New Approach for Monitoring the Underground Coal Mines Atmosphere Using IoT Technology

• Published in: Instrumentation, Mesure, Metrologie Vol. 22; no. 1; p. 29
• Main Authors: Tripathi, Abhishek Kumar, Mangalpady Aruna, Prasad, Sandeep, Jonnalagadda Pavan, Kant, Ramesh, Choubey, Chandan Kumar
• Format: Journal Article
• Language: English
• Published: Edmonton International Information and Engineering Technology Association (IIETA) 01.02.2023
• Subjects: Air temperature; Artificial neural networks; Carbon dioxide; Carbon monoxide; Coal mines; Coal mining; Connectivity; Gas detectors; Gas monitoring; Gases; Hazardous areas; Humidity; Internet of Things; Machine learning; Measurement techniques; Miners; Mines; Monitoring; Monitoring systems; Safety measures; Transmitters; Underground mines; Ventilation
• DOI: 10.18280/i2m.220104
• ISSN: 1631-4670

Because the atmosphere in underground coal mines contains toxic and flammable gasses, assessing the well-being of miners at all times while working in underground coal mines is an important task. The hazardous environment in underground coal mines reduces the miners' performance, which negatively affects the overall productivity of the mines. Therefore, it is necessary to regularly monitor the environment of underground mines so that appropriate safety measures can be taken. In this work, an IoT-based system was proposed using sensors to detect the concentration of mine gasses, air temperature, and humidity in the environment of underground mines. The developed wireless monitoring system was tested under laboratory conditions for measuring carbon dioxide, carbon monoxide, methane gas, air temperature, and humidity. The proposed monitoring system allows to store the measurement data that will help in predicting future hazardous conditions through artificial neural network and machine learning. The results of this research will help to introduce an innovative monitoring technology in underground coal mines so that miners' safety can be improved by changing safety measures from preventive to predictive.