Edge Gateway Feature Engineering for Contextual KPI Analytics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Industrial automation systems face challenges in collecting and formatting data from distributed industrial devices into meaningful presentations for users, as much of the data is unstructured and lacks context, burdening developers to define its meaning.
Innovation Solution
The implementation of structured data types, referred to as Basic Information Data Types (BIDTs), which are configured on industrial devices to represent structured information, and a gateway device that references these BIDTs to generate contextualized presentations and support feature engineering tools for defining mathematical relationships between data points and key performance indicators (KPIs).
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If unstructured data from distributed industrial devices is collected and formatted manually, then data can be presented to users, but developer burden increases and data analytics complexity rises
Solution Approach 1:
The system enables self-service data presentation by automatically generating contextualized presentations of industrial data through the gateway device. The gateway device autonomously references BIDTs defined on industrial devices to format and contextualize data without requiring manual developer intervention, thereby reducing developer burden while maintaining data presentation capabilities
Solution Approach 2:
The patent transforms unstructured industrial data into structured, contextualized information by applying parameter-based data types (BIDTs). This parameter change from raw unstructured data to typed structured data automatically enables meaningful presentations and reduces analytics complexity, as the data inherently carries context and meaning through its data type definitions
2Reliability
If all industrial data points are collected and analyzed, then comprehensive process monitoring is achieved, but time and computational resources increase
Solution Approach 1:
The gateway device extracts and references only the specific data points defined by BIDTs from the industrial devices. This extraction approach retrieves precisely the relevant data needed for process monitoring without collecting unnecessary data, thereby achieving comprehensive monitoring of critical parameters while reducing overall data volume and analytics time
Solution Approach 2:
The BIDTs are pre-defined on industrial devices with inherent context and meaning established beforehand. This preliminary structuring of data allows the system to directly use pre-configured data definitions for rapid contextualization and presentation, eliminating the need for time-consuming data interpretation and reducing analytics time while maintaining monitoring reliability
Data Source
AI summary
An industrial gateway device supports interactive feature engineering tools that guide a user through an intuitive process for configuring data analytics for key performance indicators (KPIs) of interest. A feature engineering interface renders an interactive model view that displays available data points such that the data points are organized hierarchically according to plant, machine, machine property, or other elements. The user can select, from this model view, data points having an impact on the KPI of interest. The interface also allows the user to define an executable script that defines a mathematical relationship between the selected data points and the KPI. This configuration yields an output model that defines a reduced set of data points to be collected and analyzed, as well as an executable script for assessing a state of the KPI as a function of the reduced data point values.