PLC Design Environment for Machine Learning Model Integration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Industrial manufacturing environments face challenges in extracting enterprise-level insights due to the vast amount of data generated quickly, and existing technologies do not effectively integrate machine learning models into industrial automation environments.
Innovation Solution
A system and method for surfacing machine learning models in programming environments for use in control programs, allowing users to select program tags representing target variables, identify associated machine learning models, and integrate these models into control programs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If machine learning models are integrated into industrial automation environments, then advanced analytics and optimization capabilities are enhanced, but system complexity increases
Solution Approach 1:
The patent introduces a design component as an intermediary layer between the control system and machine learning models. This component automatically identifies relevant tags from the control program, retrieves associated machine learning models, and integrates them into the control logic, thereby shielding users from the complexity of direct ML integration while enabling advanced analytics capabilities
Solution Approach 2:
The design component performs self-service by automatically querying the control program for relevant tags, autonomously retrieving machine learning models based on those tags, and seamlessly integrating them without requiring manual configuration or deep technical knowledge from the user
2Measurement precision
If users manually search through numerous program tags to identify useful variables, then specific target variables can be located, but time and effort are consumed
Solution Approach 1:
The design component automatically queries the control program to identify tags relevant to the selected machine learning model, eliminating the need for users to manually search through numerous tags. The system self-services by performing the identification task that would otherwise require significant user time and effort
3Adaptability or versatility
If machine learning models are made accessible in the programming environment, then model integration is enabled, but the interface complexity increases
Solution Approach 1:
The design component serves as an intermediary that presents machine learning models to users in a simplified manner. It automatically retrieves models based on control program tags and integrates them seamlessly, allowing users to access ML functionality through a familiar programming interface without exposing the underlying complexity of model integration
Data Source
AI summary
Various embodiments of the present technology generally relate to industrial automation environments. More specifically, embodiments include systems and methods to surface machine learning systems in a design application of an industrial automation environment. In some examples, a design component generates a control program configured for implementation by a Programmable Logic Controller (PLC). The design component receives a user input that selects a program tag that represents a target variable in an industrial automation process. In response to the user selection, the design component identifies one or more machine learning models associated with the target variable and displays the one or more machine learning models. The design component receives a user input that selects one of the one or more machine learning models and responsively integrates another program tag that represents the selected machine learning model into the control program.