Anomaly detection in injection molding process data based on unsupervised learning
Plastic processing companies in high-wage countries are facing continuously increasing cost and quality pressures. In many applications, a 100 % quality control leads to unreasonable efforts. Hence, quality forecasting or control based on process data would be desirable. Neural Networks have been applied. However, their success depends on the appropriate labeling of the process data. Since during the process, it is usually unknown whether a good or bad part has been produced in one cycle, supervised machine learning is not applicable. Here, we present approaches to anomaly detection in injection molding process data by means of unsupervised machine learning.
pdf-file, 47 Pages, 0.7 MB
The Journal of Plastics Technology is a peer reviewed internet periodical published under the auspices of the Scientific Alliance of Polymer Technology (WAK)
International Polymer Processing, the journal of the Polymer Processing Society, is a discussion forum for the world-wide community of engineers and scientists in the field of polymer processing.
The journal covers research and industrial application in the very specific areas of designing polymer products, processes, processing machinery and equipment.
The Journal of Plastics Technology is indexed in SCOPUS, the largest abstract and citation database of peer-reviewed literature.