Rotary Machine Rubbing Detection via AE and Gap Index
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for determining rubbing in rotary machines, such as those based on acoustic emission signals or gap measurements, face challenges like noise interference, high costs, and decreased accuracy due to aged deterioration, making it difficult to accurately detect rubbing occurrences.
Innovation Solution
A rubbing determination device and method that combines AE signal acquisition with gap amount measurement to generate a rubbing determination evaluation index, using both measured and estimated gap values, and a machine learning model to improve accuracy and adapt to changing conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Difficulty of detecting and measuring
If AE signal-based rubbing determination is used, then rubbing detection capability is provided, but determination accuracy deteriorates due to noise influence and weakened signals
Solution Approach 1:
The patent combines AE signal-based determination with gap amount-based determination into a unified rubbing determination system. The AE signal acquisition unit detects acoustic emissions, while the gap amount acquisition unit measures clearance between rotary and stationary parts. These two independent determination results are integrated to produce a comprehensive rubbing determination, compensating for the weaknesses of each individual method and improving overall accuracy.
2Measurement precision
If direct gap measurement using sensor is implemented, then gap amount data is obtained, but cost and labor increase due to new sensor installation
Solution Approach 1:
The patent makes existing sensors serve multiple functions. The AE sensor, originally designed for acoustic emission detection, is also utilized for gap amount determination through signal analysis. This multi-functional use of existing sensors eliminates the need for additional dedicated gap measurement sensors, thereby reducing both installation costs and labor requirements while still providing accurate gap data.
3Ease of manufacture
If estimation model based on operation parameter is used, then no new sensor installation is needed, but determination accuracy decreases due to discrepancy from aged deterioration
Solution Approach 1:
The patent implements a feedback mechanism where the estimation model's output is continuously refined based on actual measurements. The system uses operation parameters (temperature, rotation speed, load) to estimate gap amounts through a pre-established model, then compares these estimates with actual sensor measurements. This feedback loop allows the system to adapt to aged deterioration and maintain accuracy without requiring new sensor installations, as the model learns from real-world deviations over time.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach enables accurate and timely detection of rubbing in rotary machines, improving determination accuracy and reducing costs by integrating AE signals and gap measurements into a comprehensive evaluation index, even in cases of aged deterioration.
Implementation Method 1
a technique for determining whether or not rubbing occurs and a position thereof based on a result of detecting an acoustic emission (AE) signal generated at the time of rubbing occurrence by an AE sensor
Data Source
AI summary
This rubbing determination device determines rubbing of a rotary machine which comprises a fixed part and a rotary part. The present device acquires an AE signal detected by means of an AE sensor provided in the rotary machine and acquires a gap amount between the fixed part and the rotary part. A rubbing determination evaluation index is generated on the basis of the AE signal and the gap amount, and rubbing in the rotary machine is determined on the basis of the rubbing determination evaluation index.


