“Intel’s Approach to Operationalizing AI in the Manufacturing Sector,” a Presentation from Intel
•
0 likes•144 views
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2024/07/intels-approach-to-operationalizing-ai-in-the-manufacturing-sector-a-presentation-from-intel/ Tara Thimmanaik, AI Systems and Solutions Architect at Intel, presents the “Intel’s Approach to Operationalizing AI in the Manufacturing Sector,” tutorial at the May 2024 Embedded Vision Summit. AI at the edge is powering a revolution in industrial IoT, from real-time processing and analytics that drive greater efficiency and learning to predictive maintenance. Intel is focused on developing tools and assets to help domain experts operationalize AI-based solutions in their fields of expertise. In this talk, Thimmanaik explains how Intel’s software platforms simplify labor-intensive data upload, labeling, training, model optimization and retraining tasks. She shows how domain experts can quickly build vision models for a wide range of processes—detecting defective parts on a production line, reducing downtime on the factory floor, automating inventory management and other digitization and automation projects. And she introduces Intel-provided edge computing assets that empower faster localized insights and decisions, improving labor productivity through easy-to-use AI tools that democratize AI.
“Intel’s Approach to Operationalizing AI in the Manufacturing Sector,” a Presentation from Intel
- 1. Intel’s approach to Operationalizing AI in the Manufacturing Sector Tara Thimmanaik AI Systems and Solutions Architect Intel
- 2. 2 2 2 Notices & Disclaimers • Performance varies by use, configuration and other factors. Learn more on the Performance Index site. • Performance results are based on testing as of dates shown in configurations and may not reflect all publicly available updates. See backup for configuration details. No product or component can be absolutely secure. • Your costs and results may vary. • Intel technologies may require enabled hardware, software or service activation. • © Intel Corporation. Intel, the Intel logo, and other Intel marks are trademarks of Intel Corporation or its subsidiaries. Other names and brands may be claimed as the property of others. 2
- 3. The Time for Edge AI is NOW! Easy-to-use tools are democratizing AI AI is improving labor productivity Edge computing empowers faster localized insights and decisions AI solutions are more accessible and less costly than ever before 93% of industrial manufacturing business leaders wish their company would more aggressively adopt AI technology2 1 Despite productivity gains, manufacturers still struggle to find talent. HRDive, 2023. 2 Source: “Industrial Manufacturing: Bullish on AI adoption. KPMG, 2021. 3
- 4. Industrial Use Cases for Edge Inference (Analytics) People Machine Material Process Environment Worker behavior Situational monitoring Predictive maintenance Robotics pick-and- place Predictive analytics Product defect detection Raw material appearance inspection Asset management Factory operation optimization Optimization of raw material utilization Temperature optimization Humidity optimization Worker safety Visual data gathered at the Edge drives improved operations Use case can benefit from video data. 1. Notes from the AI frontier insights from hundreds of use cases, McKinsey Global Institute, 2018 4
- 5. What are YOUR barriers to adopting AI? 78% of Edge AI use cases do not reach deployment Difficulty gathering useful data Mistrust of “unexplainable AI“ Lack of AI expertise High implementation costs Available solutions are too complicated, or too limited Only 10% Companies say they are generating significant benefits from AI 1. 6 ways to help the manufacturing sector embrace AI. World Economic Forum, 2023 5
- 6. 6 Industrial Workflow with Machine Learning
- 8. Deployment of AI Model 8
- 9. Industrial workflow with AI 9
- 10. 10 Intel® TiberTM Edge Platform
- 11. Through an unmatched partner ecosystem, Intel’s new commercial software platform enables enterprises to build, deploy, run, and manage scalable edge and AI solutions on standard hardware with cloud-like simplicity. Introducing Intel® TiberTM Edge Platform Manage Deploy Run Build Secure Open & Modular | Edge & AI Optimized | Rich App Orchestration Brownfield and heterogenous component support Speed, accuracy, and power efficiency on right-sized components Remote application and AI deployment and management at scale 11
- 12. Build models with the Intel® G eti™ platform Deploy with Intel Premises AI Build and Deploy your AI Solution With Intel 12 Build models with the Intel® Geti™ platform Deploy with Intel Premises AI
- 13. Achieve a working model with fewer data. Active learning selects the most useful data to label for training Automatic optimizations are available 3 Easily label data with smart annotation features 2 Start model development with as little as 20 images or a video 1 Adjust your model by retraining with new data and exporting a new model 5 4 Export model in native framework or as an optimized model for OpenVlNO™ toolkit Accelerate Model Development One Platform for the Complete Model Development Cycle Intel® Geti™ Platform 13
- 14. See How Intel® Geti™ Platform Works Intel® Geti™ Platform 14
- 15. Intel® Edge Insights System An all-encompassing solution for management, operation and easy deployment of AI at the Edge. Intel® Edge Insights System is part of Intel® TiberTM Edge Platform User Interface designed for developers and factory experts Intel® Edge Insights System Validated cameras of your choice Validated Industrial PCs of your choice Maintenance and Support options Value-added Services Including installation, engineering and training services Intel AI Software Offerings including tools, libraries and sample models to get a customer started. Integration Tools easily connect to existing systems Easy-to-deploy, comprehensive solution Industrial focused Supporting both time series and video analytics Flexible pricing 15
- 16. Intel® Edge Insights System 16
- 17. Data Collection and Annotation Enabled Operator-Friendly User Interface Validated IPCs and Cameras Available 1. Intel® Edge Insights System is expected to be officially launched by Q3 2024. 2. Intel® Edge Insights System is compatible with Intel® Geti™ platform for model creation and ingestion. 3. Intel® Edge Insights System is part of Intel® Tiber™Edge Platform. Value-added services Installation, Training, and Engineering services Validated Industrial PC s Validated C ameras User Interface (End C ustomer) Software Offerings Maintenance and Support Options User Interface (Developer) Integrated Standard and Enhanced SKUs Compatible with Intel® Edge Insights System A Comprehensive AI Edge Inferencing Platform – Help factories put AI to work Intel® Edge Insights System (Part of Intel’s Edge Platform) 17
- 18. Operations Live Data Input Video Time series Audio Data Data Ingestion from Operations + Database Training Data Streams Model Development Data Ingress Intel® Edge Insights System (Inference) Intel® Geti™ (Training) Support through the entire ML Ops workflow Outcomes/ Report Maintenance and Support Integration Tools easily connect to existing systems Deployed Model Model Monitoring Integration Tools designed for factory experts, not data scientists User Interface designed for factory operator to make informed decisions Validated Cameras of your choice Model Training & Tuning Model Validation 18
- 19. Conclusion 19 • There is a shift in User Persona of target audience for the Industrial AI solutions • From Developer, Architect, Data Scientist to SME, Operator, IT/OT Managers • Factory wants to be independent. • Less reliance on IT, data scientists, and Systems Integrator. • The key buyer or Persona is the Business Unit lead in an organization • With recommendations from the IT, AI team and other technical buyers (security, ML/Ops, etc.) • Factory Lead Engineer is a key go/no-go decision maker • Differentiating factors like low – code functionality of Intel® Geti™ and Intel® Edge Insights System along with multi-modal analytics, ingress/egress extensibility, ML/Ops flow, and ability to connect to controls and factory analytics will enable adoption and deployment of AI solutions in factories.
- 20. Sign up for receiving the latest updates and news from the Intel’s Edge Platform CTA Intel® Tiber™ Edge Platform Product Links Intel® Tiber™ Edge Platform Product Site Related Products Intel® Distribution of OpenVINO™ Toolkit The Intel® Geti™ Platform - Intel's Computer Vision AI Platform Development Tools (intel.com) Intel® Edge Insights System Intel® Tiber™ Edge Platform IDZ Website Resources 20
- 21. 21 Thank You