Multivariate Statistical Process Control Framework Research Articles

A synergic multivariate statistical process control framework for monitoring, diagnosis, and adjustment of multiple response abrasive machining processes

A synergic multivariate statistical process control framework for monitoring, diagnosis, and adjustment of multiple response abrasive machining processes

A synergic multivariate statistical process control framework for monitoring, diagnosis, and adjustment of multiple response abrasive machining processes

In various abrasive machining processes, output quality is defined in terms of multiple critical responses and their deviations from target values. These multiple responses are often interacting and changing the process conditions for improving or controlling one response may deteriorate the quality of another. Thus, there is a need to simultaneously consider all responses and recommend a trade-off operating condition for process control and optimisation. Two important fields that consider simultaneous control and optimisation of multiple responses are the multivariate statistical process control (MSPC) and multiple response optimisation (MRO). Although various MSPC and MRO approaches have been proposed by researchers, there is limited prior research on the integration of MSPC and MRO approaches to ensure the stability and process capability. In this study, a synergic MSPC and MRO approach is proposed based on Mahalanobis-Taguchi system and nonlinear optimisation to ensure the stability and capability of the abrasive machining process.

Development and field application of a multivariate statistical process control framework for health-monitoring of transportation infrastructure

We present a two-part multivariate statistical process control framework to support health-monitoring of transportation infrastructure. The first part consists of estimation of regression and ARIMA–GARCH models to explain, predict, and control for common-cause variation in the data, i.e., changes that can be attributed to usual operating conditions, including traffic loads, environmental effects, and damage when present throughout the data. The second part of the framework consists of using multivariate control charts to simultaneously analyze the standardized innovations of the aforementioned models in order to detect possible special-cause or extraordinary events, such as unique/infrequent traffic, weather, or the onset of damage. The proposed approach revolves around construction of T2 control charts as a framework to jointly monitor the evolution and contemporaneous correlation of a set of measurements. The approach provides significant practical/computational advantages over individual analysis of multiple structural properties, and addresses technical problems stemming from ignoring the relationships among them.To illustrate the framework, we analyze strain and displacement data from the monitoring system on the Hurley Bridge (Wisconsin Structure B-26-7). Data were collected from 1 April 2010 to 28 June 2012. Analysis of 7 measurement sequences collected over the 27month planning horizon revealed 6 possible special-cause events. In terms of outlier interpretation, we use Mason–Young–Tracy Decomposition to establish the contribution of (subsets of) the measurements. Also, we link the most significant special-cause events, in terms of magnitude and duration, to unusual changes in weather and traffic. To conclude, we compare the proposed approach and benchmark the empirical results with Principal Component Analysis, perhaps, the most common alternative appearing in the literature.

Wavelet texture analysis of on-line acquired images for paper formation assessment and monitoring

Paper formation (the distribution and intermixing of fibres in a paper sheet), plays a central role in paper products, and is usually evaluated off-line, with a significant delay relative to the high production rates achieved in modern paper machines. In this paper, we address an approach for evaluating and monitor paper formation using images acquired with an especially designed sensor, in-line, in-situ and in real time. The methodology essentially consists of applying wavelet texture analysis to raw images, in order to compute a wavelet signature for each image, based on which their discrimination, according to the formation quality level, can be made. A PCA analysis of such features confirms the different formation quality levels defined a priori after visual inspection, and, furthermore, suggests a new subclass for abnormal samples, related to the bulkiness of fibre flocks. A multivariate statistical process control framework, based on such PCA description (PCA-MSPC), is proposed to monitor formation quality, which provides quite good results when applied to the available images, as analyzed with the ROC curve for the method and confirmed with a Monte Carlo simulation study using subimages with 1/4 of the size of the original ones.

Kernel-based fault diagnosis on mineral processing plants

Safe operation, environmental issues, as well as economic considerations all form part of the wide range of driving forces for the development of better fault diagnostic systems on process plants. The continuous search for novel methods for fault detection and identification resulting from these incentives has recently drawn attention to support vector machines as a means towards improved fault diagnosis. These kernel-based methods are in theory capable of better generalization, particularly as far as large systems are concerned, since their performance is not dependent on the number of variables under consideration and recent studies underlined their promising role in diagnostic systems. However, integration of these methods into the classical multivariate statistical process control framework is complicated by difficulties in the identification of the original variables associated with detected faults. In this paper, a general strategy for process fault diagnosis is proposed. First, kernel methods are used to remove nonlinear structure from the data, if present, after which the residuals from the data are used to monitor the process. A novel element of the strategy is the use of one-class support vector machines to estimate nonparametric confidence limits for these residuals. Using these limits in conjunction with Gower and Hand biplots and standard statistics collectively constitute a powerful approach to monitoring process systems, as demonstrated by several case studies on mineral processing systems.

Fault reconstruction in linear dynamic systems using multivariate statistics

Treasure et al. (2004) recently proposed a new subspace-monitoring technique, based on the N4SID algorithm, within the multivariate statistical process control framework. This dynamic-monitoring method requires considerably fewer variables to be analysed when compared with dynamic principal component analysis (PCA). The contribution charts and variable reconstruction, traditionally employed for static PCA, are analysed in a dynamic context. The contribution charts and variable reconstruction may be affected by the ratio of the number of retained components to the total number of analysed variables. Particular problems arise if this ratio is large and a new reconstruction chart is introduced to overcome these. The utility of such a dynamic contribution chart and variable reconstruction is shown in a simulation and by application to industrial data from a distillation unit.