Page 16 - EE Times Europe November 2021 final

16 EE|Times EUROPE

SMART FACTORY
How Preventive and Predictive Maintenance

Is Changing Production

By John Koon

nexpected outages, a frequent problem for most companies,
increase the cost and risk of doing business. Maintenance,
which is necessary to prevent such outages, comes in two
Utypes: reactive and preventive. Performed after an outage has
happened, reactive maintenance involves lower upfront costs and fewer
staff members. Reactive maintenance does not require planning. How-
ever, it makes budgeting, downtime, and overtime pay unpredictable.
Energy costs increase, and equipment lifespan shrinks.
The aim of preventive maintenance is to increase production effi-
ciency through regular maintenance of equipment and assets. Although
preventive maintenance
Although preventive involves higher upfront costs,
more staff members, and
maintenance involves more planning, it reduces
budgeting and downtime
higher upfront costs, unpredictability. In addi-

more staff members, tion, it reduces energy and
payroll costs while increasing
and more planning, equipment life expectancy. The modules can be integral to a battery-operated
it reduces budgeting According to a study by The infrastructure for monitoring buildings and tracking their
New Building Institute, reac-
and downtime tive maintenance can increase assets. (Source: Silicon Labs)
energy use by 30% to 60% and
unpredictability. decrease equipment lifespan.
In addition, a study by the highly reliable and interference-resistant in a variety of environments,
U.S. Department of Energy contributing to network integrity. Suitable for a broad range of appli-
Operations and Maintenance reports that preventive maintenance can cations, the modules can be used in smart manufacturing (Industry
result in energy savings of as much as 18%. Preventive maintenance 4.0), including smart HVAC controls, smart meters (submeters),
has broad applications in various sectors, including manufacturing, human-machine interface, access control, commercial lighting control,
hospitality services, fleet management, oil and gas, and property and asset-tracking tags.
management. Still, preventive maintenance interrupts normal equipment oper-
ation and requires budgeting for planning and execution. Although
SUCCESSFUL PREVENTIVE MAINTENANCE time-based preventive maintenance is typically more cost-effective
IN SMART MANUFACTURING than reactive maintenance, it can be less efficient than condition-based
Preventive maintenance can be time-based or condition-based. To strategies. Sometimes, preventive maintenance is unnecessary and
increase equipment life expectancy, reduce safety risks and energy wasteful, while at other times, warning signs during the intervals
consumption, and avoid extra costs, time-based maintenance follows between service sessions go unnoticed.
an established schedule — servicing a machine every quarter or doing
an oil change on a vehicle every 5,000 miles, for example. CONDITION-BASED PREDICTIVE MAINTENANCE
Preventive maintenance is essential in smart manufacturing. Some Condition-based preventive maintenance is more specific, efficient,
machines run 24 hours a day in three shifts. Examples include auto and informative than time-based preventive maintenance. The IoT
assembly robotics, metal part stamping, and automatic component has enabled condition-based maintenance to become predictive rather
placement. Therefore, the equipment on a factory floor, including than just preventive. IoT-based solutions enable the monitoring of an
engines, motors, fans, transformers, heat exchangers, gearboxes, drives, equipment’s use as well as its condition. By predicting when potential
pumps, valves, and circuit breakers, needs continuous monitoring. By failures will occur, maintenance can be scheduled preemptively, so
using a scalable sensor-based solution to monitor equipment, repairs take place only when necessary and downtime is minimized.
electrical, mechanical, vibrational, and thermal status information Predictive maintenance uses sensors that have been installed on
from numerous machines can be collected. equipment to capture parameters in real time. For example, obtaining
For example, Silicon Labs, in partnership with Wirepas, offers temperature, humidity, vibration, noise, magnetic field, and energy
battery-powered, scalable, and cost-effective IoT solutions that consumption data supports optimal scheduling decisions. Analyz-
connect and localize sensors, tags, and luminaires. Its EFR32BG21 ing the collected data can determine if the temperature, vibration,
(BG21) and EFR32BG22 (BG22) modules and SoCs make IoT prod- and energy consumption levels fluctuate within acceptable ranges.
ucts low-power, scalable, and secure. They solve large-scale preventive Unfavorable trends indicating potential problems can be spotted. In
maintenance and high-density asset-tracking needs. The modules addition, machine learning can be implemented in analytics to help
can be integral to a battery-operated infrastructure for monitor- detect abnormalities. Smart sensor nodes are also key enablers of pre-
ing buildings and tracking their assets. Moreover, the modules are dictive analysis when equipment needs to operate without downtime.

NOVEMBER 2021 | www.eetimes.eu