Manufacturing AI Suite (MAS) is a comprehensive toolkit for building, deploying, and scaling AI applications in industrial environments. Powered by Intel’s Edge AI technologies, it enables real-time integration and innovation with optimized hardware.
It includes: • Tools for AI acceleration (for example, MQTT/OPC UA support, analytics libraries, camera system software) • A complete AI pipeline for closed-loop systems • Benchmarking support for evaluating performance across time series, vision, and generative AI workloads
The Manufacturing AI Suite helps you develop solutions for: • Production Workflow: Detect defects, optimize efficiency • Workplace Safety: AI-driven risk reduction • Real-Time Insights: Local data processing, trend tracking • Automation: Instant alerts and corrective actions
Sample Applications
| HMI Augmented worker | A RAG-enabled HMI application deployable on type-2 hypervisors. | Documentation |
| Pallet Defect Detection | Real-time pallet condition monitoring via multiple AI models. | Documentation |
| PCB Anomaly Detection | Real-time anomaly detection in printed circuit boards (PCB) with AI vision systems. | Documentation |
| Weld Porosity | Real-time detection of welding defects. | Documentation |
| Worker Safety Gear Detection | Real-time visual analysis of safety gear compliance for workers. | Documentation |
| Wind Turbine Anomaly Detection | A time series use case of detecting anomalous power generation patterns relative to wind speed. | Documentation |
| Weld Defect Detection | A time series use case of detecting anomalous weld patterns relative to weld sensor parameters. | Documentation |
| Multimodal Weld Defect Detection | A multimodal use case combining vision and sensor data analysis to identify anomalies in welding data. | Documentation |
Main tools and AI Libraries the Suite uses
| Deep Learning Streamer | A framework for building optimized media analytics pipelines powered by OpenVINO™ toolkit. |
| Deep Learning Streamer Pipeline Server | A containerized microservice, built on top of GStreamer, for development and deployment of video analytics pipelines. |
| Model Registry | Providing capabilities to manage the lifecycle of an AI model. |
| Time Series Analytics Microservice | Built on top of Kapacitor, a containerized microservice for development and deployment of time series analytics capabilities |
| Intel® Geti™ SDK | A python package containing tools to interact with a Geti™ server via the REST API, helping you build a full MLOps for vision based use cases. |
| OpenVINO™ toolkit | An open source toolkit for deploying performant AI solutions across Intel hardware for generative and conventional AI models. |
| OpenVINO™ Model Server | An OpenVINO server solution for enabling remote model inference for AI applications deployed on low-performance devices. |