Transform troubleshooting in manufacturing with AWS gen AI services (IOT204)

Transforming Troubleshooting and Manufacturing with AWS Generative AI Services

Introduction

  • The presentation is a collaboration between Cognizant and Trane Technologies, a global climate innovator and HVAC company.
  • Cognizant is a large organization with 350,000+ employees that aims to engineer modern businesses and solve problems for manufacturers.
  • Trane Technologies is headquartered in Dublin, Ireland, with a global workforce of 45,000 employees and 45 manufacturing facilities worldwide. Their purpose is to "challenge possible to innovate for a sustainable future".

Manufacturing Challenges

  • The presenters discuss common challenges in manufacturing, including:
    • Skills gap: Dealing with a wide range of equipment, from old to new, and the difficulty in finding the right experts to troubleshoot issues.
    • Pressure to reduce downtime: Downtime can be very costly, with a manufacturing plant losing up to $22,000 per minute.
    • IT-OT collaboration: Bridging the gap between IT and operational technology (OT) teams, as they often have different processes and standards.

Collaboration and Innovation Approach

  • Cognizant has set up a Manufacturing Innovation Center in Chicago, where they work with clients like Trane Technologies to solve problems using technologies like generative AI, advanced analytics, and more.
  • Trane Technologies has also set up their own IT and OT labs to incubate and test new technologies before deploying them in their production environments.

Generative AI in Manufacturing

  • Cognizant has been working with AWS on a suite of generative AI solutions for manufacturing, including:
    • Information assistance: Using generative AI for summarization, code management, and digital twin data contextualization.
    • Insights and workflow transformation: Developing smart digital dashboards, advisor approaches, and predictive analytics.
    • Expert agents: Building automated guidance and problem-solving agents for various workflows, such as troubleshooting, IT outages, and cybersecurity incidents.

Architectural Approach

  • The presenters showcase a high-level architecture that integrates data from various sources (e.g., PLCs, IoT sensors) into Ignition Edge and Aprisa (MES), which then feeds into AWS for generative AI processing.
  • This architecture allows for flexibility in sensor choices and the ability to plug in different AI models as needed.
  • The "Factory Whisperer" is a generative AI agent built on top of this architecture to provide intelligent troubleshooting assistance, leveraging data, manuals, and standard operating procedures.

Demonstration and Next Steps

  • The presenters provide a live demonstration of the Factory Whisperer integrated into the Ignition platform, showcasing its ability to answer questions and provide troubleshooting guidance.
  • They emphasize the importance of starting somewhere with generative AI, even if the data foundations are not fully mature, and gradually evolving the solution.
  • The next steps include exploring further use cases, such as video analytics, cobot/robot integration, and moving towards an autonomous factory vision, leveraging generative AI and other advanced technologies.

Key Takeaways

  • Generative AI can be a powerful tool for addressing manufacturing challenges, but it requires a well-designed architecture and approach to be scalable and effective.
  • Collaboration between IT and OT teams, as well as between a client and a technology provider, is crucial for successful implementation.
  • Start small, test in a sandbox environment, and gradually scale the solution, rather than waiting for the perfect data foundations to be in place.
  • Integrate generative AI capabilities into existing manufacturing platforms and tools to avoid introducing new applications that operators need to learn.
  • Continuously explore new technologies and be ready to adapt and evolve the solution as the landscape changes.

Your Digital Journey deserves a great story.

Build one with us.

Cookies Icon

These cookies are used to collect information about how you interact with this website and allow us to remember you. We use this information to improve and customize your browsing experience, as well as for analytics.

If you decline, your information won’t be tracked when you visit this website. A single cookie will be used in your browser to remember your preference.

Talk to us