Predictive maintenance policy of storage tanks based on multi-source data

As one of the important equipment in the field of oil and gas storage and transportation, the oil storage tanks are in the increasingly urgent demand for scientific and effective maintenance strategies. Hence, a risk characteristics database was built by fusing the multi-source data relying on the basic information, operating conditions, process parameters, cathodic protection, inspection and monitoring, and maintenance data of oil storage tanks. Specifically, the key indicators and development trends of the health status of storage tanks were obtained by mining and analyzing the typical failure cases of storage tanks and the multi-source data based on the historical multi-source big data, in combination with the condition monitoring and inspection results. Meanwhile, a risk assessment method was developed based on the characteristics database, which could automatically generate the time points for predictive maintenance of the tank and recommend the appropriate maintenance methods. In addition, a integrated multi-source data management system (desktop and mobile) of tank was established through the customized design of data interface in B/S architecture. Thus, the collection and management of tank data and the multi-dimensional data analysis were realized, which could provide a new idea for maintenance management of storage tanks, as well as support for the digitalization and intellectualization of tank management.