US2019383780A1PendingUtilityA1

Systems and methods for predicting gas concentration values

Assignee: IND SCIENT CORPPriority: Dec 20, 2013Filed: Aug 27, 2019Published: Dec 19, 2019
Est. expiryDec 20, 2033(~7.3 yrs left)· nominal 20-yr term from priority
G01N 33/0063G01N 33/0004G01N 33/0037G01N 33/0067G01N 33/0044G01N 33/0042G01N 33/004Y02A50/20
50
PatentIndex Score
0
Cited by
0
References
0
Claims

Abstract

Methods, systems, and computer-readable media for monitoring a gas are generally described. In some embodiments, the concentration of a gas may be predicted based on gas measurement information received from a gas sensor and gas sensor response information for the gas sensor. The gas sensor response information may include a response curve. In some embodiments, the response curve may include a curve generated based on a Sigmoid function and/or a curve of the first derivative thereof. In some embodiments, the predicted gas measurement value may be generated by predicting an asymptotic value of the gas measurement information based on a rate of change of the concentration of the gas and the response curve.

Claims

exact text as granted — not AI-modified
What is claimed is: 
     
         1 . A gas monitoring system, comprising:
 a gas sensor;   a processor; and   a non-transitory, computer-readable storage medium in operable communication with the processor, wherein the computer-readable storage medium contains one or more programming instructions that, when executed, cause the processor to:   receive gas measurement information in a time series from the gas sensor for a concentration of a gas,   store the gas measurement information as historical gas measurement information,   receive a gas sensor response sigmoid function having a specific shape and corresponding to the gas sensor,   determine a rate of change of the concentration of the gas at each of a plurality of times using the gas measurement information,   generate a predicted gas measurement value for the gas sensor corresponding to the concentration of gas by predicting an asymptotic value of the gas measurement information using the gas measurement information corresponding to a specific time and a set of weighted determined rates of change prior to the specific time, wherein each corresponding weight for the set of weighted determined rates of change uses the specific shape of the gas sensor response sigmoid function, and   trigger an alarm when the predicted gas measurement value is outside a desired range.   
     
     
         2 . The gas monitoring system of  claim 1 , wherein the gas comprises carbon monoxide (CO), oxygen (O 2 ), hydrogen sulfide (H 2 S), nitrogen dioxide (NO 2 ), and/or sulfur dioxide (SO 2 ). 
     
     
         3 . The gas monitoring system of  claim 1 , wherein the computer-readable storage medium further contains one or more programming instructions that, when executed, cause the processor to update the gas sensor response sigmoid function using the historical gas measurement information. 
     
     
         4 . The gas monitoring system of  claim 1 , wherein the computer-readable storage medium further contains one or more programming instructions that, when executed, cause the processor to determine whether a change in the gas measurement information occurs responsive to an artificial factor or responsive to a gas event. 
     
     
         5 . The gas monitoring system of  claim 1 , wherein the computer-readable storage medium further contains one or more programming instructions that, when executed, cause the processor to prevent generation of the predicted gas measurement value using an artificial factor. 
     
     
         6 . A computer-implemented method for monitoring a gas, the method comprising, by a processor:
 receiving gas measurement information from a gas sensor in a time series for a concentration of a gas;   storing the gas measurement information as historical gas measurement information;   receiving a gas sensor response sigmoid function having a specific shape and corresponding to the gas sensor;   determining a rate of change of the concentration of the gas using the gas measurement information at each of a plurality of times;   generating a predicted gas measurement value for the gas sensor corresponding to the concentration of gas by predicting an asymptotic value of the gas measurement information using the gas measurement information corresponding to a specific time and a set of weighted determined rates of change prior to the specific time, wherein each corresponding weight for the set of weighted determined rates of change uses the specific shape of the gas sensor response sigmoid function; and   generating an alarm trigger when the predicted gas measurement value is outside of a predetermined range.   
     
     
         7 . The computer-implemented method of  claim 6 , wherein the gas comprises carbon monoxide (CO), oxygen (O 2 ), hydrogen sulfide (H 2 S), nitrogen dioxide (NO 2 ), and/or sulfur dioxide (SO 2 ). 
     
     
         8 . The computer-implemented method of  claim 6 , further comprising updating the gas sensor response sigmoid function using the historical gas measurement information. 
     
     
         9 . The computer-implemented method of  claim 6 , further comprising determining whether a change in the gas measurement information occurs responsive to an artificial factor or responsive to a gas event. 
     
     
         10 . The computer-implemented method of  claim 6 , further comprising preventing generation of the predicted gas measurement value using an artificial factor. 
     
     
         11 . The computer-implemented method of  claim 6 , wherein the gas sensor comprises at least one of a semiconductor sensor, an electrochemical sensor, a catalytic sensor, and a photoionization sensor. 
     
     
         12 . The computer-implemented method of  claim 6 , wherein the generation of the predicted gas measurement value comprises the following process:
     Zt=Y   t +( Y   t-1   −Y   t-2 )+½( Y   t-2   −Y   t-3 )+⅓( Y   t-3   −Y   t-4 )
   where Z 1 =predicted value at time t, and
 Y 1 =raw gas measurement information at time t.

Join the waitlist — get patent alerts

Track US2019383780A1 — get alerts on status changes and closely related new filings.

We store only your email — no account needed. See our privacy policy.