Control chart pattern recognition using learning vector quantization networks

Pham, Duc Truong; Öztemel, Ercan

doi:10.1080/00207549408956963

Cited by 122 publications

(48 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…These approaches contain LVQ networks (Pham and Oztemel 1994), MLP networks (Pham and Wani (Wang and Kuo 2007), PNN (Cheng and Ma 2008) and SVM (Kao et al 2014). And the corresponding methods of input representation include raw data (Pham and Oztemel 1994;Hassan et al 2003;Cheng and Ma 2008), shape features (Pham and Wani 1997), statistical features (Hassan et al 2003), shape features and statistical features (Ranaee and Ebrahimzadeh 2013), multi-resolution wavelets analysis (MRWA) (Al-Assaf 2004), multi-resolution discrete cosine transform (MRDCT) (Assaleh and Al-assaf 2005), wavelet filtering (Wang and Kuo 2007) and independent component analysis (ICA) (Kao et al 2014). The confusion matrix for performance comparison among the methodologies is reported in Table 7.…”

Section: Comparison With Other Approaches and Discussionmentioning

confidence: 99%

“…Since the early 1990s, numerous CCPR classifiers based on ANNs have been proposed. The most significant works include learning vector quantization (LVQ) networks (Pham and Oztemel 1994;Guh 2008;Gauri 2010;Gu et al 2013;Yang and Zhou 2013), multilayer perceptron (MLP) networks (Cheng 1997;Pham and Wani 1997;Guh and Tannock 1999;Al-Assaf 2004;Chen et al 2007;Pingyu et al 2009;Ranaee and Ebrahimzadeh 2013;Masood and Hassan 2013) and probability neural network (PNN) (Cheng and Ma 2008). Additionally, Ahmadzadeh et al (2013) applied neural networks to identify the process parameter change of multivariate exponentially weighted moving average (MEWMA) control charts and achieve quality improvement at reduced overall cost.…”

Section: Literature Reviewmentioning

confidence: 98%

“…As for the issue of input representation, two approaches have been suggested to present the characteristics of CCPs. The first is to directly use formalized raw data (Guh 2005;Pham and Oztemel 1994;Hassan et al 2003), and the other is featurebased approaches. The use of raw data suffers from the weakness that the amount of data to be processed is large.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Among these 15 common types of CCPs, normal, trend, shift and cyclic patterns are the most basic and usually researched CCPs (Guh and Tannock 1999;Al-Assaf 2004;Assaleh and Al-assaf 2005). Many researchers classified further trend pattern into upward trend and downward trend, similarly for shift pattern and investigated the recognition methods for six types CCPs, namely normal (NOR), upward trend (UT), downward trend (DT), upward shift (US), downward shift (DS) and cyclic (CYC) (Pham and Oztemel 1994;Pham and Wani 1997;Hassan et al 2003;Wani and Rashid 2005;Wang and Kuo 2007;Cheng and Ma 2008;Pingyu et al 2009;Ebrahimzadeh and Ranaee 2010;Ebrahimzadeh et al 2012). Moreover, among numerous types control charts, x chart is one of the most important and useful on-line process monitoring and control tools.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Recognition of control chart patterns using fuzzy SVM with a hybrid kernel function

2015

View full text Add to dashboard Cite

Accurate control chart patterns recognition (CCPR) plays an essential role in the implementation of control charts. However, it is a challenging problem since nonrandom control chart patterns (CCPs) are normally distorted by "common process variations". In this paper, a novel method of CCPR by integrating fuzzy support vector machine (SVM) with hybrid kernel function and genetic algorithm (GA) is proposed. Firstly, two shape features and two statistical features that do not depend on the distribution parameters and number of samples are presented to explicitly describe the characteristics of CCPs. Then, a novel multiclass method based on fuzzy SVM with a hybrid kernel function is proposed. In this method, the influence of outliers on classification accuracy of SVM-based classifiers is weakened by assigning a degree of membership for every training sample. Meanwhile, a hybrid kernel function combining Gaussian kernel and polynomial kernel is adopted to further enhance the generalization ability of the classifiers. To solve the issue of features selection and parameters optimization, GA is used to simultaneously optimize the input features subsets and parameters of fuzzy SVM-based classifier. Finally, several simulation experiments and a real example are addressed to validate the feasibility and effectiveness of the proposed methodology. And the results of simulation experiments demonstrate that it can achieve excellent performance for CCPR and outperforms other approaches, such as learning B Pingyu Jiang vector quantization network, multi-layer perceptron network, probability neural network, fuzzy clustering and SVM, in term of recognition accuracy. The results of the practical cases manifest that the proposed method has application potential for solving the problem of control chart interpretation in real-world.

show abstract

Section: Comparison With Other Approaches and Discussionmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 98%

Section: Literature Reviewmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Recognition of control chart patterns using fuzzy SVM with a hybrid kernel function

2015

View full text Add to dashboard Cite

show abstract

“…Oztemel (1992a, 1994) [5,6] used a backpropagation network (BPN) and learning vector quantization (LVQ) network to recognize shift, trend and cycle patterns on control charts. Hwarng and Hubele (1993) [7] extensively investigated CCPR by training BPNs to detect six unnatural CCPs sudden shift, trend, cycle, stratification, systematic, and mixture.…”

Section: Introductionmentioning

confidence: 99%

An Integrated Neural Network Structure for Recognizing Autocorrelated and Trending Processes

Karaoğlan

2011

MCA

View full text Add to dashboard Cite

Abstract-Data sets collected from industrial processes may have both a particular type of trend and correlation among adjacent observations (autocorrelation). In the present paper, an integrated neural network structure is used to recognize trend stationary first order autoregressive (trend AR(1)) process. The proposed integrated structure operates as follows. (i) First a combined neural network structure (CNN), that is composed of appropriate number of linear vector quantization (LVQ) and multi layer perceptron (MLP) neural networks, is used to recognize the trended data, (ii) then, the Elman's recurrent neural network (ENN) is used to diagnose the autocorrelation through the data. Correct classification rate is used as performance criteria. Results indicate that proposed structure is effective and competitive with other combined neural network structures.

show abstract

Stacked denoising autoencoder‐based feature learning for out‐of‐control source recognition in multivariate manufacturing process

Zheng

Wang

2018

Quality & Reliability Eng

View full text Add to dashboard Cite

In multivariate statistical process control (MSPC), regular multivariate control charts (eg, T2) are shown to be effective in detecting out‐of‐control signals based upon an overall statistic. But these charts do not relieve the need for multivariate process pattern recognition (MPPR). MPPR would be very useful for quality operators to locate the assignable causes that give rise to out‐of‐control situation in multivariate manufacturing process. Deep learning has been widely applied and obtained many successes in image and visual analysis. This paper presents an effective and reliable deep learning method known as stacked denoising autoencoder (SDAE) for MPPR in manufacturing processes. This study will concentrate on developing a SDAE model to learn effective discriminative features from the process signals through deep network architectures. Feature visualization is performed to explicitly present feature representations of the proposed SDAE model. The experimental results illustrate that the proposed SDAE model is capable of implementing detection and recognition of various process patterns in complicated multivariate processes. Analysis from this study provides the guideline in developing deep learning‐based MSPC systems.

show abstract

Control chart pattern recognition using learning vector quantization networks

Cited by 122 publications

References 6 publications

Recognition of control chart patterns using fuzzy SVM with a hybrid kernel function

Recognition of control chart patterns using fuzzy SVM with a hybrid kernel function

An Integrated Neural Network Structure for Recognizing Autocorrelated and Trending Processes

Stacked denoising autoencoder‐based feature learning for out‐of‐control source recognition in multivariate manufacturing process

Contact Info

Product

Resources

About