Control Device Configuration Using Pareto Trade-Off Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for configuring control systems in complex technical systems, such as traffic light systems, turbines, and robots, require significant manual effort for interactive validation and often result in configurations that lack user acceptance and safety.
Innovation Solution
A method utilizing Pareto optimization, which considers both deviation from a standard configuration and performance, to determine a configuration dataset that balances familiarity with the standard behavior and optimal performance, using machine learning techniques like genetic programming and reinforcement learning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If performance-driven optimization methods are used to configure control systems, then system performance is improved, but safety and user acceptance deteriorate
Solution Approach 1:
The patent segments the configuration process into two distinct phases: a performance optimization phase that generates candidate configurations, and a validation phase that verifies safety and user acceptance. This segmentation allows each phase to focus on its specific objective without compromising the other, resolving the contradiction between performance improvement and safety maintenance.
Solution Approach 2:
The patent performs preliminary validation by checking candidate configurations against safety constraints and user acceptance criteria before they are deployed. This preliminary action ensures that only configurations meeting both performance and safety requirements are implemented, preventing safety issues from arising after performance optimization.
2Reliability
If interactive validation methods are used to validate configuration changes, then safety and user acceptance are improved, but manual effort increases
Solution Approach 1:
The patent implements automated validation mechanisms that self-verify configuration changes against predefined safety constraints and user acceptance criteria. The system automatically evaluates candidate configurations without requiring manual intervention, thereby maintaining high safety standards while minimizing manual effort. The automated process includes checking constraints, simulating behavior, and validating configurations independently.
3Manufacturing precision
If multiple test configuration data sets are generated and evaluated using Pareto optimization, then configuration quality is improved, but computational effort increases
Solution Approach 1:
The patent applies Pareto optimization to evaluate multiple test configuration data sets, but limits the evaluation to the most promising candidates identified through preliminary filtering. Instead of exhaustively evaluating all possible configurations, the system focuses computational resources on a subset of high-potential configurations, achieving high configuration quality while managing computational effort efficiently.
Data Source
Figure 1
Figure 2
AI summary
In order to configure a control device (CTL), a predefined standard configuration data set (LO) is imported. Furthermore, a deviation from the standard configuration data set (LO) and a control performance are determined for each of a plurality of generated test configuration data sets (LT). Furthermore, a Pareto optimization is carried out for the plurality of test configuration data sets (LT), wherein the deviation and the control performance are used as Pareto target criteria. A configuration data set (LTO) resulting from the Pareto optimization is then selected for configuring the control device (CTL).