A neural network applied to pattern recognition in statistical process control

1998 ◽  
Vol 35 (1-2) ◽  
pp. 185-188 ◽  
Author(s):  
A.S. Anagun
Keyword(s):  
Neural Network ◽  
Pattern Recognition ◽  
Process Control ◽  
Statistical Process Control ◽  
Statistical Process

scholarly journals End-to-End Control Chart Pattern Classification Using a 1D Convolutional Neural Network and Transfer Learning

Processes ◽  
2021 ◽  
Vol 9 (9) ◽  
pp. 1484
Author(s):  
Chuen-Sheng Cheng ◽  
Ying Ho ◽  
Tzu-Cheng Chiu
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Pattern Recognition ◽  
Process Control ◽  
Convolutional Neural Network ◽  
Statistical Process Control ◽  
Control Chart ◽  
Statistical Process ◽  
Random Patterns ◽  
Control Chart Pattern

Control charts are an important tool in statistical process control (SPC). They have been commonly used for monitoring process variation in many industries. Recognition of non-random patterns is an important task in SPC. The presence of non-random patterns implies that a process is affected by certain assignable causes, and some corrective actions should be taken. In recent years, a great deal of research has been devoted to the application of machine learning (ML) based approaches to control chart pattern recognition (CCPR). However, there are some gaps that hinder the application of the CCPR methods in practice. In this study, we applied a control chart pattern recognition method based on an end-to-end one-dimensional convolutional neural network (1D CNN) model. We proposed some methods to generate datasets with high intra-class diversity aiming to create a robust classification model. To address the data scarcity issue, some data augmentation operations suitable for CCPR were proposed. This study also investigated the usefulness of transfer learning techniques for the CCPR task. The pre-trained model using normally distributed data was used as a starting point and fine-tuned on the unknown non-normal data. The performance of the proposed approach was evaluated by real-world data and simulation experiments. Experimental results indicate that our proposed method outperforms the traditional machine learning methods and could be a promising tool to effectively classify control chart patterns. The results and findings of this study are crucial for the further realization of smart statistical process control.

Paraconsistent Artificial Neural Network for Structuring Statistical Process Control in Electrical Engineering

2016 ◽  
pp. 77-102
Author(s):  
João Inácio da Silva Filho ◽  
Clovis Misseno da Cruz ◽  
Alexandre Rocco ◽  
Dorotéa Vilanova Garcia ◽  
Luís Fernando P. Ferrara ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Process Control ◽  
Statistical Process Control ◽  
Electrical Engineering ◽  
Statistical Process ◽  
Artificial Neural

scholarly journals PEMODELAN KERANGKA ADAPTIVE THRESHOLD UNTUK MEMONITOR PRODUKSI MINYAK SAWIT NASIONAL BERBASIS STATISTICAL PROCESS CONTROL DAN ARTIFICIAL NEURAL NETWORK-BACKPROPAGATION

2016 ◽  
Vol 11 (2) ◽  
pp. 113-122
Author(s):  
Wahyu Widji Pamungkas ◽  
Syamsul Maarif ◽  
Tun Tedja Irawadi ◽  
Yandra Arkeman
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Process Control ◽  
Statistical Process Control ◽  
Palm Oil ◽  
Historical Data ◽  
Adaptive Threshold ◽  
The Other ◽  
Production Volume ◽  
Statistical Process

Indonesia is the largest exporter of palm oil in the world, as the largest producer Indonesia still havemany problems. The problem caused by incomparable between the growth of upstream and downstreampalm oil industries. This impact to low added value of palm oil, then Indonesia exports palm oil in crudeform. On the other hand, On the other hand , orientation export of this commodity is also prone of barrier,because Indonesia was not the price setter of this commodity in the international market. Therefore it isimportant to monitor and predict the development of national palm oil production volume in order to takegood anticipation. This research develop a framework model adaptive threshold to monitor the growing ofnational palm oil production volume with techniques of statistical process control (SPC) and back propagationartificial neural network (ANN - BP) methods. Historical data production volume period from 1967 to 2015was used as a base of the behavior as data to determine the threshold and prediction volume for nextperiods. The formation of the threshold value was based on the behavior of the historical data, which areoriented by the epicenter of the average value in the last two periods .Through mapping of data historicalperiod values, existing and forecast values with adaptive threshold can show tolerant level for the threshold.Furthermore, based on the analysis, it is known that the prediction of 2016 to 2018 period, there will behappen the dynamics production volume of national palm oil within tolerance threshold. The values of thesepredictions generated from the simulation model predictions of ANN-BP with the level very good of validationmodel, demonstrated the level of squared errors is very small1 in the MSE = 0.00021136 with a degree ofoutput correlation and the target is very strong2 with R Validation is 99.98 percent.Keywords: adaptive threshold, statistical process control, artificial neural network, national palm oilproduction.

Real-time pattern recognition in statistical process control: A hybrid neural network/decision tree-based approach

2005 ◽  
Vol 219 (3) ◽  
pp. 283-298 ◽  
Author(s):  
Ruey-Shiang Guh
Keyword(s):  
Neural Networks ◽  
Pattern Recognition ◽  
Process Control ◽  
Decision Tree ◽  
Real Time ◽  
Statistical Process Control ◽  
Hybrid System ◽  
Control Charts ◽  
Statistical Process ◽  
Fine Classification

Pattern recognition is an important issue in statistical process control because unnatural patterns displayed by control charts can be associated with specific causes that adversely impact on the manufacturing process. A common problem of existing approaches to control chart pattern (CCP) recognition is false classification between different types of CCP that share similar features in a real-time process-monitoring scenario, in which only limited pattern points are available for recognition. This study proposes a hybrid learning-based system that integrates neural networks and decision tree learning to overcome the classification problem in a real-time CCP recognition scheme. This hybrid system consists of three sequential modules, namely feature extraction, coarse classification, and fine classification. The coarse-classification model employs a four-layer back propagation network to detect and classify unnatural CCPs. The fine-classification module contains four decision trees used in a simple heuristic algorithm for further classifying the detected CCPs. Simulation experiments demonstrate that the false recognition problem has been effectively addressed by the proposed hybrid system. Compared with conventional control chart approaches, the proposed system has better performance in terms of recognition speed and also can accurately identify the type of unnatural CCP. Although a real-time CCP recognizer for the individual's (X) chart is the specific application presented here, the proposed hybrid methodology based on neural networks and decision trees can be applied to other control charts.

Sign in / Sign up

Export Citation Format

Share Document