Nuclear Plant Abnormality Detection via Dynamic Normal Ranges

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing plant abnormality indication monitoring systems face challenges in detecting anomalies due to changing operation data, which can transition between normal and warning regions, leading to increased computation load and noise influence, especially in nuclear power plants performing base-load operations.

Innovation Solution

A monitoring system that sets a normal range for instrument parameters based on past operation data, allowing detection of abnormalities by comparing present data against predefined thresholds without requiring correlation calculations, and adjusts sensitivity by modifying the width of the normal range according to operation modes and cycles.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If correlation-based abnormality detection is used, then detection accuracy is improved, but computation load increases

Engineering Contradiction:
Improveabnormality detection accuracyVSAvoidcomputation load
Core Design Contradiction:
Measurement precisionVSPower

Solution Approach 1:

The patent extracts only the necessary monitoring parameters and their normal ranges from the complex correlation analysis, eliminating the need for comprehensive correlation calculations while retaining effective abnormality detection capability

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent changes the detection parameter from correlation values to direct parameter range comparisons, transforming the detection mechanism to reduce computational complexity while maintaining detection effectiveness

Inventive Principle:
Principle #35Parameter changes

2Reliability

If multiple operation data parameters are monitored with correlation analysis, then abnormality detection capability is improved, but noise influence increases

Engineering Contradiction:
Improveabnormality detection capabilityVSAvoidnoise influence
Core Design Contradiction:
ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The patent segments the monitoring approach by dividing parameters into individual monitoring units with specific normal ranges, allowing targeted detection without the noise amplification that occurs in comprehensive correlation analysis

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces normal range thresholds as intermediary reference values that mediate between raw parameter data and abnormality determination, filtering out noise while preserving detection sensitivity

Inventive Principle:
Principle #24Intermediary (Mediator)

3Ease of operation

If fixed abnormality thresholds are used, then detection simplicity is improved, but adaptability to different operation situations deteriorates

Engineering Contradiction:
Improvedetection simplicityVSAvoidadaptability to operation situations
Core Design Contradiction:
Ease of operationVSAdaptability or versatility

Solution Approach 1:

The patent makes the normal ranges dynamic by adjusting them according to operation modes and plant age, allowing the thresholds to adapt to different operational contexts while maintaining a consistent detection framework

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The patent changes the threshold parameters based on operation situations and plant lifecycle stages, enabling the same detection system to adapt to varying operational conditions without sacrificing simplicity

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP3312844B1Abnormality indication monitoring system
Publication Date: 2020.04.01 MITSUBISHI HEAVY IND LTD
  • EP3312844B1 patent drawingFigure 1
  • EP3312844B1 patent drawingFigure 2
  • EP3312844B1 patent drawingFigure 3

AI summary

A plant abnormality indication monitoring system for detectably monitoring an indication of abnormality in an atomic power generation plant is provided with: a data storage unit which stores plant operation data including an instrument parameter measured in the atomic power generation plant; and a monitoring and control unit which, on the basis of the plant operation data, detects an indication of abnormality in the atomic power generation plant, wherein the atomic power generation plant performs a base-load operation so that the instrument parameter has a prescribed target value, and wherein the monitoring and control unit, on the basis of past plant operation data, sets a normal range W that is a range in which the instrument parameter at the current time transitions normally, and detects an indication of abnormality when the instrument parameter at the current time exceeds the normal range W that has been set.