Combination of Human and Machine Intelligence to Optimize Assembly

Current research and futuristic approaches including machine learning promise the wide and thorough use of measurement data in assembly processes for analysis and optimization. However, in current assembly lines measurement data is not available in every process, e.g. not in manual assembly processes. In addition, the integration and combination of data from different sources within the assembly line will require huge efforts during the next years. Therefore, a solely data based approach is not suitable for current optimization projects that usually have to react quickly to occurring challenges. Thus, the research project “MessMo - metrologically supported assembly” uses, benchmarks and combines approaches from machine learning and methodic thinking for modelling, cause-effect-identification and optimization. Three approaches for modelling are utilized, accompanied by one approach for data and process optimization.

[1]  Paul Geladi,et al.  Principal Component Analysis , 1987, Comprehensive Chemometrics.

[2]  R.J. Marks,et al.  Implicit learning in autoencoder novelty assessment , 2002, Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290).

[3]  Ramalingam Shanmugam,et al.  Introduction to engineering statistics and lean six sigma: statistical quality control and design of experiments and systems , 2019, Journal of Statistical Computation and Simulation.

[4]  Trevor Hastie,et al.  The Elements of Statistical Learning , 2001 .

[5]  C. K. Chow,et al.  On optimum recognition error and reject tradeoff , 1970, IEEE Trans. Inf. Theory.

[6]  Tizian Schneider,et al.  Machine learning in industrial measurement technology for detection of known and unknown faults of equipment and sensors , 2019, tm - Technisches Messen.

[7]  J. Hauth.  Grey-Box Modelling for Nonlinear Systems , 2008 .

[8]  Anna C. Thornton.  Variation Risk Management: Focusing Quality Improvements in Product Development and Production , 2003 .

[9]  Andreas Schütze,et al.  Industrial condition monitoring with smart sensors using automated feature extraction and selection , 2018, Measurement Science and Technology.

[10]  Miguel Angel Ferrer-Ballester,et al.  Review of Automatic Fault Diagnosis Systems Using Audio and Vibration Signals , 2014, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[11]  Nikolai Helwig,et al.  Condition monitoring of a complex hydraulic system using multivariate statistics , 2015, 2015 IEEE International Instrumentation and Measurement Technology Conference (I2MTC) Proceedings.

[12]  Theodore T. Allen,et al.  Introduction to Engineering Statistics and Six Sigma: Statistical Quality Control and Design of Experiments and Systems , 2006 .

[13]  M. Bastuck,et al.  DAV3E – a MATLAB toolbox for multivariate sensor data evaluation , 2018, Journal of Sensors and Sensor Systems.

[14]  Gian Antonio Susto,et al.  A One-Class SVM Based Tool for Machine Learning Novelty Detection in HVAC Chiller Systems , 2014 .