Occupational safety databases and their incident records constitute a need to utilize big data analytics to manage risk and enhance safety. HSE big data analytics focus attention on main incidents, help safety champions to better recognize the near misses and make the work environment safer for employees. This paper presents a powerful HSE big data analytics platform which is capable of analyzing complex records based on area (state), category, industry, occupation, type of event and sources. An example database by Bureau of Labor Statistics (BLS) is used in this study which includes 1278 industries, 846 sources of injury, 257 events or exposures, 898 occupations, 9 age groups, 6 times of incident in a day, 18 natures of incident, 17 injured body parts and 18 worker locations between 2011 and 2014. This tool can query various scenarios, classify and pre-process details of the incidents and perform HSE risk analysis. This algorithm is capable of executing HSE predictive modeling by machine learning methods and comprehensively assists safety champions on taking appropriate preventive measures.
In this paper, we present how this HSE big data analytics algorithm promotes safety in oil and gas occupations such rotary drill operators, derrick and service unit operators, roustabouts, petroleum engineers, geological and petroleum technicians, petroleum pump system operators, refinery operators, and gaugers, wellhead pumpers, environmental engineers and mechanical engineers. These occupations were at businesses involved with drilling oil and gas wells, oil and gas extraction, support activities for oil and gas operations, oil and gas pipeline and related structures construction, pipeline transportation of crude oil, oil and gas field machinery and equipment manufacturing, pipeline transportation of natural gas, petroleum refineries, petroleum and coal products manufacturing, petroleum bulk stations and terminals, petroleum and petroleum products merchant wholesalers, natural gas distribution and gasoline stations.