Ingram Micro CoE - IBM watsonx User Group

Ingram Micro CoE - IBM watsonx User Group

Welcome to the Ingram Micro CoE - IBM watsonx User Group! 🚀 We're a passionate community of IBM partners, customers, and enthusiasts who are dedicated to promoting and leveraging the power of IBM watsonx. Our mission is to connect, collaborate, and share knowledge about this cutting-edge technology.

What We Do:

Connect: We bring together like-minded individuals who share a common interest in IBM watsonx. Whether you're a seasoned expert or just getting started, our group provides a supportive environment for networking and building meaningful relationships.

Learn: Our user group is all about learning! We organize workshops, webinars, and knowledge- sharing sessions where you can gain insights from everyday users like yourself. Discover best practices, tips, and tricks to expertly use IBM watsonx. 

Promote: As advocates for IBM watsonx, we actively promote its benefits to partners, customers, and the wider community. Whether it's through case studies, success stories, or live demos, we're committed to showcasing the value of this powerful platform. 

Join Us: Ready to dive into the world of IBM watsonx? Join our user group today! Connect with fellow enthusiasts, stay updated on the latest developments, and be part of a community that's shaping the future of AI and data-driven solutions.

 View Only
Back to discussions
Expand all | Collapse all

Use case: How watsonx can help a manufacturing company to achieve better quality of their porducts?

  • 1.  Use case: How watsonx can help a manufacturing company to achieve better quality of their porducts?

    Posted yesterday

    One more thread for our "use case" series! Once again, our team helped Ingram Micro partners to win. If you think that we can help you too, feel free to reach out!

    Client Overview

    The client is a global manufacturer specializing in fluid handling products. Their operations span multiple industries, making quality control a critical component of their manufacturing process. This case study focuses on how they leveraged AI to enhance their testing procedures and reduce inefficiencies.

    Background & Challenges

    The client faced persistent issues with low First Pass Test Yield (FPTY%) and high rework costs. Operators often relied on experience and guesswork to resolve test failures, leading to inconsistent results and wasted time. The lack of standardized feedback and incomplete logging further complicated troubleshooting and process improvement efforts.

    Objectives

    The project aimed to use AI to:

    • Provide real-time feedback to operators after test failures
    • Alert engineers to emerging trends and potential issues
    • Recommend adjustments to test parameters
    • Offer insights into process capability and tolerance optimization

    These goals were designed to create a more intelligent, responsive, and efficient testing environment.

    AI-Driven Solution

    The Proof of Concept (PoC) targeted a test bench with significant quality issues. AI was used to:

    • Analyze historical test data and operator actions
    • Correlate failure reasons with successful fixes
    • Detect trends indicating equipment degradation
    • Link upstream sub-assembly data to final test outcomes

    This approach enabled a data-driven feedback loop that continuously improved testing accuracy and efficiency.

    Implementation

    The AI solution was integrated into the client's existing architecture. Key components included:

    • A maintainable data pipeline for test logs and operator inputs
    • Algorithms for correlation and trend analysis
    • Interfaces for delivering real-time suggestions and alerts

    This setup ensured that both operators and engineers could act on insights without disrupting workflows.

    Results

    The implementation led to several impactful outcomes:

    1. Environment Assessment: Mapped inefficiencies and gaps in current workflows.
    2. AI Root Cause Suggestions: Reduced retests by 50% through guided operator actions.
    3. Test Design Optimization: Identified overly strict parameters, reducing false failures.
    4. Equipment Monitoring: Enabled proactive maintenance and improved FPTY%.
    5. Process Optimization: Highlighted upstream issues, reducing rework and improving quality.

    Quantitative Outcomes

    • +20% increase in FPTY
    • -50% reduction in retests
    • 284% ROI over 5 years

    These metrics demonstrate the tangible value of AI in quality assurance.

    Strategic Impact

    The project delivered long-term benefits:

    • Efficiency Gains: Less time spent on rework and diagnostics
    • Cost Savings: Lower scrap and rework expenses
    • Smarter Decisions: Actionable insights from complex data
    • Proactive Quality Control: Early detection of issues
    • Enhanced Support: Real-time guidance for operators and engineers
    • Optimized Testing: Better criteria and process alignment



    ------------------------------
    Dane Hinić
    ------------------------------


Related Content