Manufacturing AI Suite#
Manufacturing AI Suite is a curated, open, set of software solutions intended to demonstrate the applicability and efficiency of Intel hardware in industry-specific edge AI use cases.
The suite simplifies building, deploying, and scaling custom real time edge AI solutions for industrial environments by providing AI acceleration tools, support for IoT protocols (MQTT/OPC UA), accelerated analytics libraries, multi camera system software, and reusable sample applications, frameworks, microservices, and benchmarks.
For quick deployment of hardware components, you can use Edge Developer Kit Reference Scripts provided as part of Open Edge Platform.
Manufacturing AI Suite Samples#
RAG-enabled HMI running in a Windows® guest VM on a Type-2 hypervisor, backed by Chat Question & Answer Core on the host, for example on Edge Microvisor Toolkit.
Minimum configuration: Intel® Core™ i7-14700 (validated platform), 32 GB RAM
To learn more, follow the Get Started guide or review the System Requirements.
Real-time video quality control using DL Streamer and OpenVINO™ Toolkit, including Pallet Defect Detection, PCB Anomaly Detection, and Win Vision AI for Windows 11.
Minimum configuration: 12th Gen Intel® Core™ processor or newer, or 4th Gen Intel® Xeon® Scalable Processor, with Intel® HD Graphics; 16 GB RAM; 64 GB storage
Validated on: Intel® Core™ Ultra Processors (Series 3, 2, 1), Intel® Core™ Processors (Series 3, Series 2, and 14th/13th/12th Gen), and 4th Gen Intel® Xeon® Scalable Processors
NPU support: Intel® Core™ Ultra Processors (Series 3, 2, 1) and Intel® Core™ Processors Series 3
To learn more, follow the Get Started guide or review the System Requirements.
Predictive maintenance on a TICK Stack (Time Series Analytics and Grafana) that detects anomalies such as Wind Turbine Anomaly Detection.
Minimum configuration: 13th Gen Intel® Core™ or Intel® Xeon® processor with Intel® HD Graphics; 16 GB RAM; 64 GB storage (128 GB recommended)
Validated on: Intel® Core™ Ultra Processors (Series 3, 2) and Intel® Core™ Processors (13th Gen)
To learn more, follow the Get Started guide or review the System Requirements.
Fuses image and time-series anomaly detection with configurable AND/OR logic, as in
Multimodal Weld Defect Detection,
optionally extended with the Agentic Workflow that analyzes the fusion results, makes policy decisions, and creates maintenance tickets.
Minimum configuration: 13th Gen Intel® Core™ or Intel® Xeon® processor; 16 GB RAM; 64 GB storage (128 GB recommended)
Validated on: Intel® Core™ Ultra Processors (Series 3, 2) and Intel® Core™ Processors (13th Gen)
NPU support: Intel® Core™ Ultra Processors (Series 3, 2)
To learn more, follow the Get Started guide or review the System Requirements. For optional deployments, see the hardware requirements in the vLLM service and agentic workflow deployment guides.
Tools and Libraries#
DL StreamerOpen-source GStreamer framework-based media analytics framework used by video-centric applications.
Python code-based, containerized microservice for video analytics pipelines built using DL Streamer.
Optimizes and deploys AI models across Intel® hardware in cloud, edge, and on premises environments.
Hosts AI models via networks, e.g. enabling Pallet Defect Detection to share a single defect-detection model.
Builds production-ready vision models for deployment in applications, e.g. Smart Parking.
Visual Pipeline And Platform Evaluation Tool
Benchmarks end-to-end visual analytics pipelines, e.g. Smart Parking pipelines, on Intel® hardware.
Fuses multi camera and sensor data into a spatial scene model, e.g. for Smart Parking scene.
Intel® Edge System Qualification
Benchmarks and qualifies Intel® hardware for optimal system selection, e.g., Smart Parking system.
Intel® Edge Controls for Industrial#
Intel® Edge Controls for Industrial
Reference platform for safe, connected, and virtualization-ready industrial control systems.