Fluid Valve Position Sensing Without Hardware Sensors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electromagnetically actuated fluid valves with a single electromagnet face challenges in precise position control due to hysteresis, friction, and temperature effects, necessitating costly and space-consuming hardware sensors, which are not economically viable for many applications.
Innovation Solution
Implementing a data-based position sensor using a prediction model trained with time series data from a test procedure, eliminating the need for hardware sensors by accurately determining the position of the armature or valve element through machine learning models like artificial neural networks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If hardware position sensors are used to detect armature position, then measurement precision and control accuracy are improved, but device complexity and cost increase
Solution Approach 1:
The patent replaces hardware position sensors with a data-based position sensor that uses machine learning models (neural networks) to predict armature position based on electrical measurements. The system substitutes physical sensing components with computational algorithms that process voltage and current signals to determine position, thereby eliminating mechanical sensors while maintaining measurement precision.
Solution Approach 2:
The patent creates a virtual model of the electromagnet system using trained neural networks that replicate the physical behavior of the armature. This digital twin or copy allows position determination through computational inference rather than direct physical measurement, reducing hardware complexity while preserving measurement accuracy.
2Measurement precision
If hardware position sensors are installed, then position control accuracy is improved, but installation space requirements increase
Solution Approach 1:
The patent merges the position sensing function with the existing electrical control system by using the same coil for both actuation and measurement. The data-based position sensor integrates position detection capabilities into the control electronics, eliminating the need for separate sensor installations and reducing overall system space requirements.
Solution Approach 2:
The patent makes the coil serve multiple functions: it acts as both the actuating electromagnet and the measurement sensor. By utilizing the existing electrical components for dual purposes, the system eliminates dedicated sensor hardware and reduces installation space while maintaining position detection accuracy.
3Reliability
If additional position sensors are added, then control reliability is improved through compensation of disturbance variables, but the number of potential error sources increases
Solution Approach 1:
The patent implements feedback through trained neural networks that continuously process electrical measurements and predict armature position while compensating for disturbance variables like hysteresis and friction. The system uses the electrical signals as feedback to infer position and correct for non-ideal behaviors, improving control reliability without adding physical sensors.
Solution Approach 2:
The patent enables the electromagnet system to self-diagnose and self-measure its own state by using its electrical characteristics to determine position. The system serves its own sensing needs through computational analysis of its operational parameters, eliminating the need for external sensing components and reducing the number of potential failure points.
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 precise position and volume flow control without additional hardware, reducing costs and installation space while compensating for disturbance variables, thus enhancing the reliability and efficiency of electromagnetically actuated fluid valves.
Implementation Method 1
the movement and therefore the positioning of the valve element is achieved by energizing the coil with an actuating current and the resulting movement and positioning of the armature within the coil
Implementation Method 2
a data-based position sensor comprising a prediction model for a position of an electromagnetically actuated element of the electromagnetically actuated component
Data Source
AI summary
A method for implementing a data-based position sensor for an electromagnetically actuated component is provided. The data-based position sensor comprises a prediction model for the position of an electromagnetically actuated element of the electromagnetically actuated component. In the method, a training data set is generated using the electromagnetically actuated component and the prediction model is trained using the training data set. In particular, this makes it possible to determine the position of a valve element of an electromagnetically actuated fluid valve, which comprises only one electromagnet for actuating the valve element, without the use of hardware sensors for position measurement.