ECU Fuel Type Identification Using Dynamic Torque and Neural Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing fuel type analysis methods in vehicles are inadequate for accurately distinguishing between different fuel types, particularly when they are unknown or have varying compositions, leading to suboptimal combustion efficiency and increased fuel consumption.
Innovation Solution
An electronic control unit (ECU) with an input interface for dynamic torque sensor values, pressure sensor values, and combustion performance data, coupled with a database and artificial intelligence modules, to determine fuel types and generate optimized injection waveforms using neural networks for improved combustion performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If fuel sensors are used to determine chemical compounds using light refraction, then fuel type identification is enabled, but measurement precision is insufficient for distinguishing optically similar but chemically different fuel types
Solution Approach 1:
The patent segments the fuel type identification process into multiple independent measurement dimensions: dynamic torque characteristics, speed of sound measurements, and combustion performance data. Each dimension provides partial information about the fuel type, and their combination enables precise identification of chemically different but optically similar fuels that single-method sensors cannot distinguish.
Solution Approach 2:
The patent introduces an intermediary database that stores reference data for multiple fuel types across different measurement dimensions. This database acts as a mediator between the sensor measurements and the final fuel type identification, enabling comparison of measured values against known fuel type profiles to achieve accurate distinction between similar fuels.
2Measurement precision
If the ECU uses multiple sensor values and dynamic torque data to determine fuel type, then measurement precision improves, but device complexity increases
Solution Approach 1:
The patent makes the existing ECU multi-functional by enabling it to process multiple types of data (dynamic torque, speed of sound, combustion performance) through a unified fuel type determination algorithm. The same ECU hardware that originally handled engine control now also performs fuel identification, eliminating the need for separate dedicated identification devices and reducing overall system complexity despite the enhanced measurement capabilities.
Solution Approach 2:
The system uses the vehicle's existing operational data and sensors to perform fuel type identification without requiring additional dedicated measurement devices. The ECU leverages data already being collected for engine control purposes, making the identification system self-sufficient and avoiding increased hardware complexity.
3Adaptability or versatility
If the ECU stores specific parameter configurations for multiple known fuel types, then adaptability to different fuel types improves, but loss of information increases when dealing with unknown fuel types
Solution Approach 1:
The patent performs preliminary characterization of fuel types by measuring their dynamic torque, speed of sound, and combustion performance before actual use. These measurements are stored in the database as reference profiles, enabling the system to identify and adapt to previously unknown fuel types when they are encountered, thus preventing information loss and expanding fuel type compatibility.
Solution Approach 2:
The system implements feedback by continuously monitoring combustion performance data and using it to refine fuel type identification. When an unknown fuel type is detected, the system learns from the combustion characteristics and updates its database, transforming initially unknown fuel types into known categories over time, thereby reducing information loss and improving adaptability.
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
The ECU accurately identifies fuel types, including unknown ones, and adjusts engine parameters for optimal combustion, enhancing efficiency and reducing fuel consumption by using dynamic torque and pressure sensor data to train neural networks for specific fuel configurations.
Implementation Method 1
An actual dynamic torque value of the high pressure pump may be used to determine a fuel type
Implementation Method 2
The at least one additional sensor value may be at least one sensor value allowing a calculation of the speed of sound within the fuel
Implementation Method 3
artificial intelligence entities (e.g., artificial neural networks) may be used to provide optimized parameter configurations
Data Source
AI summary
An electronic control unit for a vehicle with a combustion engine and a method of fuel analysis are provided. At least one dynamic torque sensor value from a high pressure pump of the vehicle and at least one additional sensor value including at least one pressure sensor value and/or at least one timing value are used to determine whether a combustible fuel type currently in use is known, unknown, or similar to a known fuel type. In each case, the operation of the combustion engine is optimized using specific parameter configurations for the fuel injectors of the vehicle. The specific parameter configurations are either retrieved from a database, or are generated using artificial intelligence methods.