SHION: Towards An Interactive Digital Twin Supporting Shopfloor Operations on Real Time

Injection molding is widely used to produce plastic components with large lot size. However, guaranteeing consistency and quality of parts in injection molding is challenging. Failures occur due to variation during injection cycles. Thus, real-time detection of failures will have a high impact on quality and productivity. This article is focused on Smart tHermoplastic injectION (SHION), a cloud-based Digital Twin supported by AI-based control of process parameters. Process parameters and their interrelationship with quality failure were studied and used to generate models for real-time prediction of part quality. Two injection manufacturing lines in industry were chosen for data acquisition, implementation, and validation of the Digital Twin. While SHION successfully predicted faulty products in real time, adoption of traditional Cloud-centric Internet of Things approaches poses unforeseen practical challenges such as exposure to risk of losing data due to network issues and prohibitive cost of regularly transferring a large amount data to Cloud services.