Recognition and classification of single and concurrent unnatural patterns in control charts via neural networks and fitted line of samples

Abstract

The correct, prompt recognition and analysis of unnatural and significant patterns in Schewhart's control charts are very important since they remind out-of-control conditions. In fact, pattern extraction increases the sensitivity of charts when identifying out of control conditions. Artificial neural networks have been used to identify unnatural patterns in many research studies due to their high efficiency in pattern recognition. In most of such studies, there is a significant risk of misclassification of highly sensitive patterns. To put it more clearly, the proposed models offered for the recognition of patterns with low parametric coefficients are mistaken. This study, offers a model for the recognition and analysis of basic patterns in process control charts using LVQ and MLP networks along with a fitted line analysis. In this model, not only does risk of misclassification at different levels of sensitivity decrease remarkably, but there will also be the possibility for recognition and analysis when basic pattern occur simultaneously. The efficiency and effectiveness of the model are shown by conducting tests based on simulation.

Multi-label classification of line chart images using convolutional neural networks

“…Classifying chart patterns is a crucial task; hence it has been required to be used in many different areas, including manufacturing [15], industrial engineering [16], finance [17] and civil engineering [18]. Lesanya et al [16] used the neural network technique to automatically classify control chart patterns as Downward trend, Upward trend, Downward shift, Upward shift, Cycle, and Systematic. Wan and Si [17] proposed a rule-based method to classify chart patterns in financial time series, such as "Triple Tops", "Cup with Handle", and "Head-and-Shoulders".…”

“…Unlike these studies, we didn't use textual information when interpreting a line chart, since the underlying information is not generally available as textual in many applications and domains. In this study, we used machine learning techniques which have been proven to be useful in many fields ranging from industrial applications [16] to localization problems [22].…”

Estimation and generation of training patterns for control chart pattern recognition

“…In the literature, models that deal with the recognition and classication of patterns in addition to estimating their corresponding parameters are very rare [45].…”

Applying Two-Stage Neural Network Based Classifiers to the Identification of Mixture Control Chart Patterns for an SPC-EPC Process

“…For example, some have employed various NNs to recognize CCPs for processes [8,9]. A NN ensemble-enabled model was used to classify unnatural CCPs for an autocorrelated process [10].…”