Signature extraction from acoustic signals and its application for ANN based engine fault diagnosis

2012 ◽  
Vol 5 (3) ◽  
pp. 220
Author(s):  
Om Prakash ◽  
Vrijendra Singh ◽  
Prem Kumar Kalra
Keyword(s):  
Fault Diagnosis ◽  
Acoustic Signals ◽  
Signature Extraction

scholarly journals A Novel Deep Sparse Filtering Method for Intelligent Fault Diagnosis by Acoustic Signal Processing

2020 ◽  
Vol 2020 ◽  
pp. 1-11
Author(s):  
Guowei Zhang ◽  
Jinrui Wang ◽  
Baokun Han ◽  
Sixiang Jia ◽  
Xiaoyu Wang ◽  
...  
Keyword(s):  
Fault Diagnosis ◽  
Frequency Domain ◽  
Signal To Noise Ratio ◽  
Computing Time ◽  
Planetary Gear ◽  
Acoustic Signals ◽  
Intelligent Fault Diagnosis ◽  
Sparse Filtering ◽  
Third Stage ◽  
Learned Features

Increased attention has been paid to research on intelligent fault diagnosis under acoustic signals. However, the signal-to-noise ratio of acoustic signals is much lower than vibration signals, which increases the difficulty of signal denoising and feature extraction. To solve the above defect, a novel batch-normalized deep sparse filtering (DSF) method is proposed to diagnose the fault through the acoustic signals of rotating machinery. In the first stage, the collected acoustic signals are prenormalized to eliminate the adverse effects of singular samples, and then the normalized signal is transformed into frequency-domain signal through fast Fourier transform (FFT). In the second stage, the learned features are obtained by training batch-normalized DSF with frequency-domain signals, and then the features are fine-tuned by backpropagation (BP) algorithm. In the third stage, softmax regression is used as a classifier for heath condition recognition based on the fine-tuned features. Bearing and planetary gear datasets are used to validate the diagnostic performance of the proposed method. The results show that the proposed DSF model can extract more powerful features and less computing time than other traditional methods.

Doppler Shift Removal Based on Instantaneous Frequency Estimation for Wayside Fault Diagnosis of Train Bearings

2014 ◽  
Vol 136 (2) ◽  
Author(s):  
Ao Zhang ◽  
Fei Hu ◽  
Qingbo He ◽  
Changqing Shen ◽  
Fang Liu ◽  
...  
Keyword(s):  
Fault Diagnosis ◽  
Acoustic Signal ◽  
Instantaneous Frequency ◽  
Doppler Shift ◽  
High Speed ◽  
Frequency Estimation ◽  
Acoustic Signals ◽  
Instantaneous Frequency Estimation ◽  
Comparison Results ◽  
Short Time

The phenomenon of Doppler shift in the acoustic signal acquired by a microphone amounted beside the railway leads to the difficulty for fault diagnosis of train bearings with a high moving speed. To enhance the condition monitoring performance of the bearings on a passing train using stationary microphones, the elimination of the Doppler shift should be implemented firstly to correct the severe frequency-domain distortion of the acoustic signal recorded in these conditions. In this paper, a Doppler shift removal method is proposed based on instantaneous frequency (IF) estimation (IFE) for analyzing acoustic signals from train bearings with a high speed. Specifically, the IFE based on short-time Fourier transform is firstly applied to attain the IF vector. According to the acoustic theory of Morse, the data fitting is then carried out to achieve the fitting IFs with which the resampling sequence can be established as the resampling vector in time domain. The resampled signal can be finally reconstructed to realize fault diagnosis of train bearings. To demonstrate the effectiveness of this method, two simulations and an experiment with practical acoustic signals of train bearings with a crack on the outer raceway and the inner raceway have been carried out, and the comparison results have been presented in this paper.

A Method of Fault Signature Extraction for Improved Diagnosis

1991 ◽  
Vol 113 (4) ◽  
pp. 634-638 ◽  
Author(s):  
Hsinyung Chin ◽  
Kourosh Danai
Keyword(s):  
Fault Diagnosis ◽  
Fault Detection ◽  
Pattern Classification ◽  
False Alarms ◽  
Binary Vectors ◽  
Signature Extraction ◽  
Sensory Data ◽  
Tuning Method ◽  
Self Tuning ◽  
Efficient Extraction

Efficient extraction of fault signatures from sensory data is a major concern in fault diagnosis. This paper introduces a self-tuning method of fault signature extraction that enhances fault detection, minimizes false alarms, improves diagnosability, and reduces fault signature variability. The proposed method uses a Flagging Unit to convert the processed measurements to binary vectors, and utilizes nonparametric pattern classification techniques to estimate the fault signatures. The performance of the Flagging Unit, which relies on its adaptation algorithms to optimize its performance based upon a sample batch of measurement-fault vectors, is demonstrated in simulation.

Doppler Distortion Removal Method for Multiple Acoustic Sources

2013 ◽  
Vol 373-375 ◽  
pp. 874-879
Author(s):  
Ao Zhang ◽  
Fang Liu ◽  
Fan Rang Kong
Keyword(s):  
Fault Diagnosis ◽  
Time Domain ◽  
Acoustic Signal ◽  
Instantaneous Frequency ◽  
Signal Analysis ◽  
Acoustic Signals ◽  
Acoustic Source ◽  
Sampling Sequence ◽  
Acoustic Sources ◽  
Dopplerlet Transform

In wayside fault diagnosis of train bearings, the phenomenon of Doppler distortion in the acoustic signal of moving acoustic source acquired with a microphone leads to the difficulty for signal analysis. In this paper, a new method based on Dopplerlet transform and re-sampling is proposed to eliminate the Doppler distortion of multiple acoustic sources which provide a reference for wayside fault diagnosis of train bearings. Firstly, search the parameters space to find the primary functionsDopplerlet atoms. According to the Morse acoustic theory, the instantaneous frequency of the Dopplerlet atom which we choose to remove Doppler distortion of the corresponding acoustic source can be acquired. Then, the re-sampling sequence can be established in time domain. Through the resample, the Doppler distortion can be removed. In the end of this paper, an experiment with practical acoustic signals is carried out, and the results verified the effectiveness of this method.

scholarly journals Recognition of rotor damages in a DC motor using acoustic signals

2017 ◽  
Vol 65 (2) ◽  
pp. 187-194 ◽  
Author(s):  
A. Głowacz ◽  
Z. Głowacz
Keyword(s):  
Fault Diagnosis ◽  
Acoustic Signals ◽  
Dc Motor ◽  
Diagnostic Methods ◽  
Real World Data ◽  
Vibration Signals ◽  
Industrial Plants ◽  
Feature Extraction Method ◽  
Dc Motors ◽  
Original Feature

AbstractDiagnosis of electrical direct current motors is essential for industrial plants. The emphasis is put on the development of diagnostic methods of solutions for capturing, processing and recognition of diagnostic signals. This paper presents a technique of early fault diagnosis of a DC motor. The proposed approach is based on acoustic signals. A real-world data of the DC motor were used in the analysis. The work provides an original feature extraction method called the shortened method of frequencies selection (SMoFS-15). The obtained results of the presented analysis show that the early fault diagnostic method can be used for monitoring electrical DC motors. The proposed method can also support other fault diagnosis methods based on thermal, current, and vibration signals.

Sign in / Sign up

Export Citation Format

Share Document