Predictive maintenance employs digital sensors, artificial intelligence (AI) technologies, and intelligent data analysis tools to determine when equipment maintenance should be conducted. The ability to predict problems before they impact production is a gamechanger as it prevents costly, unexpected downtime on the shop floor.
Have you ever wished you had the ability to predict a problem before it happens when it can still be prevented? In manufacturing, where even small problems can lead to costly shutdowns and delays, the ability to predict problems on the shop floor can be critical to business success. That is why predictive maintenance is one of the fastest-growing applications of artificial intelligence technology in manufacturing today. In this article, we look at why it is gaining so much traction, its key benefits to manufacturers and machine builders, and what it means for connectivity across the manufacturing floor.
Why is predictive maintenance gaining traction?
Predictive maintenance employs digital sensors, artificial intelligence (AI) technologies, and intelligent data analysis tools to determine when equipment maintenance should be conducted. The ability to predict problems before they impact production is a gamechanger as it prevents costly, unexpected downtime on the shop floor. Instead, maintenance can be scheduled at convenient times, such as at nights or weekends or at the beginning or end of shifts. Proactive maintenance can also allow machines to continue working while they are being checked or repaired, increasing efficiency and throughput.
Knowing when maintenance is needed, eliminates the need for regularly scheduled maintenance intervals so that no resources are wasted on machines that do not actually need to be serviced at that time. This type of high-precision maintenance can often be done remotely, a capability that became critical during the height of the global pandemic.
What are the barriers that prevent implementation?
The benefits are clear. So, why have not predictive maintenance capabilities been implemented in every machine, on every shop floor?
In many cases, connectivity challenges are the main barrier to implementation. That is because predictive maintenance is only possible if sensors on the machines have reliable, continuous, industrial-standard connectivity to stream real-time data.
While wired connectivity can meet the requirements for scalability and reliability, for many types of equipment and many production floors, wiring is simply impossible. Dynamic machines with rotating parts, such as tooling machines, cannot be wired efficiently. Likewise, it is impossible to connect cables to sensors on transport tracks.
Even when it is possible to wire a machine, it is not always practical. Retrofitting machines with hundreds of wired sensors and additional cabling in complex and crowded production environments is extremely cumbersome and expensive. The challenges are amplified wherever there are rotary tables, carousels, robotic arms, and other complex moving parts. And, in the case of machines deployed in sensitive industries such as food and beverage, hygiene requirements add even more complexity. As cables need to be sterilized regularly, wired sensors require special, expensive cables, something that is neither feasible nor cost-effective.
All that points to wireless connectivity. But traditional wireless protocols, such as Wi-Fi and Bluetooth, are not suitable for the shop floor. Not designed for industrial applications, they cannot perform reliably in harsh industrial conditions and do not meet industry standards for scalability and immunity to noise and interference. Traditional wireless protocols are especially unsuited to predictive maintenance because they cannot provide a sufficiently consistent data stream, and they are prone to errors that may distort the machine learning models.
IO-Link Wireless communication is opening new options
IO-Link Wireless, an official wireless standard designed specifically for industrial automation, offers a much-needed alternative to wired and traditional wireless connectivity. Easy and cost-effective to implement, it is ideal for predictive maintenance applications and can be embedded in, or integrated with, any device. IO-Link Wireless provides reliable, consistent, industrial-standard connectivity, even in harsh and noisy industrial environments and in machines with moving parts. It can be implemented anywhere it is needed, without limitations, and can scale to numerous units in a machine or work cell area.
With full wireless connectivity via IO-Link Wireless, machine sensors can capture and transmit data to the cloud or to on-premises systems in real-time. Manufacturers can receive automated alerts about pending problems and AI machine learning tools can be used to diagnose problems and recommend a course of action, prioritizing tasks needed to maintain machine and asset health.
IO-Link Wireless is ideal for deployment in dynamic machines, such as those with track systems, to monitor vibrations and system health of the mover components. For example, it can provide the connectivity needed to monitor the bearings on the mover, something that would never have been possible with wired or traditional wireless solutions. It also makes it much easier to retrofit existing machines with sensors that enable predictive maintenance capabilities without impacting the machine performance.
The new-look of predictive maintenance
CoreTigo is leading the way in leveraging IO-Link Wireless for predictive maintenance solutions and is already working with leading machine builders on varied implementations. For example, using CoreTigo solutions, the clamping technology specialist Röhm was able to create a smart clamping mechanism that allows clamping force to be measured in real-time during machining. The solution contributes to predictive maintenance as changes in the clamping force can indicate, among other functionalities, wear-and-tear in machine parts.
With CoreTigo’s solutions, manufacturers can now identify problems before they impact productivity, precisely pinpoint problem parts, and then schedule maintenance for times that are convenient for the factory, avoiding the disruption and costs of unexpected downtime. The ability to perform precise maintenance actions increases OEE (overall equipment effectiveness) and enables higher equipment availability, quality, and performance.
Now, with CoreTigo’s IO-Link Wireless solutions, predictive maintenance is possible on every type of machine, anywhere in the factory.
Daniel is a wireless connectivity system professional with over 15 years of repeated success leading sizable, cross-functional teams in the development of product roadmaps, execution to production, and support of customers through production phases. Most recently, he led wireless programs at Apple, driving the definition of new technologies across different product lines. Daniel brings global experience leading multiple system groups, conceptualizing and managing product training & support. In prior positions, he managed system applications, chip design, and system architecture teams at companies such as Texas Instruments, Atmel, and Microchip.
Daniel holds a Bachelor’s Degree (B.Sc) in Electrical Engineering and a Master’s Degree of Business Administration (MBA) from the Hebrew University in Jerusalem.