scholarly journals Acoustical Source Tracing Using Independent Component Analysis and Correlation Analysis

2015 ◽  
Vol 2015 ◽  
pp. 1-8 ◽  
Author(s):  
Wei Cheng ◽  
Zhousuo Zhang ◽  
Jie Zhang ◽  
Jiantao Lu
Keyword(s):  
Fault Diagnosis ◽  
Correlation Analysis ◽  
Independent Component Analysis ◽  
Condition Monitoring ◽  
Component Analysis ◽  
Independent Component ◽  
Source Information ◽  
Independent Components ◽  
Source Tracing ◽  
Acoustical Signals

Acoustical signals from mechanical systems reveal the operating conditions of mechanical components and thus benefit for machinery condition monitoring and fault diagnosis. However, the acoustical signals directly measured by the sensors in essential are the mixed signals of all the sources, and normally it is very difficult to be used for source identification or operating feature extraction. Therefore, this paper studies the acoustical source tracing problem using independent component analysis (ICA) and identifies the sources using correlation analysis: the measured acoustical signals are separated into independent components by independent component analysis method, and thus all the independent information of all the sources is obtained; these independent components are identified based on the prior information of the sources and correlation analysis. Therefore, all the source information contained in the measured acoustical signals can be independently separated and traced, which can provide more purer source information for condition monitoring and fault diagnosis.

Application of Fault Diagnosis Method Based on cICA to Gearbox

2014 ◽  
Vol 664 ◽  
pp. 148-152
Author(s):  
Shuang Xi Jing ◽  
Song Tao Guo ◽  
Jun Fa Leng ◽  
Xing Yu Zhao
Keyword(s):  
Fault Diagnosis ◽  
Independent Component Analysis ◽  
Signal To Noise Ratio ◽  
Component Analysis ◽  
Independent Component ◽  
Early Application ◽  
Independent Components ◽  
Gear Fault ◽  
Constrained Independent Component Analysis ◽  
Non Gaussian

Constrained independent component analysis (cICA) is a new theory and new method derived from the independent component analysis (ICA).It can extract the desired independent components (ICs) from the data based on some prior information, thus overcoming the uncertainty of the traditional ICA. Early gearbox fault signals is often very weak ,characterized by non-Gaussian,low signal-to-noise ratio (SNR), which make the existing diagnosis methods in the diagnosis of early application restricted. In this paper,cICA algorithm is applied to gear fault diagnosis. Through the case studies verify the feasibility of this method to extract the desired independent components (ICs), indicating the applicability and effectiveness of the method.

scholarly journals Robust Independent Component Analysis Based on Two Scatter Matrices

2016 ◽  
Vol 37 (1) ◽  
Author(s):  
Klaus Nordhausen ◽  
Hannu Oja ◽  
Esa Ollila
Keyword(s):  
Independent Component Analysis ◽  
Covariance Matrix ◽  
Simulation Study ◽  
Component Analysis ◽  
Independent Component ◽  
Scatter Matrix ◽  
Independent Components

Oja, Sirkiä, and Eriksson (2006) and Ollila, Oja, and Koivunen (2007) showed that, under general assumptions, any two scatter matrices with the so called independent components property can be used to estimate the unmixing matrix for the independent component analysis (ICA). The method is a generalization of Cardoso’s (Cardoso, 1989) FOBI estimate which uses the regular covariance matrix and a scatter matrix based on fourth moments. Different choices of the two scatter matrices are compared in a simulation study. Based on the study, we recommend always the use of two robust scatter matrices. For possible asymmetric independent components, symmetrized versions of the scatter matrix estimates should be used.

A Comprehensive Study of Vibration Signals for a Thin Shell Structure Using Enhanced Independent Component Analysis and Experimental Validation

2014 ◽  
Vol 136 (4) ◽  
Author(s):  
Wei Cheng ◽  
Zhengjia He ◽  
Zhousuo Zhang
Keyword(s):  
Independent Component Analysis ◽  
Thin Shell ◽  
Component Analysis ◽  
Independent Component ◽  
Vibration Monitoring ◽  
Monitoring And Control ◽  
Source Information ◽  
Vibration Signals ◽  
Machinery Condition Monitoring ◽  
Source Number

Vibration source information (source number, source waveforms, and source contributions) of gears, bearings, motors, and shafts is very important for machinery condition monitoring, fault diagnosis, and especially vibration monitoring and control. However, it has been a challenging to effectively extract the source information from the measured mixed vibration signals without a priori knowledge of the mixing mode and sources. In this paper, we propose source number estimation, source separation, and source contribution evaluation methods based on an enhanced independent component analysis (EICA). The effects of nonlinear mixing mode and different source number on source separation are studied with typical vibration signals, and the effectiveness of the proposed methods is validated by numerical case studies and experimental studies on a thin shell test bed. The conclusions show that the proposed methods have a high accuracy for thin shell structures. This research benefits for application of independent component analysis (ICA) to solve the vibration monitoring and control problems for thin shell structures and provides important references for machinery condition monitoring and fault diagnosis.

Independent component analysis for reservoir geomorphology and unsupervised seismic facies classification in the Taranaki Basin, New Zealand

2019 ◽  
Vol 7 (3) ◽  
pp. SE19-SE42 ◽  
Author(s):  
David Lubo-Robles ◽  
Kurt J. Marfurt
Keyword(s):  
New Zealand ◽  
Independent Component Analysis ◽  
Order Statistics ◽  
Input Data ◽  
Component Analysis ◽  
Independent Component ◽  
Seismic Facies ◽  
Blue Color ◽  
Independent Components ◽  
Facies Classification

During the past two decades, the number of volumetric seismic attributes has increased to the point at which interpreters are overwhelmed and cannot analyze all of the information that is available. Principal component analysis (PCA) is one of the best-known multivariate analysis techniques that decompose the input data into second-order statistics by maximizing the variance, thus obtaining mathematically uncorrelated components. Unfortunately, projecting the information in the multiple input data volumes onto an orthogonal basis often mixes rather than separates geologic features of interest. To address this issue, we have implemented and evaluated a relatively new unsupervised multiattribute analysis technique called independent component analysis (ICA), which is based on higher order statistics. We evaluate our algorithm to study the internal architecture of turbiditic channel complexes present in the Moki A sands Formation, Taranaki Basin, New Zealand. We input 12 spectral magnitude components ranging from 25 to 80 Hz into the ICA algorithm and we plot 3 of the resulting independent components against a red-green-blue color scheme to generate a single volume in which the colored independent components correspond to different seismic facies. The results obtained using ICA proved to be superior to those obtained using PCA. Specifically, ICA provides improved resolution and separates geologic features from noise. Moreover, with ICA, we can geologically analyze the different seismic facies and relate them to sand- and mud-prone seismic facies associated with axial and off-axis deposition and cut-and-fill architectures.

SIMPLE NEURON MODELS FOR INDEPENDENT COMPONENT ANALYSIS

1996 ◽  
Vol 07 (06) ◽  
pp. 671-687 ◽  
Author(s):  
AAPO HYVÄRINEN ◽  
ERKKI OJA
Keyword(s):  
Independent Component Analysis ◽  
Negative Feedback ◽  
Single Neuron ◽  
Component Analysis ◽  
Point Of View ◽  
Independent Component ◽  
Neuron Models ◽  
Independent Components ◽  
Unit System ◽  
Learning Rules

Recently, several neural algorithms have been introduced for Independent Component Analysis. Here we approach the problem from the point of view of a single neuron. First, simple Hebbian-like learning rules are introduced for estimating one of the independent components from sphered data. Some of the learning rules can be used to estimate an independent component which has a negative kurtosis, and the others estimate a component of positive kurtosis. Next, a two-unit system is introduced to estimate an independent component of any kurtosis. The results are then generalized to estimate independent components from non-sphered (raw) mixtures. To separate several independent components, a system of several neurons with linear negative feedback is used. The convergence of the learning rules is rigorously proven without any unnecessary hypotheses on the distributions of the independent components.

Research on Fault Diagnosis for Petrochemical Running Equipments Based on ICA

2011 ◽  
Vol 48-49 ◽  
pp. 950-953
Author(s):  
Zhi Gang Chen ◽  
Xiao Jiao Lian ◽  
Ming Zhou
Keyword(s):  
Fault Diagnosis ◽  
Independent Component Analysis ◽  
Component Analysis ◽  
Independent Component ◽  
New Method ◽  
Signal Separation ◽  
Signal Extraction ◽  
Vibration Signals ◽  
Signal Preprocessing

For solving the difficulty of feature signal extraction from vibration signals, a new method based on Independent Component Analysis (ICA) is proposed to realize separation and filtering for multi-source vibration signals. Firstly, the principal and algorithm of ICA used to separate mixed signals is introduced. Secondly, application in signal separation and filtering with ICA is studied in diagnosis. In addition, imitation and field examples are given. The experiments show it is feasible to separate and extract feature signal from multi-source vibration signals and it is an effective method in signal preprocessing in fault diagnosis.

Sign in / Sign up

Export Citation Format

Share Document