An approach to monitoring quality in manufacturing using supervised machine learning on product state data

摘要: Increasing market demand towards higher product and process quality efficiency forces companies to think of new innovative ways optimize their production. In the area high-tech manufacturing products, even slight variations state during production can lead costly time-consuming rework or scrapage. Describing an individual product's along entire programme, including all relevant information involved for utilization, e.g., in-process adjustments parameters, be one way meet requirements stay competitive. Ideally, gathered directly analyzed in case identified critical trend event, adequate action, such as alarm, triggered. Traditional methods based on modelling cause-effect relations reaches its limits due fast increasing complexity high-dimensionality modern programmes. There is a need approaches that are able cope with this which, at same time, generate applicable results reasonable effort. Within paper, possibility system by applying combination Cluster Analysis Supervised Machine Learning data programme will presented. After elaborating different key aspects approach, applicability problem industrial environment discussed briefly.