The digital identification plate contains all relevant data needed for clear identification of your components.
Data is collected and stored throughout your component’s lifecycle:
Temperature, vibration, mounting position and acceleration
Sensor values are easy to monitor based on predefined or customized thresholds.
- The “cynapse Monitor” service provides a control terminal for your cynapse® gearbox, allowing all features to be used.
- You no longer need to design a separate visualization solution for the cynapse® data, meaning a lot of development time and costs are eliminated.
- cynapse® uses all sensor data such as process data, histograms or histories and also events as data input.
- You gain insights into the operating behavior of the drive axles, allowing critical operating conditions to be detected earlier.
- The “Data Gateway” is the core service for integrating and processing sensor data enabling condition monitoring applications.
- The service can provide this data to multiple target systems (databases, cloud systems, etc.) simultaneously and in parallel.
- The service supports you with an automated integration of cynapse® data – significantly reducing your manual integration effort into the machine infrastructure.
- The service provides collected sensor data in a structured format.
- In addition, it is possible to integrate control data into the Data Gateway via OPC UA.
- The “cynapse Teach-In” service helps parametrize cynapse® for your individual machine process. You no longer need to manually determine thresholds for cynapse®.
- The service helps identify and visualize abnormal events in the machine process.
- The service determines process-dependent thresholds based on statistical methods or individual computations.
- The service stores a set of learned thresholds and transfers them to cynapse® as and when necessary – giving you maximum flexibility.
- The “Anomaly-Check” service automatically detects anomalies in the machine process or component behavior. Expensive machine downtime is prevented before it occurs.
- The service uses various machine learning models to compute effective anomaly metrics.
- The service can simultaneously monitor multiple sensors at various points in the machine.
- The service can be connected and used for different applications.