Manufacturing – Opportunities for Innovation
Figure 2: Quality Assurance in Manufacturing Process
Devices, embedded with sensors and inbuilt connectivity provisions, capture and transmit
operational and health data. These datasets could be about raw material properties (i.e., initial
moisture/stress levels), equipment health (i.e., vibration level, pressure leakages, torque,
pressure generated vs. power consumption, nozzle pressure, coolant spread), tool
alignment/sharpness and/or operating conditions (i.e., temperature, humidity, gas composition,
pressure fluctuation). These data elements impact the product quality and were not considered
earlier for quality assurance, thereby “empowering” quality engineers with valuable operational
quality insights. Leveraging predefined analytical models (i.e., abnormality detection, remote
fault diagnosis) will enable “intelligent” proactive quality monitoring which will lower costs by
reducing rework on the parts and controlling rejections. Further, this near real time data from
assembly lines spread across geographies helps dynamically update centralized rule repositories
to keep a precise and “automated” eye on quality parameters.
5.
CONCLUSIONS
The industrial marketplace has initiated investment in IIoT, resulting in significantly higher
productivity achieved through higher operational efficiencies. However, this is just the tip of
iceberg. With this momentum continuing, markets will witness highly matured operating models.
With minimal infrastructure investment, these models will result in harvesting significant
incremental value. The compelling value derived from the amalgamation of Empowerment,
Intelligence and Automation will increase industrial output through precisely addressing
objectives with better quality. At the same time, this union will reduce industrial inputs through
lower rework and rejection, infrastructure costs and depreciation rates.
- 56 -
June 2016