Functional Series TARMA Models for Non-stationary Tool Vibration Signals Representation and Wear Estimation

2016 ◽  
pp. 141-151 ◽  
Author(s):  
Behrang Hosseini Aghdam ◽  
Ender Cigeroglu
Keyword(s):  
Vibration Signals ◽  
Tool Vibration ◽  
Functional Series

Influence of Cutting Speed and Offset Distance over Cutting Tool Vibration in Multi-Tool Turning Process

2014 ◽  
Vol 984-985 ◽  
pp. 100-105 ◽  
Author(s):  
R. Kalidasan ◽  
V. Ramanuj ◽  
D.K. Sarma ◽  
S. Senthilvelan
Keyword(s):  
Cutting Tool ◽  
Cutting Speed ◽  
Tangential Direction ◽  
Rear Side ◽  
Work Piece ◽  
Machining Parameters ◽  
Turning Process ◽  
Vibration Signals ◽  
Tool Vibration ◽  
Power Spectral

Multi-tool turning process employs more than one cutting tool for machining the work piece simultaneously. In the conventional turning process, effect of machining parameters over cutting forces, vibration, work piece surface finish and dimensional tolerances have been discussed in detail, however no attempt has been made in the multi-tool turning process. Cutting tool vibration is very important as it reveals the condition of cutting tool as well as work piece quality. In this study, a second cutting tool is introduced at the rear side of the lathe with some distance from conventional front cutting tool to machine the work piece simultaneously. Accelerometers are used to measure the vibration signals in the tangential direction of cutting. Obtained time domain vibration signals are converted to frequency domain signals by Fast Fourier Transform to reveal its power spectral density. In this work cutting speed and distance between front and rear cutting tool are varied to understand the cutting tool vibration. With increase in cutting speed and increase in distance between front and rear cutting tool, vibration reduces.

COMPOUND FAULT DIAGNOSIS OF BEARINGS USING AN IMPROVED SPECTRAL KURTOSIS BY MAXIMUM CORRELATION KURTOSIS DECONVOLUTION (MCKD).

2020 ◽  
Vol 9 (8) ◽  
pp. 66-72
Keyword(s):  
Fault Diagnosis ◽  
Resonance Frequency ◽  
Background Noise ◽  
Maximum Correlation ◽  
Vibration Signals ◽  
Filter Length ◽  
Frequency Bands ◽  
Noise Interference ◽  
Spectral Kurtosis

This paper discusses the use of Maximum Correlation kurtosis deconvolution (MCKD) method as a pre-processor in fast spectral kurtosis (FSK) method in order to find the compound fault characteristics of the bearing, by enhancing the vibration signals. FSK only extracts the resonance bands which have maximum kurtosis value, but sometimes it might possible that faults occur in the resonance bands which has low kurtosis value, also the faulty signals missed due to noise interference. In order to overcome these limitations FSK used with MCKD, MCKD extracts various faults present in different resonance frequency bands; also detect the weak impact component, as MCKD also dealt with strong background noise. By obtaining the MCKD parameters like, filter length & deconvolution period, we can extract the compound fault feature characteristics.

scholarly journals On the Use of Machine Learning to Detect Shocks in Road Vehicle Vibration Signals

2016 ◽  
Vol 30 (8) ◽  
pp. 387-398 ◽  
Author(s):  
Julien Lepine ◽  
Vincent Rouillard ◽  
Michael Sek
Keyword(s):  
Machine Learning ◽  
Road Vehicle ◽  
Vibration Signals

scholarly journals Deep Learning Approach for Vibration Signals Applications

Sensors ◽  
2021 ◽  
Vol 21 (11) ◽  
pp. 3929
Author(s):  
Han-Yun Chen ◽  
Ching-Hung Lee
Keyword(s):  
Surface Roughness ◽  
Tool Wear ◽  
Parameters Optimization ◽  
Frequency Spectra ◽  
Vibration Signals ◽  
Bearing Faults ◽  
Time Frequency ◽  
And Performance ◽  
The One ◽  
Short Time

This study discusses convolutional neural networks (CNNs) for vibration signals analysis, including applications in machining surface roughness estimation, bearing faults diagnosis, and tool wear detection. The one-dimensional CNNs (1DCNN) and two-dimensional CNNs (2DCNN) are applied for regression and classification applications using different types of inputs, e.g., raw signals, and time-frequency spectra images by short time Fourier transform. In the application of regression and the estimation of machining surface roughness, the 1DCNN is utilized and the corresponding CNN structure (hyper parameters) optimization is proposed by using uniform experimental design (UED), neural network, multiple regression, and particle swarm optimization. It demonstrates the effectiveness of the proposed approach to obtain a structure with better performance. In applications of classification, bearing faults and tool wear classification are carried out by vibration signals analysis and CNN. Finally, the experimental results are shown to demonstrate the effectiveness and performance of our approach.

scholarly journals Analysis method of the cavitation vibration signals in poppet valve based on EEMD

2021 ◽  
Vol 13 (2) ◽  
pp. 168781402199811
Author(s):  
Beibei Li ◽  
Qiao Zhao ◽  
Huaiyi Li ◽  
Xiumei Liu ◽  
Jichao Ma ◽  
...  
Keyword(s):  
Ensemble Empirical Mode Decomposition ◽  
Center Frequency ◽  
Analysis Method ◽  
Vibration Signals ◽  
Poppet Valve ◽  
Mode Decomposition ◽  
Marginal Spectrum ◽  
Cavitation Intensity ◽  
Eemd Method ◽  
Peak Value

To study the vibration characteristics of the poppet valve induced by cavitation, the signal analysis method based on the ensemble empirical mode decomposition (EEMD) method was studied experimentally. The component induced by cavitation was separated from the vibration signals through the EEMD method. The results show that the IMF2 component has the largest amplitude and energy of all components. The root mean square (RMS) value, peak value of marginal spectrum, and center frequency of marginal spectrum of the IMF2 component were studied in detail. The RMS value and the peak value of the marginal spectrum decrease with a decrease of cavitation intensity. The center frequency of marginal spectrum is between 12 kHz and 20 kHz, and the center frequency first increases and then decreases with a decrease of cavitation intensity. The change rate of the center frequency also decreases with an increase of inlet pressure.

scholarly journals Location Detection Method of Detector in Pipeline Using VMD Algorithm and Machine Learning Classifier

Electronics ◽  
2021 ◽  
Vol 10 (12) ◽  
pp. 1436
Author(s):  
Tuoru Li ◽  
Senxiang Lu ◽  
Enjie Xu
Keyword(s):  
Machine Learning ◽  
Magnetic Flux ◽  
Magnetic Flux Leakage ◽  
Intrinsic Mode Functions ◽  
Detection Range ◽  
Vibration Signals ◽  
Feature Vectors ◽  
Learning Classifier ◽  
Mode Decomposition ◽  
Flux Leakage

The internal detector in a pipeline needs to use the ground marker to record the elapsed time for accurate positioning. Most existing ground markers use the magnetic flux leakage testing principle to detect whether the internal detector passes. However, this paper uses the method of detecting vibration signals to track and locate the internal detector. The Variational Mode Decomposition (VMD) algorithm is used to extract features, which solves the defect of large noise and many disturbances of vibration signals. In this way, the detection range is expanded, and some non-magnetic flux leakage internal detectors can also be located. Firstly, the extracted vibration signals are denoised by the VMD algorithm, then kurtosis value and power value are extracted from the intrinsic mode functions (IMFs) to form feature vectors, and finally the feature vectors are input into random forest and Multilayer Perceptron (MLP) for classification. Experimental research shows that the method designed in this paper, which combines VMD with a machine learning classifier, can effectively use vibration signals to locate the internal detector and has the characteristics of high accuracy and good adaptability.

Sign in / Sign up

Export Citation Format

Share Document