/aq-spec/evaluations/field〉 (Accessed September 9, 2023).

[26] M. Tagle, F. Rojas, F. Reyes, Y. Vásquez, F. Hallgren, J. Lindén, D. Kolev, Å.K. Watne, P. Oyola, Field performance of a low-cost sensor in the monitoring of particulate matter in Santiago, Chile, Environ. Monit. Assess. 192 (3) (2020) 171.

[27] A. Samad, D.R. Obando Nuñez, G.C. Solis Castillo, B. Laquai, U. Vogt, Effect of relative humidity and air temperature on the results obtained from low-cost gas sensors for ambient air quality measurements, Sensors 20 (18) (2020) 5175.

[28] F. Concas, J. Mineraud, E. Lagerspetz, S. Varjonen, X.L. Liu, K. Puolamäki, P. Nurmi, S. Tarkoma, Low-cost outdoor air quality monitoring and sensor calibration, ACM Trans. Sen. Netw. 17 (2) (2021) 1-44.

[29] A. Gonzalez, A. Boies, J. Swanson, D. Kittelson, Measuring the air quality using low-cost air sensors in a parking garage at University of Minnesota, USA, Int. J. Environ. Res. Public Health 19 (22) (2022) 15223.

[30] Z. Farooqui, J. Biswas, J. Saha, Long-term assessment of PurpleAir low-cost sensor for PM_2.5 in California, USA , Pollutants 3 (4) (2023) 477-493.

[31] M. Ghamari, C. Soltanpur, P. Rangel, W.A. Groves, V. Kecojevic, Laboratory and field evaluation of three low-cost particulate matter sensors, IET Wirel. Sens. Syst. 12 (1) (2022) 21-32.

[32] M. Ghamari, H. Kamangir, K. Arezoo, K. Alipour, Evaluation and calibration of low-cost off-the-shelf particulate matter sensors using machine learning techniques, IET Wirel. Sens. Syst. 12 (5-6) (2022) 134-148.

[33] N.A. Amoah, M.M. Zaid, A.R. Kumar, P. Chang, G. Xu, Optimized canopy air curtain dust protection using a two-level manifold and computational fluid dynamics, Min. Metall. Explor 41 (4) (2024) 1807-1818.

[34] S. Munir, M. Mayfield, D. Coca, S.A. Jubb, O. Osammor, Analysing the performance of low-cost air quality sensors, their drivers, relative benefits and calibration in cities-A case study in sheffield, Environ. Monit. Assess. 191 (2) (2019) 94.

[35] A. Cavaliere, F. Carotenuto, F. Di Gennaro, B. Gioli, G. Gualtieri, F. Martelli, A. Matese, P. Toscano, C. Vagnoli, A. Zaldei, Development of low-cost air quality stations for next generation monitoring networks: calibration and validation of PM_2.5 and PM₁₀ sensors , Sensors 18 (9) (2018) 2843.

[36] P. Nowack, L. Konstantinovskiy, H. Gardiner, J. Cant, Machine learning calibration of low-cost NO₂ and PM₁₀ sensors: Non-linear algorithms and their impact on site transferability , Atmos. Meas. Tech. 14 (8) (2021) 5637-5655.

[37] C.C. Chen, C.T. Kuo, S.Y. Chen, C.H. Lin, J.J. Chue, Y.J. Hsieh, C.W. Cheng, C.M. Wu, C.M. Huang, Calibration of low-cost particle sensors by using machine-learning method, 2018 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS), IEEE, Chengdu, China, 2018, pp. 111-114.

[38] Y.W. Wang, Y.J. Du, J.N. Wang, T.T. Li, Calibration of a low-cost PM_2.5 monitor using a random forest model , Environ. Int. 133 (2019) 105161.

[39] L.O.H. Wijeratne, D.R. Kiv, A.R. Aker, S. Talebi, D.J. Lary, Using machine learning for the calibration of airborne particulate sensors, Sensors 20 (1) (2020) 99.

[40] N. Zimmerman, A.A. Presto, S.P.N. Kumar, J. Gu, A. Hauryliuk, E.S. Robinson, A.L. Robinson, R. Subramanian, A machine learning calibration model using random forests to improve sensor performance for lower-cost air quality monitoring, Atmos. Meas. Tech. 11 (1) (2018) 291-313.

[41] M.X. Si, Y. Xiong, S. Du, K. Du, Evaluation and calibration of a low-cost particle sensor in ambient conditions using machine-learning methods, Atmos. Meas. Tech. 13 (4) (2020) 1693-1707.

[42] W.V. Wang, S.C. Lung, C.H. Liu, Application of machine learning for the in-field correction of a PM_2.5 low-cost sensor network , Sensors 20 (17) (2020) 5002.

[43] J.C. Volkwein, R.P. Vinson, S.J. Page, L.J. McWilliams, G.J. Joy, S.E. Mischler, D.P. Tuchman, Laboratory and Field Performance of a Continuously Measuring Personal Respirable Dust Monitor, National Institute for Occupational Safety and Health, Cincinnati, OH, 2006.

[44] TSI Incorporated, 3321 aerodynamic particle sizer spectrometer-specification sheet, TSI, 2016. 〈 https://www.kenelec.com.au/wp-content/uploads/2016/06/TSI-3321-Aerodynamic-Particle-Sizer-SpecSheet.pdf〉 (Accessed September 11, 2023).

[45] N.B. Hall, D.J. Blackley, C.N. Halldin, A.S. Laney, Current review of pneumoconiosis among US coal miners, Curr. Environ. Health Rep. 6 (3) (2019) 137-147.

[46] A.I. Batool, N.H. Naveed, M. Aslam, J. da Silva, M.F.U. Rehman, Coal dust-induced systematic hypoxia and redox imbalance among coal mine workers, ACS Omega 5 (43) (2020) 28204-28211.

[47] N.A. Amoah, G. Xu, A.R. Kumar, Y. Wang, Calibration of low-cost particulate matter sensors for coal dust monitoring, Sci. Total Environ. 859 (2023) 160336.

[48] L. Wang, F.F. Li, Y.Y. Guo, Q.Z. Li, T.M. Chen, J.J. Wu, Numerical simulation study of dust transport of comprehensive mining working surface, in: A.J. Tallón-Ballesteros (Ed.), Modern Management based on Big Data III, IOS Press, 2022, pp. 440-446.

[49] M.L. Zamora, F. Xiong, D. Gentner, B. Kerkez, J. Kohrman-Glaser, K. Koehler, Field and laboratory evaluations of the low-cost plantower particulate matter sensor, Environ. Sci. Technol. 53 (2) (2019) 838-849.