A spatial-adaptive sampling procedure for online monitoring of big data streams By Andi Wang, Xiaochen Xian, Fugee Tsung & Kaibo Liu
With the improvement of data-acquisition technology, big data streams that involve continuous observations with high dimensionality and large volume frequently appear in modern applications, which poses significant challenges for statistical process control. In this article we consider the problem of online monitoring a class of big data streams where each data stream is associated with a spatial location. Our goal is to quickly detect shifts occurring in such big data streams when only partial information can be observed at each time and the out-of-control variables are clustered in a small and unknown region. To achieve this goal, we propose a novel spatial-adaptive sampling and monitoring (SASAM) procedure that aims to leverage the spatial information of the data streams for quick change detection. Specifically, the proposed sampling strategy will adaptively and intelligently integrate two seemingly contradictory ideas: (1) random sampling that quickly searches for possible out-of-control variables; and (2) directional sampling that focuses on highly suspicious out-of-control variables that may cluster in a small region. Simulation and real case studies show that the proposed method significantly outperforms the existing sampling strategy without taking the spatial information of the data streams into consideration.
Multiple profiles sensor-based monitoring and anomaly detection By Chen Zhang, Hao Yan, Seungho Lee & Jianjun Shi
Generally, in an advanced manufacturing system hundreds of sensors are deployed to measure key process variables in real time. Thus it is desirable to develop methodologies to use real-time sensor data for on-line system condition monitoring and anomaly detection. However, there are several challenges in developing an effective process monitoring system: (i) data streams generated by multiple sensors are high-dimensional profiles; (ii) sensor signals are affected by noise due to system-inherent variations; (iii) signals of different sensors have cluster-wise features; and (iv) an anomaly may cause only sparse changes of sensor signals. To address these challenges, this article presents a real-time multiple profiles sensor-based process monitoring system, which includes the following modules: (i) preprocessing sensor signals to remove inherent variations and conduct profile alignments, (ii) using multichannel functional principal component analysis (MFPCA)–based methods to extract sensor features by considering cluster-wise between-sensor correlations, and (iii) constructing a monitoring scheme with the top-R strategy based on the extracted features, which has scalable detection power for different fault patterns. Finally, we implement and demonstrate the proposed framework using data from a real manufacturing system.
Monitoring for changes in the nature of stochastic textured surfaces By Anh Tuan Bui & Daniel W. Apley
We propose an approach for monitoring general global changes in the nature of stochastic textured surfaces using streams of high-dimensional images or related profile data. Stochastic textured surfaces are fundamentally different than the profiles and images that are the focus of most prior profile monitoring works. We represent normal in-control behavior by using supervised learning algorithms to implicitly characterize the joint distribution of the stochastic textured surface pixels. Based on this characterization, we develop a control chart monitoring statistic using likelihood-ratio principles to quantify and detect changes in the stochastic nature of the surfaces, relative to the in-control surfaces. Unlike methods that look for changes in specific predefined features, our approach can detect very general changes in the nature of the textured surfaces. We demonstrate the implementation and effectiveness of the approach with a real textile example and a simulation example.
Phase II monitoring of free-form surfaces: An application to 3D printing By Yangyang Zang & Peihua Qiu
Three-dimensional (3D) printing techniques have become popular in recent years. Monitoring the quality of its products is thus important. In the literature, there is little existing research on this topic now, partly because it is a challenging problem with complex data structures. In this article, we propose a nonparametric control chart for Phase II monitoring of the top surfaces of 3D printing products. The top surfaces are focused in this article because they are our major concern regarding the quality of 3D printing products in some applications. Such surfaces are often free-form surfaces. Our proposed method is based on local kernel estimation of free-form surfaces. Before Phase II monitoring, observed data from different products are first geometrically aligned to account for possible movement between the products and a laser scanner during the data acquisition stage. Numerical studies show that the proposed method works well in practice.
Spatially weighted PCA for monitoring video image data with application to additive manufacturing By Bianca M. Colosimo & Marco Grasso
Machine vision systems for in-line process monitoring in advanced manufacturing applications have attracted an increasing interest in recent years. One major goal is to quickly detect and localize the onset of defects during the process. This implies the use of image-based statistical process monitoring approaches to detect both when and where a defect originated within the part. This study presents a spatiotemporal method based on principal component analysis (PCA) to characterize and synthetize the information content of image streams for statistical process monitoring. A spatially weighted version of the PCA, called ST-PCA, is proposed to characterize the temporal auto-correlation of pixel intensities over sequential frames of a video-sequence while including the spatial information related to the pixel location within the image. The method is applied to the detection of defects in metal additive manufacturing processes via in-situ high-speed cameras. A k-means clustering-based alarm rule is proposed to provide an identification of defects in both time and space. A comparison analysis based on simulated and real data shows that the proposed approach is faster than competitor methods in detecting the defects. A real case study in selective laser melting (SLM) of complex geometries is presented to demonstrate the performances of the approach and its practical use.
Change detection in a dynamic stream of attributed networks By Mostafa Reisi Gahrooei & Kamran Paynabar
While anomaly detection in static networks has been extensively studied, only recently have researchers focused on dynamic networks. This trend is mainly due to the capacity of dynamic networks to represent complex physical, biological, cyber, and social systems. This article proposes a new methodology for modeling and monitoring dynamic attributed networks for quick detection of temporal changes in network structures. In this methodology, the generalized linear model (GLM) is used to model static attributed networks. This model is then combined with a state transition equation to capture the dynamic behavior of the system. Extended Kalman filter (EKF) is used as an online, recursive inference procedure to predict and update network parameters over time. In order to detect changes in the underlying mechanism of edge formation, prediction residuals are monitored through an exponentially weighted moving average (EWMA) control chart. The proposed modeling and monitoring procedure is examined through simulations for attributed binary and weighted networks. Email communication data from the Enron corporation is used as a case study to show how the method can be applied in real-world problems.
Space-time outlier identification in a large ground deformation data set By Youjiao Yu, Austin Workman, Jacob G. Grasmick, Michael A. Mooney & Amanda S. Hering
A novel application for outlier detection is in ground deformation monitoring. During any type of underground construction in urban settings, sensors are placed on the ground surface to monitor the vertical displacement with the goal of ensuring that there is no substantial heaving or settling of the ground. As a result, a large spatial-temporal data set is produced, but the sensors are often very sensitive, and spurious readings are commonly observed, resulting in both random and systematic outliers. In this work, we present a novel, fast spatial-temporal quality control procedure that is designed to remove these spurious readings prior to subsequent ground deformation monitoring. First, a robust kriging model is applied to the spatial ground deformations at each time point to remove systematic errors; next, an exponential moving average model is applied to the time series of ground deformations at each station to remove random outliers. A case study using ground deformation data when four subway tunnels are bored under a railyard in Queens, New York is used to illustrate the methodology. Methods used to construct outlier bounds are described, and the accuracy of our outlier detection approach is evaluated by calculating the percentages of outliers detected in an introduced artificial outlier set.