A Novel Feature Extraction Method for Monitoring (Vehicular) Fuel Storage System Leaks

Abstract

System state determination with incomplete sensory information set proved to be a technically challenging problem. In this paper, authors tackle a problem of this type associated with vehicle fuel storage systems and proposed a novel feature extraction method. Federal and state regulations require fuel storage leak detection mechanism to be conducted periodically and regulate its execution rate and performance to ensure effective emission controls. Being able to robustly determine a fuel storage system’s state in terms of its effectiveness of fuel containment is therefore of great importance to all vehicle original equipment manufacturers (OEM). Prevailing practice in the industry utilizes a method relevant to natural vacuum phenomenon and is loosely associated with ideal gas law. Commonly referred to as “Entry Conditions” in in-vehicle monitoring design literature, major noise factors go through stringent pre-monitoring evaluations before monitoring program execution to ensure ideal test conditions. Differences in ambient conditions compounded with varying customer drive cycle patterns present great challenge to existing monitor designs for the purpose of leak detection. In addition, prevailing practices of evaluation in-tank fuel pressure and temperature information are generally conducted with surrogate or estmiated temperature information due to the absence of in-tank temperature sensor. All this calls for an alternative feature calculation and detection method that are less sensitive to known noise factors, can operate with incomplete sensory information yet being able provide similar or improved detection capability. In this paper, we put the main focus on the derivation of a novel method of feature calculation for the purpose of detecting presence of a leak in a fuel storage tank.