ADs: Active Data-sharing for Data Quality Assurance in Advanced Manufacturing Systems

arXiv:2404.00572v1 Announce Type: new
Abstract: Machine learning (ML) methods are widely used in industrial applications, which usually require a large amount of training data. However, data collection needs extensive time costs and investments in the manufacturing system, and data scarcity commonly exists. Therefore, data-sharing is widely enabled among multiple machines with similar functionality to augment the dataset for building ML methods. However, distribution mismatch inevitably exists in their data due to different working conditions, while the ML methods are assumed …

abstract ads advanced applications arxiv collection costs cs.lg data data collection data quality however industrial investments machine machine learning manufacturing multiple quality quality assurance systems training training data type