scholarly journals Bootstrap Aggregation Technique for Evaluating the Significance of Manufacturing Process Parameters in the Glass Industry

2021 ◽  
Vol 24 (1) ◽  
Author(s):  
Łukasz Paśko ◽  
Aneta Kuś
Keyword(s):  
Neural Networks ◽  
Process Parameters ◽  
Glass Industry ◽  
Manufacturing Process ◽  
Prediction Error ◽  
Real Data ◽  
Aggregation Technique ◽  
Single Neural Network ◽  
Glass Packaging ◽  
Bootstrap Aggregation

The article presents the application of the bootstrap aggregation technique to create a set of artificial neural networks (multilayer perceptron). The task of the set of neural networks is to predict the number of defective products on the basis of values of manufacturing process parameters, and to determine how the manufacturing process parameters affect the prediction result. For this purpose, four methods of determining the significance of the manufacturing process parameters have been proposed. These methods are based on the analysis of connection weights between neurons and the examination of prediction error generated by neural networks. The proposed methods take into account the fact that not a single neural network is used, but the set of networks. The article presents the research methodology as well as the results obtained for real data that come from a glassworks company and concern a production process of glass packaging. As a result of the research, it was found that it is justified to use a set of neural networks to predict the number of defective products in the glass industry, and besides, the significance of the manufacturing process parameters in the glassworks company was established using the developed set of neural networks.

scholarly journals Significance of Manufacturing Process Parameters in a Glassworks

2020 ◽  
Vol 44 (2) ◽  
pp. 39-45
Author(s):  
Łukasz Paśko
Keyword(s):  
Neural Networks ◽  
Sensitivity Analysis ◽  
Artificial Neural Networks ◽  
Production Process ◽  
Process Parameters ◽  
Manufacturing Process ◽  
Multilayer Perceptrons ◽  
Artificial Neural ◽  
Glass Packaging

AbstractThe article presents the use of artificial neural networks (multilayer perceptrons) to examine the significance of production process parameters. The considered problem relates to the occurrence of production periods with an increased number of defective products. The research aims to determine which of the 69 parameters of the manufacturing process most affect the number of defects. Two ways of expressing the parameters significance were used: using the sensitivity analysis and exploring the weights of connections between neurons. The results were determined using both single neural networks and a set of networks. The outcome from the research is the rankings of significance of the manufacturing process parameters. The analyzed data were obtained from a glassworks producing glass packaging.

scholarly journals Optimisation of manufacturing process parameters using deep neural networks as surrogate models

Procedia CIRP ◽  
2018 ◽  
Vol 72 ◽  
pp. 426-431 ◽  
Author(s):  
Julius Pfrommer ◽  
Clemens Zimmerling ◽  
Jinzhao Liu ◽  
Luise Kärger ◽  
Frank Henning ◽  
...  
Keyword(s):  
Neural Networks ◽  
Process Parameters ◽  
Manufacturing Process ◽  
Deep Neural Networks ◽  
Surrogate Models

Data mining in manufacturing: Significance analysis of process parameters

2008 ◽  
Vol 222 (11) ◽  
pp. 1503-1516 ◽  
Author(s):  
M Perzyk ◽  
R Biernacki ◽  
J Kozlowski
Keyword(s):  
Data Mining ◽  
Neural Networks ◽  
Process Parameters ◽  
Regression Models ◽  
Simulated Data ◽  
Real Data ◽  
Support Vector ◽  
Data Sets ◽  
Interaction Factors

Determination of the most significant manufacturing process parameters using collected past data can be very helpful in solving important industrial problems, such as the detection of root causes of deteriorating product quality, the selection of the most efficient parameters to control the process, and the prediction of breakdowns of machines, equipment, etc. A methodology of determination of relative significances of process variables and possible interactions between them, based on interrogations of generalized regression models, is proposed and tested. The performance of several types of data mining tool, such as artificial neural networks, support vector machines, regression trees, classification trees, and a naïve Bayesian classifier, is compared. Also, some simple non-parametric statistical methods, based on an analysis of variance (ANOVA) and contingency tables, are evaluated for comparison purposes. The tests were performed using simulated data sets, with assumed hidden relationships, as well as on real data collected in the foundry industry. It was found that the performance of significance and interaction factors obtained from regression models, and, in particular, neural networks, is satisfactory, while the other methods appeared to be less accurate and/or less reliable.

Application Of Cusum Chart In Control Of Paper Quality

GIS Business ◽  
2020 ◽  
Vol 14 (6) ◽  
pp. 1062-1069
Author(s):  
S.Ramesh ◽  
B.A.Vasu
Keyword(s):  
Process Parameters ◽  
Manufacturing Process ◽  
Paper Industry ◽  
Primary Data ◽  
Cusum Chart ◽  
Paper Machine ◽  
Statistical Control ◽  
Operating Characteristics ◽  
Small Shift

This paper is an attempt to assess if the manufacturing process of paper machine is in statistical control thereby improving the quality of paper being produced in a paper industry at the time of process itself. Quality is the foremost criteria for achieving the business target. Therefore, emphasis was made on controlling the quality of paper at the time of manufacturing process itself, rather than checking the finished lots at a later time.  This control on quality will help the industry deduct the small shift in the process parameters and modify the operating characteristics at the time of production itself rather than receiving complaints from customers at a later stage.  This paper describes controlling quality at the time of manufacture itself and helps the industry to concentrate on quality at low cost. The researcher has collected primary data at a leading paper industry during October, 2019.  Though X-bar and Range charges were primarily used, CUSUM charts were used to sense the minor shifts in manufacturing process, to explore the possibility of adjusting process parameters during manufacture of paper.

Correlating the 3D melt electrospun polycaprolactone fiber diameter and process parameters using neural networks

2021 ◽  
pp. 50956
Author(s):  
Pasupuleti Lakshmi Narayana ◽  
Xiao‐Song Wang ◽  
Jong‐Taek Yeom ◽  
Anoop Kumar Maurya ◽  
Won‐Seok Bang ◽  
...  
Keyword(s):  
Neural Networks ◽  
Process Parameters ◽  
Fiber Diameter

scholarly journals Asymptotic Prediction Error Variance for Feedforward Neural Networks

2020 ◽  
Vol 53 (2) ◽  
pp. 1108-1113
Author(s):  
Magnus Malmström ◽  
Isaac Skog ◽  
Daniel Axehill ◽  
Fredrik Gustafsson
Keyword(s):  
Neural Networks ◽  
Prediction Error ◽  
Feedforward Neural Networks ◽  
Error Variance ◽  
Prediction Error Variance
Sign in / Sign up

Export Citation Format

Share Document