Monitoring Target Selection for Stable Plant Anomaly Diagnosis

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing abnormality detection systems in nuclear power generation plants face difficulties in detecting anomalies due to discontinuous changes in measurement information from devices with different operation cycles, leading to inefficient and erroneous detection.

Innovation Solution

A monitoring target selecting device that classifies measurement parameter behaviors over time in different periods and selects parameters for output based on comparisons, ensuring consistent behavior and normalcy, thereby reducing erroneous detection and improving anomaly identification.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If measurement parameters from devices with different operation cycles are used for abnormality detection, then the system can monitor more comprehensive plant operations, but the correlation between parameters breaks down causing erroneous detection

Engineering Contradiction:

Improvemonitoring coverageVSAvoiddetection accuracy

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The patent segments measurement parameters into different operation cycle groups (first operation cycle and second operation cycle). By classifying parameters according to their operation cycles and selecting only those from the first operation cycle for correlation-based abnormality detection, the system maintains parameter correlation integrity while still allowing comprehensive monitoring through separate tracking of parameters from different cycles.

Inventive Principle:

Principle #1Segmentation

2Measurement precision

If all measurement parameters are used for abnormality detection, then detection comprehensiveness is improved, but erroneous detection increases due to parameter behavior inconsistency across different periods

Engineering Contradiction:

Improvedetection comprehensivenessVSAvoiddetection accuracy

Core Design Contradiction:

Measurement precisionVSReliability

Solution Approach 1:

The patent performs preliminary classification of measurement parameters into different operation cycle groups before abnormality detection. By pre-identifying which parameters belong to the first operation cycle and selecting only those for correlation-based detection, the system eliminates the problem of behavior inconsistency that would otherwise cause erroneous detection, while maintaining comprehensive monitoring capabilities.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS11480948B2Monitoring target selecting device, monitoring target selecting method, and program

Publication Date: 2022.10.25 MITSUBISHI HEAVY IND LTD

AI summary

A monitoring target selecting device configured to output a measurement parameter to an abnormality diagnosis device to diagnose an abnormal event of a plant based on a correlation value representing a mutual correlation between measurement parameters, and includes a classification unit to acquire a plurality of measurement parameters measured in the plant, classify a change behavior of measured value over a time for each of the plurality of measurement parameters in a first period, and classify a change behavior of a measured value over a time for each of the plurality of measurement parameters in each of the first period and a second period, and a selection unit to select the measurement parameter as a measurement parameter to be output to the abnormality diagnosis device on the basis of a result of comparing a behavior of the measurement parameters in the first period to the second period.