Equipment Abnormality Diagnosis Using Two-Stage PCA Waveform Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing abnormality diagnosis systems for equipment with drive members, such as sizing press equipment, often incorrectly diagnose equipment as faulty due to transient waveform anomalies, even when the equipment is undamaged, leading to unnecessary shutdowns and efficiency losses.
Innovation Solution
An abnormality diagnosis system that performs first and second principal component analyses on time series data from equipment drive members, using a Q statistic to differentiate between actual equipment abnormalities and transient anomalies, ensuring accurate diagnosis by analyzing both individual and successive waveforms.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If principal component analysis is performed on individual waveforms to detect equipment abnormalities, then measurement precision is improved, but false positives increase due to transient anomalies
Solution Approach 1:
The patent merges multiple individual waveform analyses by performing PCA collectively on a series of waveforms. Instead of analyzing each waveform independently and risking false positives from transient anomalies, the system combines multiple waveforms into a single collective PCA analysis, where transient anomalies are averaged out and true equipment abnormalities are reinforced, thereby improving diagnosis reliability while maintaining measurement precision.
2Device complexity
If simple upper and lower limit checks are used for abnormality diagnosis, then device complexity is reduced, but measurement precision deteriorates
Solution Approach 1:
The patent replaces the simple mechanical threshold-checking system with a statistical PCA-based system. Instead of using fixed upper and lower limits that require complex tuning and yield poor precision, the system uses PCA to transform waveform data into principal components with statistically determined thresholds, achieving high measurement precision while keeping the system relatively simple through automated statistical processing.
3Reliability
If PCA is performed collectively on multiple successive waveforms, then diagnosis reliability is improved, but loss of time increases due to additional analysis
Solution Approach 1:
The patent implements periodic action by analyzing waveforms in fixed cycles or batches rather than continuously analyzing each individual waveform in real-time. By collecting a series of waveforms and performing collective PCA at periodic intervals, the system achieves high diagnosis reliability through multiple data points while managing analysis time through structured, periodic processing rather than continuous computation.
Data Source
AI summary
Provided are an abnormality diagnosis system and an abnormality diagnosis method that can prevent wrongly diagnosing equipment as having an abnormality when the equipment actually does not have an abnormality. An abnormality diagnosis system 20 comprises a sampler 21 and a calculator 24. The calculator 24 is configured to: perform first abnormality determination of whether there is an abnormality based on a result of first principal component analysis; in the case where a result of the first abnormality determination is that there is an abnormality, and perform second abnormality determination of whether there is an abnormality based on a result of second principal component analysis; and in the case where a result of the second abnormality determination is that there is an abnormality, diagnose the equipment as having an abnormality.