Energy Efficiency Evaluation Using Digital Twin and Neural Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Evaluating energy efficiency at industrial or commercial sites is a complex and time-consuming process due to the high complexity and interdisciplinary nature of combining data from different sources and creating accurate physical models, which is inherently difficult.
Innovation Solution
A method involving the comparison of time-series energy consumption data using a trained artificial neural network (ANN) to identify patterns and output quality measures for energy efficiency, allowing for automated and qualitative evaluation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual analysis methods are used to evaluate energy efficiency, then deep understanding of the site can be achieved, but the process becomes time-consuming
Solution Approach 1:
The patent creates a digital twin (virtual model) of the physical site that replicates energy consumption patterns. This virtual model can be analyzed repeatedly and quickly without affecting the actual site, enabling fast evaluation while maintaining accuracy through multiple simulation iterations.
Solution Approach 2:
The patent performs preliminary data collection and model creation during off-peak periods or in advance. Energy consumption data is continuously collected and stored, and the digital twin is pre-configured with site specifications, so that when evaluation is needed, the analysis can proceed immediately without time-consuming setup.
2Measurement precision
If data from different data sources are combined for comprehensive analysis, then accurate energy consumption analysis is achieved, but the complexity of the process increases
Solution Approach 1:
The patent merges multiple data sources (energy consumption data, site specifications, operational data) into a unified digital twin model. This consolidation allows comprehensive analysis while reducing the apparent complexity by providing a single integrated view of all data through the virtual model.
Solution Approach 2:
The digital twin acts as an intermediary layer between raw data from multiple sources and the analysis process. It standardizes and harmonizes data from different formats and sources, making integration easier while maintaining the ability to perform comprehensive cross-source analysis.
3Productivity
If physical models are created for energy optimization, then optimization potential can be identified, but obtaining accurate models becomes inherently difficult
Solution Approach 1:
Instead of creating complex physical models, the patent creates a virtual copy (digital twin) of the site's energy systems. This virtual model replicates the behavior and characteristics of physical systems but is easier to manipulate, test, and optimize without the constraints of physical reality.
Solution Approach 2:
The patent uses parameter-based modeling in the digital twin, where system characteristics are represented as adjustable parameters. This allows easy modification and optimization of energy consumption patterns by changing parameters rather than redesigning physical systems, making accurate modeling more achievable.
Data Source
Figure 1a~1b
Figure 2
Figure 3
AI summary
The invention relates to the field of evaluating an energy efficiency, particularly for industrial or commercial sites. A method for evaluating an energy efficiency of a second energy consumption scenario (20) of a site comprises the steps of: obtaining a first energy consumption scenario (10), which comprises a first time-series of energy consumption data (14) of at least one device, and a quality measure (18) of the first energy consumption scenario (10); obtaining the second energy consumption scenario (20), which comprises a second time-series of energy consumption data (24), wherein the second energy consumption scenario (20) has a same or a shorter duration than the first energy consumption scenario (10); comparing the second time-series of energy consumption data (24) to the first time-series of energy consumption data (14); and if the second time-series of energy consumption data (24) is similar to the first time-series of energy consumption data (14), outputting the quality measure (18) of the first energy consumption scenario (10).