Steady state resistance estimation for overheating protection of a nicotine e-vaping device

1. A nicotine electronic vaping device (EVD) comprising:

a reservoir containing a nicotine pre-vapor formulation;

a heating element configured to heat nicotine pre-vapor formulation drawn from the reservoir; and

control circuitry configured to,

monitor a resistance value of the heating element over a first time period after a first application of negative pressure to the nicotine EVD,

determine an estimated steady state resistance value of the heating element based on the monitored resistance value using a trained neural network; and

control power to the heating element based on the estimated steady state resistance value.

2. The nicotine EVD of claim 1 , wherein the control circuitry is further configured to:

detect dry puff conditions at the nicotine EVD based on the estimated steady state resistance value of the heating element; and

disable power to the heating element in response to the detected dry puff conditions.

3. The nicotine EVD of claim 2 , wherein the control circuitry is further configured to:

prevent power from being applied to the heating element in response to detection of a second application of negative pressure to the nicotine EVD.

4. The nicotine EVD of claim 1 , wherein the control circuitry is configured to:

monitor the resistance value of the heating element by,

determining a peak resistance value of the heating element during the first time period, and

determining at least one additional resistance value of the heating element at a time after the determined peak resistance value during the first time period; and

determine the estimated steady state resistance value of the heating element by,

estimating the estimated steady state resistance value of the heating element using the trained neural network based on the peak resistance value and the at least one additional resistance value.

5. The nicotine EVD of claim 4 , wherein the trained neural network is a function-fitting network configured to:

receive the peak resistance value and the at least one additional resistance value as input values;

determine a decay in the input values over the first time period; and

output the estimated steady state resistance value of the heating element based on results of the determined decay in the resistance value of the heating element over the first time period.

6. The nicotine EVD of claim 4 , wherein

the peak resistance value is determined at a time when the power being applied to the heating element is stopped after the first application of negative pressure to the nicotine EVD.

7. The nicotine EVD of claim 6 , wherein

the at least one additional resistance value includes at least a second resistance value and a third resistance value;

the second resistance value is determined at a time following the time when the peak resistance value is determined and before the third resistance value is determined; and

the third resistance value is determined at a time following the time when the second resistance value is determined and before detecting a second application of negative pressure.

8. The nicotine EVD of claim 1 , wherein

the heating element is connected to a Wheatstone bridge circuit; and

the control circuitry is further configured to,

detect a variable resistance value corresponding to the heating element over the first time period;

detect a resistance value corresponding to the Wheatstone bridge circuit over the first time period; and

estimate the estimated steady state resistance value of the heating element using the trained neural network based on the detected variable resistance value corresponding to the heating element and the detected resistance value corresponding to the Wheatstone bridge circuit.

9. A method of operating a nicotine electronic vaping device (EVD), the method comprising:

monitoring, using control circuitry of the nicotine EVD, a resistance value of a heating element included in the nicotine EVD over a first time period after a first application of negative pressure to the nicotine EVD;

determining, using the control circuitry, an estimated steady state resistance value of the heating element based on the monitored resistance value using a trained neural network; and

controlling, using the control circuitry, power to the heating element based on the estimated steady state resistance value.

10. The method of claim 9 , further comprising:

detecting, using the control circuitry, dry puff conditions at the nicotine EVD based on the estimated steady state resistance of the heating element; and

disabling, using the control circuitry, power to the heating element in response to the detected dry puff conditions.

11. The method of claim 10 , further comprising:

detecting, using the control circuitry, a second application of negative pressure to the nicotine EVD; and

preventing, using the control circuitry, power from being applied to the heating element in response to detecting the second application of negative pressure to the nicotine EVD.

12. The method of claim 9 , wherein

the monitoring the resistance value of the heating element includes,

determining a peak resistance value of the heating element during the first time period, and

determining at least one additional resistance value of the heating element at a time after the determined peak resistance value during the first time period; and

the determining the estimated steady state resistance value of the heating element includes estimating the estimated steady state resistance value of the heating element using the trained neural network based on the peak resistance value and the at least one additional resistance value.

13. The method of claim 12 , wherein

the trained neural network is a function-fitting network; and

the method further comprises,

receiving, using the control circuitry, the peak resistance value and the at least one additional resistance value as input values;

determining, using the control circuitry, a decay in the resistance value of the heating element over the first time period; and

outputting, using the control circuitry, the estimated steady state resistance value of the heating element based on results of the determined decay in the resistance value of the heating element over the first time period.

14. The method of claim 12 , wherein

the peak resistance value is determined at a time when the power being applied to the heating element is stopped after the first application of negative pressure to the nicotine EVD.

15. The method of claim 14 , wherein

the at least one additional resistance value includes at least a second resistance value and a third resistance value;

the second resistance value is determined at a time following the time when the peak resistance value is determined and before the third resistance value is determined; and

the third resistance value is determined at a time following the time when the second resistance value is determined and before detecting a second application of negative pressure.

16. The method of claim 9 , the method further comprising:

detecting, using the control circuitry, a variable resistance value corresponding to the heating element over the first time period;

detecting, using the control circuitry, a resistance value corresponding to a Wheatstone bridge circuit over the first time period; and

estimating, using the control circuitry, the estimated steady state resistance value of the heating element using the trained neural network based on the detected variable resistance value corresponding to the heating element and the detected resistance value corresponding to the Wheatstone bridge circuit.

17. A nicotine electronic vaping device (EVD) comprising:

a reservoir containing a nicotine pre-vapor formulation;

a heating element configured heat nicotine pre-vapor formulation drawn from the reservoir;

heater resistance monitoring circuitry configured to,

determine a peak resistance value of the heating element during a first time period after a first application of negative pressure to the nicotine EVD, and

determine at least one additional resistance value of the heating element during the first time period;

a trained neural network configured to,

estimate a steady state resistance value of the heating element during the first time period based on the determined peak resistance value and the determined at least one additional resistance value; and

control circuitry configured to disable power to the heating element based on the estimated steady state resistance value.

18. The nicotine EVD of claim 17 , wherein

the trained neural network is further configured to detect dry puff conditions at the nicotine EVD based on the estimated steady state resistance value of the heating element; and

the control circuitry is further configured to disable the power to the heating element in response to the detected dry puff conditions.

19. The nicotine EVD of claim 17 , wherein the trained neural network is a function-fitting network configured to:

receive the peak resistance value and the at least one additional resistance value as input values;

determine a decay in the input values over the first time period; and

output the estimated steady state resistance value of the heating element based on results of the determined decay in the resistance value of the heating element over the first time period.

20. The nicotine EVD of claim 17 , wherein

the peak resistance value is determined at a time when the power being applied to the heating element is stopped after the first application of negative pressure to the nicotine EVD.