Polynomial Regression for Injection Valve Actuator Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for determining energization data for injection valves in motor vehicles are inefficient and inaccurate due to reliance on empirical calibration and slow correction processes, failing to meet stringent requirements for fuel injection quantity accuracy.
Innovation Solution
A method using a polynomial regression model in a control unit to determine energization data for actuator energization, considering input data such as desired piezo voltage, charge, behavior, temperature, and individual actuator parameters, allowing for precise calculation of energization periods and current profiles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If characteristic diagrams are calibrated empirically to determine energization time, then the energization data can be predefined for different operating points, but the process entails large expenditure and slow correction
Solution Approach 1:
The patent replaces the empirical mechanical calibration process with a mathematical polynomial regression model. The control unit calculates energization data by evaluating polynomial functions based on operating parameters, eliminating the need for time-consuming empirical characteristic diagram calibration while maintaining high accuracy in fuel injection quantity control
Solution Approach 2:
The system enables self-determination of energization data through the polynomial regression model, which automatically calculates the required energization time based on current operating conditions without requiring external calibration procedures or manual adjustment of characteristic diagrams
2Reliability
If characteristic diagrams are used to define energization time as a function of operating point, then energization data can be determined, but the correction process is comparatively slow and cannot ensure stringent accuracy requirements
Solution Approach 1:
The patent substitutes the slow iterative correction process of empirical characteristic diagrams with immediate polynomial function evaluation. The control unit computes energization data in real-time using polynomial expressions, achieving both high reliability through mathematical precision and high productivity through instantaneous calculation
Solution Approach 2:
The system changes the approach from fixed empirical characteristic values to dynamic polynomial parameters that can be evaluated instantly. By representing energization time as a polynomial function of operating parameters, the system achieves rapid recalculation capability while maintaining accurate fuel injection control under varying conditions
3Measurement precision
If empirical determination of influencing variables is performed to produce characteristic diagrams, then energization time can be predefined, but large expenditure is required
Solution Approach 1:
The patent replaces expensive empirical calibration procedures with a computational polynomial regression model. The control unit determines energization data through mathematical calculations based on operating parameters, eliminating the need for costly experimental characterization and repeated measurements while maintaining high measurement precision
Solution Approach 2:
The system creates a mathematical copy (polynomial regression model) of the complex physical relationships between operating parameters and energization requirements. This virtual model replicates the behavior of the physical system without requiring physical experimentation, thereby reducing calibration expenditure while preserving accuracy
Data Source
AI summary
Various embodiments includes a method for determining energization data for an actuator of an injection valve of a motor vehicle comprising: receiving input data at a control unit; and determining the energization data based on the received input data into account with the control unit. Determining the energization data includes using a polynomial regression model.