Control Device Configuration Using Pareto Front Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current control devices for technical systems, such as traffic signal systems, require extensive manual effort for interactive validation of configuration optimizations, which is time-consuming and inefficient.
Innovation Solution
A method and configuration system that utilize Pareto optimization to determine a configuration data set that balances deviation from a default configuration with performance, using machine learning methods like genetic programming and reinforcement learning to select a configuration from a Pareto front, ensuring high user acceptance and safety with reduced effort.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If performance-driven optimization methods are used to optimize control device configuration, then system performance is improved, but safety and user acceptance cannot be guaranteed
Solution Approach 1:
The configuration optimization process is segmented into two distinct optimization tasks: a performance-driven optimization to maximize system performance, and a safety-driven optimization to ensure safety and user acceptance. This segmentation allows each optimization to focus on its specific objective without compromising the other, resolving the contradiction between performance improvement and safety guarantee.
Solution Approach 2:
A simulation model acts as an intermediary between the control device and the technical system. The simulation model evaluates both performance and safety aspects of configuration changes, allowing performance-driven optimizations to be assessed for their safety implications before being applied to the actual system, thus mediating between performance gains and safety requirements.
2Reliability
If interactive validation methods are used to check configuration safety, then safety and user acceptance are improved, but manual effort increases significantly
Solution Approach 1:
The system performs self-validation through automated simulation-based evaluation. The simulation model automatically assesses the safety and user acceptance of configuration changes without requiring manual intervention, enabling the system to validate its own configurations while minimizing manual effort and time loss.
Solution Approach 2:
The simulation model provides automated feedback on the safety and user acceptance implications of configuration changes. This feedback mechanism allows the optimization process to iteratively refine configurations while automatically checking safety constraints, reducing the need for manual validation efforts.
3Productivity
If multiple configuration parameters are optimized simultaneously, then system performance is improved, but configuration complexity increases
Solution Approach 1:
The configuration parameters are segmented into performance-related parameters and safety-related parameters. Performance parameters are optimized to maximize system productivity, while safety parameters are optimized separately to ensure safety and user acceptance. This segmentation reduces configuration complexity by allowing independent optimization of different parameter groups.
Solution Approach 2:
The optimization problem is transformed from a single-dimensional performance optimization to a multi-dimensional optimization that includes both performance metrics and safety metrics as separate dimensions. This dimensional expansion allows the system to consider multiple objectives simultaneously while maintaining manageable complexity through structured evaluation.
Data Source
AI summary
In order to configure a control device, a predefined default configuration data set is read in. Furthermore, a deviation from the default configuration data set as well as a control performance are determined for each of a large number of generated test configuration data sets. In addition, a Pareto optimization is performed for the large number of test configuration data sets, wherein the deviation as well as the control performance are used as Pareto objective criteria. A configuration data set resulting from the Pareto optimization is then selected to configure the control device.