Flow metering system condition-based monitoring and failure to predictive mode
A flow metering system includes a flow meter coupled to a plurality of sensors and configured to measure volume of fluid flowing through the flow meter. The system also includes a metrology computer coupled to the flow meter and the sensors. The metrology computer is configured to receive live values from a plurality of sensors during a first time period, train an artificial intelligence engine based on the live values received during the first time period, and detect a sensor failure based on a deviation between a live value from the sensor and a predicted value for the sensor. The predicted value is based on live values from other of the plurality of sensors and the artificial intelligence engine.
1. A flow metering system, comprising:
a flow meter coupled to a plurality of sensors and configured to measure volume of fluid flowing through the flow meter; and
a metrology computer coupled to the flow meter and the sensors and configured to:
receive live values from a plurality of sensors during a first time period;
train an artificial intelligence engine based on the live values received during the first time period;
in response to detecting a sensor failure, determine an uncertainty of a predicted value for the sensor, wherein the predicted value is based on live values from other of the plurality of sensors and the artificial intelligence engine; and
in response to the uncertainty being below a threshold, use the predicted value in a flow calculation.
2. The flow metering system of claim 1 , wherein the metrology computer is further configured to:
predict a future trend in sensor values based on the live values and the trained artificial intelligence engine; and
identify an impending failure of one of the sensors.
3. The flow metering system of claim 2 , wherein the metrology computer is further configured to calculate a probability of impending failure of the sensor when the metrology computer identifies the impending failure.
4. The flow metering system of claim 1 , wherein the metrology computer is further configured to determine and display a remedial action in response to the uncertainty being above the threshold.
5. A method for monitoring operation of a flow meter, comprising:
receiving, by a metrology computer, live values from a plurality of sensors during a first time period;
training an artificial intelligence engine based on the live values received during the first time period;
in response to detecting a sensor failure, determining, by the metrology computer an uncertainty of a predicted value for the sensor, wherein the predicted value is based on live values from other of the plurality of sensors and the artificial intelligence engine; and
in response to the uncertainty being below a threshold, using, by the metrology computer, the predicted value in a flow calculation.
6. The method of claim 5 , further comprising performing a remedial action for the sensor experiencing the failure in response to the uncertainty being above the threshold.
7. The method of claim 6 , wherein the remedial action comprises at least one selected from the group consisting of: scheduling maintenance for the sensor; ordering a replacement sensor; and replacing the sensor.
8. A non-transitory, computer-readable medium containing instructions that, when executed by a processor, cause the processor to perform the method of claim 5 .