Optimizing Quality Management Through Big Data

In the Industry 4.0 period, integration of big data analytics with quality management processes opens new horizons for improving enterprise operating efficiency and decision-making in industrial companies. This study introduces a big data-oriented concept framework for optimizing quality management using distributed computing technologies. The approach adopts Apache spark for real time processing and clustering industrial process data for anomaly detection and generation of reference models from unlabeled datasets. A web application prototype was implemented with Spring MVC to facilitate interactive visualization as well as friendly user interactions with data. The framework was tested using a case study in a manufacturing environment where results showed increased accuracy when identifying defects, less time to process, and high scalability. The work reveals the application value of big data analytics for quality control and provides a scalable base for intelligent monitoring systems in the production settings.