K
Kathleen Martin
Guest
Overview
Manufacturing isn’t what it used to be. Increasingly, manufacturers are leveraging industrial internet of things (IIoT) technology to drive production efficiencies and improve quality control. One of the most common IIoT use cases is industrial monitoring, which employs data capture, analytics and artificial intelligence (AI) to improve the management and operations of production equipment, lower power consumption, and reduce costs wherever products are made, packed and shipped.
Khali Henderson, senior partner at BuzzTheory and vice chair of CompTIA’s Emerging Technology Community, and Jonathan Weiss, principal specialist at AWS for industrial and member of CompTIA’s IoT Advisory Council, discussed how manufacturers are successfully implementing IIoT-based industrial monitoring solutions in this episode of CompTIA’s From Promise to Profit series.
Challenge
The drive for improvement in manufacturing never stops: Increase production efficiency; reduce power consumption; ensure quality assurance. That’s on top of getting the basics right—keeping equipment in top running condition and meeting production quotas. Metrics such as OTIF (shipping on time and in full) and OEE (overall equipment effectiveness) are tracked constantly. Traditionally, plant operators have managed these tasks with laborious manual processes.
“Folks were running around with stopwatches and clipboards with pen and paper trying to calculate on the fly: Am I going to meet today's plan? Right of goods? And more importantly: How are my machines performing?” said Weiss. Errors were inevitable. “You don't really want to do that stuff with pen and paper, especially in a stressful environment when you're running around trying to make sure that all of these things are working correctly.”
Solution
There is a better way. Industrial monitoring provides continuous streams of data collected by sensors on production equipment as well as for power consumption. Sensors transmit machine health and performance data to improve maintenance processes. The data is analyzed in real time, enabling prompt corrective action when needed.
Predictive maintenance is a common outcome of industrial monitoring, said Weiss. “What predictive maintenance means is, basically, can I fix problems before they cause an outage or actually stop my production process? Can I repair a machine before it needs repair vs. the machine actually breaking?” For instance, if a machine starts to pull an irregular amount of power, it may be about to fail and halt production. Monitoring can prevent the interruption and keep operations running smoothly.
Outcome
IIoT and industrial monitoring help manufacturers achieve important goals. Insights from captured data can help them reduce energy consumption. Predictive maintenance optimizes equipment uses, improves lifecycles and lower maintenance costs. And the potential for error associated with manual processes is minimized.
Continue reading: https://connect.comptia.org/content/use-cases/how-to-leverage-industrial-iot-to-improve-manufacturing-processes
Manufacturing isn’t what it used to be. Increasingly, manufacturers are leveraging industrial internet of things (IIoT) technology to drive production efficiencies and improve quality control. One of the most common IIoT use cases is industrial monitoring, which employs data capture, analytics and artificial intelligence (AI) to improve the management and operations of production equipment, lower power consumption, and reduce costs wherever products are made, packed and shipped.
Khali Henderson, senior partner at BuzzTheory and vice chair of CompTIA’s Emerging Technology Community, and Jonathan Weiss, principal specialist at AWS for industrial and member of CompTIA’s IoT Advisory Council, discussed how manufacturers are successfully implementing IIoT-based industrial monitoring solutions in this episode of CompTIA’s From Promise to Profit series.
Challenge
The drive for improvement in manufacturing never stops: Increase production efficiency; reduce power consumption; ensure quality assurance. That’s on top of getting the basics right—keeping equipment in top running condition and meeting production quotas. Metrics such as OTIF (shipping on time and in full) and OEE (overall equipment effectiveness) are tracked constantly. Traditionally, plant operators have managed these tasks with laborious manual processes.
“Folks were running around with stopwatches and clipboards with pen and paper trying to calculate on the fly: Am I going to meet today's plan? Right of goods? And more importantly: How are my machines performing?” said Weiss. Errors were inevitable. “You don't really want to do that stuff with pen and paper, especially in a stressful environment when you're running around trying to make sure that all of these things are working correctly.”
Solution
There is a better way. Industrial monitoring provides continuous streams of data collected by sensors on production equipment as well as for power consumption. Sensors transmit machine health and performance data to improve maintenance processes. The data is analyzed in real time, enabling prompt corrective action when needed.
Predictive maintenance is a common outcome of industrial monitoring, said Weiss. “What predictive maintenance means is, basically, can I fix problems before they cause an outage or actually stop my production process? Can I repair a machine before it needs repair vs. the machine actually breaking?” For instance, if a machine starts to pull an irregular amount of power, it may be about to fail and halt production. Monitoring can prevent the interruption and keep operations running smoothly.
Outcome
IIoT and industrial monitoring help manufacturers achieve important goals. Insights from captured data can help them reduce energy consumption. Predictive maintenance optimizes equipment uses, improves lifecycles and lower maintenance costs. And the potential for error associated with manual processes is minimized.
Continue reading: https://connect.comptia.org/content/use-cases/how-to-leverage-industrial-iot-to-improve-manufacturing-processes
