Combination of Human and Machine Intelligence to Optimize Assembly

Abstract

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.