A Framework for Diagnosing the Out-of-Control Signals in Multivariate Process Using Optimized Support Vector Machines

Abstract

Multivariate statistical process control is the continuation and development of unitary statistical process control. Most multivariate statistical quality control charts are usually used (in manufacturing and service industries) to determine whether a process is performing as intended or if there are some unnatural causes of variation upon an overall statistics. Once the control chart detects out-of-control signals, one difficulty encountered with multivariate control charts is the interpretation of an out-of-control signal. That is, we have to determine whether one or more or a combination of variables is responsible for the abnormal signal. A novel approach for diagnosing the out-of-control signals in the multivariate process is described in this paper. The proposed methodology uses the optimized support vector machines (support vector machine classification based on genetic algorithm) to recognize set of subclasses of multivariate abnormal patters, identify the responsible variable(s) on the occurrence of abnormal pattern. Multiple sets of experiments are used to verify this model. The performance of the proposed approach demonstrates that this model can accurately classify the source(s) of out-of-control signal and even outperforms the conventional multivariate control scheme.

Metodología Integral para el Mejoramiento de la Calidad Mediante la Reducción de la Variabilidad Funcional: Un Caso de Estudio

“…El MSPC es una herramienta que permite monitorear más de una característica de calidad mediante la detección de señales fuera de control y la identificación de sus causas asignables (Li, 2013). El MSPC se soporta principalmente en la utilización de gráficos de control, mediante los cuales, las características de calidad son medidas como variables aleatorias con miras a controlar sus parámetros en relación con el comportamiento normal.…”

“… Poca atención en la optimización de múltiples características de calidad (Azadeh, 2012)  No es una herramienta para el control y mejora de los procesos (Pan et al, 2011) MSPC  Puede aplicarse con base en información histórica (Hachicha et al,2012)  Permite hibridación con otros métodos (Ferrer, 2007)  Contempla un amplio rango de opciones de gráficos de control multivariante s (Bersimis et al, 2007)  Sólo identifican señales fuera de control producidas por causas asignables (Li et al, 2013).…”

A Framework of Cloud Model Similarity-Based Quality Control Method in Data-Driven Production Process

“…With the increasing use of personalization in large-, medium-, and small-batch manufacturing processes, the quality of products is also getting higher and higher expected requirements [2,3]. In an actual production process, there are many influencing factors that affect the process fluctuation and exhibit temporal correlation, multidimensional coupling, dynamics, and high reliability [4,5]. Once the stability of fluctuation state is not timely evaluated, it will lead the abnormal state to continue to transfer, accumulate, and grow to ultimately result in the process abnormalities [6,7].…”

State entropy–based fluctuation analysis mechanism for quality state stability in data-driven manufacturing process

“…In the second step, SPC 1 aims to analyze and establish an acceptable and stable level based on statistical technique; the principle is that by analyzing whether the fluctuation pattern of control chart is normal or not to judge the process is in a stable state, 8 such as neural network (NN), 9,10 principal component analysis (PCA) 11,12 and the machining learning (ML) technology. [13][14][15] In the process monitoring and state warning step, by obtaining sufficient sample data, the established control model is used for process stability judgment and parameter estimation to monitor and evaluate the process for various stages. For instance, Zhou et al 16 adopted weighted least squares support vector machine to build the error propagation model for process capability evaluation method based on sensitivity analysis.…”