Pump Shaft Seal Life Prediction Using Vibration Spectrum Features
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for predicting the life of a pump shaft seal are inaccurate due to variations in vibration features caused by rotational speed and multiple failure factors, making it difficult to determine damage and estimate seal life accurately.
Innovation Solution
A method and system that utilizes a pump shaft seal life prediction system to obtain time domain vibration magnitudes, convert them into frequency spectrums through Fourier transform, extract characteristic amplitudes, combine and reduce dimensions, establish a life model, and set threshold values to determine seal life.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional vibration analysis methods are used to predict shaft seal life, then the prediction process can be performed, but the prediction accuracy is low due to rotational speed variations and multiple failure factors affecting vibration feature distributions
Solution Approach 1:
The patent transforms the vibration analysis from time domain to frequency domain by introducing spectral kurtosis as a new dimension of analysis. This dimensional transformation enables the identification of characteristic frequencies and their modulation patterns, which are not visible in traditional time domain analysis. The spectral kurtosis provides a new perspective for detecting shaft seal degradation that is independent of rotational speed variations.
Solution Approach 2:
The patent changes the analysis parameters from traditional vibration magnitudes to spectral kurtosis values at specific frequency bands. By monitoring changes in spectral kurtosis at characteristic frequencies (such as ball pass frequencies), the system can detect shaft seal degradation without being affected by rotational speed variations. This parameter transformation improves both prediction accuracy and robustness.
2Reliability
If multiple vibration characteristics are analyzed to identify shaft seal damage, then more comprehensive information is obtained, but the complexity of determining specific part damage increases
Solution Approach 1:
The patent extracts specific characteristic frequency components from the complex vibration spectrum, focusing on ball pass frequencies and their modulation patterns. By isolating and analyzing only the relevant frequency bands that are indicative of shaft seal damage, the system achieves reliable damage detection without needing to process all vibration characteristics. This extraction approach simplifies the analysis while maintaining high reliability.
Solution Approach 2:
The patent introduces spectral kurtosis as an intermediary parameter that bridges the gap between complex multi-frequency vibration signals and simple damage indicators. The spectral kurtosis acts as a mediator that consolidates information from multiple frequency components into a single metric that clearly indicates the presence and severity of shaft seal damage, reducing analysis complexity while maintaining detection reliability.
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
Enables accurate prediction of shaft seal life by highlighting damage characteristics and assessing the degree of damage, allowing for effective repair planning.
Implementation Method 1
obtain a plurality of time domain vibration magnitudes of vibration signals of a pump
Implementation Method 2
inputting a plurality of parameters of the pump under operation into the temporal vibration model to convert into a plurality of vibration spectrums by processing a Fourier transform
Data Source
AI summary
A life prediction method for shaft seal of pump includes following steps of: obtaining time domain vibration magnitudes of vibration signals of a pump; establishing a temporal vibration model according to time domain vibration magnitudes; inputting parameters of the pump under operation into temporal vibration model to convert into vibration spectrums by processing a Fourier transform, wherein the parameters include a rotation speed and a number of blades of the pump; extracting characteristic amplitudes of the pump according to vibration spectrums, combining characteristic amplitudes with each other and performing a dimensionality reduction process on characteristic amplitudes to generate characteristic combinations; establishing a life model according to characteristic combinations to store life model in a pump shaft seal life prediction system; and establishing at least one threshold value according to life model to compare at least one threshold value with characteristic amplitudes to determine life of shaft seal of pump.