Manufacturers are seeking ways to increase machine uptime and overall equipment effectiveness (OEE) performance while original equipment manufacturers (OEMs) are also trying to realize sustainable revenue without taking away the need for service contracts. Here we investigate modern technology that can enable predictive maintenance and offer the convergence between OEM and end user needs with machine as a service (MaaS) business models.

If there is anything that the COVID-19 global pandemic has brought to light, it is the need for manufacturers to adopt strategies in their processes that will ensure profitability despite the economic situations at hand. Part of this realization is the need to maintain high productivity and machine availability. Although this strategy is not a new concept, it is not surprising to witness many manufacturing facilities are still behind when it comes to implementing a robust predictive maintenance program for their equipment. Many manufacturers rely on preventive maintenance or, even worse – reactive maintenance programs to keep their machines in production. This strategy could rely on in-house technical staff or likely the original equipment manufacturer (OEM) through a service contract.

Service contracts are no longer sustainable revenue sources.

OEMs often rely on service contracts to sustain revenue between equipment sales. These service contracts could be short-term, emergency contracts or it could be in the form of regularly scheduled maintenance and services. Most OEMs would prefer the latter, however the key to either of these scenarios is that the OEMs revenue is dependent on the machine needing service or repairs. This is often unpredictable or sourced via in-house technical experts and staff. So, that begs the question – How can OEMs realize a strategy that enables continuous revenue, while also addressing their customer’s requirements to keep the machine running without failures?

The answer to this revolves around “predictive maintenance.” In almost every scenario of a robust predictive maintenance strategy, this will involve industrial automation equipment such as sensors, dedicated predictive maintenance software and/or hardware that can perform condition monitoring of the machine. This industrial hardware measures the performance of the machine by collecting measured data from the sensors such as mechanical vibration, temperature and other process data. The condition monitoring software then analyzes the collected data to detect anomalies within the machine. These anomalies lead to alerts to the operator that a mechanical or electrical failure is imminent.

Condition Monitoring Hardware, Cloud and Edge Technology Enable Predictive Maintenance

While the concept of condition monitoring is nothing new, modern predictive maintenance solutions can be found and adopted today. Some equipment manufacturers have developed wireless sensors to perform the data collection and limited analysis, while others have focused on software and hardware developments to pave the way for predictive maintenance. Whatever the approach, you will be sure to find a solution that enabled predictive maintenance while leveraging modern technology through industry 4.0 trends.

*SIPLUS CMS Condition Monitoring Systems create the prerequisites for the early detection of damage to machines and plants and the targeted planning of maintenance work – for a minimum of downtimes.*

Siemens’ SIPLUS Condition Monitoring System (SIPLUS CMS) enables predictive maintenance by monitoring mechanical vibration data from field sensors and simultaneously performing analysis via the embedded condition monitoring software. If an anomaly is detected, the operators can be alerted of the imminent mechanical or electrical damage via the integrated control system or via other readily-available messaging systems. Users can access recorded data in real-time, ad hoc or periodically via the integrated web-based interface reducing the need for additional analysis software and licenses. SIPLUS CMS also seamlessly integrates with MindSphere, if further analysis should be performed via cloud.

MindSphere is the cloud-based, open operating system from Siemens that lets you connect, collect and get context from the Internet of Things (IoT) data. Companies can ingest and visualize immediate, real-time data and analytic results in one centralized location. In addition, users can access the MindSphere Store to find powerful industrial applications that enable visibility into product value chains, which can provide them with confidence they are making optimal business decisions. However, performing continuous monitoring of the condition of machines is often hard to accomplish with solely a cloud solution: Comprehensive monitoring of all installed machines globally creates massive amounts of data that is difficult to manage and expensive to process. Not to mention there is latency between data acquisition cycles – latency that cannot be acceptable with high-frequency vibrations. This is where advancements in industrial edge technology can help ease implementation and enable predictive maintenance on a global scale.

Advancements in industrial edge technology enable predictive maintenance by realizing the benefits of cloud computing at a shop floor level.

Future-proof processing of machine data directly at the machine with Edge Computing

Advancements in industrial edge technology enable predictive maintenance by realizing the benefits of cloud computing at a shop floor level. Data acquisition and processing is done directly and securely at the machine with no latency using your own software and a central system for administration, deployment and updates. The optimized data points can then be transferred more quickly to the cloud where, for example, you have access to more computing power and larger storage capacities for long-term archiving. Siemens also has done a great job of providing a solution for this with their Industrial Edge solutions.

Machine as a Service (MaaS) – the convergence point between OEMs and end users

So, going back to the original conflict: End users need their machines to be at optimum productivity and availability to realize profitability, while OEMs need machines to fail or be serviced to realize maximum profitability. Despite what you might think, these two conflicting strategies have a point of convergence when adopting modern predictive maintenance technology.

This point of convergence is realized in the form of a pricing model called “Machine as a service (MaaS). This pricing model adjusts pricing strictly on machine performance benchmarks rather than a fixed subscription or service contract model.

As an example, let’s assume I am an OEM focused on various packaging machines. Rather than me selling you a palletizer traditionally via an agreed upon price, I retain ownership of the machine and instead charge a price based on agreed upon KPIs such as the number of cases palletized, erected or sealed over the life of the machine. At this point, it is within my best interest as the equipment manufacturer to maximize the palletizer’s throughput and uptime in order to realize the maximum revenue. I am no longer waiting on service contracts to repair or replace failed components or subscriptions that can be cancelled by the user at any point. For me to focus on uptime and production for my complete install base, I must implement robust, scalable predictive maintenance technology into my design and business strategy.

Looking ahead – taking MaaS and predictive maintenance to the next level

There is no doubt that more OEMs will start to realize this point of convergence between end users interest and OEM service models. Once you have implemented a robust predictive maintenance program that enables MaaS, it is important to consider the next step in optimizing performance with prescriptive maintenance. By this point you can gain insights into commonly failed components and make informed design decisions into future models. Also, by leveraging new machine learning algorithms and artificial intelligence (AI) you no longer focus just on threshold limit deviations and root-cause analysis, but the end-customer can also be given remedial actions to take based on financial and operational ramifications. The key here is to always look for ways to optimize and improve your predictive maintenance and MaaS offering.

Don’t find yourself on the tail end of innovation. To find out more on how Siemens technology that can enable predictive maintenance, check out the links below: