Plant Operation Data Monitoring via Gradient Threshold Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing techniques face difficulties in determining abnormalities in plant operation data with low physical correlation and high independency, as they rely on physical correlations between data points, making it challenging to detect anomalies solely from operation data.
Innovation Solution
A plant operation data monitoring device and method that processes operation data by calculating gradients, determining threshold values, and storing them in separate databases to differentiate between normal and abnormal values, enabling independent abnormality detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If abnormality determination is performed using physical correlation between operation data, then abnormality detection accuracy is improved for data with high physical correlation, but abnormality determination becomes difficult for operation data with low physical correlation and high independency
Solution Approach 1:
The invention changes the parameter used for abnormality determination from physical correlation between different operation data to temporal correlation within a single operation data series. By analyzing the time-series pattern and gradient changes of individual operation data points, the system can detect abnormalities in independent data without relying on relationships with other data streams.
2Device complexity
If operation data is stored and analyzed in aggregate form, then data processing complexity is reduced, but the ability to detect subtle abnormalities in independent data is lost
Solution Approach 1:
The invention segments the analysis process into distinct stages: storing raw operation data, calculating gradients between consecutive data points, separating positive and negative gradients into different databases, and determining abnormalities based on gradient patterns. This segmentation allows detailed analysis of independent data while maintaining manageable processing complexity through systematic organization.
3Measurement precision
If threshold values are determined for gradient-based abnormality determination, then abnormality detection precision is improved, but the system complexity increases due to separate processing of positive and negative gradients
Solution Approach 1:
The system segments gradient analysis into separate positive and negative gradient databases, allowing independent threshold determination for each direction of change. This segmentation enables precise abnormality detection by establishing specific criteria for increasing and decreasing trends, while the modular database structure keeps processing complexity manageable through organized separation of concerns.
Data Source
AI summary
A plant operation data monitoring device comprises: an input section that receives operation data on a plant; and a calculator that includes databases storing the operation data received, and a computing section executing a program. The computing section stores the operation data received in a first database of the databases in time series. The computing section determines from peak values of the operation data stored whether gradients of the operation data are positive or negative, and then stores the gradients in a second database of the databases for positive gradients or in the second database of the databases for negative gradients in time series. The computing section determines threshold values for abnormality determination about the positive and negative gradients, divides the positive gradients and the negative gradients into normal values and abnormal values, and additionally stores the divided gradients in the second database for the positive or negative gradients.