Augmented Model Adaptation for Industrial Asset Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing digital models of industrial assets, such as gas turbines, struggle to remain accurate over time due to physical and environmental changes, making it difficult to maintain their performance and requiring costly and error-prone manual parameter adjustments.
Innovation Solution
A system that includes an augmented model with a high-fidelity system model and a data-driven model, which generates outputs in feature space, allowing for automatic and accurate adaptation of parameters using monitoring node data to compare and adjust the model's performance in real-time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual adaptation of asset model parameters is performed, then model accuracy can be maintained, but the process becomes time consuming, costly, and error-prone
Solution Approach 1:
The system enables self-service by automatically adapting model parameters through comparison of actual asset data with model predictions. The asset model independently identifies parameter deviations and performs self-diagnosis without human intervention, transforming the manual parameter adaptation process into an autonomous self-correction mechanism that maintains accuracy while eliminating time loss.
Solution Approach 2:
The system implements feedback by continuously comparing actual asset monitoring data with model predictions and using the discrepancies to automatically adjust model parameters. This closed-loop feedback mechanism ensures model accuracy is maintained through real-time parameter adaptation, eliminating the need for time-consuming manual adjustments while preventing errors through systematic comparison and correction.
2Measurement precision
If manual adaptation of asset model parameters is performed, then model accuracy can be maintained, but the process becomes costly and error-prone
Solution Approach 1:
The system enables self-service by automatically adapting model parameters through comparison of actual asset data with model predictions. The asset model independently identifies parameter deviations and performs self-diagnosis without human intervention, transforming the manual parameter adaptation process into an autonomous self-correction mechanism that maintains accuracy while eliminating time loss.
Solution Approach 2:
The system implements feedback by continuously comparing actual asset monitoring data with model predictions and using the discrepancies to automatically adjust model parameters. This closed-loop feedback mechanism ensures model accuracy is maintained through real-time parameter adaptation, eliminating the need for time-consuming manual adjustments while preventing errors through systematic comparison and correction.
3Reliability
If a digital model is created to simulate industrial assets, then accurate analysis and cybersecurity inputs can be provided, but the model becomes difficult to keep accurate as machines and environments change
Solution Approach 1:
The system applies dynamics by transforming the static digital model into a dynamic adaptive system. The asset model continuously updates its parameters based on real-time comparison between predicted and actual asset behavior, enabling the model to automatically adapt to physical changes in machines and environmental changes. This dynamic adaptation mechanism maintains model accuracy and reliability for cybersecurity and analysis applications despite ongoing changes in the industrial asset ecosystem.
4Measurement precision
If the number of monitoring nodes is increased to improve model accuracy, then more data is available for analysis, but the complexity of manual parameter tuning increases substantially
Solution Approach 1:
The system enables self-service by automatically adapting model parameters through comparison of actual asset data with model predictions. The asset model independently identifies parameter deviations and performs self-diagnosis without human intervention, transforming the manual parameter adaptation process into an autonomous self-correction mechanism that maintains accuracy while eliminating time loss.
Solution Approach 2:
The system implements feedback by continuously comparing actual asset monitoring data with model predictions and using the discrepancies to automatically adjust model parameters. This closed-loop feedback mechanism ensures model accuracy is maintained through real-time parameter adaptation, eliminating the need for time-consuming manual adjustments while preventing errors through systematic comparison and correction.
Data Source
AI summary
An augmented system model may include a system high fidelity model that generates a first output. The augmented system model may further include a data driven model to receive data associated with the first output and to generate a second output, and a feature space version of the second output may be output from the augmented system model. Monitoring nodes may each generate a series of current monitoring node values over time representing current operation of an industrial asset. A model adaptation element may receive the current monitoring node values, calculate a feature space version of current operation, and compare the feature space version of the second output of the augmented system model with the feature space version of current operation. Parameters of the data driven model may then be adapted based on a result of the comparison.