Development of a detection device for part per billion level sulfur dioxide concentration in the air

With the acceleration of China's urbanization process, the problem of environmental pollution is becoming more and more serious and has attracted more and more public attention. In industrial activities such as thermal power generation, the incomplete combustion of fossil fuels such as coal releases sulfur dioxide (SO2), causing harm to ecosystems. Due to the uneven development between regions in China, heavy industries such as thermal power generation will exist for a long time, which will lead to a long-term process of sulfur dioxide control. Therefore, there is an urgent need to develop a simple, accurate, and reliable SO2 concentration detection equipment in order to conduct grid monitoring and implement SO2 source control throughout the country. In addition, given the vast territory of China and the significant difference between the north and south environments, the equipment also needs to have good adaptability. In this paper, variational mode decomposition (VMD) and BP neural network are used to optimize the detection data, which effectively reduces the influence of electronic noise and temperature drift by about 66% and 12%, respectively, and significantly improves the accuracy and reliability of the detection equipment.