Industrial Automation Component Runtime Prediction for Real-Time Configuration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for predicting the real-time behavior of industrial automation components are time-consuming and inadequate for flexible systems due to the large number of permutations of hardware and software versions, making it difficult to ensure consistent cycle times and jitter within predefined limits.
Innovation Solution
A method using reinforcement learning to create a model that predicts real-time behavior by measuring and storing properties of various hardware and software combinations, allowing for precise configuration and programming without extensive testing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional iterative testing methods are used to determine real-time behavior for each hardware and software combination, then measurement precision is improved, but loss of time increases significantly
Solution Approach 1:
The system performs preliminary measurements and stores results in a knowledge base before actual configuration is needed. By pre-measuring real-time behavior for multiple hardware and software combinations and storing these results, the system eliminates the need for time-consuming iterative testing during actual configuration, while maintaining measurement precision through the stored empirical data.
Solution Approach 2:
The system creates a virtual model (knowledge base) that copies and stores measured real-time behavior data from physical hardware-software combinations. This virtual representation allows prediction of real-time behavior without physically testing each combination, significantly reducing time loss while preserving measurement accuracy through the copied data.
2Reliability
If hardware is dimensioned generously to guarantee real-time behavior for untested combinations, then reliability is improved, but loss of substance increases due to over-provisioning
Solution Approach 1:
The system uses feedback from the knowledge base, which contains measured real-time behavior data from actual hardware and software combinations. This feedback mechanism allows the system to make informed predictions about untested combinations based on empirical evidence, eliminating the need for conservative over-provisioning while maintaining reliability guarantees.
Solution Approach 2:
The system changes the approach from static hardware over-provisioning to dynamic parameter-based prediction using the knowledge base. By storing and utilizing measured parameters (cycle times, jitter values) from various configurations, the system can predict real-time behavior for untested combinations without requiring generous hardware dimensioning, thus reducing resource waste while maintaining reliability.
Data Source
AI summary
A method and assembly for configuring and/or programming an industrial automation component, wherein respective properties at runtime are detected and stored in a database for a plurality of possible combinations of the hardware, the operating system and/or the application program, and wherein a model is generated from the database data and/or optimized using a reinforcement learning process, where a reinforcement learning reward function used during the learning or optimization process seeks to provide an accurate prediction of the properties, the properties at runtime are then predicted for intended or possible combinations using the model compared with a specified requirement, and a suitable combination is subsequently ascertained using the comparison, and the industrial automation component is configured or programmed according to the selected combination, such that the real-time behavior is very precisely predicted such that the industrial automation component can be optimally configured or programmed.