State Estimation Monitoring for Critical Sensor Data Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing monitoring systems for facilities, such as industrial plants, struggle to effectively identify critical measurement data influencing the state indication value and promptly detect deviations leading to a poor state, making it difficult to take corrective actions in a timely manner.

Innovation Solution

An apparatus and method that utilize a learned model to acquire and process measurement data from sensors, identifying key data influencing the state indication value and detecting signs of a poor state by comparing recent distribution changes, allowing for the display of critical measurement data and associated improvement operations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If all measurement data are displayed to monitor facility state, then monitoring completeness is improved, but information overload and difficulty in identifying critical data worsen

Engineering Contradiction:
Improvemonitoring completenessVSAvoiddata identification difficulty
Core Design Contradiction:
Loss of informationVSEase of operation

Solution Approach 1:

The patent segments measurement data into multiple categories (normal state data, pre-failure data, failure data) and applies different processing and display methods to each segment. This allows comprehensive monitoring while making critical data stand out through selective display and visualization techniques.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies different quality levels of processing to different portions of measurement data. Critical data showing signs of poor state are enhanced with special visualization, annotations, and alert mechanisms, while normal data are displayed in a standard manner, allowing operators to quickly identify important information without being overwhelmed by all data equally.

Inventive Principle:
Principle #3Local quality

2Measurement precision

If complex analysis methods are used to identify critical measurement data, then identification accuracy is improved, but processing time and system complexity worsen

Engineering Contradiction:
Improveidentification accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent performs preliminary analysis by pre-processing measurement data to identify patterns and characteristics associated with poor states before actual monitoring occurs. This includes pre-defining thresholds, patterns, and relationships in measurement data that indicate potential failures, so that during operation, the system can quickly match incoming data against these pre-established criteria rather than performing complex analysis in real-time.

Inventive Principle:
Principle #10Preliminary action

3Speed

If real-time monitoring of all parameters is implemented, then state detection speed is improved, but computational load and resource consumption worsen

Engineering Contradiction:
Improvestate detection speedVSAvoidcomputational load
Core Design Contradiction:
SpeedVSUse of energy by moving object

Solution Approach 1:

The patent extracts and focuses on specific measurement data that are most indicative of facility state and potential failures. Rather than processing all measurement data equally, the system identifies and extracts critical data points that show signs of poor state, allowing for efficient real-time monitoring with reduced computational requirements.

Inventive Principle:
Principle #2Taking out (Extraction)

Data Source

PatentEP4063984B1Apparatus, method, and program for the estimation of a state of a device
Publication Date: 2024.07.24 YOKOGAWA ELECTRIC CORP
  • EP4063984B1 patent drawingFigure 1
  • EP4063984B1 patent drawingFigure 2
  • EP4063984B1 patent drawingFigure 3

AI summary

[Solving Means] An apparatus is provided comprising an acquisition unit configured to acquire a plurality of types of measurement data indicating a state of a target, a supplying unit configured to supply, in response to the plurality of types of measurement data being input, measurement data acquired by the acquisition unit to a model that outputs a state indication value indicating a quality of a state of the target, a setting unit configured to set, as data to be displayed, at least one piece of measurement data, among the plurality of types of measurement data, having a larger influence on the state indication value than a reference, and a display control unit configured to display the state indication value output from the model along with a measurement value of the data to be displayed.