On- and offline detection of structural breaks in thermal spraying processes

Borowski, Matthias; Rudak, Nikolaus; Hussong, Birger; Wied, Dominik; Kuhnt, Sonja; Tillmann, Wolfgang

doi:10.1080/02664763.2013.860957

Cited by 5 publications

(4 citation statements)

References 17 publications

(11 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, the velocity of the particles decreases slowly and more or less linearly. Similar patterns can be observed when a pressure drop of the carrier gas occurs . Formally, this can be written as

{normalΥ}_{i} (t) = ϕ_{0} + \sum_{j = 1}^{k / 2} [ϕ_{2 j - 1} \sin (j 2 πt) x_{i, 2 j - 1} + ϕ_{2 j} \cos (j 2 πt) x_{i, 2 j}] - ϕ_{k + 1} t, t \in [0, 1]

, where ϕ k + 1 determines the degree of failure.…”

Section: Simulation Studymentioning

confidence: 78%

See 1 more Smart Citation

Residual Analysis in Generalized Function‐on‐Scalar Regression for an HVOF Spraying Process

Kuhnt

Rehage

Becker-Emden

et al. 2016

Quality & Reliability Eng

Self Cite

View full text Add to dashboard Cite

The coating of materials plays an important role in various fields of engineering. Essential properties such as wear protection can be improved by a suitable coating technique. One of these techniques is high‐velocity oxygen‐fuel spraying. A drawback of high‐velocity oxygen‐fuel spraying is that it lacks reproducibility due to effects which are hard to measure directly. However, coating powder particles are observable over time during their flight towards the material and contain valuable information about the state of the process. Because of their smooth nature, measures of temperature and velocity can be assumed as target variables in generalized function‐on‐scalar regression. We propose methods to perform residual analysis in this framework aiming at the detection of individual residual functions which deviate from the majority of residuals. These methods help to detect anomalies in the process and hence improve the estimators. Functional target variables result in functional residuals whose analysis is barely explored. One reason might be that ordinary residual plots should be inspected at each observed point in time. We circumvent this infeasible procedure by the use of functional depths that help to identify unusual residuals and thereby gain deeper insight of the data‐generating process. In a simulation study, we find that a good depth for detecting trend outliers is the h‐modal depth as long as the link function is chosen correctly. In case of shape outliers rFUNTA pseudo‐depth performs well. Copyright © 2016 John Wiley & Sons, Ltd.

show abstract

{normalΥ}_{i} (t) = ϕ_{0} + \sum_{j = 1}^{k / 2} [ϕ_{2 j - 1} \sin (j 2 πt) x_{i, 2 j - 1} + ϕ_{2 j} \cos (j 2 πt) x_{i, 2 j}] - ϕ_{k + 1} t, t \in [0, 1]

, where ϕ k + 1 determines the degree of failure.…”

Section: Simulation Studymentioning

confidence: 78%

“…Similar patterns can be observed when a pressure drop of the carrier gas occurs. 18 Formally, this can be written…”

Section: Outlier Generating Mechanismsmentioning

confidence: 99%

Residual Analysis in Generalized Function‐on‐Scalar Regression for an HVOF Spraying Process

Kuhnt

Rehage

Becker-Emden

et al. 2016

Quality & Reliability Eng

Self Cite

View full text Add to dashboard Cite

show abstract

“…Moreover, we discuss selected aspects of asymptotic and bootstrap corrections for the cases where the residual eect is not asymptotically negligible. For instance, it turns out that the residual eect does not emerge in the scenario of Borowski et al (2014) (which is based on the variance constancy test in Wied, Arnold, Bissantz, and Ziggel, 2012) if the signal function is piecewise constant and the break point fractions can be consistently estimated. Borowski et al (2014) provided simulation evidence for this conjecture, but did not give a formal proof.…”

mentioning

confidence: 99%

“…For instance, it turns out that the residual eect does not emerge in the scenario of Borowski et al (2014) (which is based on the variance constancy test in Wied, Arnold, Bissantz, and Ziggel, 2012) if the signal function is piecewise constant and the break point fractions can be consistently estimated. Borowski et al (2014) provided simulation evidence for this conjecture, but did not give a formal proof. Furthermore, the theoretical result in our paper complements the applicability of the variance constancy test in Dette et al (2015), who only consider a smooth signal function and do not deal with the question if there might be situations in which the limit distribution remains the same.…”

mentioning

confidence: 99%

Residual-Based Inference on Moment Hypotheses, With an Application to Testing for Constant Correlation

Demetrescu¹,

Wied²

2018

SSRN Journal

Self Cite

View full text Add to dashboard Cite

Often, inference on moment properties of unobserved processes are conducted on the basis of estimated counterparts obtained in a preliminary step. In some situations, the use of residuals instead of the true quantities aects inference even in the limit, while in others there is no asymptotic residual eect. For the case of statistics based on partial sums of nonlinear functions of the residuals, we give here a characterization of the conditions under which the residual eect does not vanish as the sample size goes to innity (generic regularity conditions provided). An o verview of methods to account for the residual eect is also provided. The analysis extends to models with change points in parameters at estimated time, in spite of the discontinuous manner in which the break time enters the model of interest. To illustrate the usefulness of the results, we propose a test for constant correlations allowing for breaks at unknown time in the marginal means and variances. We nd, in Monte Carlo simulations and in an application to US and German stock returns, that not accounting for changes in the marginal moments has severe consequences.

show abstract

Predicting ROSC in out-of-hospital cardiac arrest using expiratory carbon dioxide concentration: Is trend-detection instead of absolute threshold values the key?

Brinkrolf

Borowski²,

Metelmann

et al. 2018

Resuscitation

View full text Add to dashboard Cite

On- and offline detection of structural breaks in thermal spraying processes

Cited by 5 publications

References 17 publications

Residual Analysis in Generalized Function‐on‐Scalar Regression for an HVOF Spraying Process

Residual Analysis in Generalized Function‐on‐Scalar Regression for an HVOF Spraying Process

Residual-Based Inference on Moment Hypotheses, With an Application to Testing for Constant Correlation

Predicting ROSC in out-of-hospital cardiac arrest using expiratory carbon dioxide concentration: Is trend-detection instead of absolute threshold values the key?

Contact Info

Product

Resources

About