Seite wählen

Leider ist der Eintrag nur auf Amerikanisches Englisch verfügbar. Der Inhalt wird unten in einer verfügbaren Sprache angezeigt. Klicken Sie auf den Link, um die aktuelle Sprache zu ändern.



Predictive Maintenance in a waste-to-energy power plant

A supplier of electricity, natural gas and heating operates complex machinery with embedded sensors that generate operational data. The data had not been used effectively and the unscheduled machine downtime was hurting production yield rates. Presenso’s Machine Learning based Predictive Maintenance solution, streams sensor data from across the plant, including the rotary kiln incinerator and flue gas treatment system.  Advanced Unsupervised Machine Learning algorithms are applied.

Anomaly detection and pattern recognition are used to identify evolving failures across multiple machines.

Almost two thirds of evolving shutdowns are predicted on average of four days before occurrence. By isolating the root cause of the failure, repairs can be scheduled before shutdown is necessary.

Early intervention of evolving failure has increased yield rates and improves the Overall Equipment Efficiency (OEE).

OEM Digital

Turbine and compressors manufacturer digital transformation

An OEM that serves the Energy, Oil & Gas and Process Industries is changing its business and delivery models.  The company has based its new strategic direction on digital transformation and is moving to replace hardware sales model with a Hardware as a Service offering.

Prior to deploying the Presenso solution, there was no way to systematically analyze the vast amounts of sensor data embedded in the industrial machinery at its customers’ sites. As part of its new model, the OEM needs to access operational from multiple plants that are dispersed geographically in real time.

OEM’s own digitalization team was in the process of manually modelling their various types of equipment which in some cases took them months to complete for a specific model and make.

Using Presenso Automated Machine Leaning approach, the modelling and deployment process was reduced to few hours or days which provided the OEM the scalable solution they were after.

With Presenso’s Remote Asset Monitoring, the OEM can now service the industrial assets leased to its customers cost effectively.  The visualization of Machine Learning outputs is accessible on easy-to-use and intuitive dashboards.  Technicians in remote facilities can repair  evolving equipment failure prioritize scheduling based on their availability.


Improved operational efficiencies in a warehouse operation

A warehouse serves as the logistics backbone of a 5,000-employee industrial plant.  It is fully automated.  Except for asset breakdown, all tasks within the warehouse are performed by pick-and-place robots that maneuverer on multi-axis platforms.

The warehouse’s two functions are to feed raw materials to the production lines and to move finished goods to shipment area for the end-customers. Each robot action generates multiple entries in the log file. Prior to using the Presenso solution, the data from these log files were only accessed after a failure already occurred.

With the Presenso solution, all the robot log data is extracted and streamed to the cloud in real time. Presenso delivers a Business Intelligence dashboard that also generates alerts when log files identify specific error events.

The warehouse has improved operational efficiency and it can react to evolving failure prior to occurrence.  Furthermore, by using Presenso’s dashboards and analyzing the exact root cause of failure, technicians can be dispatched to repair the exact relevant part.

Learn more about our solution