Gear Fault Diagnosis via Joint Weighted Envelope Correlation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing gear fault diagnosis technologies for rotating machinery gearbox devices face challenges in limited system signal availability and complex noise interference, which hinder the accurate extraction of fault characteristics.
Innovation Solution
A gear fault diagnosis method based on joint weighted envelope noise-resistant correlation of sub-signals, involving vibration acceleration signal analysis, element-wise squaring, low-pass filtering, envelope signal reconstruction, fault information representation using L-moment theoretical indices, weight assignment via Sigmoid transformation, and calculation of a joint weighted envelope noise-resistant correlation function to identify characteristic frequencies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional spectrum analysis methods are used for gear fault diagnosis, then fault characteristics can be extracted, but the method fails under limited system signal availability and complex noise interference
Solution Approach 1:
The patent segments the vibration signal into multiple sub-signals based on different time intervals, allowing independent analysis of each segment. This segmentation enables the system to process limited signal data more effectively and reduces the impact of noise by analyzing local characteristics of each segment rather than the entire signal.
Solution Approach 2:
The patent transforms the vibration signal through multiple parameter changes including element-wise squaring, low-pass filtering, and envelope signal reconstruction. These parameter transformations convert the original signal into a form that is more susceptible to fault characteristics while being less sensitive to noise, enabling accurate fault diagnosis under limited and noisy conditions.
2Extent of automation
If wireless vibration sensors are used for monitoring, then real-time monitoring is enabled, but signal length is limited due to power consumption and communication bandwidth constraints
Solution Approach 1:
The patent divides the limited signal into multiple sub-signals based on different time intervals, maximizing the utilization of available signal data. This segmentation allows the system to extract meaningful fault characteristics from short signal segments without requiring extended signal acquisition, thus maintaining real-time monitoring capability while overcoming signal length limitations.
Solution Approach 2:
The patent applies partial action by analyzing only the necessary portions of the signal (sub-signals) rather than requiring the complete signal sequence. This approach enables effective fault diagnosis using partial signal information, allowing real-time monitoring with wireless sensors while compensating for the limited signal length through intelligent signal processing.
3Measurement precision
If complex noise interference is present in the vibration signal, then accurate fault diagnosis becomes difficult, but the proposed method achieves noise-resistant fault identification
Solution Approach 1:
The patent extracts the envelope signal from the vibration signal through element-wise squaring and low-pass filtering, separating the fault-related information from the noise. This extraction process isolates the characteristic frequency components while suppressing noise interference, enabling accurate fault diagnosis even in noisy environments.
Solution Approach 2:
The patent introduces an intermediary processing stage involving envelope signal reconstruction and joint weighted correlation analysis. This intermediary process transforms the raw vibration signal into a processed form that highlights fault characteristics while attenuating noise, serving as a mediator between the noisy input signal and the final fault diagnosis output.
Data Source
AI summary
A gear fault diagnosis method based on joint weighted envelope noise-resistant correlation of sub-signals, comprising: converting an original vibration signal sequence into an envelope signal through a signal sequence element-wise squaring-low-pass filtering-square root computation process, reconstructing the envelope signal according to different time intervals to obtain a series of sub-signals, calculating a fault information representation measure of each sub-signal based on an L-moment theoretical index, assigning a weight to each sub-signal with Sigmoid transformation, calculating a joint weighted envelope noise-resistant correlation function of the envelope signal sequence and the reconstructed sub-signals based on the envelope signal, the reconstructed sub-signals and the corresponding weights thereof, and determining a characteristic frequency according to a reciprocal of a time interval value corresponding to the characteristic peak in a plot of the joint weighted envelope noise-resistant correlation function with the time interval to eventually identifying a gear fault.