CN116597635A - Wireless communication intelligent gas meter controller and control method thereof - Google Patents

Wireless communication intelligent gas meter controller and control method thereof Download PDF

Info

Publication number
CN116597635A
CN116597635A CN202310561914.4A CN202310561914A CN116597635A CN 116597635 A CN116597635 A CN 116597635A CN 202310561914 A CN202310561914 A CN 202310561914A CN 116597635 A CN116597635 A CN 116597635A
Authority
CN
China
Prior art keywords
gas pressure
time sequence
feature
vector
dynamic
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
Application number
CN202310561914.4A
Other languages
Chinese (zh)
Other versions
CN116597635B (en
Inventor
宋向东
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hangzhou Xinli Meter Co ltd
Original Assignee
Hangzhou Xinli Meter Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Hangzhou Xinli Meter Co ltd filed Critical Hangzhou Xinli Meter Co ltd
Priority to CN202310561914.4A priority Critical patent/CN116597635B/en
Publication of CN116597635A publication Critical patent/CN116597635A/en
Application granted granted Critical
Publication of CN116597635B publication Critical patent/CN116597635B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
    • F17D—PIPE-LINE SYSTEMS; PIPE-LINES
    • F17D3/00—Arrangements for supervising or controlling working operations
    • F17D3/01—Arrangements for supervising or controlling working operations for controlling, signalling, or supervising the conveyance of a product
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M3/00—Investigating fluid-tightness of structures
    • G01M3/02—Investigating fluid-tightness of structures by using fluid or vacuum
    • G01M3/26—Investigating fluid-tightness of structures by using fluid or vacuum by measuring rate of loss or gain of fluid, e.g. by pressure-responsive devices, by flow detectors
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G—PHYSICS
    • G08—SIGNALLING
    • G08C—TRANSMISSION SYSTEMS FOR MEASURED VALUES, CONTROL OR SIMILAR SIGNALS
    • G08C17/00—Arrangements for transmitting signals characterised by the use of a wireless electrical link
    • G08C17/02—Arrangements for transmitting signals characterised by the use of a wireless electrical link using a radio link

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Mechanical Engineering (AREA)
  • Arrangements For Transmission Of Measured Signals (AREA)

Abstract

A wireless communication intelligent gas meter controller and a control method thereof acquire gas pressure values at a plurality of preset time points in a preset time period; and adopting an artificial intelligence technology based on deep learning to excavate implicit characteristic information of the gas pressure value and fully express time sequence change characteristics of the gas pressure value so as to accurately detect gas leakage, thereby avoiding safety accidents caused by gas leakage and ensuring the use safety of gas.

Description

Wireless communication intelligent gas meter controller and control method thereof
Technical Field
The application relates to the technical field of intelligent control, in particular to a wireless communication intelligent gas meter controller and a control method thereof.
Background
The known intelligent gas meter or the traditional gas meter at home and abroad is a gas meter which can not set time for controlling the opening and closing of a gas valve by family personnel. The main functions of the existing intelligent gas meter or traditional gas meter are gas metering and collecting, and the gas meter and the gas cooking bench are connected for a long time through a gas pipeline, so that the gas pipeline of the gas cooking bench always has gas pressure, gas leakage is easy to cause, and potential safety hazards exist.
Therefore, a wireless communication intelligent gas meter controller is expected to automatically detect gas leakage and ensure the safety of gas use.
Disclosure of Invention
The present application has been made to solve the above-mentioned technical problems. The application provides a wireless communication intelligent gas meter controller and a control method thereof, wherein the wireless communication intelligent gas meter controller acquires gas pressure values at a plurality of preset time points in a preset time period; and adopting an artificial intelligence technology based on deep learning to excavate implicit characteristic information of the gas pressure value and fully express time sequence change characteristics of the gas pressure value so as to accurately detect gas leakage, thereby avoiding safety accidents caused by gas leakage and ensuring the use safety of gas.
In a first aspect, a wireless communication intelligent gas meter controller is provided, which includes:
the gas pressure acquisition module is used for acquiring gas pressure values of a plurality of preset time points in a preset time period;
the pressure time sequence distribution module is used for arranging the gas pressure values of the plurality of preset time points into gas pressure time sequence input vectors according to the time dimension;
the pressure change module is used for calculating the difference value between the gas pressure values of every two adjacent positions in the gas pressure time sequence input vector to obtain a gas pressure change time sequence input vector;
The pressure dynamic and static information fusion module is used for cascading the gas pressure time sequence input vector and the gas pressure change time sequence input vector to obtain a gas pressure time sequence dynamic and static input vector;
the pressure time sequence change feature extraction module is used for enabling the gas pressure time sequence dynamic-static input vector to pass through a time sequence feature extractor comprising a first convolution layer and a second convolution layer so as to obtain a gas pressure time sequence dynamic-static feature vector;
the Gaussian enhancement module is used for carrying out characteristic data enhancement on the gas pressure time sequence dynamic-static characteristic vector by using a Gaussian density chart so as to obtain a classification characteristic matrix;
the feature optimization module is used for carrying out feature distribution optimization on the classification feature matrix to obtain an optimized classification feature matrix;
and the fuel gas leakage detection module is used for enabling the optimized classification feature matrix to pass through a classifier to obtain a classification result, wherein the classification result is used for indicating whether fuel gas leakage exists or not.
In the above wireless communication intelligent gas meter controller, the pressure dynamic and static information fusion module is configured to: cascading the gas pressure time sequence input vector and the gas pressure change time sequence input vector by using the following cascading formula to obtain a gas pressure time sequence dynamic-static input vector; wherein, the cascade formula is:
V c ＝Concat[V 1 ，V 2 ]
Wherein V is 1 ，V 2 Representing the gas pressure time sequence input vector and the gas pressure change time sequence input vector, concat [. Cndot.]Representing a cascade function, V c Representing the gas pressure time sequence dynamic-static input vector.
In the above wireless communication intelligent gas meter controller, the pressure time sequence change feature extraction module includes: a first scale feature extraction unit, configured to input the gas pressure time sequence dynamic-static input vector into a first convolution layer of the time sequence feature extractor to obtain a first scale gas pressure feature vector, where the first convolution layer has a one-dimensional convolution kernel of a first scale; a second scale feature extraction unit configured to input the gas pressure time sequence dynamic-static input vector into a second convolution layer of the time sequence feature extractor to obtain a second scale gas pressure feature vector, where the second convolution layer has a one-dimensional convolution kernel of a second scale, and the first scale is different from the second scale; and the multi-scale cascading unit is used for cascading the first-scale gas pressure characteristic vector and the second-scale gas pressure characteristic vector to obtain the gas pressure time sequence dynamic-static characteristic vector.
In the above wireless communication intelligent gas meter controller, the gaussian enhancement module includes: a Gaussian density map construction unit for constructing a Gaussian density map of the gas pressure time-series dynamic-static feature vector in a Gaussian formula using the Gaussian density map;
wherein, the Gaussian formula is:
wherein mu μ Representing the dynamic-static characteristic vector of the gas pressure time sequence and sigma σ The value of each position of (c) represents the variance between the characteristic values of the respective positions in the gas pressure time series dynamic-static characteristic vector, x represents the variable of the gaussian density map,representing a gaussian probability density function; and the Gaussian discretization unit is used for discretizing the Gaussian distribution of each position of the Gaussian density map to obtain the classification characteristic matrix.
In the above wireless communication intelligent gas meter controller, the feature optimization module is configured to: carrying out feature distribution optimization on the classification feature matrix by using the following optimization formula to obtain the optimized classification feature matrix; wherein, the optimization formula is:
m' i,j ＝(μσ)m i,j 2 +m i,j μ+(m i,j -σ)μ 2
wherein m is i,j Is the eigenvalue of the (i, j) th position of the classification characteristic matrix, mu and sigma are the mean and standard deviation of the respective position eigenvalue sets of the classification characteristic matrix, and m' i,j Is the eigenvalue of the (i, j) th position of the optimized classification eigenvalue matrix.
In the above-mentioned wireless communication intelligent gas table controller, the gas leakage detection module includes: the matrix unfolding unit is used for unfolding the optimized classification feature matrix into classification feature vectors according to row vectors or column vectors; the full-connection coding unit is used for carrying out full-connection coding on the classification characteristic vectors by using a plurality of full-connection layers of the classifier so as to obtain coded classification characteristic vectors; and the classification unit is used for passing the coding classification feature vector through a Softmax classification function of the classifier to obtain the classification result.
In a second aspect, a method for controlling a wireless communication intelligent gas meter is provided, which includes:
acquiring gas pressure values at a plurality of preset time points in a preset time period;
arranging the gas pressure values of the plurality of preset time points into gas pressure time sequence input vectors according to the time dimension;
calculating the difference value between the gas pressure values of every two adjacent positions in the gas pressure time sequence input vector to obtain a gas pressure change time sequence input vector;
cascading the gas pressure time sequence input vector and the gas pressure change time sequence input vector to obtain a gas pressure time sequence dynamic-static input vector;
Passing the gas pressure time sequence dynamic-static input vector through a time sequence feature extractor comprising a first convolution layer and a second convolution layer to obtain a gas pressure time sequence dynamic-static feature vector;
performing feature data enhancement on the gas pressure time sequence dynamic-static feature vector by using a Gaussian density chart to obtain a classification feature matrix;
performing feature distribution optimization on the classification feature matrix to obtain an optimized classification feature matrix;
and the optimized classification feature matrix passes through a classifier to obtain a classification result, wherein the classification result is used for indicating whether gas leakage exists or not.
In the above-mentioned wireless communication intelligent gas meter control method, cascade the gas pressure time sequence input vector and the gas pressure change time sequence input vector to obtain a gas pressure time sequence dynamic-static input vector, comprising: cascading the gas pressure time sequence input vector and the gas pressure change time sequence input vector by using the following cascading formula to obtain a gas pressure time sequence dynamic-static input vector; wherein, the cascade formula is:
V c ＝Concat[V 1 ，V 2 ]
wherein V is 1 ，V 2 Representing the gas pressure time sequence input vector and the gas pressure change time sequence inputIncoming vector, concat [. Cndot. ], the vector of the input vector is calculated by the code ]Representing a cascade function, V c Representing the gas pressure time sequence dynamic-static input vector.
In the above-mentioned wireless communication intelligent gas meter control method, passing the gas pressure time sequence dynamic-static input vector through a time sequence feature extractor comprising a first convolution layer and a second convolution layer to obtain a gas pressure time sequence dynamic-static feature vector, including: inputting the gas pressure time sequence dynamic-static input vector into a first convolution layer of the time sequence feature extractor to obtain a first scale gas pressure feature vector, wherein the first convolution layer is provided with a one-dimensional convolution kernel of a first scale; inputting the gas pressure time sequence dynamic-static input vector into a second convolution layer of the time sequence feature extractor to obtain a second scale gas pressure feature vector, wherein the second convolution layer is provided with a one-dimensional convolution kernel of a second scale, and the first scale is different from the second scale; and cascading the first-scale gas pressure feature vector and the second-scale gas pressure feature vector to obtain the gas pressure time sequence dynamic-static feature vector.
In the above wireless communication intelligent gas meter control method, the feature data enhancement is performed on the gas pressure time sequence dynamic-static feature vector by using a gaussian density chart to obtain a classification feature matrix, including: constructing a gaussian density map of the gas pressure time sequence dynamic-static characteristic vector in the following gaussian formula by using the gaussian density map;
Wherein, the Gaussian formula is:
wherein mu u Representing the dynamic-static characteristic vector of the gas pressure time sequence and sigma σ The value of each position of (c) represents the variance between the characteristic values of the respective positions in the gas pressure time series dynamic-static characteristic vector, x represents the variable of the gaussian density map,representing a gaussian probability density functionA number; and discretizing the Gaussian distribution of each position of the Gaussian density map to obtain the classification characteristic matrix.
Compared with the prior art, the wireless communication intelligent gas meter controller and the control method thereof provided by the application acquire gas pressure values at a plurality of preset time points in a preset time period; and adopting an artificial intelligence technology based on deep learning to excavate implicit characteristic information of the gas pressure value and fully express time sequence change characteristics of the gas pressure value so as to accurately detect gas leakage, thereby avoiding safety accidents caused by gas leakage and ensuring the use safety of gas.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is an application scenario diagram of a wireless communication intelligent gas meter controller according to an embodiment of the application;
FIG. 2 is a block diagram of a wireless communication intelligent gas meter controller according to an embodiment of the present application;
FIG. 3 is a block diagram of the pressure time sequence variation feature extraction module in the wireless communication intelligent gas meter controller according to an embodiment of the application;
FIG. 4 is a block diagram of the Gaussian enhancement module in the wireless communication intelligent gas meter controller according to an embodiment of the application;
FIG. 5 is a block diagram of the gas leak detection module in the wireless communication intelligent gas meter controller according to an embodiment of the application;
FIG. 6 is a flow chart of a method for controlling a wireless communication intelligent gas meter according to an embodiment of the application;
fig. 7 is a schematic diagram of a system architecture of a wireless communication intelligent gas meter control method according to an embodiment of the application.
Detailed Description
The following description of the technical solutions according to the embodiments of the present application will be given with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Unless defined otherwise, all technical and scientific terms used in the embodiments of the application have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the present application is for the purpose of describing particular embodiments only and is not intended to limit the scope of the present application.
In describing embodiments of the present application, unless otherwise indicated and limited thereto, the term "connected" should be construed broadly, for example, it may be an electrical connection, or may be a communication between two elements, or may be a direct connection, or may be an indirect connection via an intermediate medium, and it will be understood by those skilled in the art that the specific meaning of the term may be interpreted according to circumstances.
It should be noted that, the term "first\second\third" related to the embodiment of the present application is merely to distinguish similar objects, and does not represent a specific order for the objects, it is to be understood that "first\second\third" may interchange a specific order or sequence where allowed. It is to be understood that the "first\second\third" distinguishing objects may be interchanged where appropriate such that embodiments of the application described herein may be practiced in sequences other than those illustrated or described herein.
As described above, the main function of the existing intelligent gas meter or the traditional gas meter is gas metering and collecting, and the gas meter and the gas cooking bench are connected for a long time through the gas pipeline, so that the gas pipeline of the gas cooking bench always has gas pressure, gas leakage is easy to cause, and unsafe hidden danger exists. Therefore, a wireless communication intelligent gas meter controller is expected to automatically detect gas leakage and ensure the safety of gas use.
Accordingly, in order to effectively perform gas leakage detection, the gas pressure value needs to be monitored in real time, considering that the gas pressure exists in the gas pipeline of the gas cooking bench all the time, but hysteresis of gas leakage detection is easily caused in the gas pressure value monitoring process, so that gas leakage is caused. Based on the above, in the technical scheme of the application, the time sequence change of the gas pressure value is expected to be analyzed so as to evaluate the time sequence change trend of the gas pressure value, thereby accurately detecting and judging whether the gas leaks or not. However, since the time sequence variation information of the gas pressure value is small-scale fine hidden variation characteristic information, capturing and extracting are difficult to carry out in a traditional mode, so that the sensitivity to the time sequence variation condition of the gas pressure value is low, and the accuracy of gas leakage detection is affected. Therefore, in this process, it is difficult to fully express the time sequence variation characteristics of the gas pressure value so as to accurately perform gas leakage detection, thereby avoiding safety accidents caused by gas leakage and ensuring the use safety of the gas.
In recent years, deep learning and neural networks have been widely used in the fields of computer vision, natural language processing, text signal processing, and the like. The development of deep learning and neural networks provides new solutions and schemes for mining time sequence change characteristic information of the gas pressure values.
Specifically, in the technical scheme of the application, first, gas pressure values at a plurality of preset time points in a preset time period are acquired. Next, considering that the gas pressure value has a dynamic change rule in a time dimension, in order to effectively capture change characteristic information of the gas pressure value in the time dimension, in the technical scheme of the application, the gas pressure values at a plurality of preset time points are arranged into gas pressure time sequence input vectors according to the time dimension, so that distribution information of the gas pressure values in time sequence is integrated.
Further, in order to accurately monitor the gas pressure value in real time to accurately evaluate the saturation state of the adsorbent, it is necessary to extract the dynamic variation characteristic of the gas pressure value in the time dimension, and considering that the variation information of the gas pressure value in the time dimension is weak, the weak variation characteristic is small-scale variation characteristic information relative to the gas pressure value, if the time-series dynamic variation characteristic of the gas pressure value is extracted only by absolute variation information, the over-fitting is caused, and the small-scale weak variation characteristic of the gas pressure value in the time dimension is difficult to be perceived, so that the accuracy of the subsequent classification is affected.
Based on the above, in the technical scheme of the application, the time sequence change characteristic extraction of the gas pressure value is comprehensively performed by adopting the time sequence relative change characteristic and the absolute change characteristic of the gas pressure value. Specifically, first, the difference between the gas pressure values at every adjacent two positions in the gas pressure timing input vector is calculated to obtain a gas pressure variation timing input vector. Then, considering that the correlation relation between the time sequence relative change characteristic and the time sequence absolute change characteristic of the gas pressure value is related to the time sequence change of the gas pressure, in order to fully explore the time sequence change rule of the gas pressure value in the time dimension so as to accurately monitor gas leakage, in the technical scheme of the application, the gas pressure time sequence input vector and the gas pressure change time sequence input vector are further cascaded so as to obtain a gas pressure time sequence dynamic-static input vector, which is beneficial to fully expressing the time sequence change characteristic of the gas pressure value subsequently.
Then, the gas pressure value exhibits different time-series variation characteristics at different time period spans within the predetermined period of time, taking into account that it has a fluctuation and uncertainty in the time dimension. Therefore, in the technical scheme of the application, in order to fully express the time sequence change characteristic of the gas pressure value, the gas pressure time sequence dynamic-static input vector is further passed through a time sequence characteristic extractor comprising a first convolution layer and a second convolution layer to obtain the gas pressure time sequence dynamic-static characteristic vector. In particular, the first convolution layer and the second convolution layer adopt one-dimensional convolution kernels with different scales to perform feature mining of the dynamic-static input vector of the gas pressure time sequence, so as to extract multi-scale neighborhood correlation characteristics of dynamic-static multi-dimensional data information of the gas pressure value under different time spans, namely multi-scale time sequence change feature information of the gas pressure value.
Further, it is also considered that since the time-series dynamic change of the gas pressure value is not obvious in the actual monitoring process, it is desirable to perform the feature expression enhancement of the gas pressure time-series dynamic-static feature vector after it is obtained. It should be understood that, as a learning target of the neural network model, the gaussian density map may represent a joint distribution in the case where a plurality of feature values constitute an overall distribution due to probability density thereof, that is, a feature distribution is taken as a priori distribution, and probability density under the influence of correlation with other a priori distribution positions at each a priori distribution position is obtained as a posterior distribution, thereby describing the feature distribution more accurately in a higher dimension. Therefore, in the technical scheme of the application, the multi-scale time sequence change characteristic information of the gas pressure value can be subjected to data enhancement through the prior distribution, namely the Gaussian distribution, of the gas pressure value, namely, the characteristic data enhancement is performed on the gas pressure time sequence dynamic-static characteristic vector by using a Gaussian density chart so as to obtain a classification characteristic matrix. That is, in order to enhance the richness of the feature expression, feature level data enhancement is performed on the gas pressure time sequence dynamic-static feature vector with gaussian distribution as a priori knowledge to obtain the classification feature matrix.
And then, further carrying out classification processing on the classification characteristic matrix in a classifier to obtain a classification result for indicating whether gas leakage exists. That is, in the technical solution of the present application, the labels of the classifier include that there is gas leakage (first label) and that there is no gas leakage (second label), wherein the classifier determines to which classification label the classification feature matrix belongs through a soft maximum function. It should be noted that the first tag p1 and the second tag p2 do not include a manually set concept, and in fact, during the training process, the computer model does not have a concept of "whether there is gas leakage", which is only two kinds of classification tags, and the probability that the output feature is under the two classification tags, that is, the sum of the probabilities of p1 and p2 is one. Therefore, the classification result of whether the gas leakage exists is actually converted into the class probability distribution conforming to the two classes of the natural law through classifying the tag, and the physical meaning of the natural probability distribution of the tag is essentially used instead of the language text meaning of whether the gas leakage exists. It should be understood that, in the technical solution of the present application, the classification label of the classifier is a detection judgment label for whether there is gas leakage, so after the classification result is obtained, gas leakage detection can be performed based on the classification result, thereby avoiding safety accidents caused by gas leakage.
In particular, in the technical solution of the present application, when the gas pressure time series dynamic-static input vector is passed through the time series feature extractor including the first convolution layer and the second convolution layer to obtain the gas pressure time series dynamic-static feature vector, the gas pressure time series dynamic-static feature vector has a correlation feature of a pressure absolute value and a pressure variation value in addition to a multi-scale time series correlation feature including the pressure absolute value and the pressure trend value, in the vicinity of a cascade position of the gas pressure time series input vector and the gas pressure variation time series input vector, taking into consideration that the gas pressure time series dynamic-static input vector is obtained by cascading the gas pressure time series input vector and the gas pressure variation time series input vector. Further, in order to enhance the richness of feature expression, feature level data enhancement is performed on the gas pressure time sequence dynamic-static feature vector by taking Gaussian distribution as priori knowledge, however, the local distribution of the classification feature matrix is difficult to be consistent, the regularization degree of the overall feature distribution of the classification feature matrix is low, and therefore the classification accuracy of the classification feature matrix is affected.
Based on the above, the applicant of the present application performs gaussian probability density parameter quadratic regularization of the manifold curved surface on the classification feature matrix M, specifically expressed as:
m' i,j ＝(μσ)m i,j 2 +m i,j μ+(m i,j -σ)μ 2
wherein μ and σ are the eigenvalue set m i,j E means and standard deviation of M, and M' i,j Is the eigenvalue of the (i, j) th position of the optimized classification eigenvalue matrix M'.
Specifically, in order to solve the problem of irregular distribution of high-dimensional feature distribution of the feature set of the classification feature matrix M in the associated and fused high-dimensional feature space, secondary regularization of each feature value of the classification feature matrix M is performed by using feature values for likelihood of gaussian probability density parameters of regression probability distribution of a decoder, so that smooth constraint of feature values is performed on equidistant distribution in a parameter space of gaussian probability density parameters based on target regression probability, and regularized reformation of an original probability density likelihood function expressed by a manifold curved surface of the high-dimensional feature in the parameter space is obtained, thereby improving regularity of feature distribution of the optimized classification feature matrix M ', and improving accuracy of classification judgment of the optimized classification feature matrix M' by a classifier. Therefore, the gas leakage detection can be accurately carried out, so that safety accidents caused by gas leakage are avoided, and the use safety of the gas is ensured.
Fig. 1 is an application scenario diagram of a wireless communication intelligent gas meter controller according to an embodiment of the application. As shown in fig. 1, in the application scenario, first, gas pressure values (e.g., C as illustrated in fig. 1) at a plurality of predetermined time points within a predetermined period of time are acquired; then, the acquired gas pressure value is input to a server (e.g., S as illustrated in fig. 1) in which a wireless communication intelligent gas meter control algorithm is deployed, wherein the server is capable of processing the gas pressure value based on the wireless communication intelligent gas meter control algorithm to generate a classification result for indicating whether or not there is gas leakage.
Having described the basic principles of the present application, various non-limiting embodiments of the present application will now be described in detail with reference to the accompanying drawings.
In one embodiment of the present application, fig. 2 is a block diagram of a wireless communication intelligent gas meter controller according to an embodiment of the present application. As shown in fig. 2, a wireless communication intelligent gas meter controller 100 according to an embodiment of the present application includes: the gas pressure acquisition module 110 is configured to acquire gas pressure values at a plurality of predetermined time points within a predetermined time period; the pressure timing distribution module 120 is configured to arrange the gas pressure values at the plurality of predetermined time points into a gas pressure timing input vector according to a time dimension; the pressure change module 130 is configured to calculate a difference value between the gas pressure values of every two adjacent positions in the gas pressure time sequence input vector to obtain a gas pressure change time sequence input vector; the pressure dynamic and static information fusion module 140 is configured to concatenate the gas pressure time sequence input vector and the gas pressure change time sequence input vector to obtain a gas pressure time sequence dynamic and static input vector; a pressure time sequence change feature extraction module 150, configured to pass the gas pressure time sequence dynamic-static input vector through a time sequence feature extractor comprising a first convolution layer and a second convolution layer to obtain a gas pressure time sequence dynamic-static feature vector; the gaussian enhancement module 160 is configured to perform feature level data enhancement on the gas pressure time sequence dynamic-static feature vector by using a gaussian density chart to obtain a classification feature matrix; the feature optimization module 170 is configured to perform feature distribution optimization on the classification feature matrix to obtain an optimized classification feature matrix; and a gas leakage detection module 180, configured to pass the optimized classification feature matrix through a classifier to obtain a classification result, where the classification result is used to indicate whether there is gas leakage.
Specifically, in the embodiment of the present application, the gas pressure acquisition module 110 is configured to acquire gas pressure values at a plurality of predetermined time points within a predetermined time period. As described above, the main function of the existing intelligent gas meter or the traditional gas meter is gas metering and collecting, and the gas meter and the gas cooking bench are connected for a long time through the gas pipeline, so that the gas pipeline of the gas cooking bench always has gas pressure, gas leakage is easy to cause, and unsafe hidden danger exists. Therefore, a wireless communication intelligent gas meter controller is expected to automatically detect gas leakage and ensure the safety of gas use.
Accordingly, in order to effectively perform gas leakage detection, the gas pressure value needs to be monitored in real time, considering that the gas pressure exists in the gas pipeline of the gas cooking bench all the time, but hysteresis of gas leakage detection is easily caused in the gas pressure value monitoring process, so that gas leakage is caused. Based on the above, in the technical scheme of the application, the time sequence change of the gas pressure value is expected to be analyzed so as to evaluate the time sequence change trend of the gas pressure value, thereby accurately detecting and judging whether the gas leaks or not. However, since the time sequence variation information of the gas pressure value is small-scale fine hidden variation characteristic information, capturing and extracting are difficult to carry out in a traditional mode, so that the sensitivity to the time sequence variation condition of the gas pressure value is low, and the accuracy of gas leakage detection is affected. Therefore, in this process, it is difficult to fully express the time sequence variation characteristics of the gas pressure value so as to accurately perform gas leakage detection, thereby avoiding safety accidents caused by gas leakage and ensuring the use safety of the gas.
In recent years, deep learning and neural networks have been widely used in the fields of computer vision, natural language processing, text signal processing, and the like. The development of deep learning and neural networks provides new solutions and schemes for mining time sequence change characteristic information of the gas pressure values.
Specifically, in the technical scheme of the application, first, gas pressure values at a plurality of preset time points in a preset time period are acquired.
Specifically, in the embodiment of the present application, the pressure timing distribution module 120 is configured to arrange the gas pressure values at the plurality of predetermined time points into a gas pressure timing input vector according to a time dimension. Next, considering that the gas pressure value has a dynamic change rule in a time dimension, in order to effectively capture change characteristic information of the gas pressure value in the time dimension, in the technical scheme of the application, the gas pressure values at a plurality of preset time points are arranged into gas pressure time sequence input vectors according to the time dimension, so that distribution information of the gas pressure values in time sequence is integrated.
Specifically, in the embodiment of the present application, the pressure variation module 130 is configured to calculate a difference between the gas pressure values of each two adjacent positions in the gas pressure time sequence input vector to obtain a gas pressure variation time sequence input vector. Further, in order to accurately monitor the gas pressure value in real time to accurately evaluate the saturation state of the adsorbent, it is necessary to extract the dynamic variation characteristic of the gas pressure value in the time dimension, and considering that the variation information of the gas pressure value in the time dimension is weak, the weak variation characteristic is small-scale variation characteristic information relative to the gas pressure value, if the time-series dynamic variation characteristic of the gas pressure value is extracted only by absolute variation information, the time-series dynamic variation characteristic of the gas pressure value will not only cause overfitting, but also make the small-scale weak variation characteristic of the gas pressure value in the time dimension difficult to be perceived, thereby affecting the accuracy of subsequent classification.
Based on the above, in the technical scheme of the application, the time sequence change characteristic extraction of the gas pressure value is comprehensively performed by adopting the time sequence relative change characteristic and the absolute change characteristic of the gas pressure value. Specifically, first, the difference between the gas pressure values at every adjacent two positions in the gas pressure timing input vector is calculated to obtain a gas pressure variation timing input vector.
Specifically, in the embodiment of the present application, the pressure dynamic and static information fusion module 140 is configured to concatenate the gas pressure time sequence input vector and the gas pressure change time sequence input vector to obtain a gas pressure time sequence dynamic and static input vector. Next, it is considered that there is a correlation with respect to the timing change of the gas pressure between the timing relative change characteristic and the timing absolute change characteristic due to the gas pressure value. Therefore, in order to fully explore the time sequence change rule of the gas pressure value in the time dimension so as to accurately monitor gas leakage, in the technical scheme of the application, the gas pressure time sequence input vector and the gas pressure change time sequence input vector are further cascaded to obtain a gas pressure time sequence dynamic-static input vector, which is beneficial to fully expressing the time sequence change characteristics of the gas pressure value subsequently.
The pressure dynamic and static information fusion module 140 is configured to: cascading the gas pressure time sequence input vector and the gas pressure change time sequence input vector by using the following cascading formula to obtain a gas pressure time sequence dynamic-static input vector; wherein, the cascade formula is:
V c ＝Concat[V 1 ，V 2 ]
wherein V is 1 ，V 2 Representing the gas pressure time sequence input vector and the gas pressure change time sequence input vector, concat [. Cndot.]Representing a cascade function, V c Representing the gas pressure time sequence dynamic-static input vector.
Specifically, in the embodiment of the present application, the pressure time sequence variation feature extraction module 150 is configured to pass the gas pressure time sequence dynamic-static input vector through a time sequence feature extractor including a first convolution layer and a second convolution layer to obtain a gas pressure time sequence dynamic-static feature vector. Then, the gas pressure value exhibits different time-series variation characteristics at different time period spans within the predetermined period of time, taking into account that it has a fluctuation and uncertainty in the time dimension. Therefore, in the technical scheme of the application, in order to fully express the time sequence change characteristic of the gas pressure value, the gas pressure time sequence dynamic-static input vector is further passed through a time sequence characteristic extractor comprising a first convolution layer and a second convolution layer to obtain the gas pressure time sequence dynamic-static characteristic vector. In particular, the first convolution layer and the second convolution layer adopt one-dimensional convolution kernels with different scales to perform feature mining of the dynamic-static input vector of the gas pressure time sequence, so as to extract multi-scale neighborhood correlation characteristics of dynamic-static multi-dimensional data information of the gas pressure value under different time spans, namely multi-scale time sequence change feature information of the gas pressure value.
Fig. 3 is a block diagram of the pressure time sequence variation feature extraction module in the wireless communication intelligent gas meter controller according to the embodiment of the application, as shown in fig. 3, the pressure time sequence variation feature extraction module 150 includes: a first scale feature extraction unit 151, configured to input the gas pressure time sequence dynamic-static input vector into a first convolution layer of the time sequence feature extractor to obtain a first scale gas pressure feature vector, where the first convolution layer has a one-dimensional convolution kernel of a first scale; a second scale feature extraction unit 152 for inputting the gas pressure time sequence dynamic-static input vector into a second convolution layer of the time sequence feature extractor to obtain a second scale gas pressure feature vector, wherein the second convolution layer has a one-dimensional convolution kernel of a second scale, and the first scale is different from the second scale; and a multi-scale cascade unit 153, configured to cascade the first-scale gas pressure feature vector and the second-scale gas pressure feature vector to obtain the gas pressure time sequence dynamic-static feature vector.
Specifically, in the embodiment of the present application, the gaussian enhancement module 160 is configured to perform feature level data enhancement on the gas pressure time sequence dynamic-static feature vector by using a gaussian density map to obtain a classification feature matrix. Further, it is also considered that since the time-series dynamic change of the gas pressure value is not obvious in the actual monitoring process, it is desirable to perform the feature expression enhancement of the gas pressure time-series dynamic-static feature vector after it is obtained. It should be understood that, as a learning target of the neural network model, the gaussian density map may represent a joint distribution in the case where a plurality of feature values constitute an overall distribution due to probability density thereof, that is, a feature distribution is taken as a priori distribution, and probability density under the influence of correlation with other a priori distribution positions at each a priori distribution position is obtained as a posterior distribution, thereby describing the feature distribution more accurately in a higher dimension.
Therefore, in the technical scheme of the application, the multi-scale time sequence change characteristic information of the gas pressure value can be subjected to data enhancement through the prior distribution, namely the Gaussian distribution, of the gas pressure value, namely, the characteristic data enhancement is performed on the gas pressure time sequence dynamic-static characteristic vector by using a Gaussian density chart so as to obtain a classification characteristic matrix. That is, in order to enhance the richness of the feature expression, feature level data enhancement is performed on the gas pressure time sequence dynamic-static feature vector with gaussian distribution as a priori knowledge to obtain the classification feature matrix.
Fig. 4 is a block diagram of the gaussian enhancement module in the wireless communication intelligent gas meter controller according to an embodiment of the present application, as shown in fig. 4, the gaussian enhancement module 160 includes: a gaussian density map construction unit 161 for constructing a gaussian density map of the gas pressure time-series dynamic-static feature vector in a gaussian formula using the gaussian density map;
wherein, the Gaussian formula is:
wherein mu μ Representing the dynamic-static characteristic vector of the gas pressure time sequence and sigma σ The value of each position of (c) represents the variance between the characteristic values of the respective positions in the gas pressure time series dynamic-static characteristic vector, x represents the variable of the gaussian density map, Representing a gaussian probability density function; and a gaussian discretization unit 162, configured to discretize a gaussian distribution of each position of the gaussian density map to obtain the classification feature matrix.
It should be understood that, as a learning target of the neural network model, the gaussian density map may represent a joint distribution in the case where a plurality of feature values constitute an overall distribution due to probability density thereof, that is, a feature distribution is taken as a priori distribution, and probability density under the influence of correlation with other a priori distribution positions at each a priori distribution position is obtained as a posterior distribution, thereby describing the feature distribution more accurately in a higher dimension.
Specifically, in the embodiment of the present application, the feature optimization module 170 is configured to perform feature distribution optimization on the classification feature matrix to obtain an optimized classification feature matrix. In particular, in the technical solution of the present application, when the gas pressure time series dynamic-static input vector is passed through the time series feature extractor including the first convolution layer and the second convolution layer to obtain the gas pressure time series dynamic-static feature vector, the gas pressure time series dynamic-static feature vector has a correlation feature of a pressure absolute value and a pressure variation value in addition to a multi-scale time series correlation feature including the pressure absolute value and the pressure trend value, in the vicinity of a cascade position of the gas pressure time series input vector and the gas pressure variation time series input vector, taking into consideration that the gas pressure time series dynamic-static input vector is obtained by cascading the gas pressure time series input vector and the gas pressure variation time series input vector. Further, in order to enhance the richness of feature expression, feature level data enhancement is performed on the gas pressure time sequence dynamic-static feature vector by taking Gaussian distribution as priori knowledge, however, the local distribution of the classification feature matrix is difficult to be consistent, the regularization degree of the overall feature distribution of the classification feature matrix is low, and therefore the classification accuracy of the classification feature matrix is affected.
Based on the above, the applicant of the present application performs gaussian probability density parameter quadratic regularization of the manifold curved surface on the classification feature matrix M, specifically expressed as: the feature optimization module 170 is configured to: carrying out feature distribution optimization on the classification feature matrix by using the following optimization formula to obtain the optimized classification feature matrix; wherein, the optimization formula is:
m' i,j ＝(μσ)m i,j 2 +m i,j μ+(m i,j -σ)μ 2
wherein m is i,j Is the eigenvalue of the (i, j) th position of the classification characteristic matrix, mu and sigma are the mean and standard deviation of the respective position eigenvalue sets of the classification characteristic matrix, and m' i,j Is the eigenvalue of the (i, j) th position of the optimized classification eigenvalue matrix.
Specifically, in order to solve the problem of irregular distribution of high-dimensional feature distribution of the feature set of the classification feature matrix M in the associated and fused high-dimensional feature space, secondary regularization of each feature value of the classification feature matrix M is performed by using feature values for likelihood of gaussian probability density parameters of regression probability distribution of a decoder, so that smooth constraint of feature values is performed on equidistant distribution in a parameter space of gaussian probability density parameters based on target regression probability, and regularized reformation of an original probability density likelihood function expressed by a manifold curved surface of the high-dimensional feature in the parameter space is obtained, thereby improving regularity of feature distribution of the optimized classification feature matrix M ', and improving accuracy of classification judgment of the optimized classification feature matrix M' by a classifier. Therefore, the gas leakage detection can be accurately carried out, so that safety accidents caused by gas leakage are avoided, and the use safety of the gas is ensured.
Specifically, in the embodiment of the present application, the gas leakage detection module 180 is configured to pass the optimized classification feature matrix through a classifier to obtain a classification result, where the classification result is used to indicate whether there is gas leakage. And then, further carrying out classification processing on the classification characteristic matrix in a classifier to obtain a classification result for indicating whether gas leakage exists. That is, in the technical solution of the present application, the labels of the classifier include that there is gas leakage (first label) and that there is no gas leakage (second label), wherein the classifier determines to which classification label the classification feature matrix belongs through a soft maximum function. It should be noted that the first tag p1 and the second tag p2 do not include a manually set concept, and in fact, during the training process, the computer model does not have a concept of "whether there is gas leakage", which is only two kinds of classification tags, and the probability that the output feature is under the two classification tags, that is, the sum of the probabilities of p1 and p2 is one.
Therefore, the classification result of whether the gas leakage exists is actually converted into the class probability distribution conforming to the two classes of the natural law through classifying the tag, and the physical meaning of the natural probability distribution of the tag is essentially used instead of the language text meaning of whether the gas leakage exists. It should be understood that, in the technical solution of the present application, the classification label of the classifier is a detection judgment label for whether there is gas leakage, so after the classification result is obtained, gas leakage detection can be performed based on the classification result, thereby avoiding safety accidents caused by gas leakage.
Fig. 5 is a block diagram of the gas leakage detection module in the wireless communication intelligent gas meter controller according to an embodiment of the present application, as shown in fig. 5, the gas leakage detection module 180 includes: a matrix expansion unit 181, configured to expand the optimized classification feature matrix into classification feature vectors according to row vectors or column vectors; a full-connection encoding unit 182, configured to perform full-connection encoding on the classification feature vector by using multiple full-connection layers of the classifier to obtain an encoded classification feature vector; and a classification unit 183, configured to pass the encoded classification feature vector through a Softmax classification function of the classifier to obtain the classification result.
In summary, the wireless communication intelligent gas meter controller 100 according to the embodiment of the present application is illustrated, which obtains gas pressure values at a plurality of predetermined time points within a predetermined period of time; and adopting an artificial intelligence technology based on deep learning to excavate implicit characteristic information of the gas pressure value and fully express time sequence change characteristics of the gas pressure value so as to accurately detect gas leakage, thereby avoiding safety accidents caused by gas leakage and ensuring the use safety of gas.
In one embodiment of the present application, fig. 6 is a flowchart of a method for controlling a wireless communication intelligent gas meter according to an embodiment of the present application. As shown in fig. 6, a wireless communication intelligent gas meter control method according to an embodiment of the present application includes: 210, acquiring gas pressure values at a plurality of preset time points in a preset time period; 220, arranging the gas pressure values of the plurality of preset time points into gas pressure time sequence input vectors according to a time dimension; 230, calculating the difference value between the gas pressure values of every two adjacent positions in the gas pressure time sequence input vector to obtain a gas pressure change time sequence input vector; 240, cascading the gas pressure time sequence input vector and the gas pressure change time sequence input vector to obtain a gas pressure time sequence dynamic-static input vector; 250, passing the gas pressure time sequence dynamic-static input vector through a time sequence feature extractor comprising a first convolution layer and a second convolution layer to obtain a gas pressure time sequence dynamic-static feature vector; 260, performing feature data enhancement on the gas pressure time sequence dynamic-static feature vector by using a Gaussian density chart to obtain a classification feature matrix; 270, performing feature distribution optimization on the classification feature matrix to obtain an optimized classification feature matrix; and 280, passing the optimized classification feature matrix through a classifier to obtain a classification result, wherein the classification result is used for indicating whether gas leakage exists or not.
Fig. 7 is a schematic diagram of a system architecture of a wireless communication intelligent gas meter control method according to an embodiment of the application. As shown in fig. 7, in the system architecture of the wireless communication intelligent gas meter control method, first, gas pressure values at a plurality of predetermined time points within a predetermined time period are obtained; then, arranging the gas pressure values of the plurality of preset time points into gas pressure time sequence input vectors according to a time dimension; then, calculating the difference value between the gas pressure values of every two adjacent positions in the gas pressure time sequence input vector to obtain a gas pressure change time sequence input vector; then, cascading the gas pressure time sequence input vector and the gas pressure change time sequence input vector to obtain a gas pressure time sequence dynamic-static input vector; then, the gas pressure time sequence dynamic-static input vector is passed through a time sequence feature extractor comprising a first convolution layer and a second convolution layer to obtain a gas pressure time sequence dynamic-static feature vector; then, using a Gaussian density chart to carry out characteristic data enhancement on the dynamic-static characteristic vector of the gas pressure time sequence so as to obtain a classification characteristic matrix; then, carrying out feature distribution optimization on the classification feature matrix to obtain an optimized classification feature matrix; and finally, the optimized classification feature matrix is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating whether gas leakage exists or not.
In a specific example, in the above wireless communication intelligent gas meter control method, concatenating the gas pressure time sequence input vector and the gas pressure change time sequence input vector to obtain a gas pressure time sequence dynamic-static input vector includes: cascading the gas pressure time sequence input vector and the gas pressure change time sequence input vector by using the following cascading formula to obtain a gas pressure time sequence dynamic-static input vector; wherein, the cascade formula is:
V c ＝Concat[V 1 ，V 2 ]
wherein V is 1 ，V 2 Representing the gas pressure time sequence input vector and the gas pressure change time sequence input vector, concat [. Cndot.]Representing a cascade function, V c Representing the gas pressure time sequence dynamic-static input vector.
In a specific example, in the above wireless communication intelligent gas meter control method, the step of passing the gas pressure time sequence dynamic-static input vector through a time sequence feature extractor including a first convolution layer and a second convolution layer to obtain a gas pressure time sequence dynamic-static feature vector includes: inputting the gas pressure time sequence dynamic-static input vector into a first convolution layer of the time sequence feature extractor to obtain a first scale gas pressure feature vector, wherein the first convolution layer is provided with a one-dimensional convolution kernel of a first scale; inputting the gas pressure time sequence dynamic-static input vector into a second convolution layer of the time sequence feature extractor to obtain a second scale gas pressure feature vector, wherein the second convolution layer is provided with a one-dimensional convolution kernel of a second scale, and the first scale is different from the second scale; and cascading the first-scale gas pressure feature vector and the second-scale gas pressure feature vector to obtain the gas pressure time sequence dynamic-static feature vector.
In a specific example, in the above wireless communication intelligent gas meter control method, performing feature data enhancement on the gas pressure time sequence dynamic-static feature vector by using a gaussian density chart to obtain a classification feature matrix, including: constructing a gaussian density map of the gas pressure time sequence dynamic-static characteristic vector in the following gaussian formula by using the gaussian density map;
wherein, the Gaussian formula is:
wherein mu u Representing the dynamic-static characteristic vector of the gas pressure time sequence and sigma σ The value of each position of (c) represents the variance between the characteristic values of the respective positions in the gas pressure time series dynamic-static characteristic vector, x represents the variable of the gaussian density map,representing a gaussian probability density function; and discretizing the Gaussian distribution of each position of the Gaussian density map to obtain the classification characteristic matrix.
In a specific example, in the above wireless communication intelligent gas meter control method, performing feature distribution optimization on the classification feature matrix to obtain an optimized classification feature matrix includes: carrying out feature distribution optimization on the classification feature matrix by using the following optimization formula to obtain the optimized classification feature matrix; wherein, the optimization formula is:
m' i,j ＝μ(μσ)m i,j 2 +m i,j μ+(m i,j -σ)μ 2
Wherein m is i,j Is the eigenvalue of the (i, j) th position of the classification characteristic matrix, mu and sigma are the mean and standard deviation of the respective position eigenvalue sets of the classification characteristic matrix, and m' i,j Is the eigenvalue of the (i, j) th position of the optimized classification eigenvalue matrix.
In a specific example, in the above wireless communication intelligent gas meter control method, the optimizing classification feature matrix is passed through a classifier to obtain a classification result, where the classification result is used to indicate whether there is gas leakage, and the method includes: expanding the optimized classification feature matrix into classification feature vectors according to row vectors or column vectors; performing full-connection coding on the classification feature vectors by using a plurality of full-connection layers of the classifier to obtain coded classification feature vectors; and passing the coding classification feature vector through a Softmax classification function of the classifier to obtain the classification result.
It will be appreciated by those skilled in the art that the specific operations of the respective steps in the above-described wireless communication intelligent gas meter control method have been described in detail in the above description of the wireless communication intelligent gas meter controller with reference to fig. 1 to 5, and thus, repetitive descriptions thereof will be omitted.
In one embodiment of the application, there is also provided a computer program product comprising instructions which, when executed, cause an apparatus to perform operations corresponding to the above-described method.
In one embodiment of the present application, there is also provided a computer-readable storage medium storing a computer program for executing the above-described method.
It should be appreciated that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the forms of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects may be utilized. Furthermore, the computer program product may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
Methods, systems, and computer program products of embodiments of the present application are described in the flow diagrams and/or block diagrams. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The basic principles of the present application have been described above in connection with specific embodiments, however, it should be noted that the advantages, benefits, effects, etc. mentioned in the present application are merely examples and not intended to be limiting, and these advantages, benefits, effects, etc. are not to be considered as essential to the various embodiments of the present application. Furthermore, the specific details disclosed herein are for purposes of illustration and understanding only, and are not intended to be limiting, as the application is not necessarily limited to practice with the above described specific details.
The block diagrams of the devices, apparatuses, devices, systems referred to in the present application are only illustrative examples and are not intended to require or imply that the connections, arrangements, configurations must be made in the manner shown in the block diagrams. As will be appreciated by one of skill in the art, the devices, apparatuses, devices, systems may be connected, arranged, configured in any manner. Words such as "including," "comprising," "having," and the like are words of openness and mean "including but not limited to," and are used interchangeably therewith. The terms "or" and "as used herein refer to and are used interchangeably with the term" and/or "unless the context clearly indicates otherwise. The term "such as" as used herein refers to, and is used interchangeably with, the phrase "such as, but not limited to.
It is also noted that in the apparatus, devices and methods of the present application, the components or steps may be disassembled and/or assembled. Such decomposition and/or recombination should be considered as equivalent aspects of the present application.
The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the application. Thus, the present application is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or terminal device comprising the element.
The foregoing description has been presented for purposes of illustration and description. Furthermore, this description is not intended to limit embodiments of the application to the form disclosed herein. Although a number of example aspects and embodiments have been discussed above, a person of ordinary skill in the art will recognize certain variations, modifications, alterations, additions, and subcombinations thereof.

Claims (10)

1. A wireless communication intelligent gas meter controller, comprising:
the gas pressure acquisition module is used for acquiring gas pressure values of a plurality of preset time points in a preset time period;
the pressure time sequence distribution module is used for arranging the gas pressure values of the plurality of preset time points into gas pressure time sequence input vectors according to the time dimension;
the pressure change module is used for calculating the difference value between the gas pressure values of every two adjacent positions in the gas pressure time sequence input vector to obtain a gas pressure change time sequence input vector;
the pressure dynamic and static information fusion module is used for cascading the gas pressure time sequence input vector and the gas pressure change time sequence input vector to obtain a gas pressure time sequence dynamic and static input vector;
the pressure time sequence change feature extraction module is used for enabling the gas pressure time sequence dynamic-static input vector to pass through a time sequence feature extractor comprising a first convolution layer and a second convolution layer so as to obtain a gas pressure time sequence dynamic-static feature vector;
the Gaussian enhancement module is used for carrying out characteristic data enhancement on the gas pressure time sequence dynamic-static characteristic vector by using a Gaussian density chart so as to obtain a classification characteristic matrix;
The feature optimization module is used for carrying out feature distribution optimization on the classification feature matrix to obtain an optimized classification feature matrix;
and the fuel gas leakage detection module is used for enabling the optimized classification feature matrix to pass through a classifier to obtain a classification result, wherein the classification result is used for indicating whether fuel gas leakage exists or not.
2. The wireless communication intelligent gas meter controller according to claim 1, wherein the pressure dynamic and static information fusion module is configured to: cascading the gas pressure time sequence input vector and the gas pressure change time sequence input vector by using the following cascading formula to obtain a gas pressure time sequence dynamic-static input vector;
wherein, the cascade formula is:
V c ＝Concat[V 1 ，V 2 ]
wherein V is 1 ，V 2 Representing the gas pressure time sequence input vector and the gas pressure change time sequence input vector, concat [. Cndot.]Representing a cascade function, V c Representing the gas pressure time sequence dynamic-static input vector.
3. The wireless communication intelligent gas meter controller according to claim 2, wherein the pressure time sequence variation feature extraction module comprises:
a first scale feature extraction unit, configured to input the gas pressure time sequence dynamic-static input vector into a first convolution layer of the time sequence feature extractor to obtain a first scale gas pressure feature vector, where the first convolution layer has a one-dimensional convolution kernel of a first scale;
A second scale feature extraction unit configured to input the gas pressure time sequence dynamic-static input vector into a second convolution layer of the time sequence feature extractor to obtain a second scale gas pressure feature vector, where the second convolution layer has a one-dimensional convolution kernel of a second scale, and the first scale is different from the second scale;
and the multi-scale cascading unit is used for cascading the first-scale gas pressure characteristic vector and the second-scale gas pressure characteristic vector to obtain the gas pressure time sequence dynamic-static characteristic vector.
4. The wireless communication intelligent gas meter controller of claim 3, wherein the gaussian enhancement module comprises:
a Gaussian density map construction unit for constructing a Gaussian density map of the gas pressure time-series dynamic-static feature vector in a Gaussian formula using the Gaussian density map;
wherein, the Gaussian formula is:
wherein mu u Representing the dynamic-static characteristic vector of the gas pressure time sequence and sigma σ The value of each position of (c) represents the variance between the characteristic values of the respective positions in the gas pressure time series dynamic-static characteristic vector, x represents the variable of the gaussian density map,representing a gaussian probability density function;
And the Gaussian discretization unit is used for discretizing the Gaussian distribution of each position of the Gaussian density map to obtain the classification characteristic matrix.
5. The wireless communication intelligent gas meter controller of claim 4, wherein the feature optimization module is configured to: carrying out feature distribution optimization on the classification feature matrix by using the following optimization formula to obtain the optimized classification feature matrix;
wherein, the optimization formula is:
m' i,j ＝(μσ)m i,j 2 +m i,j μ+(m i,j -σ)μ 2
wherein mi ,j Is the eigenvalue of the (i, j) th position of the classification characteristic matrix, mu and sigma are the mean and standard deviation of the respective position eigenvalue sets of the classification characteristic matrix, and m' i,j Is the eigenvalue of the (i, j) th position of the optimized classification eigenvalue matrix.
6. The wireless communication intelligent gas meter controller of claim 5, wherein the gas leak detection module comprises:
the matrix unfolding unit is used for unfolding the optimized classification feature matrix into classification feature vectors according to row vectors or column vectors;
the full-connection coding unit is used for carrying out full-connection coding on the classification characteristic vectors by using a plurality of full-connection layers of the classifier so as to obtain coded classification characteristic vectors;
And the classification unit is used for passing the coding classification feature vector through a Softmax classification function of the classifier to obtain the classification result.
7. The control method of the wireless communication intelligent gas meter is characterized by comprising the following steps of:
acquiring gas pressure values at a plurality of preset time points in a preset time period;
arranging the gas pressure values of the plurality of preset time points into gas pressure time sequence input vectors according to the time dimension;
calculating the difference value between the gas pressure values of every two adjacent positions in the gas pressure time sequence input vector to obtain a gas pressure change time sequence input vector;
cascading the gas pressure time sequence input vector and the gas pressure change time sequence input vector to obtain a gas pressure time sequence dynamic-static input vector;
passing the gas pressure time sequence dynamic-static input vector through a time sequence feature extractor comprising a first convolution layer and a second convolution layer to obtain a gas pressure time sequence dynamic-static feature vector;
performing feature data enhancement on the gas pressure time sequence dynamic-static feature vector by using a Gaussian density chart to obtain a classification feature matrix;
performing feature distribution optimization on the classification feature matrix to obtain an optimized classification feature matrix;
And the optimized classification feature matrix passes through a classifier to obtain a classification result, wherein the classification result is used for indicating whether gas leakage exists or not.
8. The method for controlling a wireless communication intelligent gas meter according to claim 7, wherein concatenating the gas pressure timing input vector and the gas pressure variation timing input vector to obtain a gas pressure timing dynamic-static input vector, comprises: cascading the gas pressure time sequence input vector and the gas pressure change time sequence input vector by using the following cascading formula to obtain a gas pressure time sequence dynamic-static input vector;
wherein, the cascade formula is:
V c ＝Concat[V 1 ，V 2 ]
wherein V is 1 ，V 2 Representing the gas pressure time sequence input vector and the gas pressure change time sequence input vector, concat [. Cndot.]Representing a cascade function, V c Representing the gas pressure time sequence dynamic-static input vector.
9. The method of claim 8, wherein passing the gas pressure time sequence dynamic-static input vector through a time sequence feature extractor comprising a first convolution layer and a second convolution layer to obtain a gas pressure time sequence dynamic-static feature vector, comprises:
Inputting the gas pressure time sequence dynamic-static input vector into a first convolution layer of the time sequence feature extractor to obtain a first scale gas pressure feature vector, wherein the first convolution layer is provided with a one-dimensional convolution kernel of a first scale;
inputting the gas pressure time sequence dynamic-static input vector into a second convolution layer of the time sequence feature extractor to obtain a second scale gas pressure feature vector, wherein the second convolution layer is provided with a one-dimensional convolution kernel of a second scale, and the first scale is different from the second scale;
and cascading the first-scale gas pressure characteristic vector and the second-scale gas pressure characteristic vector to obtain the gas pressure time sequence dynamic-static characteristic vector.
10. The method for controlling a wireless communication intelligent gas meter according to claim 9, wherein the feature level data enhancement of the gas pressure time sequence dynamic-static feature vector by using a gaussian density chart to obtain a classification feature matrix comprises:
constructing a gaussian density map of the gas pressure time sequence dynamic-static characteristic vector in the following gaussian formula by using the gaussian density map;
wherein, the Gaussian formula is:
wherein mu u Representing the dynamic-static characteristic vector of the gas pressure time sequence and sigma σ The value of each position of (c) represents the variance between the characteristic values of the respective positions in the gas pressure time series dynamic-static characteristic vector, x represents the variable of the gaussian density map,representing a gaussian probability density function;
and discretizing the Gaussian distribution of each position of the Gaussian density map to obtain the classification characteristic matrix.
CN202310561914.4A 2023-05-18 2023-05-18 Wireless communication intelligent gas meter controller and control method thereof Active CN116597635B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310561914.4A CN116597635B (en) 2023-05-18 2023-05-18 Wireless communication intelligent gas meter controller and control method thereof

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310561914.4A CN116597635B (en) 2023-05-18 2023-05-18 Wireless communication intelligent gas meter controller and control method thereof

Publications (2)

Publication Number Publication Date
CN116597635A true CN116597635A (en) 2023-08-15
CN116597635B CN116597635B (en) 2024-02-23

Family

ID=87595077

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310561914.4A Active CN116597635B (en) 2023-05-18 2023-05-18 Wireless communication intelligent gas meter controller and control method thereof

Country Status (1)

Country Link
CN (1) CN116597635B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116772944A (en) * 2023-08-25 2023-09-19 克拉玛依市燃气有限责任公司 Intelligent monitoring system and method for gas distribution station

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN206248155U (en) * 2016-12-08 2017-06-13 四川海力智能科技股份有限公司 A kind of intelligent gas meter
KR101896015B1 (en) * 2018-01-25 2018-09-06 (주)베스트인포텍 Ai type remote meter reading system
CN208192787U (en) * 2017-07-05 2018-12-07 佛山市顺德区美的电热电器制造有限公司 Steam sprays cooking apparatus
CN115993268A (en) * 2023-03-22 2023-04-21 福建天甫电子材料有限公司 Sampling system and method for anhydrous hydrogen fluoride
CN116025319A (en) * 2023-01-31 2023-04-28 新疆广陆能源科技股份有限公司 Multi-medium thermal fluid operation monitoring system and method thereof

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN206248155U (en) * 2016-12-08 2017-06-13 四川海力智能科技股份有限公司 A kind of intelligent gas meter
CN208192787U (en) * 2017-07-05 2018-12-07 佛山市顺德区美的电热电器制造有限公司 Steam sprays cooking apparatus
KR101896015B1 (en) * 2018-01-25 2018-09-06 (주)베스트인포텍 Ai type remote meter reading system
CN116025319A (en) * 2023-01-31 2023-04-28 新疆广陆能源科技股份有限公司 Multi-medium thermal fluid operation monitoring system and method thereof
CN115993268A (en) * 2023-03-22 2023-04-21 福建天甫电子材料有限公司 Sampling system and method for anhydrous hydrogen fluoride

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116772944A (en) * 2023-08-25 2023-09-19 克拉玛依市燃气有限责任公司 Intelligent monitoring system and method for gas distribution station
CN116772944B (en) * 2023-08-25 2023-12-01 克拉玛依市燃气有限责任公司 Intelligent monitoring system and method for gas distribution station

Also Published As

Publication number Publication date
CN116597635B (en) 2024-02-23

Similar Documents

Publication Publication Date Title
CN104123500B (en) A kind of Android platform malicious application detection method and device based on deep learning
CN108027594A (en) For detecting the abnormal method in water distribution system
CN116086790B (en) Performance detection method and system for high-pressure valve of hydrogen fuel cell
CN116336400B (en) Baseline detection method for oil and gas gathering and transportation pipeline
CN116597635B (en) Wireless communication intelligent gas meter controller and control method thereof
CN111079861A (en) Power distribution network voltage abnormity diagnosis method based on image rapid processing technology
CN113919540A (en) Method for monitoring running state of production process and related equipment
CN117077075A (en) Water quality monitoring system and method for environmental protection
CN115017513A (en) Intelligent contract vulnerability detection method based on artificial intelligence
CN115081641A (en) Model training method, estimation result prediction method, device and storage medium
CN116759053A (en) Medical system prevention and control method and system based on Internet of things system
CN116432184A (en) Malicious software detection method based on semantic analysis and bidirectional coding characterization
Racheal et al. Evaluation of optimized machine learning models for nuclear reactor accident prediction
Zhang et al. An enhanced temporal algorithm-coupled optimized adaptive sparse principal component analysis methodology for fault diagnosis of chemical processes
CN117521063A (en) Malicious software detection method and device based on residual neural network and combined with transfer learning
Lin et al. Feature extraction and sensor selection for NPP initiating event identification
CN117289736A (en) Temperature control method and system for high-temperature anti-corrosion storage tank
Zhang et al. Colour‐patterned fabric‐defect detection using unsupervised and memorial defect‐free features
CN117134958A (en) Information processing method and system for network technology service
CN116624903A (en) Intelligent monitoring method and system for oil smoke pipeline
JP7332190B2 (en) METHOD AND DEVICE FOR PROVIDING MACHINE LEARNING FOUNDATION INFORMATION
CN114565051B (en) Method for testing product classification model based on influence degree of neurons
CN115587358A (en) Binary code similarity detection method and device and storage medium
CN113821571A (en) Food safety relation extraction method based on BERT and improved PCNN
CN115962340B (en) Intelligent fluid control valve and control method thereof

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