Documentation
Get detailed guidance on platform features
XMPRO’s Data Stream Designer lets you visually design the data flow and orchestration for your real-time applications. Our drag & drop connectors make it easy to bring in real-time data from a variety of sources, add contextual data from systems like EAM, apply native and third-party analytics and initiate actions based on events in your data.
XMPro’s Data Stream Designer is a user friendly tool for designing data flow in real-time applications. Its drag & drop system facilitates the integration of real-time data from various sources, allowing the addition of contextual data from systems like EAM. Users can also employ native and third-party analytics, and act based on specific data events.
Most companies spend 50% of digital transformation project costs on integration.
With XMPro’s growing library of 150+ pre-built connectors for enterprise, industrial and emerging technologies, you don’t have to.
Consume or ingest data as it arrives from a third-party system or sensor, making it available for further evaluation or processing.
Add additional information to a specific event from a 3rd party system, database or service. This is generally static or slow changing data.
Add data wrangling steps into your data stream, like replacing missing values and converting data into different types.
Perform mathematical and statistical operations like Fast Fourier Transformations on the data being ingested.
Add predictive capability to your apps with anomaly detection, R scripts and advanced machine learning algorithms.
Trigger actions in 3rd party systems, like sending SMS alerts or creating work orders in SAP.
Real-world data isn’t perfect. It needs to be cleaned and transformed before you can use it. The Data Stream Designer makes it easy to add data wrangling steps into your data stream, like replacing missing values and converting data into different types.
XMPro’s transformation agents simplify data preparation, ensuring data quality and accuracy. This leads to better decision-making and stronger data-driven outcomes.
You can use a range of analytics functions to add intelligence to your XMPRO data streams. Run algorithms for fast fourier transformations, anomaly detection and custom R scripts on your real-time data. Or use advanced machine learning algorithms to add predictive capability to your apps.
XMPro Data Stream Designer is a core component of our Intelligent Digital Twin Suite, seamlessly working from the agents that visually orchestrate your data flow to enabling efficient integration and reuse of data patterns.
Watch this demo to see how XMPro Data Stream Designer can optimize data flow and enhance real-time applications in your organization.
In the power utility sector, the use of an AI-based ‘heat-rate optimizer,’ which analyzes numerous data points in real-time and suggests performance enhancements, can overcome optimization challenges, potentially increasing efficiency by 1%, leading to substantial annual savings, reduced greenhouse gas emissions, and more efficient use of workers’ time
AI-powered Digital Twins in manufacturing can streamline cycle times, automate defect detection, and enhance inspection success, while also lowering CO2 emissions by over 10%, reducing product testing time by 45% for cost savings, and nearly eliminating defects and false alarms, a significant improvement over the previous error rate from human inspections.
AI-powered Digital Twins used for predictive maintenance of underground conveyors have facilitated real-time failure anticipation and efficient scheduling of maintenance, leading to significantly reduced downtime and an additional 44,000 tons of ore mined in a potash mine over five months which equates to millions of dollars of additional revenue.
AI-powered Digital Twins are effectively used for real-time detection of pipe bursts in water distribution systems, where the system processes pressure and flow sensor data, predicts future values using artificial neural networks (ANN), and compares these with actual observations to gauge the probability of a failure event, thereby raising relevant alarms.