Data mining in manufacturing: Significance analysis of process parameters

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.

[1]  Thomas Hill.  Statistics: Methods and Applications , 2005 .

[2]  M Perzyk,et al.  Detection of causes of casting defects assisted by artificial neural networks , 2003 .

[3]  H. K. D. H. Bhadeshia,et al.  Estimation of the amount of retained austenite in austempered ductile irons using neural networks , 2001 .

[4]  Geoffrey Vining.  Multivariate Quality Control Procedures A. J. Hay ter , 1999 .

[5]  Shian-Shyong Tseng,et al.  A novel manufacturing defect detection method using association rule mining techniques , 2005, Expert Syst. Appl..

[6]  Andrew Kusiak,et al.  Data mining: manufacturing and service applications , 2006 .

[7]  Andrew Kusiak,et al.  Data Mining in Manufacturing: A Review , 2006 .

[8]  Armen Zakarian,et al.  Data mining algorithm for manufacturing process control , 2006 .

[9]  G. David Garson,et al.  Interpreting neural-network connection weights , 1991 .

[10]  Kurt Hornik,et al.  The support vector machine under test , 2003, Neurocomputing.

[11]  Dianliang Wu,et al.  Product Quality Improvement Analysis Using Data Mining: A Case Study in Ultra-Precision Manufacturing Industry , 2005, FSKD.

[12]  Marcin Perzyk,et al.  Prediction of ductile cast iron quality by artificial neural networks , 2001 .

[13]  Kesheng Wang,et al.  Applying data mining to manufacturing: the nature and implications , 2007, J. Intell. Manuf..

[14]  Henry C. W. Lau,et al.  Development of a Data Mining System for Continual Process Quality Improvement , 2007 .

[15]  M Srinivas,et al.  Product Design and Manufacturing Process Improvement Using Association Rules , 2006 .

[16]  Timothy Masters,et al.  Probabilistic Neural Networks , 1993 .

[17]  Zakład Odlewnictwa,et al.  Statistical and Visualization Data Mining Tools for Foundry Production , 2009 .

[18]  Robert Biernacki,et al.  Modeling of manufacturing processes by learning systems: The naïve Bayesian classifier versus artificial neural networks , 2005 .

[19]  Timothy Masters,et al.  Practical neural network recipes in C , 1993 .

[20]  Paulo J. G. Lisboa,et al.  Orthogonal search-based rule extraction (OSRE) for trained neural networks: a practical and efficient approach , 2006, IEEE Transactions on Neural Networks.

[21]  Liangsheng Qu,et al.  Fault diagnosis using Rough Sets Theory , 2000 .