Model-Based State Quantity Estimation for Plant Device Management
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In power generation plants, not all instruments are equipped with measurement instruments to collect state quantities, making it challenging to estimate and manage device operations effectively, as there is ambiguity about which models to use for calculation.
Innovation Solution
An information processing device is designed with a measurement value acquisition unit, a model determination unit, an estimation unit, and a management unit to acquire, determine, and estimate state quantities using appropriate models for each evaluation item, allowing for accurate management of target devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple models are used for estimating state quantities, then the accuracy of estimation can be improved, but it becomes unclear which model to use for appropriate plant management
Solution Approach 1:
The patent implements a feedback mechanism where the system evaluates the appropriateness of each model based on plant management requirements and measurement data quality, then selects the most suitable model. The system continuously monitors estimation results and adjusts model selection accordingly, creating a closed-loop system that resolves the ambiguity of model choice while maintaining high estimation accuracy.
Solution Approach 2:
The patent changes the parameter of model selection from a static choice to a dynamic decision based on evaluation criteria. By introducing evaluation items that assess model appropriateness according to plant management needs and data quality, the system adapts model selection to varying conditions, thereby resolving the contradiction between having multiple models and knowing which one to use.
2Loss of information
If measurement instruments are installed on all instruments, then complete state quantity data can be collected, but the cost and complexity of the system increases
Solution Approach 1:
The patent introduces an information processing device as an intermediary that bridges the gap between incomplete measurement data and complete state quantity information. This mediator uses appropriate models to estimate missing state quantities based on available measurement data, thereby achieving data completeness without requiring physical measurement instruments on all devices.
Solution Approach 2:
The patent creates virtual copies of measurement data through model-based estimation. Instead of physically measuring all state quantities, the system generates estimated values that replicate the information that would be obtained from physical sensors, thereby achieving data completeness while avoiding the complexity of installing numerous measurement instruments.
3Reliability
If models are selected based on evaluation items, then appropriate model selection for plant management is achieved, but additional processing steps are required
Solution Approach 1:
The patent performs preliminary evaluation of models based on predetermined criteria related to plant management requirements. By pre-establishing evaluation items and assessing model appropriateness before actual estimation, the system prepares the optimal model selection in advance, thereby reducing the time required during actual operation while ensuring reliable plant management.
Data Source
AI summary
An acquisition unit is configured to acquire a measurement value of a first state quantity of a target device. A model determination unit is configured to determine a model for estimating a value of a second state quantity of the target device for each evaluation item for management of the target device. An estimation unit is configured to estimate the value of the second state quantity on the basis of the measurement value using the model determined by the model determination unit. A management unit calculates a value of the evaluation item using the value estimated by the estimation unit.