AI Control Application Timing for Real-Time Industrial Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
AI accelerators are not suitable for real-time critical control flows in industrial automation due to their inability to meet strict cycle time requirements, limiting their integration to non-real-time critical control systems.
Innovation Solution
A computer-implemented method that reads hardware configuration parameters of both the control unit and AI computing unit, determines processing time for an AI-based control application, checks if it meets real-time requirements, and adapts the application to ensure compliance, allowing AI accelerators to be integrated into real-time critical control flows.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Power
If AI accelerators are integrated into control systems, then computing speed and AI processing capability are improved, but real-time cycle time requirements cannot be met
Solution Approach 1:
The patent performs preliminary determination of processing time for AI control applications before actual execution. The system calculates expected processing times based on hardware configuration parameters and control application characteristics, allowing real-time feasibility assessment before deployment. This preliminary action enables the system to identify whether AI accelerators can meet real-time requirements in advance, preventing time constraint violations during actual control operations.
2Productivity
If AI-based algorithms are used in industrial automation, then computational efficiency is improved, but strict real-time requirements cannot be complied with
Solution Approach 1:
The patent implements a feedback mechanism where the determined processing time is checked against real-time requirement values. The system compares the calculated processing time with the maximum allowable cycle time and provides feedback on whether the AI control application can meet real-time requirements. This feedback loop enables reliable determination of real-time compliance before deployment, ensuring that AI-based algorithms maintain both computational efficiency and real-time reliability.
3Adaptability or versatility
If specialized AI computing units are integrated into industrial controllers, then AI functionality is enhanced, but integration into real-time critical control flows is limited
Solution Approach 1:
The patent changes the approach from attempting to integrate AI accelerators directly into real-time control flows to instead determining processing time as a separate parameter. By treating processing time as a calculable parameter based on hardware configuration and application characteristics, the system enables AI functionality integration without directly complicating the real-time control flow structure. This parameter-based approach simplifies integration while maintaining AI versatility.
Data Source
AI summary
A computer-implemented method for controlling a technical system is provided, including: —reading in hardware configuration parameters and a value of a real-time requirement of a control unit, —reading in hardware configuration parameters of a computing unit for artificial intelligence, —reading in a control application for controlling the technical system, the control application being configured to generate an input value for the control unit in accordance with an artificial intelligence, —determining a processing time of the control application for execution of the control application on the computing unit for artificial intelligence, considering the hardware configuration parameters of the control unit and the hardware configuration parameters of the computing unit for artificial intelligence, —checking the determined processing time based on the value of the real-time requirement of the control unit and outputting a check result, and —the control application, depending on the check result, for the control of the technical system.