Adaptive Fuel Pump Model for Mass Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional fuel delivery systems in internal combustion engines require disruptive shutdowns and provide inaccurate results when characterizing the amount of fuel delivered by the fuel pump, necessitating an improved method to predict fuel pumped mass during operation.
Innovation Solution
An adaptive model is generated to predict the mass of fuel pumped by estimating the start of pumping position, using pressure and temperature measurements, and adjusting pumping events to control the pump operation, allowing for non-intrusive prediction and control of fuel delivery.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the fuel pump is shut down to measure fuel delivery variables, then measurement accuracy is improved, but engine operation is disrupted
Solution Approach 1:
The patent replaces physical shutdown measurements with a mathematical model-based prediction system. The control module uses an adaptive model that incorporates pressure sensor data, temperature sensor data, and pump operation parameters to calculate fuel mass delivered without requiring pump shutdown. This substitutes mechanical interruption with computational prediction, maintaining both measurement accuracy and operational continuity.
Solution Approach 2:
The patent introduces intermediate sensors (pressure sensors and temperature sensors) that continuously monitor fuel conditions during pump operation. These sensors serve as intermediaries between the pump operation and the control module, providing real-time data that enables accurate fuel delivery prediction without interrupting the pump. The adaptive model acts as another intermediary, translating sensor readings into accurate fuel mass calculations.
2Reliability
If conventional measurement methods are used, then fuel delivery can be characterized, but the results are inaccurate due to disruptive shutdowns
Solution Approach 1:
The patent implements a feedback mechanism where the adaptive model continuously receives real-time data from pressure and temperature sensors during pump operation. The control module compares predicted fuel mass with actual sensor measurements and adjusts the model parameters accordingly. This feedback loop ensures both reliable fuel delivery characterization and high measurement precision without requiring disruptive shutdowns.
Solution Approach 2:
The patent employs a dynamic adaptive model that continuously updates its parameters based on real-time operating conditions. Rather than using static measurement methods that require shutdowns, the model adapts to changing pressure, temperature, and pump operation conditions dynamically during operation, maintaining both reliability and precision of fuel delivery measurements.
Data Source
AI summary
A method of adaptively predicting, during operation of a pump, a mass of fuel pumped by the pump during a pumping event to a fuel accumulator (“Qpump”) to control operation of the pump is provided, comprising: generating an adaptive model of operation of the pump, including estimating a start of pumping (“SOP”) position of a plunger of the pump, estimating Qpump, determining a converged value of the estimated SOP position, and determining a converged value of the estimated Qpump; using the adaptive model to predict Qpump by inputting to the model the converged value of the estimated SOP position, a measured pressure of fuel in the fuel accumulator and a measured temperature of fuel in the fuel accumulator; and controlling operation of the pump in response to the predicted Qpump.