[신간의 별자리x] 우리/미술, 그리고 ‘슬픔의 박물관’

The minimum Covariance Determinant (MCD) scatter estimator is a highly robust estimator for the dispersion matrix of a multivariate, elliptically symmetric distribution. It is fast to compute and intuitively appealing. In this note we derive its influence function and compute the asymptotic variances of its elements. A comparison with the one step reweighted MCD and with S-estimators is made. Also finite-sample results are reported.

Influence Function and Efficiency of the Minimum Covariance Determinant Scatter MAtrix Estimator

Process monitoring is crucial for maintaining favorable operating conditions and has received considerable attention in previous decades. Currently, a plant-wide process generally consists of multiple operational units and a large number of measured variables. The correlation among the variables and units is complex and results in the imperative but challenging monitoring of such plant-wide processes. With the rapid advancement of industrial sensing techniques, process data with meaningful process information are collected. Data-driven multivariate statistical plant-wide process monitoring (DMSPPM) has become popular. The key idea of DMSPPM is first decomposing a plant-wide process into multiple subprocesses and then establishing a data-driven model for monitoring the process, in which process variable decomposition is important for guaranteeing the monitoring performance. In the current review, we first introduce the basics of multivariate statistical process monitoring and highlight the necessity of des...

Review and Perspectives of Data-Driven Distributed Monitoring for Industrial Plant-Wide Processes

Review and big data perspectives on robust data mining approaches for industrial process modeling with outliers and missing data

Traditional spectral-based methods such as PCA are popular for anomaly detection in a variety of problems and domains. However, if data includes tensor (multiway) structure (e.g. space-time-measurements), some meaningful anomalies may remain invisible with these methods. Although tensor-based anomaly detection (TAD) has been applied within a variety of disciplines over the last twenty years, it is not yet recognized as a formal category in anomaly detection. This survey aims to highlight the potential of tensor-based techniques as a novel approach for detection and identification of abnormalities and failures. We survey the interdisciplinary works in which TAD is reported and characterize the learning strategies, methods and applications; extract the important open issues in TAD and provide the corresponding existing solutions according to the state-of-the-art.

/pdf/tensor-based-anomaly-detection-4h82npudmq.pdf

Tensor-based anomaly detection

Data-driven process monitoring methods often use classical multivariate statistical analysis (MSA) techniques for data analysis and modeling, with the assumption that the training data contains only observations associated with normal operating conditions of a process. In practice, the training data of an industrial process may contain outliers. Classical MSA methods can be affected by outliers so strongly that the resulting monitoring methods do not allow to detect true process faults. In this paper, a robust process monitoring method is proposed to cope with the presence of outliers in the training data. First, the minimum covariance determinant (MCD) estimator is used for outlier detection and to obtain the robust estimation of location and scatter of training data. A robust fault detection index, called the robust T2 statistic, is then defined based on the MCD estimator. Squared variable deviation magnitude (SVDM) is defined as a robust measure of the deviation of a process variable from the normal ra...

Robust Monitoring of Industrial Processes in the Presence of Outliers in Training Data

A CFD/CSD coupled method with high order and its applications in flow induced vibrations of tube arrays in cross flow

A novel generalized canonical variate analysis (GCVA) algorithm is formulated and then applied for data-driven dynamic process monitoring. The proposed GCVA algorithm seeks for different projecting bases for the time-serial samples, so that the sum of squared canonical correlation coefficients between all pairs of the projected latent variables could be maximized. The corresponding dynamic process monitoring scheme first utilizes GCVA to explicitly extract dynamic and static latent variables from the time-serial data, simultaneously. Second, a multivariate regression model is employed for describing the time-serial relationship between the dynamic latent variables, the model residual then services as a good indicator for the inconsistency in the defined time-serial mechanism. For online monitoring purposes, two combined monitoring indices are proposed for detecting abnormalities in the time-dependent and time-independent variations, respectively. Additionally, reconstruction-based contribution indices are also derived for fault diagnosis accordingly. Finally, the capability of the GCVA algorithm in exploiting the time-serial correlation inherited in the given data is demonstrated, the effectiveness and superiority of the proposed GCVA-based approach over other counterparts are validated as well, through comparisons on two dynamic industrial processes.

Dynamic statistical process monitoring based on generalized canonical variate analysis

Principal component analysis (PCA) has been widely used in the field of fault detection. A main difficulty in using PCA is the selection of principal components (PCs). Different PC selection criteria have been developed in the past, but most of them do not connect the selection of PCs with the fault detection. The selected PCs may be optimal for data modeling but not for fault detection. In this paper, the just-in-time cumulative percent contribution (JITCPC) criterion and the just-in-time contribution quantile (JITCQ) criterion are proposed to select PCs from the viewpoint of fault detection. In the JITCPC and JITCQ criteria, the contributions of PCs to the sample Mahalanobis distance are used to evaluate the importance of PCs to fault detection. The larger contribution the PC makes, the more important it is to detect a fault. The JITCPC criterion selects the leading PCs with the cumulative percent contribution (CPC) larger than a predefined threshold (e.g., 90%). The JITCQ criterion selects the PCs with...

Just-in-Time Selection of Principal Components for Fault Detection: The Criteria Based on Principal Component Contributions to the Sample Mahalanobis Distance

In a traditional fault detection and diagnosis (FDD) scheme, all of variables in a multivariate system are examined together as a single group. This FDD scheme may suffer from the amplification and...

Lijia Luo

Papers

Robust Monitoring of Industrial Processes in the Presence of Outliers in Training Data

A CFD/CSD coupled method with high order and its applications in flow induced vibrations of tube arrays in cross flow

Dynamic statistical process monitoring based on generalized canonical variate analysis

Just-in-Time Selection of Principal Components for Fault Detection: The Criteria Based on Principal Component Contributions to the Sample Mahalanobis Distance

Multivariate Fault Detection and Diagnosis Based on Variable Grouping