An approach based on singular spectrum analysis and the Mahalanobis distance for tool breakage detection

The failure of cutting tools significantly decreases machining productivity and product quality; thus, tool condition monitoring is significant in modern manufacturing processes. A new method that is based on singular spectrum analysis and Mahalanobis distance are combined to extract the crucial characteristics from spindle motor current to monitor the tool's condition. The singular spectrum analysis is a novel nonparametric technique for extracting the properties of nonlinear and nonstationary signals. However, because the components are not completely independent, the original singular spectrum analysis eventually leads to misinterpretation of the final results. The proposed method is used to overcome the weakness of the original singular spectrum analysis. The singular spectrum analysis algorithm is adopted to decompose the original signal and the useful singular values that correspond to the tool condition can be extracted. The Mahalanobis distance of the singular values is proposed as a feature that can effectively express the tool condition. The experiments on a CNC Vertical Machining Center demonstrate that this method is effective and can accurately detect the tool breakage in mill process.

Download Full-text

Study of Spindle Current Signals for Tool Breakage Detection in Milling

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.853.482 ◽

2013 ◽

Vol 853 ◽

pp. 482-487 ◽

Cited By ~ 1

Author(s):

Ling Neng Lian ◽

Bin Li ◽

Hong Qi Liu

Keyword(s):

End Milling ◽

Cutting Tools ◽

Singular Values ◽

Milling Process ◽

Spindle Motor ◽

Tool Breakage ◽

Linear Discriminant ◽

Spindle Motor Current ◽

Value Decomposition ◽

Machining Productivity

Failure of cutting tools significantly decreases machining productivity and product quality, thus, tool condition monitoring is significant in modern manufacturing processes. In this paper, a novel method based on singular value decomposition (SVD) and Linear Discriminant analysis (LDA) is proposed for detection of different broken tooth via spindle-motor current signals generated in end milling process. First, SVD algorithm is adopted to extract the useful singular values as salient features for indicating the tool state. Then classify the tool breakage event based on the selected features through the LDA technique. The experiments on a CNC Vertical Machining Centre show that this method is effective and can accurately classify the different broken tooth in end mill process.

Download Full-text

Modified singular spectrum analysis in identifying rainfall trend over peninsular Malaysia

Indonesian Journal of Electrical Engineering and Computer Science ◽

10.11591/ijeecs.v15.i1.pp283-293 ◽

2019 ◽

Vol 15 (1) ◽

pp. 283

Author(s):

S.M. Shaharudin ◽

N. Ahmad ◽

N.H. Zainuddin

Keyword(s):

Time Series ◽

Spectrum Analysis ◽

Time Series Data ◽

Singular Spectrum Analysis ◽

Singular Values ◽

Peninsular Malaysia ◽

Series Data ◽

Rainfall Time Series ◽

Singular Spectrum ◽

Torrential Rainfall

<p>Identifying the local time scale of the torrential rainfall pattern through Singular Spectrum Analysis (SSA) is useful to separate the trend and noise components. However, SSA poses two main issues which are torrential rainfall time series data have coinciding singular values and the leading components from eigenvector obtained from the decomposing time series matrix are usually assesed by graphical inference lacking in a specific statistical measure. In consequences to both issues, the extracted trend from SSA tended to flatten out and did not show any distinct pattern. This problem was approached in two ways. First, an Iterative Oblique SSA (Iterative O-SSA) was presented to make adjustment to the singular values data. Second, a measure was introduced to group the decomposed eigenvector based on Robust Sparse K-means (RSK-Means). As the results, the extracted trend using modification of SSA appeared to fit the original time series and looked more flexible compared to SSA.</p>

Download Full-text

On the singular values decoupling in the Singular Spectrum Analysis of volcanic tremor at Stromboli

Natural Hazards and Earth System Science ◽

10.5194/nhess-6-903-2006 ◽

2006 ◽

Vol 6 (6) ◽

pp. 903-909 ◽

Cited By ~ 14

Author(s):

R. Carniel ◽

F. Barazza ◽

M. Tárraga ◽

R. Ortiz

Keyword(s):

Spectrum Analysis ◽

Seismic Data ◽

Seismic Station ◽

Singular Spectrum Analysis ◽

Volcanic Tremor ◽

Singular Values ◽

Paroxysmal Activity ◽

Singular Spectrum ◽

Short Period ◽

Degree Of Coupling

Abstract. The well known strombolian activity at Stromboli volcano is occasionally interrupted by rarer episodes of paroxysmal activity which can lead to considerable hazard for Stromboli inhabitants and tourists. On 5 April 2003 a powerful explosion, which can be compared in size with the latest one of 1930, covered with bombs a good part of the normally tourist-accessible summit area. This explosion was not forecasted, although the island was by then effectively monitored by a dense deployment of instruments. After having tackled in a previous paper the problem of highlighting the timescale of preparation of this event, we investigate here the possibility of highlighting precursors in the volcanic tremor continuously recorded by a short period summit seismic station. We show that a promising candidate is found by examining the degree of coupling between successive singular values that result from the Singular Spectrum Analysis of the raw seismic data. We suggest therefore that possible anomalies in the time evolution of this parameter could be indicators of volcano instability to be taken into account e.g. in a bayesian eruptive scenario evaluator. Obviously, further (and possibly forward) testing on other cases is needed to confirm the usefulness of this parameter.

Download Full-text

Application of singular spectrum analysis to tool wear detection using sound signals

Proceedings of the Institution of Mechanical Engineers Part B Journal of Engineering Manufacture ◽

10.1243/095440505x32634 ◽

2005 ◽

Vol 219 (9) ◽

pp. 703-710 ◽

Cited By ~ 24

Author(s):

F J Alonso ◽

D R Salgado

Keyword(s):

Time Series ◽

Spectrum Analysis ◽

Flank Wear ◽

Singular Spectrum Analysis ◽

Back Propagation ◽

Processing Technique ◽

Sound Signal ◽

Singular Spectrum ◽

Tool Condition ◽

Cutting Zone

The aim of the present work is to study the applicability of singular spectrum analysis (SSA) to the processing of the sound signal from the cutting zone during a turning process, in order to extract information correlated with the state of the tool. SSA is a novel non-parametric technique of time series analysis that decomposes a given time series into an additive set of independent time series. The correspondence between the singular spectrum obtained using SSA and the frequency spectrum of the signal is the basis of this processing technique. Finally, some of the features extracted from the SSA-processed sound signal were presented to a feedforward back-propagation (FFBP) neural network to determine the tool flank wear. The results showed that the proposed processing technique is well suited to the task of signal processing in the area of tool condition monitoring (TCM).

Download Full-text

Diffraction separation and imaging using multichannel singular-spectrum analysis

Geophysics ◽

10.1190/geo2019-0201.1 ◽

2020 ◽

Vol 85 (1) ◽

pp. V11-V24 ◽

Cited By ~ 3

Author(s):

Peng Lin ◽

Suping Peng ◽

Jingtao Zhao ◽

Xiaoqin Cui

Keyword(s):

Spectrum Analysis ◽

Dynamic Properties ◽

Singular Spectrum Analysis ◽

Synthetic Data ◽

Singular Values ◽

Small Scale ◽

Diffraction Reflection ◽

Singular Spectrum ◽

Diffraction Imaging ◽

Time Linear

Seismic diffractions are the responses of small-scale discontinuous structures. They contain subwavelength geologic information. Thus, diffractions can be used for high-resolution imaging. The energy of diffractions is generally much weaker than that of reflections. Therefore, diffracted energy is typically masked by specular reflected energy. Diffraction/reflection separation is a crucial preprocessing step for diffraction imaging. To resolve the diffraction-separation problem, we have developed a method based on the multichannel singular-spectrum analysis (MSSA) algorithm for diffraction separation by reflection suppression. The MSSA algorithm uses the differences in the kinematic and dynamic properties between reflections and diffractions to suppress time-linear signals (reflections) and separate weaker time-nonlinear signals (diffractions) in the common-offset or poststack domain. For the time-linear signals, the magnitudes of the singular values are proportional to the energy strength of the signals. The stronger the energy of a component of the linear signals is, the larger the corresponding singular values will be. The singular values of reflections and diffractions have dissimilar spatial distributions in the singular-value spectrum because of the differences in their linear properties and energy. Only the singular values representing diffractions are selected to reconstruct seismic signals. Synthetic data and field data are used to test our method. The results reveal the good performance of the MSSA algorithm in enhancing diffractions and suppressing reflections.

Download Full-text