Wear Monitoring in Turning Operations Using Vibration and Strain Measurements

Scheffer, Cornie; Heyns, P.S.

doi:10.1006/mssp.2000.1364

Cited by 112 publications

(53 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Jemielniak et al [81] noted that, despite constant cutting conditions in single micro-milling cut, AE was not constant; thus, separate SFs were calculated for all the cut and for the 1st and the 2nd third of the cut. skewness [79,[83][84][85][86][87]91]; (v) kurtosis [79,[83][84][85][86][87]91,92]; (vi) signal power [77,87,91]; (vii) peak-to-peak, range, or peak-tovalley amplitude, [69,73,75,79,83,87] [68,71,89,90,94]; (b) pulse width: the percentage of time during which AE raw remains above the threshold level [71,94]; (c) burst rate number of times AE RMS signal exceeds preset thresholds per second [68,71,87]; and (d) burst width -percentage of time AE RMS signal remains above each threshold [71,94]. Kannatey-Asibu and Dornfeld [95] assumed that AE RMS signal has a b distribution.…”

Section: Signal Pre-processingmentioning

confidence: 99%

Advanced monitoring of machining operations

et al. 2010

View full text Add to dashboard Cite

Section: Signal Pre-processingmentioning

confidence: 99%

Advanced monitoring of machining operations

et al. 2010

View full text Add to dashboard Cite

“…The parameters of time series model contains important information about the signals modeled and they are sensitive to the change of state [1]. Parametric based spectral estimation is a commonly used method for signal analysis.…”

Section: Introductionmentioning

confidence: 99%

A Fault Degree Classification Method for AE Signal Based on VAR-DBN

Zhou¹,

Li²,

Li³

2018

dtcse

View full text Add to dashboard Cite

Abstract. It is difficult to find the train axle fault earlier by traditional calculation method. In this paper, a time series analysis and pattern recognition analysis based model is presented to improve the performance on diagnosing fault of AE signal. The suggested methodology mainly involves three parts. First, empirical mode decomposition (EMD) is used to transform the AE signals into stationary signals by decomposing the original signal into several intrinsic mode functions (IMFs) and one residue. Then, vector autoregressive (VAR) model is selected to reflect the characteristic included in IMFs by establishing feature vector comprised by the coefficients of the VAR model. In the end, a Deep Belief Network(DBN) is introduced to classify the AE signals and detect the fault signals caused by faults. The result of the experiment shows that compared with other time series parameter analysis based classification study, the proposed method has better behavior in accuracy when identifies different conditions of railway vehicle axle on AE signal.

show abstract

“…In indirect methods of wear estimation, the obtained signals are applied into signal features, used to predict the values of wear by a suitable wear model. Sche er and Heyns [3] and Balazinski et al [4] reported that most TCM systems employ forces and only a few systems utilize vibration signal as input parameters. Combinations of both force and vibration signals are more appropriate to improve the performance of prediction models.…”

Section: Introductionmentioning

confidence: 99%

Applying a multi sensor system to predict and simulate the tool wear using of artificial neural networks

2017

View full text Add to dashboard Cite

Abstract. Cutting tool wear in machining processes reduces the product surface quality, a ects the dimensional and geometrical tolerances, and causes tool breakage during the metal cutting. Therefore, online tool wear monitoring is needed to prevent reduction in machining quality. An Arti cial Neural Network (ANN) model was developed in this study to predict and simulate the tool ank wear. To achieve this aim, an experiment array was provided using full factorial method, and the tests were conducted on a CNC lathe machine tool. Vibration amplitude of the cutting tool and cutting forces were considered as criterion variables in monitoring the tool ank wear. For designing the model, the cutting parameters, cutting forces, and vibration amplitude were de ned as model inputs, and tool ank wear was selected as an output. The model was also introduced as a simulation block diagram to be used as a useful model in online and automated manufacturing systems. The estimated and measured results were then compared with each other. Based on the comparison results, maximum squared error values are under 6 10 14 mm, and R 2 is 1, meaning that the designed model can predict the results with high and reliable accuracy.

show abstract

Wear Monitoring in Turning Operations Using Vibration and Strain Measurements

Cited by 112 publications

References 20 publications

Advanced monitoring of machining operations

Advanced monitoring of machining operations

A Fault Degree Classification Method for AE Signal Based on VAR-DBN

Applying a multi sensor system to predict and simulate the tool wear using of artificial neural networks

Contact Info

Product

Resources

About