Analysis of spatiotemporal influence patterns of toxic gas monitoring concentrations in an urban drainage network based on IoT and GIS

摘要

Urban underground pipelines have complex structures, long service lives, and are susceptible to illegal interference, corrosion, and external force damage. Therefore, they are a constant security risk that seriously threaten the public security of the city. Due to the complexity of the underground environment, lack of various monitoring technologies, high cost, backwardness of emergency technology research, incongruity of safety management, and the transport of flammable, explosive, toxic, and harmful hazardous sources to densely populated areas, the boundary between industrial, residential, and living areas has become increasingly blurred, causing a major threat to public security, people's lives, industrial production, and social stability. Traditional underground pipeline accident prevention and control technology is currently unable to meet the increasing demands of public security. Combining pipeline accident prevention and control with internet of things and artificial intelligence technology can achieve urban disaster prevention, and therefore is of great interest to researchers. Herein, the research status of underground pipeline accident prevention and control technology is summarized, and an analysis of the advantages of applying big data for risk factor monitoring, risk assessment, risk early warning, and emergency decision-making technology is discussed. Further, the application difficulties and difficulties regarding big data technology in underground pipeline accident prevention and control and their potential solutions are detailed. Based on the internet of things data, spatiotemporal model mining, and Geographic Information System (GIS), we analyze the distribution and influencing factors of harmful gases in the urban underground sewage pipe network of Chongqing City, and explore the influence of smart city developments on harmful gases in the urban underground sewage pipe network. (C) 2020 Elsevier B.V. All rights reserved.