Self-Learning Compatibility Checks for Control Program Naming
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing planning tools face challenges in ensuring compatibility of control program names with data processing facilities, leading to errors during transmission due to incomplete and complex rules, which are difficult to implement and change over time, resulting in laborious reassignment of names.
Innovation Solution
Implementing a machine learning-based checking routine that learns from assessments received from the data processing facility, allowing the planning tool to adapt and improve over time without requiring constant programmer intervention, enabling immediate corrective action during name specification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a complete set of rules is created for checking compatibility, then checking accuracy is improved, but implementation complexity and effort increase unacceptably
Solution Approach 1:
The system uses feedback from the data processing facility to automatically improve its own checking capability through machine learning, eliminating the need for manual rule creation and maintenance. The checking routine learns compatibility rules autonomously from actual transmission outcomes.
Solution Approach 2:
The system implements a feedback loop where the data processing facility communicates assessment results back to the planning tool, which then uses this feedback to retrain and improve the checking routine's compatibility assessment accuracy over time.
2Reliability
If manual reassignment of names is performed to ensure compatibility, then transmission reliability is improved, but time consumption and labor increase
Solution Approach 1:
The checking routine performs preliminary compatibility verification of names before transmission occurs. By checking and identifying incompatibilities in advance, the system prevents transmission errors and eliminates the need for time-consuming manual reassignment operations.
3Difficulty of detecting and measuring
If comprehensive checking rules are implemented, then error detection capability is improved, but the system becomes difficult to maintain and adapt when rules change
Solution Approach 1:
The checking routine transitions from a static rule-based system to a dynamic machine learning model that continuously adapts to changing compatibility requirements. The system can automatically adjust to new rules and restrictions without requiring manual reconfiguration when the data processing facility's requirements change.
Data Source
AI summary
A control program for an industrial technical control system is created via a planning tool, wherein the control program includes program data that are assigned names by the planning tool, where beforehand, the planning tool checks the names of the program data of the control program via a checking routine for compatibility with the data processing device, and if the planning tool identifies an incompatibility by means of the checking routine, then it outputs a corresponding error message to the user, otherwise it outputs to the user either no message or a message indicating that no errors have been identified, and the planning tool receives an assessment of the control program from the data processing device and post-trains the checking routine based on the relevant control program and received assessment such that the checking routine gradually learns which names for the program data are compatible with the data processing device.