Early abnormal warning for fuel dispensers driven by data

As an important equipment of gas stations, fuel dispenser is an important part of the petroleum retail industry, where it only undertakes the function of providing fuel to consumers, but also involves multiple aspects such as metering, payment processing, and safety control. Abnormal operation of fuel dispenser equipment will seriously affect the normal operation and service quality of gas stations. Early warning of abnormal states of fuel dispenser equipment is of great significance. This paper proposes an abnormal early warning method for fuel dispenser equipment based on the analytic hierarchy process. Specifically, we combine limited abnormal data with expert experience, and uses the analytic hierarchy process to divide the abnormality degree of fuel dispenser equipment into different evaluation levels. After solving the real-time collected data, this method constructs an abnormal early warning index system for fuel dispenser equipment based on the real-time operation data of equipment collected by sensors and statistical historical data, and represents the abnormal state of the current equipment in the form of a percentage. When the fuel dispenser is abnormal, the system can classify the abnormal level, so that it can be judged whether to dispatch maintenance personnel for emergency maintenance according to the abnormal level.