Motor Noise Detection Using AE Sensor Frequency Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional acoustic emission test devices face challenges in accurately distinguishing motor noise signals from composite signals, leading to inconsistent detection results due to external noise interference, requiring improved methods for signal extraction and analysis.
Innovation Solution
A motor noise detecting device using an AE sensor with a signal sensing part, data acquisition part, and data analysis part, incorporating both rule-based and deep learning-based diagnostic models to analyze acoustic signals and RPM signals, effectively filtering and processing audible and non-audible bands to determine motor abnormalities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional acoustic emission test devices detect elastic wave signals, then defects can be identified, but motor noise signals and external noise interfere with accurate detection
Solution Approach 1:
The patent segments the acoustic signal into multiple frequency bands (low frequency band below 1kHz and high frequency band above 1kHz) and processes each band separately. This allows selective filtering of motor noise signals in the low frequency band while preserving defect-related elastic wave signals in the high frequency band, thereby improving detection accuracy in noisy environments.
Solution Approach 2:
The patent changes the processing parameters differently for different frequency bands. Low frequency signals are filtered out below a threshold, while high frequency signals are processed with different amplification and analysis parameters. This parameter differentiation enables the system to eliminate noise while preserving useful defect signals.
2Measurement precision
If workers manually analyze elastic wave signals to distinguish noise from defects, then detection results can be obtained, but analysis time increases significantly
Solution Approach 1:
The patent replaces manual mechanical analysis with automated electronic signal processing systems. The system automatically separates low frequency motor noise from high frequency defect signals using electronic filters and digital signal processing algorithms, eliminating the need for time-consuming manual analysis while maintaining or improving detection accuracy.
Solution Approach 2:
The patent performs preliminary signal processing by pre-separating and pre-processing different frequency bands before detailed analysis. Low frequency noise components are filtered out in advance, and high frequency defect signals are pre-amplified and prepared for analysis, reducing the complexity and time required for subsequent defect identification.
3Adaptability or versatility
If acoustic emission testing is performed in noisy environments, then on-site testing is enabled, but external noise reduces measurement reliability
Solution Approach 1:
The patent segments signals by frequency to distinguish between on-site motor noise (low frequency) and defect signals (high frequency). This frequency-based segmentation allows the system to operate reliably in noisy on-site environments by automatically filtering out environmental noise while preserving defect detection capability.
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
The solution enables accurate detection of motor abnormalities with reduced external noise interference, shortening analysis time and improving defect judgment accuracy, allowing for on-site testing without anechoic chambers, thus reducing production costs and man-hours.
Implementation Method 1
Acoustic Emission Testing (AET) is one of the non-destructive detecting methods to detect through a detector that the energy accompanied during a process when an object to be tested is deformed, cracked, or destroyed, is emitted as an elastic wave
Data Source
AI summary
A motor noise detecting device according to an embodiment of the present disclosure includes a signal sensing part for sensing an acoustic signal generated from an object to be tested, a data acquisition part for receiving the acoustic signal sensed by the signal sensing part and converting it into an acoustic digital signal, and a data analysis part for receiving and analyzing the acoustic digital signal to perform a detection on whether the object to be tested is abnormal. In addition, the signal sensing part includes an AE (Acoustic Emission) sensor for sensing an elastic wave included in the acoustic signal, and the data analysis part generates result data of analyzing the acoustic digital signal, analyzes the generated result data through a pre-learned model, and detects whether the object to be tested is abnormal.