Back to results
US 2017/0322120 A1Published application
Fault detection using event-based predictive models
AssigneeSap SE
InventorChen WANG
Life of this patent
Estimating the term…
Abstract
A proposed solution to analyze event data from sensors of devices of a manufacturing environment to identify relationships of events to predict faults in devices is disclosed. The analysis includes conditional probability model and Apriori model. The relationships are used to determine a device health index which is compared to real-time event data to predict faults in a device.
Claims20
A method for diagnosing faults to predict faults comprising:
- providing, to an analyzer server, event data of events from sensors for measuring operating metrics of devices of a system of devices, wherein the event data comprises alarm events of devices;
- analyzing the event data to identify relationships of events;
- defining a device health index (DHI) based on identified relationships of events to predict failures based on the DHI;
- and
- monitoring, by the analyzer server, events from sensors of the devices to determine possible failures based on the DHI.
2 more elements
A system for diagnosing faults to predict faults comprising:
- a database module, wherein the database module stores event data of events from sensors for measuring operating metrics of devices of a system of devices, wherein the event data comprises alarm events of devices;
- and
- a processor module, wherein the processor module
- analyzes the event data to identify relationships of events,
- monitors events and comparing the events with a DHI which is defined based on identified relationships of events,
- predicts failures based on the DHI.
3 more elements
A non-transitory computer-readable medium having stored thereon program code, the program code executable by a computer, the program code comprising:
- providing, to an analyzer server, event data of events from sensors for measuring operating metrics of devices of a system of devices, wherein the event data comprises alarm events of devices;
- analyzing the event data to identify relationships of events using a conditional probability analysis and an Apriori analysis;
- and
- monitoring, by the analyzer server, events from sensors of the devices to determine possible failures based on the DHI which is defined based on identified relationships of events to predict failures based on the DHI.
1 more element
Dependencies are inferred from the claim text.