Various methods have been proposed to monitor changes in a process covariance matrix. In view that a covariance matrix can be fully defined by its eigenvalues and eigenvectors, this paper suggests monitoring the covar...
详细信息
Various methods have been proposed to monitor changes in a process covariance matrix. In view that a covariance matrix can be fully defined by its eigenvalues and eigenvectors, this paper suggests monitoring the covariance matrix based on eigenvalues as another alternative. Although there are some recent discussions about the use of eigenvalues for hypothesis testing in multivariate analysis, the use of them for monitoring covariance matrix changes has been less studied in multivariate quality control. The simulation results show that the proposed method performs especially well under simultaneous shifts in both variance and correlation elements and competitively under shifts in variance or correlation elements only, compared to the existing approaches. This demonstrates a good property of the proposed method being able to provide a robust detection performance under a wide variety of scenarios. A real example is also provided to illustrate the implementation of the proposed method.
In this paper, we introduce a methodology for efficiently monitoring a health process that classify the intervention outcome, in two dependent characteristics, as "absolutely successful", "with minor bu...
详细信息
In this paper, we introduce a methodology for efficiently monitoring a health process that classify the intervention outcome, in two dependent characteristics, as "absolutely successful", "with minor but acceptable complications" and "unsuccessful due to severe complications". The monitoring procedure is based on appropriate 2-dimensional scan rules. The run length distribution is acquired by studying the waiting time distribution for the first occurrence of a 2-dimensional scan in a bivariate sequence of trinomial trials. The waiting time distribution is derived through a Markov chain embedding technique. The proposed procedure is applied on two simulated cases while it is tested against a competing method showing an excellent performance.
The FORTRAN code in Bodden and Rigdon (1999) for the in-control average run length (ARL) of multivariate exponentially weighted moving average charts (MEWMA) became quite popular and is widely used in statistical soft...
详细信息
The FORTRAN code in Bodden and Rigdon (1999) for the in-control average run length (ARL) of multivariate exponentially weighted moving average charts (MEWMA) became quite popular and is widely used in statistical software systems such as MINITAB and STATISTICA. We find that the algorithms' accuracy is poor for low-dimensional processes. The Markov chain approximation described in Runger and Prabhu (1996) is not able to resolve the issue. The same holds for the calculation of the out-of-control ARL as proposed in Ridgon (1995b). We present two concepts that achieve higher accuracy for all dimensions. The competing numerical procedures are implemented in the R package spc.
The primary objective of this note is to reduce the false alarms in multivariate statistical process control (MSPC). The issue of false alarms is inherent within MSPC as a result of the definition of control limits. I...
详细信息
The primary objective of this note is to reduce the false alarms in multivariate statistical process control (MSPC). The issue of false alarms is inherent within MSPC as a result of the definition of control limits. It has been observed that under normal operating conditions, the occurrence of "out-of-control" data, i.e. false alarms, conforms to a Bernoulli distribution. Therefore, this issue can be formally addressed by developing a Binomial distribution for the number of "out-of-control" data points within a given time window, and a second-level control limit can be established to reduce the false alarms. This statistical approach is further extended to consider the combination of multiple control charts. The proposed methodology is demonstrated through its application to the monitoring of a benchmark simulated chemical process, and it is observed to effectively reduce the false alarms whilst retaining the capability of detecting process faults. (C) 2009 The Institution of Chemical Engineers. Published by Elsevier B.V. All rights reserved.
Conventional multivariate cumulative sum control charts are more sensitive to small shifts than T2 control charts, but they cannot get the knowledge of manufacturing process through the learning of in-control data due...
详细信息
Conventional multivariate cumulative sum control charts are more sensitive to small shifts than T2 control charts, but they cannot get the knowledge of manufacturing process through the learning of in-control data due to the characteristics of their own structures. To address this issue, a modified multivariate cumulative sum control chart based on support vector data description for multivariate statistical process control is proposed in this article, which is named D-MCUSUM control chart. The proposed control chart will have both advantages of the multivariate cumulative sum control charts and the support vector data description algorithm, namely, high sensitivities to small shifts and learning abilities. The recommended values of some key parameters are also given for a better application. Based on these, a bivariate simulation experiment is conducted to evaluate the performance of the D-MCUSUM control chart. A real industrial case illustrates the application of the proposed control chart. The results also show that the D-MCUSUM control chart is more sensitive to small shifts than other traditional control charts (e.g. T2 and multivariate cumulative sum) and a D control chart based on support vector data description.
multivariate statistical process control (MSPC) techniques such as Principal Component Analysis (PCA) and Partial Least Squares (PLS) have found wide application especially in the statistical modeling and monitoring o...
详细信息
multivariatestatisticalprocess monitoring methods aim at detecting and identifying faults in the performance of processes over time in order to keep the process under control. Singular spectrum analysis (SSA) is a p...
详细信息
multivariatestatisticalprocess monitoring methods aim at detecting and identifying faults in the performance of processes over time in order to keep the process under control. Singular spectrum analysis (SSA) is a potential tool for multivariateprocess monitoring. It allows the decomposition of dynamic process variables or time series into additive components that can be monitored separately to identify hidden faults that may otherwise not be detectable. However, SSA is a linear method and can give misleading information when it is applied to dynamic processes with strong nonlinearity. Therefore, in this paper, nonlinear versions of SSA based on the use of auto-associative neural networks or auto encoders and dissimilarity matrices are considered. This is done based on the benchmark Tennessee Eastman process that is widely used in the evaluation of statisticalprocess monitoring methods. (C) 2017, IFAC (International Federation of Automatic control) Hosting by Elsevier Ltd. All rights reserved.
In today's world, structural development with reliability and integrity is an ever demanding process. Fault detection is the identification of normal healthy behavior of a system or process and recognition of any ...
详细信息
ISBN:
(纸本)9781509054541
In today's world, structural development with reliability and integrity is an ever demanding process. Fault detection is the identification of normal healthy behavior of a system or process and recognition of any deviation from such normal behavior. Fault detection in structural systems provides important liability and financial advantages since it gives the decision-makers lead-time and flexibility to manage the health of the system. Structural systems are critical systems that require continuous monitoring of damage accumulation caused by earthquake loads that may cause catastrophic failures. We present in this research a data-driven methodology for fault detection of structural systems using multivariate statistical process control (MVSPC). The proposed method based on modeling overall structural damage using artificial neural networks (ANN) as a function of the earthquake load intensity. Hotelling T-2 U technique is then used to identify any shifts of the ANN model weights from their healthy states. The proposed method is tested and validated using simulation data fora four-story RC building with varying concrete strengths. The methodology presented in this paper is scalable and can be applied to a wide range of systems to assess their health via an inspection check to anticipate and potentially avoid failures.
multivariatestatisticalprocess monitoring methods aim at detecting and identifying faults in the performance of processes over time in order to keep the process under control. Singular spectrum analysis (SSA) is a p...
详细信息
This article proposes a methodology to select a subset of variables to measure and monitor for multivariate statistical process control (SPC). In contrast with most dimensionality reduction approaches for SPC, we redu...
详细信息
This article proposes a methodology to select a subset of variables to measure and monitor for multivariate statistical process control (SPC). In contrast with most dimensionality reduction approaches for SPC, we reduce the number of variables that must be measured, thereby reducing the time and cost associated with inspection. We develop a two-stage procedure that selects the variables in a manner that retains as much information on the full set of variables as possible. In the first stage, the variables are sorted according to some measure of information content, which has broad applicability outside of SPC. In the second stage, the selected variables are determined using two alternative tools. The first tool is a general criterion based on the amount of residual information in the nonselected variables. The second tool is based on the performance of the control chart in detecting simulated out-of-control events. We illustrate the usefulness of the approach with simulation results and a real metal-forming application.
暂无评论