SVM and ANN Application to Multivariate Pattern Recognition Using Scatter Data

Abstract

several methods of Statistical Process Control (SPC) are used to analyze process measurements with the purpose to detect faults that affect the process stability. SPC has a major drawback because it indicates the presence of faults without explaining which ones and where are the faults. In practical applications, SPC just analyses univariate signals limiting the study of multiple measures. Nowadays, novel methods have been developed for fault analysis based on pattern recognition in control charts. However, the majority of these studies follow a univariate approach. This article proposes a multivariate pattern recognition approach using machine learning algorithms in conjunction with a scatter diagram as the proposed method. In particular the aim of this approach is to monitor quality characteristics of a product in a multivariate environment considering states in control and out of control without the constraints of statistical conditions with the possibility of its application in real time. Results using Support Vector Machines (SVM) and the FuzzyARTMAP neural network showed that multivariate patterns can be recognized successfully in 81% of the cases.

Multivariate Pattern Recognition in MSPC Using Bayesian Inference

“…The use of Hotelling's T 2 CCs as such has made it possible to generate various modifications and is used as the comparative reference method with new proposals. The CCs' logic of operation and use in the processes allows adaptations to achieve better performance in observable cases [7][8][9][10][11][12][13][14][15][16][17]. Furthermore, with them as reference, the ongoing development of Multivariate Pattern Recognition (MVPR) using Artificial Neural Networks is to achieve the joint monitoring of random variables [12][13][14][15][16].…”

“…The CCs' logic of operation and use in the processes allows adaptations to achieve better performance in observable cases [7][8][9][10][11][12][13][14][15][16][17]. Furthermore, with them as reference, the ongoing development of Multivariate Pattern Recognition (MVPR) using Artificial Neural Networks is to achieve the joint monitoring of random variables [12][13][14][15][16]. The reasons for generating modifications to the Hotelling's CCs are: (1) the limitation in its design since it can only detect out-of-control signals for the special pattern of "changes in the mean" when the process has lost stability due to non natural variation causes and, (2) its inability to detect the random variables that cause instability in the process and to identify the type of failure that occurs as discussed in [17].…”

A quality-driven stability analysis framework based on state fluctuation space model for manufacturing process

“…For instance, Hu et al 16 used an intelligent ensemble model to estimate the variance change point in multivariable process, and the estimating result shows how to quickly search the cause of abnormal signal and provides guidance for identifying assignable causes for quality fluctuation in production process. In order to monitor quality characteristics of a product in a multivariate environment, Chinas et al 17 propose a multivariate pattern recognition method using machine learning algorithms in conjunction with a scatter diagram. Aslam et al 18 designed a mixed control chart for monitoring the process quality using attribute data and variable data, and the method provides the quick indication when the process is going to be out-of-control.…”

Integration of cuckoo search and fuzzy support vector machine for intelligent diagnosis of production process quality

“…Yang proposed an effective learning vector quantization network selective integration MSPC model based on two-stage discrete particle swarm optimization, which was used to monitor and diagnose mean drift in multivariable manufacturing process [49]. Chinas et al combined the scatter diagram, a multivariate pattern recognition method using machine learning algorithm was proposed to monitor the quality characteristics of multivariate products [10]. Masood and Shyen developed a series of methods for pattern recognition (PRS) based on control chart pattern recognition technology [33].…”

“…The basic data comes from the belt diameter (D), belt height (L) and seal diameter (E) in the production process of capacitor products. Firstly, 50 groups of process controlled sample data are collected, and the mean value is µ = 6.858, 8.018, 19.122, standard deviation is σ = 0.035, 0.023, 0.to the statistical model(10), 700 sets of samples including each abnormal mode were obtained by Matlab software simulation, and 100 sets of each abnormal mode were used as training and test data of the model. The corresponding fractal visualization diagram is shown inFigure 4:…”