Methods and apparatus for fluid flow monitoring and leak detection
According to at least one aspect, a fluid flow monitoring system includes an ultrasonic sensor for generating measurement signals associated with respective ultrasonic signals propagating through the fluid in the lumen, a shut-off valve for blocking fluid flow in the lumen, and a controller. The controller can be communicatively coupled to the ultrasonic sensor and to the shut-off valve. The controller can be configured to compute a plurality of fluid flow parameter estimates based on a plurality of measurement signals generated by the ultrasonic sensor over a time window while the shut-off valve is open. The controller can obtain an offset value associated with fluid flow parameter measurements during a zero flow state of the shut-off valve. The controller can then check for presence of a fluid leak event based on the fluid flow parameter estimates over the time window and the offset value.
1. A system to detect a leak in a pipe, the leak detection system comprising:
an ultrasonic sensor generating measurement signals associated with respective ultrasonic signals propagating through a fluid in the pipe;
a shut-off valve for blocking fluid flow in the pipe; and
a processor communicatively coupled to the ultrasonic sensor and to the shut-off valve, the processor configured to:
compute a plurality of fluid flow parameter estimates of a fluid flow parameter based on a plurality of measurement signals generated by the ultrasonic sensor over a time window while the shut-off valve is open, the fluid flow parameter including fluid flow rate or fluid flow velocity;
obtain an offset value representing a measurement of the fluid flow parameter during a zero flow state;
calibrate the fluid flow parameter estimates associated with the time window by subtracting the offset value from the fluid flow parameter estimates; and
detect a fluid leak event based on the calibrated fluid flow parameter estimates.
2. The leak detection system of claim 1 , wherein the at least one processor is further configured, upon detecting a fluid leak event:
actuate the shut-off valve to block fluid flow in the pipe; or
send a warning message to a client device via a communication interface, the fluid flow monitoring system including the communication interface.
3. The leak detection system of claim 1 further including an inline leak detector, wherein the processor is configured to:
receive an indication of a zero flow state from the inline leak detector;
obtain at least one second measurement signal generated by the ultrasonic sensor during the zero flow state; and
compute the offset value based on at the least one second measurement signal.
4. The leak detection system of claim 1 , wherein detecting the leak event based on the calibrated fluid flow parameter estimates includes:
comparing the calibrated fluid flow parameter estimates to a threshold value; and
detecting the fluid leak event upon determining that all the calibrated fluid flow parameter estimates over the time window exceed the threshold value.
5. The leak detection system of claim 4 , wherein the threshold value includes at least a first threshold value associated with a first duration of the time window and a second threshold value smaller than the first threshold value and associated with a second duration of the time window, the second time duration greater than the first time duration.
6. The leak detection system of claim 1 , wherein the processor is configured to detect the fluid leak event upon determining that the calibrated fluid flow parameter estimates are non-zero and substantially constant over the time window.
7. The leak detection system of claim 1 , wherein detecting the leak event based on the calibrated fluid flow parameter estimates includes employing a statistical model to determine whether the calibrated fluid flow parameter estimates over the time window are indicative of the leak event.
8. The leak detection system of claim 7 , wherein the statistical model includes a maximum likelihood detection module or a maximum a-posteriori detection module.
9. The leak detection system of claim 1 further comprising at least one of a check valve for preventing reversal fluid flow and a pressure regulating device for regulating fluid pressure.
10. A method of detecting a leak in a pipe, comprising:
computing, by a processor, a plurality of fluid flow parameter estimates of a fluid flow parameter based on measurement signals generated by an ultrasonic sensor over a time window while a shut-off valve associated with the pipe is open, the fluid flow parameter including fluid flow rate or fluid flow velocity;
obtaining, by the processor, an offset value representing a measurement of the fluid flow parameter during a zero flow state, wherein the offset value is indicative of a drift in measurements of the fluid flow parameter;
calibrating, by the processor, the fluid flow parameter estimates associated with the time window by subtracting the offset value from the fluid flow parameter estimates; and
detecting, by the processor, a fluid leak event based on the calibrated fluid flow parameter estimates.
11. The method of claim 10 further comprising:
actuating the shut-off valve to block fluid flow in the pipe upon detecting a fluid leak event; or
sending a warning message to a client device via a communication interface upon detecting a fluid leak event.
12. The method of claim 10 further comprising:
receiving, by the processor, an indication of a zero flow state from an inline leak detector;
obtaining at least one second measurement signal generated by the ultrasonic sensor during the zero flow state; and
computing the offset value based on at the least one second measurement signal.
13. The method of claim 10 , wherein detecting the leak event based on the calibrated fluid flow parameter estimates includes:
comparing the calibrated fluid flow parameter estimates to a threshold value; and
detecting the fluid leak event upon determining that all the calibrated fluid flow parameter estimates over the time window exceed the threshold value.
14. The method of claim 13 , wherein the threshold value includes at least a first threshold value associated with a first duration of the time window and a second threshold value smaller than the first threshold value and associated with a second duration of the time window, the second time duration greater than the first time duration.
15. The method of claim 10 comprising detecting the fluid leak event upon determining that the calibrated fluid flow parameter estimates are non-zero and substantially constant over the time window.
16. The method of claim 10 , wherein detecting the leak event based on the calibrated fluid flow parameter estimates includes employing a statistical model to determine whether the calibrated fluid flow parameter estimates over the time window are indicative of the leak event.
17. The method of claim 16 , wherein the statistical model includes a maximum likelihood detection module or a maximum a-posteriori detection module.