Control Model Execution for Flexible Technical System Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The control of large technical systems, such as gas turbines and manufacturing installations, faces challenges in using learning-based control systems due to complexity and variability, making it difficult to implement and certify safe and flexible control models.
Innovation Solution
A method and device that utilize a data container with encoded control models, allowing for the selection of model-specific execution modules and assignment of operating data channels, enabling flexible execution of different control models on various systems while ensuring data security and integrity through encryption and digital signatures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If learning-based control models are used to optimize technical systems, then system optimization capability is improved, but control structure complexity increases
Solution Approach 1:
The patent introduces an intermediary layer (execution module selection mechanism and data container structure) between the control model and the technical system. This intermediary handles the complexity of model execution and data mapping, allowing the optimization capability to be improved while the control structure complexity is managed through standardized interfaces and automated model selection.
2Adaptability or versatility
If multiple different control models are implemented on the same technical system, then adaptability is improved, but device complexity increases
Solution Approach 1:
The patent implements a universal execution module framework that can handle multiple different control models through a common interface. The system uses model type information in data containers to automatically select appropriate execution modules, enabling one control structure to support multiple models without proportionally increasing complexity.
Solution Approach 2:
The control system is segmented into distinct functional components: data container with model type information, execution module selection mechanism, and model-specific execution modules. This segmentation allows different control models to be implemented independently while managing complexity through modular architecture.
3Loss of information
If control models are encrypted for security, then information protection is improved, but model execution complexity increases
Solution Approach 1:
The patent performs preliminary decryption or validation of control models during the model loading or initialization phase, before execution. The system uses model type information to prepare appropriate execution modules in advance, so that during actual operation the encrypted models can be executed without adding real-time complexity.
Data Source
AI summary
In order to control a technical system by means of control model a data container is received, in which data container a control model having a training structure and model type information are encoded over all the model types. One of multiple model-type specific execution modules is selected for the technical system as a function of the model type information. Furthermore, operating data channels of the technical system are assigned input channels of the control model as a function of the model type information. Operating data of the technical system are acquired via a respective operating data channel and are transferred to the control model via an input channel assigned to this operating data channel. The control model is executed by means of the selected execution module, wherein control data are derived from the transferred operating data according to the training structure and are output to control the technical system.