Time-Series Trigger Detection for Waveform-Aligned Equipment Diagnosis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional abnormality diagnosis methods require manual determination of trigger conditions for cutting out monitored sections, which is time-consuming and labor-intensive, and the waveforms in the monitored sections need to overlap significantly for accurate modeling.
Innovation Solution
A method and device that use machine learning to automatically determine trigger conditions by generating a learning model, such as a decision tree, to cut out monitored sections based on correlation with trigger candidate signals, adjusting for one-pulse signals by converting them to sawtooth waves, and iteratively refining the process for accurate alignment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual determination of trigger conditions is used to cut out monitored sections, then waveform alignment can be achieved, but it requires significant time and labor
Solution Approach 1:
The system performs self-alignment by automatically calculating correlation coefficients between trigger candidate signals and monitored signals, eliminating the need for manual trigger condition determination while achieving accurate waveform alignment through computational methods
Solution Approach 2:
The manual mechanical process of comparing waveforms and determining trigger conditions is replaced with an automated computational system that calculates correlation coefficients and identifies optimal trigger points algorithmically
2Reliability
If monitored sections are cut out using manually determined trigger conditions, then accurate abnormality diagnosis can be performed, but the process becomes complex and time-consuming
Solution Approach 1:
The system changes the approach from manual parameter adjustment to automated parameter calculation by computing correlation coefficients and using these calculated parameters to automatically determine trigger conditions, simplifying the overall process while maintaining diagnostic accuracy
3Measurement precision
If waveforms are required to overlap significantly for model creation, then accurate normal operation model can be generated, but it limits the flexibility in trigger condition selection
Solution Approach 1:
The system introduces dynamic adaptability by allowing the trigger condition to be automatically adjusted based on correlation coefficient calculations, enabling the monitored section extraction to adapt to different signal characteristics while maintaining waveform alignment accuracy for model generation
Data Source
AI summary
A trigger condition determination method for a time series signal determines a trigger condition for cutting out a monitored section being a target for abnormality diagnosis, from a monitored signal being a time series signal indicating a condition of a monitored facility in the abnormality diagnosis for the monitored facility, and includes: collecting signal groups including one or more monitored signals and a trigger candidate signal; cutting out the monitored section of the monitored signal; generating a learning model specifying a start time point of the cut-out monitored section, generating label data, and using one or more trigger candidate signals at each time point as an input and using the label data at each time point as an output, by using machine learning; and determining the trigger condition by using the learning model, for the monitored signal for which the abnormality diagnosis is performed.