How Predictive Maintenance Can Boost a Business's Bottom Line

Predictive maintenance predicts machine failures before they occur by means of infrared thermal imaging, vibration and oil analysis, as well as integrated sensors and monitoring modules.

In manufacturing, preventive maintenance is already popular and can be used in conjunction with mobile workforce management software. It is triggered by time, events, or meter readings. The age of a piece of equipment in addition to manufacturer service recommendations is also taken into consideration for preventive maintenance. Another way to say preventive maintenance is planned scheduled maintenance. However, this time-based maintenance approach may not accurately reflect the usage of a piece of equipment and could lead to unnecessary maintenance fixes, regardless of the actual state of the equipment or parts.

With the increased networking of machines and manufacturing facilities in the Internet of Things and Industry 4.0, predictive maintenance is increasingly becoming an essential component in keeping pace in the global marketplace. Companies are figuring out ways to marry mathematical calculations, integrated sensors and computer monitoring to determine when machine components need to be changed based on the actual condition of the equipment. Predictive maintenance is used to predict machine failures before they occur, and also gives companies enough time to schedule a future service appointment in advance.

“Predictive maintenance is a milestone in the history of machine design,’’ says Richard Habering, head of the newly-created smart plastics divisions at Germany-based Igus. Among other things, the company manufactures energy chains and cables used in CNC machining centers, milling and grinding machines. The motion plastics company runs its North American operations out of Providence, Rhode Island. “Intelligent maintenance and intelligent production give value to a product. A product is only as good as the process behind its production.”

The process behind a product’s production involves machine tools, which are exposed to rough operating conditions. Hot chips significantly compromise the service life of cables and hoses. In the medium term, this leads to machine failures and, as a result, expensive downtimes.

The Importance of Predictive Maintenance

Many suppliers to the machine tool industry are now integrating sensors into their products and using monitoring modules to gather information to help tell them when parts need replacement. The sensors measure wear during the operation and alert the user early enough to plan repair or replacement. Recommendations are based on sensor and long-term testing data. The data can also be sent to a PC, tablet or smart phone to help business leaders stay aware of developments.

Most predictive maintenance procedures can be used while machines are operational, which minimizes workplace disruption. Predictive maintenance is also more reliable and cost efficient than preventive maintenance, which usually occurs when plants are in operation, thereby reducing efficiency. Furthermore, with preventive maintenance, sometimes parts are replaced based on historical records or OEM recommendations, which can lead to unnecessary part replacement.

Common testing technologies that can be monitored online include vibration, power, temperature, corrosion, current and lubrication. Extensive testing and algorithms also factor into predictive maintenance calculations.

Among the key advantages for predictive maintenance is the ability to recognize how external factors impact factory parts. Dirt, grease, temperature as well as the application can all impact how quickly a component will deteriorate.

Smart Plastics Measure Wear During Operation

Igus energy chains used in machine tools now inhibit so-called “smart plastics,” where various intelligent sensors and monitoring modules measure wear during operation and trigger in-house maintenance. According to Habering, the concept is a combination of mathematical calculation and experience, which are updated with real-time sensors. “For example, if the first, experienced-based calculation after setup shows 1,000 days until the next recommended maintenance, and the sensors show wear much faster than expected, only the suggested days need to be updated or re-calculated,’’ Habering says. “Together with the sensor data, the system will realize it and the next time, the first live-time prediction will be calculated more carefully.”

As a newer technology, there will be some business and manufacturing leaders who will remain skeptical about the benefits of predictive maintenance. Then again, Habering notes, progress and innovation have always faced doubters and critics. “One hundred years ago, people thought that driving faster than 30 miles per hour in steam trains will cause brain disease,’’ Habering says. “It’s a question of believing. All of the companies with predictive maintenance technologies need to convince people that it really does work.”

Data analytics and digitalization drive the advancement of predictive maintenance. As more programs evolve, with better feedback and more sophisticated analysis, they will continue to be a primary source for gathering information to timely part replacement. It is also essential, however, to rely on testing. Igus runs a large test lab with more than 40,300 square feet. It collects data on 41,000 energy chain systems annually at 180 test stations, monitoring such things as the impact of climate, noise and even being outdoors.

With all of its advantages, predictive maintenance in Industry 4.0 appears to be an idea that will become standard in the years ahead. Manufacturers who fail to invest in predictive maintenance will eventually fall behind their competition in productivity and sales. “Costs in sales, marketing, quality control, certifications and any after-sale costs add to the cost of a product,’’ Habering says. “If you are able to make reliable prognoses on the state and maintenance needs of a product, you are a step ahead of the competitor.”