From reactive to proactive quality management with IoT
In 9 ways the IoT is Redefining Manufacturing, Brian Buntz succinctly enumerates examples of companies who are implementing or benefiting from IoT capabilities. Each example shows how IoT is reshaping or redefining industry practices. One example of particular interest is Proactive Quality Assurance, enabled by placement of sensing and measuring devices in critical areas throughout the supply chain and production process.
The promise of significant cost reduction
With IoT, the ability to monitor and analyze process and product quality at critical points in the supply chain and production processes, and detect when sub-standard materials are introduced or product attributes deviate from specifications promises significant cost reductions.
Consider examples where improved monitoring of supplies, manufacturing processes, and even products in usage by customers can contribute to improved product and process quality. First, IBM has long been a practitioner of proactive quality management, developing the Quality Early Warning System (QEWS) algorithms for earlier, more definitive detection of problems throughout its own supply chain. The QEWS algorithms have been incorporated into the IBM Prescriptive Quality on Cloud offering to help manufacturers detect problems in supplier materials as well as in production processes.
The added assurance of detecting quality problems at source
Through instrumentation and monitoring of production equipment manufacturers can detect when equipment calibration is drifting beyond the required settings which could result in assemblies, components or products that do not meet specifications. For example, a gradual change in actuator speed could result in component misalignment. Concurrently, products can be tested or measured after key manufacturing steps to determine if attributes are within specifications. The ability to monitor both equipment settings and results of a completed manufacturing step gives manufacturers added assurance of detecting quality problems at the source.
Beyond monitoring, many manufactures are beginning to employ robotics as a means to improve process quality. The ability for robots to execute processes more accurately and efficiently and apply cognitive to continually learn to improve, or automatically adapt to variations in manufacturing requirements, will significantly enhance quality and throughput. IBM’s new report How the Emergence of Adaptive Robotics and IoT Transforms Businesses cites the role of robots in improving quality control and customization, and provides numerous use-case examples of the impact of robotics across industries.
Beyond the factory, with an increasing number of products imbued with sensors, intelligence and connectivity, the ability to monitor usage “in the field” can provide accurate and detailed perspective regarding product performance, potentially alerting customer service, warranty management, and even product design to shortcomings in product performance or unusual or unanticipated usage. Early detection of impending trends enables companies to proactively address and remedy problems before they become unmanageable and potentially ruin corporate reputation.
An earlier, more definitive detection of problems
A key benefit of the QEWS algorithm employed in IBM Prescriptive Quality on Cloud is the earlier, more definitive detection of problems, often using fewer data points and avoiding false alarms associated with traditional statistical process control methods. Additionally, considering the volume of data generated by applying IoT capabilities to process and product quality, the solution prioritizes alerts to enable lines of business to address those problems needing immediate attention while making it easy to quickly evaluate status of all activities being monitored.
With capabilities made available via the IoT to capture and analyze data throughout the supply chain and manufacturing processes, there’s never been a better time to adopt a proactive quality management strategy.