Data mining in manufacturing: Significance analysis of process parameters

Abstract

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.

A location prediction method for work-in-process based on frequent trajectory patterns

“…In the past few years, data miming and advanced analytics have been utilized to investigate the manufacturing system. 21 For example, association rule mining was used to identify mapping relationships between important factors in the manufacturing process. [22][23][24] Meanwhile, another topic is rapidly developing, which is mining trajectory patterns, aiming to discover groups of trajectories based on their spatial or temporal similarity.…”

Methodology of Fault Diagnosis in Ductile Iron Melting Process

“…those with the greatest influences on a given output, are usually the first candidates for being responsible for appearance of the out-ofcontrol signal. Application of the significance analysis in production processes was a subject of some previous works [8,9]. The relative significance of the process input can be understood, defined and calculated in different ways.…”

“…The relative significance of the process input can be understood, defined and calculated in different ways. For the purpose of the present study the methodology based on one-way ANOVA (analysis of variance) was utilized [8], giving reasonable accuracies for the regression type relationships. The results are presented in Fig.…”

Applications of Data Mining to Diagnosis and Control of Manufacturing Processes

“…The definition of interaction coefficient between two variables tested in the present work is based on the test statistics F for the interaction of the two variables in the two--way ANOVA. Further details concerning the above presented definitions and methodology can be found in (Perzyk et al, 2008). In Fig.…”

“…It is worth adding that the decompositional approach, based on the weight values of ANNs, e.g. the Garson's proposal, turned out to be decidedly unsatisfactory (Perzyk et al, 2008). The network learns in a different way during each training session and large differences in the network weights are the source of large differences in significance factors based solely on their values.…”