Sensors and Measuring Points in Asset Intelligence Network


It is common fact that many of existing industrial Equipment’s are constantly streaming out data on various parameters. At present there is no easy way to collect and analyze this data. It is also not simple for a comparison of the data with the benchmarks provided by the OEMs. Due to this situation, gaining more insights based on the massive amounts of data becomes impossible.

This blog explains how SAP Asset Intelligence Network and SAP Predictive Maintenance and Service solutions helps to solve the problems faced by plant managers and equipment analysts to proactively fix problems before they arise.


SAP Asset Intelligence Network is a novel business network that combines information from manufacturers, service providers, and equipment operators on a single cloud-based platform. With SAP Asset Intelligence Network, manufacturers, service providers, and equipment operators can exchange data with one another through a cloud-based platform. A manufacturer, for example, can make the master data available for a specific model. Customers who use this machine or component model can transfer data to their systems and link it with their own master data. As a result, the data remains up-to-date without complex manual work or integration gaps. SAP Asset Intelligence Network is a business network based on SAP HANA Cloud platform.



SAP Predictive Maintenance and Services (SAP PdMS) provides holistic management of asset health and decision support for maintenance schedules and optimization of resources based on health scores, anomaly detection, and spectral analysis. SAP PdMS OPE provides out-of-the-box business applications to check the health of assets and optimize their operation and servicing. It runs on an extendable, high-performing data processing platform which can process huge amounts of fused information technology (IT) and operations technology (OT) data. It makes advanced data science methods available to find and mitigate previously hidden patterns of asset failures.

A term frequently used in Manufacturing or Production industry is relativity and Measurement. What’s the temperature of this? What is the speed of that? And how precise is the other. The relative measurement is always helpful in analysis and case studies to analyze something or for gauging a particular metric. The concept of measuring point is about generalizing the metric for consumption of the contemporary modules, for example, to define the Rotor bearing temperature as a metric for a particular equipment.



L_B11F.tmp.PNG




The attached block diagram shows how to get sensor data from an external system into AIN. This architectural diagram illustrates the connection of sensor data, which is performed in a ‘system-agnostic’ manner. The AIN system establishes a connection via Hana Cloud Integration (HCI), which is a cloud connector accepting the URL and an artifact of a unique connection establishment using which we can connect to PDMS or any other IoT backend.



The below diagram shows the details of an AIN application on central HCP provider account. This solution is the key to connect AIN with physical devices, which are connected to one of the currently supported backends (PdMS, IoT Services) making it an excellent IoT use case in the manufacturing world.

Since the majority of measuring points are already defined by standards SAP is providing in AIN, operating companies can compare measuring point readings across manufacturers, which was only hardly possible before. In addition to current readings, a company can also fetch historical data from AIN to perform analytics on it.



From the existing system (Asset Intelligence Network) as a platform, the connection can be established to external landscapes. Currently, we have implemented the connection to HCP IoT service and PdMS. This service for connection to external system will make way for connect and discovery of physical machines via an ID along with other technical details.

Essentially, to connect to any external system one would need an attribute of type measuring point.

Once the data is pulled from the above mentioned external systems, it will be available as a service, to AIN, in which the user can map these data points (measuring points) to predefined attributes. With this, it is possible to plot an analysis of past readings to evaluate how that sensor is performing. You can auto refresh the readings from the AIN for analysis.

The sensor data can also be exported as csv in order to use Excel or other tools to run even more sophisticated analytics.

Connecting backend systems and historians to AIN measuring point provides a holistic overview to stakeholders interested in comparing measuring point readings across systems and companies.

sensors&mp2.png

All said and done, what if the same measuring points are already present in an external system? In such a scenario, we can map the external measuring points to the AIN measuring points and save the configuration. As a technical user, we need to map measuring points carefully based on name and ID. In this case, we will avoid redundancies and duplicates and guarantee correctness of device IDs and data.

Also, none of the sensor data is persisted in AIN. It always resides in the customer or external landscapes, making AIN a secure IoT application.

Creation of measuring points is available as a public service (API). You can use this to create an attribute as measuring point. With AIN measuring points and sensors, we can connect various devices, machines to gain insights on them on a single platform.

For more information, see:

For more information, see:

To report this post you need to login first.

Be the first to leave a comment

You must be Logged on to comment or reply to a post.

Leave a Reply