Data transformation for PdM

Senseye PdM Stream logo

We are passionate about making Predictive Maintenance available to everyone; indeed, this was a founding principle when Senseye was established. We quickly realized that everyone was at different stages of their maintenance journey. Some have well-established technologies and processes in place to make use of the data available on the factory floor, others are just starting their journey.

Therefore, we developed Senseye PdM Stream to enable companies to accelerate their maintenance journey and allow them to reuse as much existing data (and investments!) as possible.

What are the benefits?

  • Rapidly scale your Condition Monitoring installations
  • Leverage existing investments
  • Senseye PdM Stream takes care of all data transformation

What is condition monitoring data?

It is accepted that Predictive Maintenance requires condition monitoring data. Condition monitoring is a well-versed discipline and has been leveraged for decades for use in understanding machine health.

Collecting condition monitoring data means capturing sensor data at a known state and sampling frequency, often also applying statistical filtering to enhance the data future. The quality of the condition monitoring data is very much related to the business requirement of the warning required before machine failure.

Unfortunately, condition monitoring know-how isn’t common across all industries. Moreover, businesses won’t necessarily have suitable data to hand, and converting what is available into a suitable form can be time-intensive and frustrating.

This is where Senseye PdM Stream helps

Senseye PdM Stream

Senseye PdM Stream provides a place for Senseye’s condition monitoring specialists to apply pre-processing rules and algorithms to raw sensor and process data and generate suitable condition monitoring data.

This enables Senseye to implement the necessary data conversion without drawing on the precious resources of a customer’s IT department. Alternatively, a customer can leverage their own know-how or IP about their machines to implement this processing capability. Raw sensor and process data is captured via real-time streaming analytics, typically in sample rates of just seconds, and used to generate condition monitoring data

Senseye PdM Stream enables an increase in an organization’s PdM Index while allowing it to retain control over its Senseye PdM implementation and any subsequent refinements, as well as dramatically accelerating timescales for scaling projects.

Senseye PdM Stream Diagram

Senseye PdM Stream in practice

Senseye PdM Stream is ideally suited to relatively complex PdM cases, such as those which require time aggregation of the raw data. Unusual cases can benefit from Senseye PdM Stream, too, such as those using rules based on a combination of measures taken from different sensors and/or assets, or where there is a recognized need for extensive data pre-processing.

Senseye’s condition monitoring engineers will work with customers to configure and deploy Senseye PdM Stream according to their unique needs.

Next Steps:

Find out more

Looking for more information

We have a comprehensive gallery of white papers, case studies and blog content available where you can learn more