An augmented neural network classification approach to detecting mean shifts in correlated manufacturing process parameters

Zobel, Christopher W.; Cook, Deborah F.; Nottingham, Quinton

doi:10.1080/00207540310001602856

Cited by 25 publications

(12 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Statistical process control (SPC) is an effective tool used to detect whether the observed process variables deviate from the normal state. Although the regular SPC technique has witnessed many successes for monitoring discrete manufacturing processes (Deming), they are not applicable in continuous and batch process industries (Zobel et al). The fundamental assumption using SPC is independent of the observed process variables.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep recurrent neural network‐based residual control chart for autocorrelated processes

Chen

2019

Quality & Reliability Eng

View full text Add to dashboard Cite

With the growth of automation in process industries, there is correlation in the process variables. Deep learning has achieved many great successes in image and visual analysis. This paper concentrates on developing a deep recurrent neural network (RNN) model to characterize process variables at vary time lags, and then a residual chart is developed to detect mean shifts in autocorrelated processes. The experiment results indicate that the RNN‐based residual chart outperforms other typical methods (eg, autoregressive [AR]‐based control chart, back propagation network [BPN]‐based residual chart). This paper provides guideline for deep learning technique employed as an effective tool in autocorrelated process control.

show abstract

Section: Introductionmentioning

confidence: 99%

“…Once a false alarm is triggered in the process, quality engineers need to investigate and eliminate these assignable causes from the processes (English et al), which results in the costly over‐control of process. Hence, some alternative approaches are developed to monitor mean shifts in autocorrelated processes (Zobel et al).…”

Section: Introductionmentioning

confidence: 99%

Deep recurrent neural network‐based residual control chart for autocorrelated processes

Chen

2019

Quality & Reliability Eng

View full text Add to dashboard Cite

show abstract

“…Patrones cíclicos se observan como una serie de máximos y mínimos ocurridos en el proceso; pueden indicar la fluctuación del voltaje de la fuente de alimentación. En los últimos años, varios autores [3,[5][6][7][8][9][10][11][12][13][14][15][16], han propuesto el uso de Redes Neuronales Artificiales (RNA) en el reconocimiento de patrones en los gráficos de control con el fin de examinar patrones, mejorar la eficiencia en comparación con los métodos usuales y obtener un diagnóstico automático de los patrones.…”

Section: Introductionunclassified

SVM and ANN Application to Multivariate Pattern Recognition Using Scatter Data

Chinas

Lopez

Vázquez

et al. 2015

IEEE Latin Am. Trans.

View full text Add to dashboard Cite

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.

show abstract

“…These rules are commonly referred to as: points outside the control limits, run of consecutive points, non-random patterns and points near the control limits [1]. The efficiency of the use of these rules has been investigated and it has been found that is not enough to recognise the type of statistical pattern ( [3], [4], [5], [6], [7], [8], [9], [10], [11], [12]), which would give the correct answer to the questions of where and what to look for. This is why researchers suggest the use of the neural networks as an alternative approach to identify variation data in statistical patterns [4].…”

Section: Introductionmentioning

confidence: 99%

“…Neural networks are efficient in recognizing data variation [2], [5], [14], especially in asymmetric probability distributions [2]. Among the existing neural networks, the Fuzzy ARTMAP Network is widely recognized due to its on-line and fast learning capability for pattern recognition tasks [15], [16].…”

Section: Introductionmentioning

confidence: 99%

On the Use of the FuzzyARTMAP Neural Network for Pattern Recognition in Statistical Process Control using a Factorial Design

Vázquez-López

López-Juárez²,

Peña‐Cabrera

2010

INT J COMPUT COMMUN

View full text Add to dashboard Cite

Time-series statistical pattern recognition is of prime importance in statistics, especially in quality control techniques for manufacturing processes. A frequent problem in this application is the complexity when trying to determine the behaviour (pattern) from sample data. There have been identified standard patterns which are commonly present when using the X chart; its detection depends on human judgement supported by norms and graphical criteria. In the last few years, it has been demonstrated that Artificial Neural Networks (ANN's) are useful to predict the type of time-series pattern instead of the use of rules. However, the ANN control parameters have to be fixed to values that maximize its performance. This research proposes an experimental design methodology to determine the most appropriate values for the control parameters of the FuzzyARTMAP ANN such as: learning rate (β ) and network vigilance (ρ a , ρ b , ρ ab ) in order to increment the neural network efficiency during unnatural pattern recognition.

show abstract

An augmented neural network classification approach to detecting mean shifts in correlated manufacturing process parameters

Cited by 25 publications

References 20 publications

Deep recurrent neural network‐based residual control chart for autocorrelated processes

Deep recurrent neural network‐based residual control chart for autocorrelated processes

SVM and ANN Application to Multivariate Pattern Recognition Using Scatter Data

On the Use of the FuzzyARTMAP Neural Network for Pattern Recognition in Statistical Process Control using a Factorial Design

Contact Info

Product

Resources

About