Servicing and maintaining machinery and equipment is a core element of a functional production system. Its impact in terms of cost and time must not be underestimated. To minimise maintenance costs in these times of global JiT (just-in-time) supply chains, and open up opportunities for new business models, companies are increasingly relying on predictive maintenance in the context of Industry 4.0, taking advantage of big data and SAP Predictive Asset Insights.
Predictive maintenance – 5 stages of connectivity
The basic technological prerequisite for implementation of predictive maintenance is a connected production system. Connected machines that communicate with each other and provide information that the system can analyse in an overall context are essential for the full benefits of predictive maintenance to be tapped, whether using SAP or other solutions. The extent of connectivity corresponds to one of various stages of development or system maturity:
All of the machines in the plant are autonomous and unconnected. Any data that is collected stays isolated. Potential synergies are untapped and maintenance is based on intuition and experience.
The machines are connected to each other but any operating data is barely used. Process data that could indicate an impending problem is not collected.
The system supplies machine data in real time. This provides information on the plant status, but does not warn of required maintenance.
A set of fixed rules allows the current machine status to be read along with the date and time of the next service based on information about operating hours, wear and tear, etc.
Fully data-driven maintenance
A fully integrated system not only informs the operators of upcoming servicing requirements but also takes the appropriate initial steps, such as automatically ordering the right spare parts.
Benefits of predictive maintenance with SAP Predictive Asset Insights
Many companies use SAP solutions, more specifically SAP Predictive Asset Insights, for the purposes of predictive maintenance. This solution is the successor to SAP Predictive Maintenance and Service and offers users a range of advantages:
Data-driven, planned and automated maintenance measures combined with timely provisioning of the necessary maintenance resources (such as spare parts and auxiliary materials) minimise downtime and increase efficiency.
Lower production costs
Machinery that is maintained before thresholds are exceeded run more reliably and produce fewer faulty items. This not only reduces losses, but also optimises overall production costs in the long term.
Lower transport costs
Timely maintenance interventions prevent unpleasant surprises. Predictive maintenance reduces unplanned shutdowns and therefore freight costs for special deliveries that might be required when delays impact scheduling.
Greater cost efficiency
Instead of incurring avoidable costs from shutdowns and preventive maintenance, companies that use SAP Asset Insights can choose the optimum time for maintenance based on data. All machinery parts are used until their level of wear and tear makes them a risk factor for downtime.
Improved supply chain
Predictive maintenance is essential for logistics-oriented just-in-time production since it helps maximise uptime.
If you know in advance what part needs replacing next or which service engineer is needed where, you can plan accordingly.
Use cases for predictive maintenance
The advantages of predictive maintenance benefit a wide range of manufacturing and production industries in different disciplines. Here are two potential areas:
The packaging industry involves the production of very large batches but with relatively low margins on each individual product. To break even, each shift must produce a large volume of goods and every shutdown costs money. Our customer worked with Syntax to implement SAP Predictive Asset Insights to maximise the efficiency of maintenance stoppages within its largely automated production systems. Historical data was used to generate new insights and minimise interruptions in production.
New business models
In conjunction with connected machines, companies can use predictive maintenance and SAP as the basis for new business models. In line with the latest concepts and requirements, rather than selling machines to customers, they sell access to operating hours in the context of Uptime as a Service. In this situation, predictive maintenance provides the foundations for secure, constant revenue.
Syntax: Your partner for predictive maintenance – not just with SAP
Anyone who wants to tap into all the benefits of predictive maintenance first needs to understand and put in place the required technologies. As an IT services provider, Syntax has already designed and implemented numerous projects with customers in a variety of industries. Companies have many good reasons for choosing to partner with us, but in particular they appreciate our comprehensive understanding of the processes, characteristics and requirements of production systems. We know what drives companies that want to take full advantage of the value of predictive maintenance. As an SAP partner from the very beginning, we ensure the rapid, smooth integration of SAP Predictive Asset Insights with existing SAP systems. In addition, our proven cloud expertise enables us to effortlessly develop and implement individual architectures and provisioning models. The cloud also provides the foundation for the Syntax IIoT Portal, through which companies can deploy tailored solutions and apps that open a window to the future performance of their machines and their maintenance cycles. From process consulting to IT, OT and the cloud: Syntax provides companies with all the services they need from a single source.
+49 173 305 4112
FAQ: Predictive Maintenance
What is predictive maintenance?
Predictive maintenance is all about the opportunity for operators to identify impending servicing and maintenance requirements at an early stage, so that appropriate measures can be planned and unscheduled interventions avoided. Data collected by and from the machines themselves is used to make predictions about maintenance requirements. When analytics are used, supported for example by AI and ML algorithms, patterns in the data can be identified to pinpoint problems before they occur. This knowledge enables companies to optimise their maintenance and servicing operations, utilising planned intervals to rectify issues. That means they can make their entire production process more efficient, in terms of people and materials, while increasing productivity and overall revenue thanks to the decrease in unscheduled machine downtime.
What is the difference between predictive and preventive maintenance?
Predictive maintenance uses machine data to identify the next maintenance requirement. Historical and current data is used to forecast the precise time of the anticipated machine failure as accurately as possible. This gives companies the opportunity to optimise installation of affected spare parts and similar measures in terms of cost of time and materials. Preventive maintenance also seeks to avoid unplanned machine downtime, however parts are switched and maintenance carried out according to predefined service intervals. As a result, parts are replaced at the same intervals irrespective of their state, even if they still work perfectly. While this approach also minimises machine failure, it is more expensive and less efficient in terms of materials than predictive maintenance based on data.