Industrial Automation Agent Creation Using Data Clustering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The creation of agents in industrial automation systems is a costly and labor-intensive process due to the need for significant human interaction in data collection, programming, and deployment, which hinders efficiency and scalability.
Innovation Solution
A method utilizing cluster analysis to process data from automation devices into clusters, allowing for automated analysis and generation of agents, with the option for manual or semi-automatic selection, leveraging supervised machine learning algorithms and context data to create mathematical models for agent development.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional manual processes are used for agent creation including data collection, programming and deployment, then agents can be created with high reliability and control, but the process becomes highly cost and labor intensive with low productivity
Solution Approach 1:
The system enables automated agent creation through self-service mechanisms where the agent suggestion component automatically processes data from the data sink, performs cluster analysis, and generates agent models without requiring manual data collection or programming intervention, thereby dramatically improving productivity while managing complexity through automation
Solution Approach 2:
The patent replaces manual mechanical processes (human data collection, programming, and deployment activities) with automated computational systems including cluster analysis algorithms and agent generation components that process data and create agent models automatically, substituting human labor with automated information processing mechanisms
2Extent of automation
If automated cluster analysis is used to process data into clusters, then the analysis can be performed in a fully automated manner improving productivity, but requires sophisticated algorithms and data processing infrastructure increasing device complexity
Solution Approach 1:
The patent introduces an intermediary agent suggestion component that bridges the gap between raw data in the data sink and final agent models. This intermediary performs cluster analysis using algorithms like k-means or DBSCAN, automating the transformation process while managing complexity by encapsulating sophisticated algorithms within a standardized component interface
Solution Approach 2:
The system utilizes parameter changes in data characteristics to automatically form clusters through unsupervised learning algorithms. By detecting patterns and similarities in data parameters without manual intervention, the system achieves full automation in agent creation while the algorithmic processing handles the computational complexity internally
Data Source
AI summary
An automation system, a method and an apparatus for suggesting and/or creating an agent in an industrial automation system that includes automation devices having a framework which is formed to execute the agent and which at least partially includes a data source that collects and/or processes data of the automation devices, and includes a data sink, in which data, in particular status data, of the data sources is saved, wherein an agent suggestion component processes data of the data sink into clusters via a cluster analysis, and wherein the agent suggestion component makes the clusters available at an interface such that a model for the agents becomes creatable by an agent generation component based on at least one selection of the clusters such that it becomes possible to suggest and/or create agents in a simpler and more efficient manner.