Fuel leak determination via predictive modeling
Data characterizing a fuel storage facility can be received from one or more of a plurality of sensors disposed in the fuel storage facility. A fuel leak prediction for the fuel storage facility can be determined by a server, based on the received data, and further based on at least one predictive model that predicts whether a fuel leak exists in the fuel storage facility. The fuel leak prediction can be provided by the server. Related apparatus, systems, methods, techniques, and articles are also described.
1. A method comprising:
receiving, from one or more of a plurality of sensors disposed in a fuel storage facility, data characterizing the fuel storage facility;
determining, by a server and based on the received data, a predicted fuel leakage rate for the fuel storage facility, the determining further based on at least one predictive model that predicts whether a fuel leak exists in the fuel storage facility;
determining, by a server and based on whether a predicted fuel leakage rate exceeds a first, second, and/or third threshold, a fuel leak prediction for the fuel storage facility; and
providing, by the server, the fuel leak prediction,
wherein the predicted fuel leakage rate being:
less than the first threshold indicates a non-leaking fuel storage facility,
greater than the first threshold but less than the second threshold indicates a leaking storage facility, and
greater than the second threshold and the third threshold indicates an inconclusive prediction.
2. The method of claim 1 , wherein the at least one predictive model includes a predetermined calibration parameter for the fuel storage facility, a physics model for the fuel storage facility, and an error model indicative of at least one degree of error in the data.
3. The method of claim 2 , wherein the determining of the predicted fuel leakage rate is further based on
the predetermined calibration parameter for the fuel storage facility, the physics model, and an optimization of the error model.
4. The method of claim 3 , wherein the fluid balance model determines a predicted fuel level for the fuel storage facility based on the received data.
5. The method of claim 3 , further comprising:
providing, by the server, the predicted fuel leakage rate to a graphical user interface for depiction on a display.
6. The method of claim 3 , further comprising:
determining a second fuel leak prediction for the fuel storage facility based on a second fluid balance model and a second predetermined threshold, the second fluid balance model based on the fluid balance model and the second predetermined threshold greater than the predetermined threshold.
7. The method of claim 3 , wherein the determining of the fuel leak prediction is further based on mathematical programing and includes maximizing or minimizing a function characterized by the physics model and by at least varying input values of the function, the input valves characterizing the received data, and computing an output value of the function, the output value characterizing the predicted fuel leakage rate.
8. The method of claim 3 , further comprising determining a source of the fuel leak based on the predicted fuel leakage rate, the fuel leak prediction, and the received data.
9. The method of claim 2 , wherein the physics model is a fluid balance model.
10. The method of claim 1 , wherein the one or more of the plurality of sensors includes any one of a dipstick, an automated tank gauge, a fuel leak detection sensor, a magnetostrictive probe, a point of sale device, a forecourt controller, a back office system, and a fuel dispenser.
11. The method of claim 1 , wherein the server is communicatively coupled to the one or more of the plurality of sensors.
12. The method of claim 1 , wherein the fuel leak prediction is a daily fuel leak prediction.
13. The method of claim 1 , wherein the fuel leak prediction is provided to a graphical user interface of a display communicatively coupled to the server, the graphical user interface configured to present a visual characterization of the fuel leak prediction on the display.
14. The method of claim 1 , wherein the fuel leak prediction is provided to an automatic tank gauge for display to a user.
15. The method of claim 1 , further comprising determining the fuel leak prediction at a repeatable time interval.
16. A system comprising:
at least one data processor; and
memory storing instructions configured to cause the at least one data processor to perform operations comprising:
receiving, from one or more of a plurality of sensors disposed in a fuel storage facility, data characterizing the fuel storage facility;
determining, based on the received data, a predicted fuel leakage rate for the fuel storage facility, the determining further based on at least one predictive model that predicts whether a fuel leak exists in the fuel storage facility;
determining, based on whether a predicted fuel leakage rate exceeds a first, second, and/or third threshold; and
providing the fuel leak prediction,
wherein the predicted fuel leakage rate being:
less than the first threshold indicates a non-leaking fuel storage facility,
greater than the first threshold but less than the second threshold indicates a leaking storage facility, and
greater than the second threshold and the third threshold indicates an inconclusive prediction.
17. The system of claim 16 , wherein the at least one predictive model includes a predetermined calibration parameter for the fuel storage facility, a physics model for the fuel storage facility, and an error model indicative of at least one degree of error in the data.
18. The system of claim 17 , wherein the determining of the predicted fuel leakage rate is further based on
the predetermined calibration parameter for the fuel storage facility, the physics model, and an optimization of the error model.
19. The system of claim 18 , wherein the fluid balance model determines a predicted fuel level for the fuel storage facility based on the received data.
20. The system of claim 18 , further comprising:
providing the predicted fuel leakage rate to a graphical user interface for depiction on a display.
21. The system of claim 18 , further comprising:
determining a second fuel leak prediction for the fuel storage facility based on a second fluid balance model and a second predetermined threshold, the second fluid balance model based on the fluid balance model and the second predetermined threshold greater than the predetermined threshold.
22. The system of claim 18 , wherein the determining of the fuel leak prediction is further based on mathematical programing and includes maximizing or minimizing a function characterized by the physics model and by at least varying input values of the function, the input valves characterizing the received data, and computing an output value of the function, the output value characterizing the predicted fuel leakage rate.
23. The system of claim 18 , further comprising determining a source of the fuel leak based on the predicted fuel leakage rate, the fuel leak prediction, and the received data.
24. The system of claim 17 , wherein the physics model is a fluid balance model.
25. The system of claim 16 , wherein the one or more of the plurality of sensors includes any one of a dipstick, an automated tank gauge, a fuel leak detection sensor, a magnetostrictive probe, a point of sale device, a forecourt controller, a back office system, and a fuel dispenser.
26. The system of claim 16 , wherein the at least one data processor is communicatively coupled to the one or more of the plurality of sensors.
27. The system of claim 16 , wherein the fuel leak prediction is a daily fuel leak prediction.
28. The system of claim 16 , wherein the fuel leak prediction is provided to a graphical user interface of a display communicatively coupled to the at least one data processor, the graphical user interface configured to present a visual characterization of the fuel leak prediction on the display.
29. The system of claim 16 , wherein the fuel leak prediction is provided to an automatic tank gauge for display to a user.
30. The system of claim 16 , further comprising determining the fuel leak prediction at a repeatable time interval.
31. A non-transitory computer program product storing instructions which, when executed by at least one data processor forming part of at least one computing system, cause the at least one data processor to implement operations comprising:
receiving, from one or more of a plurality of sensors disposed in a fuel storage facility, data characterizing the fuel storage facility;
determining, based on the received data, a predicted fuel leakage rate for the fuel storage facility, the determining further based on at least one predictive model that predicts whether a fuel leak exists in the fuel storage facility;
determining, based on weather a predicted fuel leakage rate exceeds a first, second, and/or third threshold; and
providing the fuel leak prediction,
wherein the predicted fuel leakage rate being:
less than the first threshold indicates a non-leaking fuel storage facility,
greater than the first threshold but less than the second threshold indicates a leaking storage facility, and
greater than the second threshold and the third threshold indicates an inconclusive prediction.