Compressed Air Control Parameter Mapping for Closed-Loop Tuning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing compressed air provision devices struggle with adapting controller parameters to the specific physical characteristics of the system they are used in, leading to suboptimal closed-loop control performance due to user ignorance in setting these parameters.
Innovation Solution
A compressed air provision device equipped with a machine-learning model that maps system parameters to controller parameters, allowing for automatic adaptation of closed-loop control based on entered system characteristics, utilizing methods like support vector regression or artificial neural networks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual setting of controller parameters is used, then device complexity is reduced, but control performance deteriorates due to user ignorance in setting parameters
Solution Approach 1:
The system automatically determines controller parameters by receiving sensor data, identifying physical characteristics, and selecting parameters through a determination unit without requiring manual user input. This self-service approach resolves the contradiction by eliminating the need for user expertise while maintaining optimal control performance.
Solution Approach 2:
The system pre-establishes a database of controller parameters associated with different physical characteristics before operation. During runtime, the determination unit quickly retrieves and applies the appropriate parameters based on sensor data, avoiding the need for manual setting while ensuring optimal performance is achieved immediately.
2Ease of operation
If automatic parameter adaptation is implemented, then ease of operation is improved, but device complexity increases due to machine-learning model
Solution Approach 1:
The determination unit acts as an intermediary layer between sensor data input and controller parameter application. It receives sensor data, identifies physical characteristics, determines appropriate controller parameters, and applies them automatically. This intermediary structure manages complexity by organizing the parameter adaptation process into distinct, manageable functional blocks.
Solution Approach 2:
The system segments the parameter adaptation process into distinct functional units: sensor data reception, physical characteristic identification, controller parameter determination, and parameter application. This segmentation makes the complex automatic adaptation process more manageable and maintainable while preserving ease of operation.
3Reliability
If system-specific parameter adaptation is performed, then control performance is improved, but loss of time increases due to parameter determination process
Solution Approach 1:
The system pre-establishes a comprehensive database of controller parameters associated with different physical characteristics before operation begins. During runtime, the determination unit performs rapid parameter selection by comparing sensor data against this pre-prepared database, significantly reducing the time required for parameter determination while maintaining system-specific optimization.
Data Source
AI summary
A compressed air provision device (4) for carrying out a closed-loop control, in particular a closed-loop position control and/or a closed-loop pressure control, on the basis of controller parameters (RP), wherein the compressed air provision device (4) has a machine-learning model (55) and is designed to provide, using the machine-learning model (55), the controller parameters (RP) on the basis of entered system parameters (SP) which describe physical properties of a system (100) in which the compressed air provision device (4) is to be used, and to carry out the closed-loop control on the basis of the provided controller parameters (RP).