CN111080976A - Method and device for monitoring natural gas leakage in real time under temperature change scene - Google Patents
Method and device for monitoring natural gas leakage in real time under temperature change scene Download PDFInfo
- Publication number
- CN111080976A CN111080976A CN201911343856.8A CN201911343856A CN111080976A CN 111080976 A CN111080976 A CN 111080976A CN 201911343856 A CN201911343856 A CN 201911343856A CN 111080976 A CN111080976 A CN 111080976A
- Authority
- CN
- China
- Prior art keywords
- natural gas
- gas leakage
- leakage concentration
- concentration
- real
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/12—Alarms for ensuring the safety of persons responsive to undesired emission of substances, e.g. pollution alarms
- G08B21/16—Combustible gas alarms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Abstract
The invention discloses a method and a device for monitoring natural gas leakage in real time under a temperature change scene, wherein the method comprises the following steps: acquiring corresponding original data of a detector by using a natural gas concentration detector, and storing the temperature, the real natural gas leakage concentration and the original data of the detector in a correlation manner as a data set I; creating a BP neural network by using the data set I and training: acquiring the real natural gas leakage concentration in a use scene by using a natural gas concentration detector and a BP neural network prediction function; calculating the real natural gas leakage concentration variation in the use scene; calculating the real natural gas leakage concentration change rate in the use scene; calculating the sum of the concentration variation in a period of time; predicting natural gas leakage concentration in a use scene after a period of time in the future; and if the alarm threshold value is exceeded, alarming. The invention realizes the high-precision and high-sensitivity detection of the natural gas leakage condition under the use scene of severe temperature change, reduces the condition of difference of monitoring results caused by individual difference of the sensitive probe, can predict the future natural gas concentration, gives an alarm in advance and has lower cost.
Description
Technical Field
The invention relates to the technical field of natural gas leakage monitoring, in particular to a method and a device for monitoring natural gas leakage in real time under a temperature change scene.
Background
Most of the current various natural gas leakage monitoring systems monitor the concentration of leaked gas under a normal-temperature use scene or a certain specific-temperature use scene (a high-temperature or low-temperature use scene), cannot be continuously used under scenes with severe changes of high temperature, low temperature and temperature, and do not take the influence of temperature changes on monitoring results into targeted consideration. The breadth of our country is broad, the seasons are alternative and obvious, and the temperature change is severe near the vehicle engine along with the increase of the vehicle running time, for example, under the use scene of minus 10 degrees in winter, the engine temperature can be as high as more than 60 degrees when the vehicle runs for half an hour, so that the common natural gas concentration detector cannot adapt to the severe scene.
The current detection method for the leakage concentration of various natural gases is only to obtain the original data of a natural gas concentration detector to perform simple mean value, filtering extreme value and other processing, and each sensing head has certain discreteness, so that the monitoring result has deviation, and the detection alarm can only be performed when the leakage concentration reaches a threshold value, and the concentration variation trend cannot be pre-judged according to the concentration variation condition.
Currently, a specially-made natural gas concentration detector is used in a special use scene, and the number of the detectors is increased, which causes higher cost.
Disclosure of Invention
The method and the device for monitoring the natural gas leakage in real time under the temperature change scene provided by the invention can realize high-precision and high-sensitivity detection of the natural gas leakage condition under the use scene with severe temperature change, reduce the condition of difference of monitoring results caused by individual difference of the sensitive probes, predict the future natural gas concentration, give an alarm in advance and have lower cost.
The method for monitoring the natural gas leakage in real time under the temperature change scene is characterized by comprising the following steps of:
s1: obtaining a data set one, specifically: under different temperatures T and different natural gas leakage concentrations N, the natural gas concentration detector is utilized to obtain corresponding detector original data N0The temperature T, the real natural gas leakage concentration N and the original data N of the detector are used0The association is stored as a data set one;
s2: training a BP neural network by using the data set I:
N=g(T)*N0(formula one)
Where N represents true natural gas leakage concentration, T represents temperature, N0The natural gas leakage concentration and temperature relation function is represented by g (T) and g (T);
s3: calculating the real natural gas leakage concentration in the use scene, specifically: using the natural gas concentration detector and the BP neural network N ═ g (t) × N obtained in step S20Obtaining the real natural gas leakage concentration N in the use scene;
s4: calculating the real natural gas leakage concentration increment in the use scene:
ΔNi=Ni-Ni-1(formula two)
Wherein, Δ NiRepresenting the real natural gas leakage concentration variation, N, in the usage scenarioiIndicating the true natural gas leakage concentration, N, in the usage scenario obtained in the ith usage step S3i-1Representing the real natural gas leakage concentration in the use scene obtained by the step S3 in the (i-1) th time, wherein i is an integer greater than 1;
s5: calculating the real natural gas leakage concentration change rate in the use scene:
αi=ΔNi/ti(formula three)
Wherein, tiα representing the time interval between the acquisition of the true natural gas leakage concentration in the usage scenario by the i-th and i-1-th utilization step S3iRepresenting a time interval tiInternal useTrue natural gas leakage concentration change rate, Δ N, in a sceneiRepresenting a time interval tiThe real natural gas leakage concentration variation in the internal use scene;
s6: predicting natural gas leakage concentration in a use scene after a period of time in the future specifically comprises:
calculating the sum of the concentration variations over a period of time:
wherein S represents the sum of the real natural gas leakage concentration variation in a use scene in a period of time, and delta NiRepresenting a time interval tiThe real natural gas leakage concentration variation in the internal use scene, wherein n is an integer greater than 1;
substituting the formula three into the formula four
The sum S of the real natural gas leakage concentration variation in the use scene in a period of time is the integral of a natural gas leakage concentration variation function f (x), and a formula six is obtained:
predicting the natural gas leakage concentration in the usage scenario after a period of time in the future using equation six:
wherein N isjFor natural gas leakage concentrations in a usage scenario after a period of time in the future, N1Indicating the actual natural gas leakage concentration in the current usage scenario calculated by step S3;
wherein, the real natural gas leakage concentration N in the use scene is obtained by using the formula IIIiAnd using the formula four to obtainUsing the real natural gas leakage concentration N in the sceneiTrue natural gas leakage concentration change rate α in corresponding usage scenarioiTraining a BP neural network to obtain a natural gas leakage concentration change function f (x);
s7: and alarm judgment, specifically comprising: calculating the natural gas leakage concentration in the use scene after a period of time in the future by using a formula seven, comparing the natural gas leakage concentration in the use scene with a preset alarm threshold value, and alarming if the natural gas leakage concentration exceeds the preset alarm threshold value.
Preferably, formula eight is used instead of formula seven
The invention relates to a device for monitoring natural gas leakage in real time under a temperature change scene, which is characterized by comprising:
a data set acquisition module for acquiring corresponding original data N of the detector by using the natural gas concentration detector at different temperatures T and different natural gas leakage concentrations N0The temperature T, the real natural gas leakage concentration N and the original data N of the detector are used0The association is stored as a data set one;
a BP neural network training module, configured to train the BP neural network using the first data set:
N=g(T)*N0(formula one)
Where N represents true natural gas leakage concentration, T represents temperature, N0The natural gas leakage concentration and temperature relation function is represented by g (T) and g (T);
using a real natural gas leakage concentration N calculation module in a scene, and using the BP neural network N (g) (T) N obtained in the natural gas concentration detector and the BP neural network training device0Obtaining the real natural gas leakage concentration N in the use scene;
the real natural gas leakage concentration increment calculation module in the use scene is used for calculating the real natural gas leakage concentration increment in the use scene:
ΔNi=Ni-Ni-1(formula two)
Wherein, Δ NiRepresenting the real natural gas leakage concentration variation, N, in the usage scenarioiIndicating the true natural gas leakage concentration, N, in the usage scenario obtained in the ith usage step S3i-1Representing the real natural gas leakage concentration in the use scene obtained by the step S3 in the (i-1) th time, wherein i is an integer greater than 1;
the real natural gas leakage concentration change rate calculation module in the use scene is used for calculating the real natural gas leakage concentration change rate in the use scene:
αi=ΔNi/ti(formula three)
Wherein, tiα representing the time interval between the acquisition of the true natural gas leakage concentration in the usage scenario by the i-th and i-1-th utilization step S3iRepresenting a time interval tiTrue natural gas leakage concentration change rate, Δ N, in internal usage scenariosiRepresenting a time interval tiThe real natural gas leakage concentration variation in the internal use scene;
a natural gas leakage concentration prediction module in a usage scenario after a period of time in the future, to:
calculating the sum of the concentration variations over a period of time:
wherein S represents the sum of the real natural gas leakage concentration variation in a use scene in a period of time, and delta NiRepresenting a time interval tiThe real natural gas leakage concentration variation in the internal use scene, wherein n is an integer greater than 1;
substituting the formula three into the formula four
The sum S of the real natural gas leakage concentration variation in the use scene in a period of time is the integral of a natural gas leakage concentration variation function f (x), and a formula six is obtained:
predicting the natural gas leakage concentration in the usage scenario after a period of time in the future using equation six:
wherein N isjFor natural gas leakage concentrations in a usage scenario after a period of time in the future, N1Indicating the actual natural gas leakage concentration in the current usage scenario calculated by step S3;
wherein, the real natural gas leakage concentration N in the use scene is obtained by using the formula IIIiAnd the real natural gas leakage concentration N in the use scene is obtained by using the formula fouriTrue natural gas leakage concentration change rate α in corresponding usage scenarioiTraining a BP neural network to obtain a natural gas leakage concentration change function f (x);
and the alarm judgment module is used for calculating the natural gas leakage concentration in the use scene after a period of time in the future by using a formula seven, comparing the natural gas leakage concentration in the use scene with a preset alarm threshold value, and alarming if the natural gas leakage concentration exceeds the preset alarm threshold value.
The invention relates to a system for monitoring natural gas leakage in real time under a temperature change scene, which is characterized by comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, which when executed by the processor, performs the method described above.
The computer-readable storage medium of the present invention, on which a computer program is stored, is characterized in that the program realizes the above-described method when executed by a processor.
Compared with the prior art, the invention has the advantages that:
(1) the BP neural network is trained by using big data, then the data under various use scenes are used for testing, the trained BP neural network is used for obtaining the real natural gas leakage concentration in the use scenes, the influence of temperature on the natural gas concentration detector is eliminated, the natural gas concentration detector can be applied to scenes of high temperature, low temperature, severe temperature change and the like, and the use scenes of the natural gas concentration detector are widened.
(2) The change trend of the natural gas leakage concentration is calculated, and the change rate of the natural gas leakage concentration is used as a judgment condition, so that the problems that different natural gas concentration detectors give inaccurate and inconsistent alarms to the same leakage scene due to individual performance differences of the natural gas concentration detectors can be solved. In addition, the concentration change rate is used for predicting the natural gas leakage concentration after a period of time in the future so as to carry out leakage concentration detection alarm, and the alarm is not carried out after the natural gas leakage concentration really reaches a certain value, so that the alarm time is advanced, and the possible safety risk is reduced.
(3) Software upgrading is only carried out on the existing natural gas concentration detector, hardware equipment cannot be increased, and a use scene and a use mode cannot be changed.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is a flow chart of a method for real-time monitoring of natural gas leaks under temperature change scenarios according to the present invention.
Detailed Description
Example one
FIG. 1 is a flow chart of a method for real-time monitoring of natural gas leaks under temperature change scenarios according to the present invention. As shown in fig. 1, the method comprises the steps of:
s1: obtaining a data set one, specifically: under different temperatures T and different natural gas leakage concentrations N, the natural gas concentration detector is utilized to obtain corresponding detector original data N0The temperature T, the real natural gas leakage concentration N and the original data N of the detector are used0The association is stored as dataset one. For example, 1500 sets of temperature T, true natural gas leak concentration N, and raw probe data N are obtained0The data set one is constructed.
S2: training a BP neural network by using the data set I:
N=g(T)*N0(formula one)
Where N represents true natural gas leakage concentration, T represents temperature, N0The natural gas leakage concentration and temperature relation function is represented by g (T) and g (T). For example, 1400 groups of data in the first data set are substituted into a BP neural network, a relation function g (T) between the natural gas leakage concentration and the temperature is obtained through training, and the rest 100 groups of data in the first data set are used for test verification.
S3: calculating the real natural gas leakage concentration in the use scene, specifically: using the natural gas concentration detector and the BP neural network N ═ g (t) × N obtained in step S20And obtaining the real natural gas leakage concentration N in the use scene. For example, in actual use, a natural gas concentration detector is used to acquire natural gas concentration in a scene, namely, raw detector data N0And meanwhile, acquiring the temperature of the use scene in the scene, and substituting the data into the formula I to obtain the real natural gas leakage concentration N in the use scene.
Therefore, the BP neural network is trained by using big data, the data under various use scenes are used for testing, the trained BP neural network is used for obtaining the real natural gas leakage concentration in the use scenes, the influence of temperature on the natural gas concentration detector is eliminated, the natural gas concentration detector can be applied to scenes with high temperature, low temperature, violent temperature change and the like, and the use scenes of the natural gas concentration detector are widened.
S4: calculating the real natural gas leakage concentration variation in the use scene:
ΔNi=Ni-Ni-1(formula two)
Wherein, Δ NiRepresenting the real natural gas leakage concentration variation, N, in the usage scenarioiIndicating the true natural gas leakage concentration, N, in the usage scenario obtained in the ith usage step S3i-1And (3) the real natural gas leakage concentration in the use scene obtained by the step S3 at the (i-1) th time is shown, wherein i is an integer larger than 1.
S5: calculating the real natural gas leakage concentration change rate in the use scene:
αi=ΔNi/ti(formula three)
Wherein, tiα representing the time interval between the acquisition of the true natural gas leakage concentration in the usage scenario by the i-th and i-1-th utilization step S3iRepresenting a time interval tiTrue natural gas leakage concentration change rate, Δ N, in internal usage scenariosiRepresenting a time interval tiThe real natural gas leakage concentration variation in the internal use scene.
S6: predicting natural gas leakage concentration in a use scene after a period of time in the future specifically comprises:
calculating the sum of the concentration variations over a period of time:
wherein S represents the sum of the real natural gas leakage concentration variation in a use scene in a period of time, and delta NiRepresenting a time interval tiThe real natural gas leakage concentration variation in the internal use scene, wherein n is an integer greater than 1;
substituting the formula three into the formula four
It can be seen that the sum S of the real natural gas leakage concentration variation amounts in the usage scenario over a period of time can be regarded as the integral of the natural gas leakage concentration variation function f (x), so that the formula six can be obtained:
predicting the natural gas leakage concentration in the usage scenario after a period of time in the future using equation six:
wherein N isjFor natural gas leakage concentrations in a usage scenario after a period of time in the future, N1Indicating the actual natural gas leakage concentration in the current usage scenario calculated by step S3;
in normal situations, no natural gas leakage occurs, so the leakage concentration principle should change from 0 after leakage occurs, and therefore the formula seven can be written as follows:
wherein, the real natural gas leakage concentration N in the use scene is obtained by using the formula IIIiAnd the real natural gas leakage concentration N in the use scene is obtained by using the formula fouriTrue natural gas leakage concentration change rate α in corresponding usage scenarioiAnd training the BP neural network to obtain a natural gas leakage concentration change function f (x). For example: obtaining real natural gas leakage concentration N in 1500 use scenes by using formula IIIiMeanwhile, the formula four is utilized to obtain the actual natural gas leakage concentration N in 1500 natural gas leakage concentration and using scenesiTrue natural gas leakage concentration change rate α in corresponding usage scenarioiForming a data set II containing 1500 groups of data, substituting 1400 groups of data in the data set II into the BP neural network, and training to obtain the natural dataAnd (f) (x) performing test verification by using the rest 100 groups of data in the data set II.
S7: and alarm judgment, specifically comprising: and calculating the natural gas leakage concentration in the use scene after a period of time in the future by using a formula seven or a formula eight, comparing the natural gas leakage concentration in the use scene with a preset alarm threshold value, and alarming if the natural gas leakage concentration exceeds the preset alarm threshold value.
Therefore, by calculating the change trend of the natural gas leakage concentration and using the change rate of the natural gas leakage concentration as a judgment condition, the problems that different natural gas concentration detectors give inaccurate and inconsistent alarms to the same leakage scene due to individual performance differences of the natural gas concentration detectors can be solved. In addition, the concentration change rate is used for predicting the natural gas leakage concentration after a period of time in the future so as to carry out leakage concentration detection alarm, and the alarm is not carried out after the natural gas leakage concentration really reaches a certain value, so that the alarm time is advanced, and the possible safety risk is reduced.
Example two
The invention also provides a device for monitoring the natural gas leakage in real time under the temperature change scene, which comprises the following components:
a data set acquisition module for acquiring corresponding original data N of the detector by using the natural gas concentration detector at different temperatures T and different natural gas leakage concentrations N0The temperature T, the real natural gas leakage concentration N and the original data N of the detector are used0The association is stored as a data set one;
a BP neural network training module, configured to train the BP neural network using the first data set:
N=g(T)*N0(formula one)
Where N represents true natural gas leakage concentration, T represents temperature, N0The natural gas leakage concentration and temperature relation function is represented by g (T) and g (T);
true natural gas leakage in usage scenariosA leakage concentration N calculation module for using the BP neural network obtained from the natural gas concentration detector and the BP neural network training device to obtain N ═ g (T) × N0Obtaining the real natural gas leakage concentration N in the use scene;
the real natural gas leakage concentration increment calculation module in the use scene is used for calculating the real natural gas leakage concentration increment in the use scene:
ΔNi=Ni-Ni-1(formula two)
Wherein, Δ NiRepresenting the real natural gas leakage concentration variation, N, in the usage scenarioiIndicating the true natural gas leakage concentration, N, in the usage scenario obtained in the ith usage step S3i-1Representing the real natural gas leakage concentration in the use scene obtained by the step S3 in the (i-1) th time, wherein i is an integer greater than 1;
the real natural gas leakage concentration change rate calculation module in the use scene is used for calculating the real natural gas leakage concentration change rate in the use scene:
αi=ΔNi/ti(formula three)
Wherein, tiα representing the time interval between the acquisition of the true natural gas leakage concentration in the usage scenario by the i-th and i-1-th utilization step S3iRepresenting a time interval tiTrue natural gas leakage concentration change rate, Δ N, in internal usage scenariosiRepresenting a time interval tiThe real natural gas leakage concentration variation in the internal use scene;
a natural gas leakage concentration prediction module in a usage scenario after a period of time in the future, to:
calculating the sum of the concentration variations over a period of time:
wherein S represents the sum of the real natural gas leakage concentration variation in a use scene in a period of time, and delta NiRepresenting a time interval tiReal natural gas leaks in-service scenariosThe concentration variation, n is an integer greater than 1;
substituting the formula three into the formula four
The sum S of the real natural gas leakage concentration variation in the use scene in a period of time is the integral of a natural gas leakage concentration variation function f (x), and a formula six is obtained:
predicting the natural gas leakage concentration in the usage scenario after a period of time in the future using equation six:
wherein N isjFor natural gas leakage concentrations in a usage scenario after a period of time in the future, N1Indicating the actual natural gas leakage concentration in the current usage scenario calculated by step S3;
wherein, the real natural gas leakage concentration N in the use scene is obtained by using the formula IIIiAnd the real natural gas leakage concentration N in the use scene is obtained by using the formula fouriTrue natural gas leakage concentration change rate α in corresponding usage scenarioiTraining a BP neural network to obtain a natural gas leakage concentration change function f (x);
and the alarm judgment module is used for calculating the natural gas leakage concentration in the use scene after a period of time in the future by using a formula seven, comparing the natural gas leakage concentration in the use scene with a preset alarm threshold value, and alarming if the natural gas leakage concentration exceeds the preset alarm threshold value.
The invention only upgrades the software on the existing natural gas concentration detector, thus not increasing hardware equipment and changing the use scene and the use mode.
EXAMPLE III
The invention also provides a system for monitoring the natural gas leakage in real time under the temperature change scene, which is characterized by comprising the following components: memory, processor and computer program stored on the memory and executable on the processor, which when executed by the processor implements the method as described above.
Example four
The invention also proposes a computer-readable storage medium, on which a computer program is stored, characterized in that the program, when executed by a processor, implements the method as described above.
It should be understood that the above-mentioned embodiments are merely preferred examples of the present invention, and not restrictive, but rather, all the changes, substitutions, alterations and modifications that come within the spirit and scope of the invention as described above may be made by those skilled in the art, and all the changes, substitutions, alterations and modifications that fall within the scope of the appended claims should be construed as being included in the present invention.
Claims (5)
1. A method for monitoring natural gas leakage in real time under a temperature change scene is characterized by comprising the following steps:
s1: acquiring a data set I, specifically: under different temperatures T and different natural gas leakage concentrations N, the natural gas concentration detector is utilized to obtain corresponding detector original data N0The temperature T, the real natural gas leakage concentration N and the original data N of the detector are used0The association is stored as a data set one;
s2: training a BP neural network by using the data set I:
N=g(T)*N0(formula one)
Where N represents true natural gas leakage concentration, T represents temperature, N0The natural gas leakage concentration and temperature relation function is represented by g (T) and g (T);
s3: calculating the real natural gas leakage concentration in the use scene,the method specifically comprises the following steps: using the natural gas concentration detector and the BP neural network N ═ g (t) × N obtained in step S20Obtaining the real natural gas leakage concentration N in the use scene;
s4: calculating the real natural gas leakage concentration increment in the use scene:
ΔNi=Ni-Ni-1(formula two)
Wherein, Δ NiRepresenting the real natural gas leakage concentration variation, N, in the usage scenarioiIndicating the true natural gas leakage concentration, N, in the usage scenario obtained in the ith usage step S3i-1Representing the real natural gas leakage concentration in the use scene obtained by the step S3 in the (i-1) th time, wherein i is an integer greater than 1;
s5: calculating the real natural gas leakage concentration change rate in the use scene:
αi=ΔNi/ti(formula three)
Wherein, tiα representing the time interval between the acquisition of the true natural gas leakage concentration in the usage scenario by the i-th and i-1-th utilization step S3iRepresenting a time interval tiTrue natural gas leakage concentration change rate, Δ N, in internal usage scenariosiRepresenting a time interval tiThe real natural gas leakage concentration variation in the internal use scene;
s6: predicting natural gas leakage concentration in a use scene after a period of time in the future specifically comprises:
calculating the sum of the concentration variations over a period of time:
wherein S represents the sum of the real natural gas leakage concentration variation in a use scene in a period of time, and delta NiRepresenting a time interval tiThe real natural gas leakage concentration variation in the internal use scene, wherein n is an integer greater than 1;
substituting the formula three into the formula four
The sum S of the real natural gas leakage concentration variation in the use scene in a period of time is the integral of a natural gas leakage concentration variation function f (x), and a formula six is obtained:
predicting the natural gas leakage concentration in the usage scenario after a period of time in the future using equation six:
wherein N isjFor natural gas leakage concentrations in a usage scenario after a period of time in the future, N1Indicating the actual natural gas leakage concentration in the current usage scenario calculated by step S3;
wherein, the real natural gas leakage concentration N in the use scene is obtained by using the formula IIIiAnd the real natural gas leakage concentration N in the use scene is obtained by using the formula fouriTrue natural gas leakage concentration change rate α in corresponding usage scenarioiTraining a BP neural network to obtain a natural gas leakage concentration change function f (x);
s7: and alarm judgment, specifically comprising: calculating the natural gas leakage concentration in the use scene after a period of time in the future by using a formula seven, comparing the natural gas leakage concentration in the use scene with a preset alarm threshold value, and alarming if the natural gas leakage concentration exceeds the preset alarm threshold value.
3. A device for monitoring natural gas leakage in real time under temperature change scene is characterized by comprising:
a data set acquisition module for acquiring corresponding original data N of the detector by using the natural gas concentration detector at different temperatures T and different natural gas leakage concentrations N0The temperature T, the real natural gas leakage concentration N and the original data N of the detector are used0The association is stored as a data set one;
a BP neural network training module, configured to train the BP neural network using the first data set:
N=g(T)*N0(formula one)
Where N represents true natural gas leakage concentration, T represents temperature, N0The natural gas leakage concentration and temperature relation function is represented by g (T) and g (T);
using a real natural gas leakage concentration N calculation module in a scene, and using the BP neural network N (g) (T) N obtained in the natural gas concentration detector and the BP neural network training device0Obtaining the real natural gas leakage concentration N in the use scene;
the real natural gas leakage concentration increment calculation module in the use scene is used for calculating the real natural gas leakage concentration increment in the use scene:
ΔNi=Ni-Ni-1(formula two)
Wherein, Δ NiRepresenting the real natural gas leakage concentration variation, N, in the usage scenarioiIndicating the true natural gas leakage concentration, N, in the usage scenario obtained in the ith usage step S3i-1Representing the real natural gas leakage concentration in the use scene obtained by the step S3 in the (i-1) th time, wherein i is an integer greater than 1;
the real natural gas leakage concentration change rate calculation module in the use scene is used for calculating the real natural gas leakage concentration change rate in the use scene:
αi=ΔNi/ti(formula three)
Wherein, tiα representing the time interval between the acquisition of the true natural gas leakage concentration in the usage scenario by the i-th and i-1-th utilization step S3iRepresenting a time interval tiTrue natural gas leakage concentration change rate, Δ N, in internal usage scenariosiRepresenting a time interval tiThe real natural gas leakage concentration variation in the internal use scene;
a natural gas leakage concentration prediction module in a usage scenario after a period of time in the future, to:
calculating the sum of the concentration variations over a period of time:
wherein S represents the sum of the real natural gas leakage concentration variation in a use scene in a period of time, and delta NiRepresenting a time interval tiThe real natural gas leakage concentration variation in the internal use scene, wherein n is an integer greater than 1;
substituting the formula three into the formula four
The sum S of the real natural gas leakage concentration variation in the use scene in a period of time is the integral of a natural gas leakage concentration variation function f (x), and a formula six is obtained:
predicting the natural gas leakage concentration in the usage scenario after a period of time in the future using equation six:
wherein N isjFor the futureNatural gas leakage concentration, N, in a usage scenario after a period of time1Indicating the actual natural gas leakage concentration in the current usage scenario calculated by step S3;
wherein, the real natural gas leakage concentration N in the use scene is obtained by using the formula IIIiAnd the real natural gas leakage concentration N in the use scene is obtained by using the formula fouriTrue natural gas leakage concentration change rate α in corresponding usage scenarioiTraining a BP neural network to obtain a natural gas leakage concentration change function f (x);
and the alarm judgment module is used for calculating the natural gas leakage concentration in the use scene after a period of time in the future by using a formula seven, comparing the natural gas leakage concentration in the use scene with a preset alarm threshold value, and alarming if the natural gas leakage concentration exceeds the preset alarm threshold value.
4. A system for real-time monitoring of natural gas leaks in temperature change scenarios, the system comprising: memory, processor and computer program stored on the memory and executable on the processor, which when executed by the processor implements the method of any of claims 1-2.
5. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-2.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911343856.8A CN111080976B (en) | 2019-12-24 | 2019-12-24 | Method and device for monitoring natural gas leakage in real time under temperature change scene |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911343856.8A CN111080976B (en) | 2019-12-24 | 2019-12-24 | Method and device for monitoring natural gas leakage in real time under temperature change scene |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111080976A true CN111080976A (en) | 2020-04-28 |
CN111080976B CN111080976B (en) | 2021-09-10 |
Family
ID=70317168
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911343856.8A Active CN111080976B (en) | 2019-12-24 | 2019-12-24 | Method and device for monitoring natural gas leakage in real time under temperature change scene |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111080976B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112489402A (en) * | 2020-11-27 | 2021-03-12 | 罗普特科技集团股份有限公司 | Early warning method, device and system for pipe gallery and storage medium |
CN113516831A (en) * | 2021-07-05 | 2021-10-19 | 南京盛航海运股份有限公司 | Ship safety detection method, system, equipment and storage medium |
CN114112251A (en) * | 2022-01-29 | 2022-03-01 | 长扬科技(北京)有限公司 | Natural gas leakage point positioning method and device |
EP4160493A4 (en) * | 2020-05-29 | 2023-11-08 | Qingdao Haier Refrigerator Co., Ltd | Coal gas concentration prediction method based on collaborative filtering, and device and refrigerator |
Citations (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6987459B2 (en) * | 2003-01-24 | 2006-01-17 | Honeywell International, Inc. | Portable combustible gas detector |
TW201129946A (en) * | 2009-09-09 | 2011-09-01 | Mitsubishi Heavy Ind Ltd | Disaster-affected area estimation device and program |
US20140180986A1 (en) * | 2012-12-24 | 2014-06-26 | Google Inc. | System and method for addressing overfitting in a neural network |
CN104123476A (en) * | 2014-08-12 | 2014-10-29 | 大连海事大学 | Gas concentration prediction method and device based on extreme learning machine |
JP2015170136A (en) * | 2014-03-07 | 2015-09-28 | Jfeスチール株式会社 | Announcement prediction method of photochemical oxidant warning |
CN105486807A (en) * | 2015-11-25 | 2016-04-13 | 南京缔尔达智能科技有限公司 | Method for analyzing hidden safety trouble of dangerous chemical gas |
CN105701980A (en) * | 2016-03-31 | 2016-06-22 | 中冶南方工程技术有限公司 | Poisonous gas alarm and alarm method |
CN107085732A (en) * | 2017-05-12 | 2017-08-22 | 淮阴工学院 | Cowshed environment ammonia intelligent monitor system based on wireless sensor network |
CN107313808A (en) * | 2016-06-12 | 2017-11-03 | 中国石油化工股份有限公司 | Inflammable gas concentration monitor and the method for early warning |
CN108562697A (en) * | 2018-03-30 | 2018-09-21 | 歌尔股份有限公司 | A kind of indoor harmful gas monitoring device |
CN109190828A (en) * | 2018-09-07 | 2019-01-11 | 苏州大学 | Gas leakage concentration distribution determines method, apparatus, equipment and readable storage medium storing program for executing |
JP2019074855A (en) * | 2017-10-13 | 2019-05-16 | 東京瓦斯株式会社 | Electric load control device and control method of electric load control device |
CN110009874A (en) * | 2019-04-12 | 2019-07-12 | 泰州职业技术学院 | A kind of flammable gas alarm, combustible gas alarm method and system |
CN110046834A (en) * | 2019-05-13 | 2019-07-23 | 苏州大学 | Workplace pernicious gas health risk quantitative evaluating system and its appraisal procedure |
CN110470802A (en) * | 2019-09-10 | 2019-11-19 | 常州市科能电器有限公司 | A kind of dam toxic and harmful gas monitoring and warning system and method |
-
2019
- 2019-12-24 CN CN201911343856.8A patent/CN111080976B/en active Active
Patent Citations (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6987459B2 (en) * | 2003-01-24 | 2006-01-17 | Honeywell International, Inc. | Portable combustible gas detector |
TW201129946A (en) * | 2009-09-09 | 2011-09-01 | Mitsubishi Heavy Ind Ltd | Disaster-affected area estimation device and program |
US20140180986A1 (en) * | 2012-12-24 | 2014-06-26 | Google Inc. | System and method for addressing overfitting in a neural network |
JP2015170136A (en) * | 2014-03-07 | 2015-09-28 | Jfeスチール株式会社 | Announcement prediction method of photochemical oxidant warning |
CN104123476A (en) * | 2014-08-12 | 2014-10-29 | 大连海事大学 | Gas concentration prediction method and device based on extreme learning machine |
CN105486807A (en) * | 2015-11-25 | 2016-04-13 | 南京缔尔达智能科技有限公司 | Method for analyzing hidden safety trouble of dangerous chemical gas |
CN105701980A (en) * | 2016-03-31 | 2016-06-22 | 中冶南方工程技术有限公司 | Poisonous gas alarm and alarm method |
CN107313808A (en) * | 2016-06-12 | 2017-11-03 | 中国石油化工股份有限公司 | Inflammable gas concentration monitor and the method for early warning |
CN107085732A (en) * | 2017-05-12 | 2017-08-22 | 淮阴工学院 | Cowshed environment ammonia intelligent monitor system based on wireless sensor network |
JP2019074855A (en) * | 2017-10-13 | 2019-05-16 | 東京瓦斯株式会社 | Electric load control device and control method of electric load control device |
CN108562697A (en) * | 2018-03-30 | 2018-09-21 | 歌尔股份有限公司 | A kind of indoor harmful gas monitoring device |
CN109190828A (en) * | 2018-09-07 | 2019-01-11 | 苏州大学 | Gas leakage concentration distribution determines method, apparatus, equipment and readable storage medium storing program for executing |
CN110009874A (en) * | 2019-04-12 | 2019-07-12 | 泰州职业技术学院 | A kind of flammable gas alarm, combustible gas alarm method and system |
CN110046834A (en) * | 2019-05-13 | 2019-07-23 | 苏州大学 | Workplace pernicious gas health risk quantitative evaluating system and its appraisal procedure |
CN110470802A (en) * | 2019-09-10 | 2019-11-19 | 常州市科能电器有限公司 | A kind of dam toxic and harmful gas monitoring and warning system and method |
Non-Patent Citations (3)
Title |
---|
JING WANG等: ""Visual prediction of gas diffusion concentration based on regression analysis and BP neural network"", 《THE JOURNAL OF ENGINEERING》 * |
于浩等: ""基于神经网络的气体预警穿戴***的温度补偿"", 《软件与算法》 * |
袁方红: ""气体预警穿戴***的传感器校正与浓度预测"", 《万方数据知识服务平台》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP4160493A4 (en) * | 2020-05-29 | 2023-11-08 | Qingdao Haier Refrigerator Co., Ltd | Coal gas concentration prediction method based on collaborative filtering, and device and refrigerator |
CN112489402A (en) * | 2020-11-27 | 2021-03-12 | 罗普特科技集团股份有限公司 | Early warning method, device and system for pipe gallery and storage medium |
CN113516831A (en) * | 2021-07-05 | 2021-10-19 | 南京盛航海运股份有限公司 | Ship safety detection method, system, equipment and storage medium |
CN114112251A (en) * | 2022-01-29 | 2022-03-01 | 长扬科技(北京)有限公司 | Natural gas leakage point positioning method and device |
Also Published As
Publication number | Publication date |
---|---|
CN111080976B (en) | 2021-09-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111080976B (en) | Method and device for monitoring natural gas leakage in real time under temperature change scene | |
CN109447263B (en) | Space abnormal event detection method based on generation of countermeasure network | |
Santer et al. | Correlation methods in fingerprint detection studies | |
US20150308919A1 (en) | Intelligent adaptive system and method for monitoring leakage of oil pipeline networks based on big data | |
US20150121160A1 (en) | Systems and methods for detecting, correcting, and validating bad data in data streams | |
CN110455490B (en) | Method and device for calculating supersonic velocity and hypersonic velocity wind tunnel flow field turbulence | |
US20160369777A1 (en) | System and method for detecting anomaly conditions of sensor attached devices | |
CN112101554B (en) | Abnormality detection method and apparatus, device, and computer-readable storage medium | |
US9910081B2 (en) | Performance analysis of power grid monitors | |
CN114564629B (en) | Abnormal data processing method and device, computer equipment and storage medium | |
CN107516279A (en) | A kind of method of network public-opinion automatic early-warning | |
CN110672332A (en) | Gas turbine fault early warning system based on SARIMA model | |
US20210080614A1 (en) | Weather Prediction Correction Method and Weather Prediction System | |
CN106767898B (en) | A method of detection measuring system of satellite attitude small fault | |
US10742535B2 (en) | Monitoring a resource consumption of an application | |
CN113343541B (en) | Vortex-induced vibration early warning method, device and terminal for long and large bridge span | |
CN113009077B (en) | Gas detection method, gas detection device, electronic equipment and storage medium | |
Qian et al. | State of health estimation of lithium-ion battery using energy accumulation-based feature extraction and improved relevance vector regression | |
CN105722129A (en) | Wireless sensing network event detection method and system based on FSAX-MARKOV model | |
KR20190128420A (en) | IoT sensor abnormality diagnosing method and system using cloud-based virtual sensor | |
CN109341650B (en) | Unmanned aerial vehicle elevation error double-threshold correction method based on minimum detection cost | |
US7366639B2 (en) | Methods for establishing alerts and/or alert limits for monitoring mechanical devices | |
Wang et al. | A state monitoring method of gas regulator station based on evidence theory driven by time-domain information | |
Zheng et al. | Reliability analysis of multi-stage degradation with stage-varying noises based on the nonlinear Wiener process | |
US20210271989A1 (en) | Method for predicting vessel density in a surveillance area |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |