Integrated machine learning approaches for complementing statistical process control procedures

Kang, Bo Gyeong; Park, Sang C.

doi:10.1016/s0167-9236(00)00063-4

Cited by 20 publications

(14 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many researches have been conducted to prove the good performance of neural networks in process control [12,13]. For example, Smith [14] uses neural network models to inspect changes of process means and variations.…”

Section: Back Propagation Networkmentioning

confidence: 99%

See 1 more Smart Citation

Automated Detection of Color Non-Uniformity Defects in TFT-LCD

Lin

Chien

2006

The 2006 IEEE International Joint Conference on Neural Network Proceedings

View full text Add to dashboard Cite

Thin Film Transistor-Liquid Crystal Displays (TFT-LCD), owing to their space saving, energy efficiency, and low radiation, have been replacing Cathode-Ray Tubes (CRT). However, defects such as screen flaw points and small color deviations often exist in TFT-LCD's. To detect the MURA-type defects, the color non-uniformity regions, this research proposes a new automated visual inspection method. We first use multivariate Hotelling T 2 statistic to integrate different coordinates of color models and construct a T 2 energy diagram to represent the degree of color deviations for selecting suspected defect regions. Then, an Ant Colony based approach that integrates computer vision techniques precisely identifies the flaw point defects in the T 2 energy diagram. And, the Back Propagation Neural Network model determines the regions of small color variation defects based on the T 2 energy values. Results of experiments on real TFT-LCD panel samples demonstrate the effects and practicality of the proposed system.

show abstract

Section: Back Propagation Networkmentioning

confidence: 99%

“…The stop criterion of the proposed model is based on the proposition of Hush and Horne [12], who use methods of Root Mean Square Error and fixed learning cycles to set the parameters. Fig.…”

Section: Back Propagation Neural Network Model Applied To Detectiomentioning

confidence: 99%

Automated Detection of Color Non-Uniformity Defects in TFT-LCD

Lin

Chien

2006

The 2006 IEEE International Joint Conference on Neural Network Proceedings

View full text Add to dashboard Cite

show abstract

“…There is widespread interest in the use of neural networks in manufacturing [1][2][3][4][5]. Successful cases of applying neural networks for detecting the special disturbance in control charts and histograms have been presented by many researchers.…”

Section: Introductionmentioning

confidence: 99%

Statistical process control with intelligence using fuzzy ART neural networks

Wang

Zan

Ren-yuan

2010

Front. Mech. Eng. China

View full text Add to dashboard Cite

With the automation development of manufacturing processes, artificial intelligence technology has been gradually employed to increase the automation and intelligence degree in quality control using statistical process control (SPC) method. In this paper, an SPC method based on a fuzzy adaptive resonance theory (ART) neural network is presented. The fuzzy ART neural network is applied to recognize the special disturbance of the manufacturing processes based on the classification on the histograms, which shows that the fuzzy ART neural network can adaptively learn the features of the histograms of the quality parameters in manufacturing processes. As a result, the special disturbance can be automatically detected when a feature of the special disturbance starts to appear in the histograms. At the same time, combined with spectrum analysis of the autoregressive model of quality parameters, the fuzzy ART neural network can also be utilized to adaptively detect the abnormal patterns in the control chart.

show abstract

“…Maki and Teranishi (2001) used data mining methods to model associations between product fault and machines. Kang and Park (2000) integrated learning from data with statistical process control; neural network learning contributed to the reduction of features that are used in statistical process control.…”

Section: Introductionmentioning

confidence: 99%

Using machine learning to support quality management

2005

View full text Add to dashboard Cite

PurposeTo demonstrate the applicability of machine‐learning tools in quality management.Design/methodology/approachTwo popular machine‐learning approaches, decision tree induction and association rules mining, were applied on a set of 960 production case records. The accuracy of results was investigated using randomized experimentation and comprehensibility of rules was assessed by experts in the field.FindingsBoth machine‐learning approaches exhibited very good accuracy of results (average error was about 9 percent); however, association rules mining outperformed decision tree induction in comprehensibility and correctness of learned rules.Research limitations/implicationsThe proposed methodology is limited with respect to case representation. Production cases are described via attribute‐value sets and the relation between attribute values cannot be determined by the selected machine‐learning methods.Practical implicationsResults demonstrate that machine‐learning techniques may be effectively used to enhance quality management procedures and modeling of cause‐effect relationships, associated with faulty products.Originality/valueThe article proposes a general methodology on how to use machine‐learning techniques to support quality management. The application of the technique in ISDN modem manufacturing demonstrates the effectiveness of the proposed general methodology.

show abstract

Integrated machine learning approaches for complementing statistical process control procedures

Cited by 20 publications

References 14 publications

Automated Detection of Color Non-Uniformity Defects in TFT-LCD

Automated Detection of Color Non-Uniformity Defects in TFT-LCD

Statistical process control with intelligence using fuzzy ART neural networks

Using machine learning to support quality management

Contact Info

Product

Resources

About