Hybrid State Estimation for Plant Equipment Deterioration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing information processing devices for managing industrial plants do not accurately set values for omission state quantities, failing to consider adaptation conditions of models used in complementary processes, which affects the accuracy of state quantity estimation.
Innovation Solution
An information processing device that combines statistical and physical models to estimate state quantities, using a specification unit to determine management values based on deterioration of the target device over time, with optional features like notification for discrepancies and model updating.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a statistical model is used to estimate state quantities, then estimation can be performed based on past operational data, but accuracy deteriorates when the device deteriorates over time
Solution Approach 1:
The patent combines statistical models and physical models into a hybrid estimation system. The statistical model processes operational data while the physical model incorporates device deterioration characteristics, allowing the system to maintain accuracy even as the device ages and deteriorates over time.
Solution Approach 2:
The system dynamically adjusts model parameters based on device operation time and deterioration state. As the device deteriorates, the physical model parameters are updated to reflect current device conditions, enabling the statistical model to continue providing accurate estimations despite changes in device performance.
2Reliability
If a physical model is used to estimate state quantities, then device deterioration can be accounted for, but the model requires accurate design data and may not adapt to actual operational variations
Solution Approach 1:
The patent merges physical models with statistical models to create a hybrid system. The physical model provides the theoretical framework for device deterioration while the statistical model adapts to actual operational data, combining the strengths of both approaches to achieve accurate estimations under varying conditions.
Solution Approach 2:
The system uses operational data feedback to continuously refine and update model parameters. The statistical model processes actual operational measurements and feeds this information back to adjust the physical model parameters, ensuring the model remains accurate as device conditions change during operation.
3Measurement precision
If multiple models are used for estimation, then accuracy can be improved, but system complexity increases
Solution Approach 1:
The patent segments the estimation system into distinct statistical and physical model components, each handling specific aspects of state quantity estimation. This modular segmentation allows the complex multi-model system to be managed through separate, specialized sub-systems that can be independently developed and maintained.
Solution Approach 2:
The system introduces a model integration mechanism that acts as an intermediary between the statistical and physical models. This intermediary component coordinates the interactions between models, manages parameter exchanges, and synthesizes final estimations, reducing the overall system complexity by providing a structured interface between components.
Data Source
AI summary
In an information processing device according to the present invention, a statistics estimation unit estimates a value of a state quantity by using a statistical model constructed based on values of past state quantities of a target device. A physical estimation unit estimates a value of a state quantity by using a physical model constructed based on design data of the target device. A specification unit specifies a value to be used to manage the target device from the value estimated by the statistics estimation unit and the value estimated by the physical estimation unit based on deterioration of the target device with time.