On-Board Fuel Classification Using Multi-Sensor Engine Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing internal combustion engines face challenges in identifying and adapting to various alternative fuels, such as renewable diesel and biodiesel, due to their complex fuel options and varying properties, which affect engine compatibility and performance.
Innovation Solution
A multi-sensor approach using on-board sensors like flex-fuel, knock, and crankshaft sensors, combined with machine learning, to classify fuels based on properties like oxygen content and cetane number, enabling real-time fuel identification and optimization for improved engine performance and emissions control.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Object-affected harmful factors
If multiple alternative fuels are used to improve sustainability and reduce emissions, then environmental performance is improved, but fuel identification complexity increases
Solution Approach 1:
The patent segments the fuel identification process into multiple independent sensor measurements, each detecting specific fuel properties (ignition delay, cetane number, oxygen content, heating value). By dividing the complex identification task into separate measurable parameters, the system can identify alternative fuels without overwhelming complexity.
Solution Approach 2:
The patent employs existing multi-functional sensors already present in the engine system (knock sensors, crankshaft position sensors, oxygen sensors) to perform dual purposes: their original functions plus fuel identification. This universal approach allows fuel classification without adding dedicated identification hardware, reducing overall system complexity.
2Device complexity
If existing sensors are used for fuel classification, then device complexity is minimized, but measurement precision for fuel properties may be insufficient
Solution Approach 1:
The patent introduces a classification system that acts as an intermediary, translating existing sensor measurements into accurate fuel property estimates. Rather than requiring precise direct measurement of all fuel properties, the system uses sensor data as intermediaries to infer fuel characteristics through comparison with reference fuel matrices, achieving sufficient precision without additional sensors.
Solution Approach 2:
The patent replaces direct mechanical/chemical measurement methods with an information-processing approach. Instead of using complex measurement devices to directly quantify fuel properties, the system substitutes sensor observations combined with computational classification and machine learning to determine fuel characteristics, achieving high precision through data processing rather than physical measurement.
3Adaptability or versatility
If real-time fuel identification is implemented, then engine adaptability is improved, but processing time and computational load increase
Solution Approach 1:
The patent performs preliminary action by pre-establishing fuel matrices containing reference data for multiple alternative fuels and their properties. During operation, the system compares real-time sensor measurements against these pre-prepared matrices, enabling rapid classification without extensive real-time computation. The machine learning models are also trained in advance to accelerate real-time decision-making.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables accurate and efficient classification of fuels, allowing engines to adapt for optimal performance, reduced emissions, and extended component durability by leveraging sensor data and machine learning for real-time fuel recognition.
Implementation Method 1
a flex-fuel sensor originally developed for ethanol/gasoline application has demonstrated good sensitivity with varying biodiesel content
Implementation Method 2
a production accelerometer (knock sensor) or crankshaft sensor can provide analysis and input on the combustion performance of fuels, such as the start of ignition
Implementation Method 3
a production accelerometer (knock sensor) or crankshaft sensor can provide analysis and input on the combustion performance of fuels
Data Source
AI summary
A method of identifying an unknown fuel used by an internal combustion engine in a vehicle. A set of sensor models is prepared, each model representing measurements of an on-board sensor for different known fuels. The sensor models are for sensors from various sensors carried on-board the vehicle, such as a crank sensor, NOx sensor, soot sensor, and exhaust temperature sensor. While the vehicle is in operation, measurement data from two or more sensors of the sensor group is acquired and delivered to an on-board fuel identification process, which applies a statistical analysis to identify the fuel as being one of the known fuels.