Quality control: a transformational opportunity with IoT

By | 2 minute read | November 22, 2016

leadspace image of a quality inspection

The application of statistical process control (SPC) methods over recent decades has greatly improved quality processes globally. However, headline news in 2016 clearly indicates that quality remains a costly problem – Samsung Galaxy Note7Takata Airbags, and dozens of recalls listed by the Consumer Safety Products Commission.

Grace Duffy’s  The ASQ Quality Improvement Pocket Guide: Basic History, Concepts, Tools, and Relationships estimates that “Many organizations will have true quality-related costs as high as 15 to 20 percent of sales revenue, some going as high as 40 percent of total operations. A general rule of thumb is that costs of poor quality in a thriving company will be about 10 to 15 percent of operations.” There is clearly room for improvement.  IoT offers opportunity to make significant gains in this space.

Earlier and more definitive detection

SPC methods are well-established standard tools for quality control.  However there are limitations with the SPC approach – false positives, slow detection of small and moderate changes, and trends not readily visible. IBM research has developed a set of algorithms – Quality Early Warning System (QEWS) – that detect and prioritize problems and parametric shifts earlier and more definitively than can be done using traditional techniques of statistical process control. These algorithms are used by IBM throughout its own supply chain and manufacturing processes to meet established quality standards. The result: earlier identification of nascent quality problems, increased production yield, and reduction of problems that lead to service and warranty costs. IBM has incorporated the QEWS capability into its Prescriptive Quality on Cloud offering to help manufacturers address quality control throughout the supply chain.

At the beginning of the manufacturing process QEWS analytics can be employed to measure or test components, materials and supplies to insure conformance with contracted specifications. Ideally, this inspection is performed by the supplier to insure that substandard parts never enter the supply chain, employing steps and techniques described below.

Pinpointing issues and prescribing remedial actions

In the factory and critical manufacturing steps, QEWS analytics can be applied to monitor equipment operational parameters such as temperature, pressure, speed, air-flow, and humidity in real-time to identify when parameters are trending beyond prescribed calibrations that could result in substandard products or components. At the earliest indications of deviation from desired calibrations an alert is issued to pinpoint the source and time the problem was first identified, and prescribe specific remedial actions with the goal of minimizing production of substandard components or products.

QEWS analytics can be employed to monitor the results of critical manufacturing steps, by measuring or testing completed components or products to insure they conform to specifications. In the event that measurements or tests on completed components drift from the desired specifications, perhaps because of differences in material quality, changes in equipment performance, or even environmental conditions, here too an alert is issued to pinpoint the problem and time it was first identified, with the goal of maintaining manufacturing line quality.

Why improve quality?

Why consider investigating the potential benefits of IBM’s approach?  If you face any of these challenges due to quality issues:

  • experiencing increasing costs associated with maintaining standards
  • would like to improve yield, reduce scrap and rework
  • not meeting production schedules
  • dissatisfied with current ability to monitor and identify problems
  • would like to obtain earlier, more definitive warnings
  • plan on improving monitoring practices as a result of implementing IoT technologies.

Please consider learning more about IBM Prescriptive Quality on Cloud offering and the benefits of IBM’s Quality Early Warning System via this demo or investigate the opportunity to quality for a free 30-day trial.