Equipment Abnormality Diagnosis Using Two-Stage PCA Screening
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing abnormality diagnosis systems for equipment drive members, such as sizing press equipment, often incorrectly diagnose equipment as faulty due to sporadic waveform fluctuations caused by non-damage related issues like pinch roll slip, leading to unnecessary equipment shutdowns and production inefficiencies.
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 non-damage related waveform anomalies, thereby preventing false positive diagnoses.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If PCA is performed on single pattern time series data for abnormality diagnosis, then measurement precision is improved, but reliability deteriorates due to random waveform fluctuations
Solution Approach 1:
The patent merges multiple successive pattern data into a single analysis set. Instead of analyzing one pattern at a time, the system collects N successive patterns (where N≥2) and performs PCA on the combined dataset. This merging approach allows the system to distinguish between random fluctuations (which average out) and genuine abnormalities (which persist across multiple patterns), thereby improving diagnosis reliability while maintaining measurement precision.
2Productivity
If single pattern PCA is used for quick diagnosis, then productivity is improved, but reliability deteriorates due to false positives
Solution Approach 1:
The system performs preliminary collection of multiple successive patterns before conducting the final PCA analysis. By pre-collecting N patterns in a buffer and then analyzing them together, the system prepares the data in advance, enabling quick batch processing. This preliminary action ensures that enough data is available for reliable diagnosis without requiring lengthy real-time analysis, thus maintaining productivity while improving reliability.
3Reliability
If multiple successive patterns are analyzed collectively, then reliability is improved, but device complexity increases
Solution Approach 1:
The patent changes the parameter of data quantity from single pattern to multiple successive patterns (N≥2). By adjusting this parameter, the system achieves better reliability without fundamentally changing the PCA algorithm itself. The existing PCA computational framework is reused, and only the input data structure changes, thus improving reliability while minimizing increases in system complexity.
Data Source
Figure 1
Figure 2~3
Figure 4
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.