Contextualization Engine Correlates Energy and Production Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing energy management systems in manufacturing facilities lack the ability to correlate energy consumption data with production activity data, hindering informed business decisions regarding energy usage.
Innovation Solution
Implementing an energy management system that includes a contextualization engine to correlate production activity data from automation and process control systems with energy consumption data, providing Key Performance Indicators (KPIs) such as value-added and non-value-added energy consumption, and direct and indirect energy consumption metrics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If energy consumption data is collected separately from production activity data, then data collection is simple, but the ability to make informed energy decisions is hindered
Solution Approach 1:
The patent combines separate energy consumption data and production activity data into a unified energy management system. The contextualization engine merges these previously separate data streams, allowing correlation analysis between energy usage and production activities, thereby eliminating information loss while managing complexity through integrated architecture.
Solution Approach 2:
The contextualization engine acts as an intermediary component that receives both energy consumption data and production activity data from separate sources. It processes and correlates these data streams, providing contextualized energy metrics without requiring complete system redesign, thus balancing information integration with manageable complexity.
2Loss of information
If energy consumption data is not contextualized with production activity, then data processing is simple, but actionable metrics for decision making are unavailable
Solution Approach 1:
The contextualization engine segments the complex task of energy data analysis into distinct processing stages: receiving energy consumption data, receiving production activity data, correlating these data streams, and generating contextualized metrics. This segmentation enables actionable insights while managing processing complexity through structured modular operations.
3Loss of information
If traditional energy management systems are used, then system cost is lower, but the ability to differentiate value-added from non-value-added energy consumption is lost
Solution Approach 1:
The system applies local quality by categorizing energy consumption at specific production stages and equipment levels rather than providing only aggregate data. The contextualization engine generates differentiated metrics for value-added and non-value-added energy consumption at various hierarchical levels, enabling targeted decision-making without requiring complete system overhaul.
Data Source
AI summary
Systems, methods, and other embodiments associated with contextualizing energy consumption are described. One example method includes accessing stored energy consumption data and stored operation status data from production-related equipment; correlating the operation status data with the energy consumption data; and categorizing energy consumed by the production-related equipment as value-added or non-value-added based, at least in part, on the correlating of the operation status data with the energy consumption data. The example methods may also include determining an energy classification for an energy-consuming entity; identifying child entities of the energy-consuming entity; accessing energy consumption data for the energy-consuming entity and the child entities; aggregating the energy consumption data for the energy-consuming entity and the child entities; and classifying the aggregated energy consumption data with the energy classification for the energy-consuming entity.