TY - JOUR

T1 - Self-adjusting process monitoring system in series production

AU - Denkena, B.

AU - Dahlmann, D.

AU - Damm, J.

N1 - Funding information: At this point, the authors would like to thank the German Research Foundation (DFG) for its support of the research project Proceed (DE 447/96–1).

PY - 2015/1/1

Y1 - 2015/1/1

N2 - Modern monitoring systems in machine tools are able to detect process errors promptly. Still, the application of monitoring systems is restricted by the complexity of parameterization for save monitoring. In most cases, only specially trained personnel can handle this job especially for multi-purpose machines. The aim of the research project "Proceed" is to figure out in which extent a self-parameterization and autonomous optimization of monitoring systems in industrial series production can be realized. Therefore, a self-adjusting and self-tuning process monitoring system for series production has been developed. This system is based on multi-criteria sensor signal evaluation and is able to assess its monitoring quality quantitatively. For this purpose, the complete process chain of parameterization has been automated. For series production it is assumed, that the first process is not defective. So, process sensitive features are identified by a correlation analysis with a reference signal. The reference signal is selected through an analysis of the process state by an expert system. To assess the monitoring quality resulting from automatic parameterization, normed specific values were used. These values describe the monitoring quality with the help of the distance between a feature and its threshold normed to signal amplitude and noise. A second indicator is the reaction of the monitoring system to a synthetic error added to signal a sequence. Thus it is possible to estimate monitoring quality corresponding to automatic parameterization. The validation is carried out by a comparison between the result of the assessment and the reaction ability of the monitoring system to real process errors from milling, drilling and turning processes.

AB - Modern monitoring systems in machine tools are able to detect process errors promptly. Still, the application of monitoring systems is restricted by the complexity of parameterization for save monitoring. In most cases, only specially trained personnel can handle this job especially for multi-purpose machines. The aim of the research project "Proceed" is to figure out in which extent a self-parameterization and autonomous optimization of monitoring systems in industrial series production can be realized. Therefore, a self-adjusting and self-tuning process monitoring system for series production has been developed. This system is based on multi-criteria sensor signal evaluation and is able to assess its monitoring quality quantitatively. For this purpose, the complete process chain of parameterization has been automated. For series production it is assumed, that the first process is not defective. So, process sensitive features are identified by a correlation analysis with a reference signal. The reference signal is selected through an analysis of the process state by an expert system. To assess the monitoring quality resulting from automatic parameterization, normed specific values were used. These values describe the monitoring quality with the help of the distance between a feature and its threshold normed to signal amplitude and noise. A second indicator is the reaction of the monitoring system to a synthetic error added to signal a sequence. Thus it is possible to estimate monitoring quality corresponding to automatic parameterization. The validation is carried out by a comparison between the result of the assessment and the reaction ability of the monitoring system to real process errors from milling, drilling and turning processes.

KW - Intelligent

KW - Monitoring

KW - Process

UR - http://www.scopus.com/inward/record.url?scp=84939790372&partnerID=8YFLogxK

U2 - 10.1016/j.procir.2015.06.042

DO - 10.1016/j.procir.2015.06.042

M3 - Conference article

AN - SCOPUS:84939790372

VL - 33

SP - 233

EP - 238

JO - Procedia CIRP

JF - Procedia CIRP

SN - 2212-8271

T2 - 9th CIRP International Conference on Intelligent Computation in Manufacturing Engineering, CIRP ICME 2014

Y2 - 23 July 2014 through 25 July 2014

ER -