Neural Network Fuel Temperature Estimation for High Pressure Pump Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing control systems for high pressure fuel pumps in internal combustion engines face challenges in accurately estimating fuel vapor generation due to the temperature difference between engine cooling water and fuel, leading to inefficient engine startup and fuel consumption.
Innovation Solution
A control device utilizing a neural network to estimate the fuel temperature by learning from parameters such as engine speed, lubrication oil temperature, fuel supply, intake air temperature, and vehicle speed, allowing precise control of fuel pressure to prevent vapor generation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If engine cooling water temperature is used to estimate fuel temperature, then the system complexity is reduced, but the measurement precision of fuel temperature deteriorates
Solution Approach 1:
The patent introduces a neural network as an intermediary computational model that processes multiple engine parameters (intake air temperature, engine speed, load, injection timing) to indirectly estimate fuel temperature. This mediator transforms readily available sensor data into accurate fuel temperature predictions without direct fuel temperature sensing, resolving the contradiction between system simplicity and measurement precision.
Solution Approach 2:
The neural network model serves multiple functions: it processes various engine operating parameters, adapts to different engine conditions through learning, and provides temperature compensation for fuel pressure control. This multi-functional approach allows the system to achieve precise fuel temperature estimation using existing sensors and computational resources already present in the engine control system.
2Reliability
If high pressure fuel pump operates longer before engine startup, then fuel vapor generation is prevented, but fuel consumption increases
Solution Approach 1:
The system performs preliminary estimation of fuel temperature and vapor generation risk before engine startup using the neural network model. Based on this advance assessment, the high pressure fuel pump is activated only when and for as long as necessary to prevent vapor generation, rather than operating for a fixed extended period. This preliminary action optimizes the balance between reliability and energy consumption.
Solution Approach 2:
The system continuously monitors engine operating parameters and uses feedback from the neural network's temperature estimation to dynamically adjust the high pressure fuel pump operation duration. The control strategy adapts pump operation based on real-time conditions, extending operation only when vapor generation is predicted, thereby preventing unnecessary energy consumption while ensuring vapor prevention when needed.
3Ease of operation
If simple temperature estimation methods are used, then the ease of operation is improved, but the productivity of engine startup deteriorates
Solution Approach 1:
The patent replaces simple mechanical or rule-based temperature estimation methods with a neural network-based computational system. Although the neural network requires computational resources, it processes multiple parameters simultaneously and provides accurate fuel temperature estimation, enabling efficient engine startup control. The system achieves both ease of operation through automated computation and improved productivity through accurate, rapid temperature assessment.
Data Source
AI summary
A control device for a high pressure fuel pump (33) for fuel injection (14) in which values of at least seven parameters of an engine speed, an engine load, a lubrication oil temperature, an amount of fuel supplied to the high pressure fuel pump (33), a temperature of intake air fed into the engine, a temperature of fuel discharged from the high pressure fuel pump (33), and a vehicle speed are acquired, and a learned neural network learned in weights using acquired values of the seven parameters as input values of the neural network and using as training data the temperature of fuel discharged from the high pressure fuel pump (33) acquired after a fixed time period from when acquiring the values of the seven parameters is stored, At the time of an engine operation, the temperature of fuel discharged from the high pressure fuel pump (33) after the fixed time period is estimated by using the learned neural network from the current estimated temperature of fuel discharged from the high pressure fuel pump (33).