Discover what the world is thinking. Join us at Think 2018 | March 19–22 | Las Vegas
Get $500 USD off registration with any purchase in IBM Marketplace

Feature spotlights

QEWSL algorithms developed and used by IBM supply chain

IBM Prescriptive Warranty on Cloud uses sophisticated analytic algorithms - Quality Early Warning System for Lifetime data (QEWSL) developed by IBM research and used throughout IBM’s supply chain - to identify instances of accelerated product wear or replacement rates . Algorithms are sensitive to subtle changes in data values. For a given level of statistical confidence, it typically alerts with fewer data points than traditional SPC methods, resulting in earlier identification of problems.

Easily organize warranty analyses

Designed to make it easy for lines of business associated with warranty management to upload data, analyze it, organize warranty analyses per product or individual warranty program, and share warranty analyses.

Wear-out analysis

The wear out analysis looks for unacceptable levels of wear out and alerts when it finds evidence that product failures are not random but are indicative of wear-out. Products in use for a longer time typically fail more often than products in use for a shorter time. Because wear out can have serious consequences, the model alerts when it detects evidence of wear out regardless of how many product units indicate unusual wear.

Replacement rate analysis

The replacement rate analysis looks for unacceptable levels of replacements and alerts when a product's random failure rate exceeds a computed threshold. The threshold can reflect product reliability goals, such as a threshold stating that product population in the field must not exceed a specified failure rate or financial liability goals.

How customers use it

  • Identify truly significant trends

    Identify truly significant trends

    Problem

    Traditional SPC methods used to identify process quality problems can lead to false alarms and delayed identification of problems when sample sizes are small. They can also alert on abnormal patterns which may have no practical significance.

    Solution

    IBM Prescriptive Warranty on Cloud is sensitive to subtle changes in data values, such as shifts that are small in magnitude. For a given level of statistical confidence, it typically alerts with fewer data points than traditional SPC methods.

  • Identify sources of warranty issues

    Identify sources of warranty issues

    Problem

    Root cause of warranty problems can be difficult to identify. They can occur at any step throughout the supply chain or manufacturing cycle and be caused by human or mechanical error.

    Solution

    QEWSL algorithms can help accurately identify root cause of warranty claims based upon vintage, production date, manufacturing date, or sales date when product wear-out and replacement rates exceed pre-specified unacceptable levels.

Technical details

Software requirements

A workstation that runs one of the supported web browsers.

    Hardware requirements

    This solution is hosted in secure IBM Cloud data centers.

      You may also be interested in

      IBM IoT for Manufacturing drives intelligent assets, cognitive processes and smarter resources.

      IBM Prescriptive Quality on Cloud

      Identify process and product quality issues earlier

      Learn more

      IBM Visual Insights

      Identify defects via cognitive visual inspection to improve quality.

      Learn more

      IBM Plant Performance Analytics

      Predicts future failures in production line, prescribes remedies

      Learn more

      See how it works