CN114352947B - Gas pipeline leakage detection method, system, device and storage medium - Google Patents
Gas pipeline leakage detection method, system, device and storage medium Download PDFInfo
- Publication number
- CN114352947B CN114352947B CN202111494477.6A CN202111494477A CN114352947B CN 114352947 B CN114352947 B CN 114352947B CN 202111494477 A CN202111494477 A CN 202111494477A CN 114352947 B CN114352947 B CN 114352947B
- Authority
- CN
- China
- Prior art keywords
- gas
- sequence
- leakage
- gas pipeline
- training
- 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.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 58
- 238000012549 training Methods 0.000 claims abstract description 118
- 238000013528 artificial neural network Methods 0.000 claims abstract description 38
- 238000000034 method Methods 0.000 claims abstract description 28
- 125000004122 cyclic group Chemical group 0.000 claims abstract description 17
- 238000012545 processing Methods 0.000 claims abstract description 17
- 238000010606 normalization Methods 0.000 claims abstract description 16
- 230000006870 function Effects 0.000 claims description 32
- 230000000306 recurrent effect Effects 0.000 claims description 20
- 238000012360 testing method Methods 0.000 claims description 10
- 230000015654 memory Effects 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 5
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000007689 inspection Methods 0.000 description 13
- 230000009194 climbing Effects 0.000 description 7
- 230000003287 optical effect Effects 0.000 description 6
- 239000013307 optical fiber Substances 0.000 description 6
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000006467 substitution reaction Methods 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000004880 explosion Methods 0.000 description 2
- 238000003331 infrared imaging Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000000191 radiation effect Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Landscapes
- Examining Or Testing Airtightness (AREA)
Abstract
The invention discloses a gas pipeline leakage detection method, a system, a device and a storage medium, wherein the method comprises the following steps: acquiring first data of a preset gas pipeline, wherein the first data comprises pipeline pressure, gas flow and gas concentration; carrying out sequential and normalization processing on the first data to obtain a first sequence, wherein the first sequence comprises a pipeline pressure sequence, a gas flow sequence and a gas concentration sequence; determining a training sample and a corresponding label according to the first sequence and a preset expert scoring model, and further obtaining a training data set according to the training sample and the label; and inputting the training data set into a pre-constructed cyclic neural network for training to obtain a trained gas pipeline leakage identification model, and further identifying and detecting the gas pipeline to be detected according to the gas pipeline leakage identification model. The invention improves the accuracy and the detection efficiency of gas pipeline leakage detection, can accurately position the gas pipeline leakage position, and can be widely applied to the technical field of artificial intelligence.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a gas pipeline leakage detection method, a gas pipeline leakage detection system, a gas pipeline leakage detection device and a storage medium.
Background
With the acceleration of the urban process, the laying and transmission of the gas pipeline become important contents of urban construction. But the safety problems in the operation process of the gas pipeline, such as gas leakage, gas explosion and the like, cause great threat to the social and civil property safety. The existing gas pipeline detection methods comprise an artificial inspection method, an in-pipe intelligent climbing machine detection method, an infrared imaging detection method and a distributed optical fiber detection method.
1) The manual inspection method needs an inspection worker to inspect the gas leakage detector or the leakage detection vehicle along the pipeline laying path regularly, judges whether gas leakage exists or not in various modes such as watching, smelling and listening, and has heavy work and easy occurrence of the condition of leakage detection and false detection.
2) Various sensors are configured on the climbing machine in the intelligent climbing machine detection method in the pipe to form an intelligent climbing machine detection system, the climbing machine can be used for detecting the pressure, the flow, the temperature and the integrity of the pipe wall in the pipe, but the climbing machine is only suitable for the pipes without too many elbows and joints, and the operation of the climbing machine needs to have abundant experience.
3) Infrared imaging. When the pipeline leaks, the temperature field of the soil around the leakage point can change, the geothermal radiation effect around the gas pipeline can be recorded through the infrared remote sensing camera device, and the leakage position can be detected through spectral analysis. The method can accurately locate the leakage point, has higher sensitivity, and is not suitable for the leakage detection of the buried pipeline with deeper depth.
4) A distributed optical fiber leak detection method. An optical cable is laid side by side along the pipeline near the pipeline, or a communication optical cable laid along the same ditch as the pipeline can be utilized, when the pipeline leaks according to the interference principle of the optical fiber, the test optical fiber near the pipeline leakage point is caused to generate stress strain, so that the optical wave phase modulation at the position is caused, and the optical wave with the phase modulation is transmitted to the two ends of the sensor along the optical fiber. The two photoelectric detection sensors are used for detecting the time difference of the change of the interference signals at the two ends, so that the position of the leakage can be accurately calculated, but the detection method has higher cost.
From the above, the gas pipeline detection method in the prior art has the disadvantages of high cost, low accuracy, use field Jing Shouxian and the like.
Disclosure of Invention
The present invention aims to solve at least one of the technical problems existing in the prior art to a certain extent.
Therefore, an object of the embodiments of the present invention is to provide a gas pipeline leakage detection method, which improves accuracy and detection efficiency of gas pipeline leakage detection, avoids false detection and missing detection of manual inspection, and can accurately locate a gas pipeline leakage position, so as to facilitate subsequent fault processing.
It is another object of an embodiment of the present invention to provide a gas pipeline leak detection system.
In order to achieve the technical purpose, the technical scheme adopted by the embodiment of the invention comprises the following steps:
in a first aspect, an embodiment of the present invention provides a gas pipeline leakage detection method, including the following steps:
acquiring first data of a preset gas pipeline, wherein the first data comprise pipeline pressure, gas flow and gas concentration;
carrying out time sequence and normalization processing on the first data to obtain a first sequence, wherein the first sequence comprises a pipeline pressure sequence, a gas flow sequence and a gas concentration sequence;
determining a training sample and a corresponding label according to the first sequence and a preset expert scoring model, and further obtaining a training data set according to the training sample and the label;
and inputting the training data set into a pre-constructed cyclic neural network for training to obtain a trained gas pipeline leakage identification model, and further identifying and detecting the gas pipeline to be detected according to the gas pipeline leakage identification model.
Further, in one embodiment of the present invention, the step of acquiring the first data of the preset gas pipeline specifically includes:
the method comprises the steps that first data of a preset gas pipeline and position data of the gas pipeline sensors are collected through a plurality of gas pipeline sensors, the plurality of gas pipeline sensors comprise NB-IoT pressure sensors, NB-IoT flow sensors, NB-IoT concentration sensors and a GPS (global positioning system) positioner, and the plurality of gas pipeline sensors are installed in the preset gas pipeline according to preset distance intervals.
Further, in one embodiment of the present invention, the step of performing time-series and normalization processing on the first data to obtain a first sequence specifically includes:
carrying out time sequence and normalization processing on the first data to obtain a pipeline pressure sequence, a gas flow sequence and a gas concentration sequence corresponding to each gas pipeline sensor;
and marking the pipeline pressure sequence, the gas flow sequence and the gas concentration sequence according to the position data to obtain the first sequence.
Further, in one embodiment of the present invention, the step of determining a training sample and a corresponding label according to the first sequence and a preset expert scoring model, and further obtaining a training data set according to the training sample and the label specifically includes:
acquiring two groups of first sequences of adjacent positions, and determining time sequence data corresponding to two gas pipeline sensors of the adjacent positions at each moment;
scoring the time sequence data according to a preset expert scoring model, and determining a gas leakage scoring result;
determining a training sample according to the time sequence data, and determining a label of the training sample according to the gas leakage scoring result;
and constructing a training data set according to the training sample and the label.
Further, in one embodiment of the present invention, the expert scoring model is:
where l denotes the gas leakage level, l=1, 2,3,4,5, l=1 corresponds to an uncontrollable leakage, l=2 corresponds to a severe leakage, l=3 corresponds to a general leakage, l=4 corresponds to a slight leakage, l=5 corresponds to no leakage occurring,representing the position S m+1 At t n Pipe pressure at time,/>Representing the position S m At t n Pipeline pressure, delta at time 2|l And delta 1|l Respectively represent the upper and lower limits of the pipeline pressure when the gas leakage level is l,/>Representing the position S m+1 At t n Gas flow at time,/->Representing the position S m At t n Gas flow at time epsilon 2|l And epsilon 1|l The upper and lower limits of the gas flow at the gas leakage level of l are respectively indicated,representing the position S m+1 At t n Gas concentration at time->Representing the position S m At t n Gas concentration, delta at time 2|l And delta 1|l Separate tableThe upper and lower limits of the gas concentration at the gas leakage level l are shown.
Further, in an embodiment of the present invention, the step of inputting the training data set into a pre-constructed recurrent neural network to perform training, and obtaining a trained gas pipeline leakage recognition model specifically includes:
inputting the training data set into the cyclic neural network to obtain a prediction classification result;
determining a loss value of the recurrent neural network according to the prediction classification result and the label;
updating parameters of the recurrent neural network through a back propagation algorithm according to the loss value;
and stopping training when the loss value reaches a preset first threshold value or the iteration number reaches a preset second threshold value or the test precision reaches a preset third threshold value, and obtaining a trained gas pipeline leakage identification model.
Further, in one embodiment of the present invention, the recurrent neural network is formed by stacking two layers of LSTM networks, and the loss function of the recurrent neural network is:
wherein,representing t n Real tag value of moment +_>Representing the predicted value of the recurrent neural network, N representing the total number of time steps.
In a second aspect, an embodiment of the present invention provides a gas pipeline leakage detection system, including:
the first data acquisition module is used for acquiring first data of a preset gas pipeline, wherein the first data comprise pipeline pressure, gas flow and gas concentration;
the first sequence determining module is used for carrying out time sequence and normalization processing on the first data to obtain a first sequence, wherein the first sequence comprises a pipeline pressure sequence, a gas flow sequence and a gas concentration sequence;
the training data set construction module is used for determining a training sample and a corresponding label according to the first sequence and a preset expert scoring model, and further obtaining a training data set according to the training sample and the label;
the model training and identifying module is used for inputting the training data set into a pre-constructed cyclic neural network for training to obtain a trained gas pipeline leakage identifying model, and further identifying and detecting the gas pipeline to be detected according to the gas pipeline leakage identifying model.
In a third aspect, an embodiment of the present invention provides a gas pipeline leakage detection device, including:
at least one processor;
at least one memory for storing at least one program;
the at least one program, when executed by the at least one processor, causes the at least one processor to implement a gas pipeline leak detection method as described above.
In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium in which a processor-executable program is stored, which when executed by a processor is configured to perform a gas pipeline leak detection method as described above.
The advantages and benefits of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
According to the embodiment of the invention, a plurality of data sources in the gas pipeline are considered, the gas pipeline leakage identification model is trained by adopting multi-dimensional time sequence data, and meanwhile, the accuracy of gas pipeline leakage detection is improved by adopting a training mode of a continuous optimization model; the labor cost and the time cost of gas pipeline inspection can be reduced, and false inspection and missing inspection of the manual inspection are avoided; the data of the gas pipeline can be monitored remotely, so that the efficiency of gas pipeline leakage detection is improved; in addition, the leakage position of the gas pipeline can be accurately positioned according to the data acquisition points which are arranged in advance, so that the subsequent fault treatment is facilitated.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following description will refer to the drawings that are needed in the embodiments of the present invention, and it should be understood that the drawings in the following description are only for convenience and clarity to describe some embodiments in the technical solutions of the present invention, and other drawings may be obtained according to these drawings without any inventive effort for those skilled in the art.
FIG. 1 is a flow chart of steps of a gas pipeline leakage detection method according to an embodiment of the present invention;
FIG. 2 is a data flow chart of a gas pipeline leakage detection method according to an embodiment of the present invention;
FIG. 3 is a block diagram of a gas pipeline leak detection system according to an embodiment of the present invention;
fig. 4 is a block diagram of a gas pipeline leakage detection device according to an embodiment of the present invention.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative only and are not to be construed as limiting the invention. The step numbers in the following embodiments are set for convenience of illustration only, and the order between the steps is not limited in any way, and the execution order of the steps in the embodiments may be adaptively adjusted according to the understanding of those skilled in the art.
In the description of the present invention, the plurality means two or more, and if the description is made to the first and second for the purpose of distinguishing technical features, it should not be construed as indicating or implying relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the precedence of the indicated technical features. Furthermore, unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art.
Referring to fig. 1, an embodiment of the present invention provides a gas pipeline leakage detection method, which specifically includes the following steps:
s101, acquiring first data of a preset gas pipeline, wherein the first data comprise pipeline pressure, gas flow and gas concentration.
Specifically, when the gas pipeline leaks, the pipeline pressure, the gas flow and the gas concentration are generally changed, and the embodiment of the invention collects the pipeline pressure, the gas flow and the gas concentration at each position of the gas pipeline through various sensors, so that a data source can be continuously provided for subsequent model training.
Further as an optional implementation manner, the step of acquiring the first data of the preset gas pipeline specifically includes:
the method comprises the steps that first data of a preset gas pipeline and position data of the gas pipeline sensors are collected through a plurality of gas pipeline sensors, each gas pipeline sensor comprises an NB-IoT pressure sensor, an NB-IoT flow sensor, an NB-IoT concentration sensor and a GPS (global positioning system) positioner, and the gas pipeline sensors are installed in the preset gas pipeline according to preset distance intervals.
Specifically, the gas pipeline sensor integrates an NB-IoT pressure sensor, an NB-IoT flow sensor, an NB-IoT concentration sensor and a GPS (global positioning system) positioner, and is arranged in the gas pipeline in advance according to a set distance interval and used for collecting data of pressure, gas flow and gas concentration of the pipeline in a fixed-point position in real time.
As shown in fig. 2, the pipeline pressure, gas flow and gas concentration data collected by each gas pipeline sensor can be uploaded to the internet of things management platform through the NB-IoT communication module, and meanwhile, the position data of each gas pipeline sensor is uploaded to the internet of things management platform through the GPS, so that the subsequent processing of the data is facilitated.
S102, carrying out time sequence and normalization processing on the first data to obtain a first sequence, wherein the first sequence comprises a pipeline pressure sequence, a gas flow sequence and a gas concentration sequence.
Specifically, the time sequence processing can form time sequence data of each index, and the normalization processing can reduce the complexity of the data, so that the calculated amount is reduced, and the training efficiency of the neural network model is improved. The step S102 specifically includes the following steps:
s1021, carrying out time sequence and normalization processing on the first data to obtain a pipeline pressure sequence, a gas flow sequence and a gas concentration sequence corresponding to each gas pipeline sensor;
and S1022, marking the pipeline pressure sequence, the gas flow sequence and the gas concentration sequence according to the position data to obtain a first sequence.
Specifically, the data center platform in the internet of things management platform performs time sequence serialization and data normalization processing on the acquired pipeline pressure, gas flow and gas concentration data, and the pipeline pressure sequence { P (t) 1 ),P(t 2 ),P(t 3 ),...,P(t n ) Sequence of gas flows { L (t) 1 ),L(t 2 ),L(t 3 ),...,L(t n ) Sequence of gas concentration { C (t) 1 ),C(t 2 ),C(t 3 ),...,C(t n )}。
Each gas pipeline sensor corresponds to a pipeline pressure sequence, a gas flow sequence and a gas concentration sequence, and in order to distinguish data acquired by different gas pipeline sensors, position data acquired by each gas pipeline sensor can be marked to obtain the marked pipeline pressure sequence, gas flow sequence and gas concentration sequence.
S103, determining a training sample and a corresponding label according to the first sequence and a preset expert scoring model, and further obtaining a training data set according to the training sample and the label.
Specifically, two sets of time sequence data at adjacent positions are selected from the first sequence determined in the previous step, and scored by a preset expert scoring model to obtain scoring results corresponding to the time sequence data, namely sample tags, so that a training data set can be formed. Step S103 specifically includes the following steps:
s1031, acquiring two groups of first sequences of adjacent positions, and determining time sequence data corresponding to two gas pipeline sensors of the adjacent positions at each moment;
s1032, scoring the time sequence data according to a preset expert scoring model, and determining a gas leakage scoring result;
s1033, determining a training sample according to the time sequence data, and determining a label of the training sample according to the gas leakage scoring result;
s1034, constructing a training data set according to the training samples and the labels.
Specifically, in order to train the gas leakage detection model, an expert scoring model is required to judge the gas leakage event and collect a training sample. Setting two adjacent acquisition positions S m And S is m+1 At t n The pipeline pressure, gas flow and gas concentration data acquired at the moment are respectivelyAnd->Selecting data of the same index at two positions at the moment to form a data set, inputting the data set into a preset expert scoring model for scoring to obtain a scoring result, and then forming a training sample and a label according to the data set and the scoring result.
Further as an alternative embodiment, the expert scoring model is:
where l denotes the gas leakage level, l=1, 2,3,4,5, l=1 corresponds to uncontrollable leakage, l=2 corresponds to severe leakage,l=3 corresponds to a general leak, l=4 corresponds to a slight leak, l=5 corresponds to no leak occurring,representing the position S m+1 At t n Pipe pressure at time,/>Representing the position S m At t n Pipeline pressure, delta at time 2|l And delta 1|l Respectively represent the upper and lower limits of the pipeline pressure when the gas leakage level is l,/>Representing the position S m+1 At t n Gas flow at time,/->Representing the position S m At t n Gas flow at time epsilon 2|l And epsilon 1|l The upper and lower limits of the gas flow at the gas leakage level of l are respectively indicated,representing the position S m+1 At t n Gas concentration at time->Representing the position S m At t n Gas concentration, delta at time 2|l And delta 1|l The upper and lower limits of the gas concentration at the gas leakage level l are indicated, respectively.
Specifically, the expert scoring model can score each index in the first sequence of two adjacent positions, and when the difference value of certain index data falls into a corresponding interval, the gas leakage grade corresponding to the index can be determined; and respectively determining the gas leakage grades corresponding to the pipeline pressure, the gas flow and the gas concentration, and then carrying out weighted summation on the grades of the pipeline pressure, the gas flow and the gas concentration to obtain the final gas leakage grade. When the gas leakage grade obtained by the data acquired by the two adjacent positions at the same time is 1 to 4, judging that the gas leakage exists in the pipeline between the two positions, otherwise, judging that the gas pipe has no leakage phenomenon. The gas leakage hazard classes are classified into primary leakage (uncontrollable leakage), secondary leakage (severe leakage), tertiary leakage (general leakage), and quaternary leakage (slight leakage).
Alternatively, position S may be m And S is m+1 At t n Time sequence data acquired at moment respectivelyAnd->Combined into vector->The vector is used as training sample, and the obtained training data set can be recorded as +.>The training data set is used as the input of the recurrent neural network, wherein the input vector is +.>Is set to t step I.e. every interval time t step Acquisition position S m And S is m+1 Time series data at. Scoring results of expert scoring model>As a training sample. When the scoring result is first-order leakage, the tag value +.>When the scoring result is a secondary leak, the tag value +.>When scoring resultFor three-level leakage, the tag value +.>When the scoring result is a four-level leak, the tag valueWhen the scoring result is no leakage, the tag value +.>
S104, inputting the training data set into a pre-constructed cyclic neural network for training, obtaining a trained gas pipeline leakage identification model, and further identifying and detecting the gas pipeline to be detected according to the gas pipeline leakage identification model.
Specifically, as shown in fig. 2, the AI center station of the internet of things management platform trains the gas leakage detection model by using a recurrent neural network. 70% of the data collected in the above steps can be used for supervised training of the model and 30% of the data can be used for testing of the model.
Further as an optional implementation manner, the step of inputting the training data set into a pre-constructed cyclic neural network to perform training to obtain a trained gas pipeline leakage recognition model specifically includes:
a1, inputting a training data set into a cyclic neural network to obtain a prediction classification result;
a2, determining a loss value of the cyclic neural network according to the prediction classification result and the label;
a3, updating parameters of the cyclic neural network through a back propagation algorithm according to the loss value;
and A4, stopping training when the loss value reaches a preset first threshold value or the iteration number reaches a preset second threshold value or the test precision reaches a preset third threshold value, and obtaining a trained gas pipeline leakage identification model.
Specifically, after data in the training data set is input into the initialized cyclic neural network, a prediction classification result output by the model can be obtained, and the accuracy of the gas pipeline leakage recognition model can be evaluated by the prediction classification result and the label, so that parameters of the model are updated. For gas pipeline leakage identification, the accuracy of the model prediction result can be measured by a Loss Function (Loss Function), wherein the Loss Function is defined on single training data and is used for measuring the prediction error of one training data, and particularly determining the Loss value of the training data through the label of the single training data and the prediction result of the model on the training data. In actual training, one training data set has a lot of training data, so that a Cost Function (Cost Function) is generally adopted to measure the overall error of the training data set, and the Cost Function is defined on the whole training data set and is used for calculating the average value of the prediction errors of all the training data, so that the prediction effect of the model can be better measured. For a general machine learning model, based on the cost function, a regular term for measuring the complexity of the model can be used as a training objective function, and based on the objective function, the loss value of the whole training data set can be obtained. There are many kinds of common loss functions, such as 0-1 loss function, square loss function, absolute loss function, logarithmic loss function, cross entropy loss function, etc., which can be used as the loss function of the machine learning model, and will not be described in detail herein. In the embodiment of the application, one loss function can be selected to determine the loss value of training. Based on the trained loss value, updating the parameters of the model by adopting a back propagation algorithm, and iterating for several rounds to obtain the trained point cloud pole tower identification model. Specifically, the number of iteration rounds may be preset, or training may be considered complete when the test set meets the accuracy requirements.
Further as an alternative embodiment, the recurrent neural network is formed by stacking two layers of LSTM networks, and the loss function of the recurrent neural network is:
wherein,representing t n Real tag value of moment +_>Representing the predicted value of the recurrent neural network, N representing the total number of time steps.
Specifically, the recurrent neural network of the embodiment of the invention is formed by stacking two layers of LSTM (long short term memory network), and the input layer inputs the training data setMeanwhile, layer standardization (Layer Normalization) is adopted in the model to avoid gradient disappearance and gradient explosion problems in the training process, and the training speed and accuracy of the model can be improved, so that the model is more robust.
The hyper-parameters of the model were set, the model was trained using the BPTT (Back-Propagation Through Time) algorithm, while the following cross entropy functions were used to optimize the objective:
wherein,representing t n Real tag value of moment +_>Representing the predicted value of the recurrent neural network, N representing the total number of time steps.
Optionally, when training the model by using the training data set, the training accuracy can be visualized, when the training accuracy reaches 100%, the trained model is tested by using the test set, then the setting of the model super-parameters is continuously adjusted, the training steps are repeated until the testing accuracy of the model reaches 100%, and the trained gas pipeline leakage recognition model can be obtained.
After the gas pipeline leakage recognition model is obtained through training, the gas pipeline leakage recognition model can be directly used for detecting the leakage condition of the gas pipeline, and the time sequence data of the pipeline pressure, the gas concentration and the gas flow of each position of the gas pipeline to be detected are output to the model, so that the monitoring result can be directly obtained. Compared with expert scoring models, manual detection and other methods, the trained gas pipeline leakage recognition model has better detection effects, meanwhile, monitoring data (gas pipeline pressure, gas concentration, gas flow and GPS position) of the gas pipeline and positioning results of gas leakage pipe sections are displayed through an IOC large screen of an Internet of things management platform, and then information is synchronized to a gas management system, so that gas leakage problems can be conveniently researched, judged and analyzed according to leakage grades, and emergency measures and solutions are formulated.
In the business scene of a gas company, the gas pipeline can be monitored remotely by the method, and meanwhile, the gas leakage condition can be predicted and early-warned without on-site investigation and inspection, so that the cost of manpower input is reduced, and the remote monitoring and maintenance of the gas pipeline are facilitated.
The method steps of the embodiments of the present invention are described above. As shown in fig. 2, in the embodiment of the present invention, a gas pipe sensor is additionally installed on a gas pipe, the sensor integrates a NB-IoT-based pressure sensor, a flow sensor, a concentration sensor and a GPS positioner, and is configured to collect pipe pressure, gas flow, gas concentration and position data of the sensor of the gas pipe in real time, then transmit the data to an internet of things management platform through a NB-IoT communication module, and a data center in the internet of things management platform performs time serialization and data normalization on the collected data, uses the preprocessed data as input, performs supervised training and testing through an AI center using a circulating neural network, and finally feeds back the monitored data and predicted gas leakage information to the gas pipe management system.
It should be appreciated that the embodiment of the invention considers a plurality of data sources in the gas pipeline, adopts multi-dimensional time sequence data to train the gas pipeline leakage identification model, and adopts a continuous optimization model training mode to improve the accuracy of gas pipeline leakage detection; the labor cost and the time cost of gas pipeline inspection can be reduced, and false inspection and missing inspection of the manual inspection are avoided; the data of the gas pipeline can be monitored remotely, so that the efficiency of gas pipeline leakage detection is improved; in addition, the leakage position of the gas pipeline can be accurately positioned according to the data acquisition points which are arranged in advance, so that the subsequent fault treatment is facilitated.
Referring to fig. 3, an embodiment of the present invention provides a gas pipeline leakage detection system, including:
the first data acquisition module is used for acquiring first data of a preset gas pipeline, wherein the first data comprise pipeline pressure, gas flow and gas concentration;
the first sequence determining module is used for carrying out time sequence and normalization processing on the first data to obtain a first sequence, wherein the first sequence comprises a pipeline pressure sequence, a gas flow sequence and a gas concentration sequence;
the training data set construction module is used for determining a training sample and a corresponding label according to the first sequence and a preset expert scoring model, and further obtaining a training data set according to the training sample and the label;
the model training and identifying module is used for inputting the training data set into a pre-constructed cyclic neural network for training to obtain a trained gas pipeline leakage identifying model, and then identifying and detecting the gas pipeline to be detected according to the gas pipeline leakage identifying model.
The content in the method embodiment is applicable to the system embodiment, the functions specifically realized by the system embodiment are the same as those of the method embodiment, and the achieved beneficial effects are the same as those of the method embodiment.
Referring to fig. 4, an embodiment of the present invention provides a gas pipeline leakage detection device, including:
at least one processor;
at least one memory for storing at least one program;
the at least one program, when executed by the at least one processor, causes the at least one processor to implement a gas pipeline leak detection method as described above.
The content in the method embodiment is applicable to the embodiment of the device, and the functions specifically realized by the embodiment of the device are the same as those of the method embodiment, and the obtained beneficial effects are the same as those of the method embodiment.
The embodiment of the invention also provides a computer-readable storage medium in which a processor-executable program is stored, which when executed by a processor is used to perform the above-described gas pipe leakage detection method.
The computer readable storage medium of the embodiment of the invention can execute the method for detecting the leakage of the gas pipeline, which is provided by the embodiment of the method of the invention, and can execute the steps of the embodiment of the method in any combination, thereby having the corresponding functions and beneficial effects of the method.
Embodiments of the present invention also disclose a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The computer instructions may be read from a computer-readable storage medium by a processor of a computer device, and executed by the processor, to cause the computer device to perform the method shown in fig. 1.
In some alternative embodiments, the functions/acts noted in the block diagrams may occur out of the order noted in the operational illustrations. For example, two blocks shown in succession may in fact be executed substantially concurrently or the blocks may sometimes be executed in the reverse order, depending upon the functionality/acts involved. Furthermore, the embodiments presented and described in the flowcharts of the present invention are provided by way of example in order to provide a more thorough understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed, and in which sub-operations described as part of a larger operation are performed independently.
Furthermore, while the present invention has been described in the context of functional modules, it should be appreciated that, unless otherwise indicated, one or more of the functions and/or features described above may be integrated in a single physical device and/or software module or one or more of the functions and/or features may be implemented in separate physical devices or software modules. It will also be appreciated that a detailed discussion of the actual implementation of each module is not necessary to an understanding of the present invention. Rather, the actual implementation of the various functional modules in the apparatus disclosed herein will be apparent to those skilled in the art from consideration of their attributes, functions and internal relationships. Accordingly, one of ordinary skill in the art can implement the invention as set forth in the claims without undue experimentation. It is also to be understood that the specific concepts disclosed are merely illustrative and are not intended to be limiting upon the scope of the invention, which is to be defined in the appended claims and their full scope of equivalents.
The above functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied in essence or a part contributing to the prior art or a part of the technical solution in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the above-described method of the various embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium upon which the program described above is printed, as the program described above may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted, or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
In the foregoing description of the present specification, reference has been made to the terms "one embodiment/example", "another embodiment/example", "certain embodiments/examples", and the like, means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that: many changes, modifications, substitutions and variations may be made to the embodiments without departing from the spirit and principles of the invention, the scope of which is defined by the claims and their equivalents.
While the preferred embodiment of the present invention has been described in detail, the present invention is not limited to the above embodiments, and various equivalent modifications and substitutions can be made by those skilled in the art without departing from the spirit of the present invention, and these equivalent modifications and substitutions are intended to be included in the scope of the present invention as defined in the appended claims.
Claims (7)
1. The gas pipeline leakage detection method is characterized by comprising the following steps of:
acquiring first data of a preset gas pipeline, wherein the first data comprise pipeline pressure, gas flow and gas concentration;
carrying out time sequence and normalization processing on the first data to obtain a first sequence, wherein the first sequence comprises a pipeline pressure sequence, a gas flow sequence and a gas concentration sequence;
determining a training sample and a corresponding label according to the first sequence and a preset expert scoring model, and further obtaining a training data set according to the training sample and the label;
inputting the training data set into a pre-constructed cyclic neural network for training to obtain a trained gas pipeline leakage identification model, and further identifying and detecting a gas pipeline to be detected according to the gas pipeline leakage identification model;
the step of determining a training sample and a corresponding label according to the first sequence and a preset expert scoring model, and further obtaining a training data set according to the training sample and the label specifically includes:
acquiring two groups of first sequences of adjacent positions, and determining time sequence data corresponding to two gas pipeline sensors of the adjacent positions at each moment;
scoring the time sequence data according to a preset expert scoring model, and determining a gas leakage scoring result;
determining a training sample according to the time sequence data, and determining a label of the training sample according to the gas leakage scoring result;
constructing a training data set according to the training sample and the label;
the expert scoring model is as follows:
where l denotes the gas leakage level, l=1, 2,3,4,5, l=1 corresponds to an uncontrollable leakage, l=2 corresponds to a severe leakage, l=3 corresponds to a general leakage, l=4 corresponds to a slight leakage, l=5 corresponds to no leakage occurring,representing the position S m+1 At t n Pipe pressure at time,/>Representing the position S m At t n Pipeline pressure, delta at time 2l And delta 1l Respectively represent the upper and lower limits of the pipeline pressure when the gas leakage level is l,/>Representing the position S m+1 At t n Gas flow at time,/->Representing the position S m At t n Gas flow at time epsilon 2l And epsilon 1l Respectively represent the upper and lower limits of the gas flow when the gas leakage level is l,/for the gas leakage level>Representing the position S m+1 At t n Gas concentration at time->Representing the position S m At t n Gas concentration, delta at time 2l And delta 1l Respectively representing the upper limit and the lower limit of the gas concentration when the gas leakage level is l;
the step of inputting the training data set into a pre-constructed cyclic neural network for training to obtain a trained gas pipeline leakage identification model comprises the following steps:
inputting the training data set into the cyclic neural network to obtain a prediction classification result;
determining a loss value of the recurrent neural network according to the prediction classification result and the label;
updating parameters of the recurrent neural network through a back propagation algorithm according to the loss value;
and stopping training when the loss value reaches a preset first threshold value or the iteration number reaches a preset second threshold value or the test precision reaches a preset third threshold value, and obtaining a trained gas pipeline leakage identification model.
2. The gas pipeline leakage detection method according to claim 1, wherein the step of acquiring the first data of the preset gas pipeline comprises the following specific steps:
the method comprises the steps that first data of a preset gas pipeline and position data of the gas pipeline sensors are collected through a plurality of gas pipeline sensors, the plurality of gas pipeline sensors comprise NB-IoT pressure sensors, NB-IoT flow sensors, NB-IoT concentration sensors and a GPS (global positioning system) positioner, and the plurality of gas pipeline sensors are installed in the preset gas pipeline according to preset distance intervals.
3. The gas pipeline leakage detection method according to claim 2, wherein the step of performing time-series and normalization processing on the first data to obtain a first sequence specifically comprises:
carrying out time sequence and normalization processing on the first data to obtain a pipeline pressure sequence, a gas flow sequence and a gas concentration sequence corresponding to each gas pipeline sensor;
and marking the pipeline pressure sequence, the gas flow sequence and the gas concentration sequence according to the position data to obtain the first sequence.
4. A gas pipeline leak detection method according to any one of claims 1 to 3, wherein the recurrent neural network is formed by stacking two LSTM networks, and the loss function of the recurrent neural network is:
wherein,representing t n Real tag value of moment +_>Representing the predicted value of the recurrent neural network, N representing the total number of time steps.
5. A gas pipeline leak detection system, comprising:
the first data acquisition module is used for acquiring first data of a preset gas pipeline, wherein the first data comprise pipeline pressure, gas flow and gas concentration;
the first sequence determining module is used for carrying out time sequence and normalization processing on the first data to obtain a first sequence, wherein the first sequence comprises a pipeline pressure sequence, a gas flow sequence and a gas concentration sequence;
the training data set construction module is used for determining a training sample and a corresponding label according to the first sequence and a preset expert scoring model, and further obtaining a training data set according to the training sample and the label;
the model training and identifying module is used for inputting the training data set into a pre-constructed cyclic neural network for training to obtain a trained gas pipeline leakage identifying model, and further identifying and detecting the gas pipeline to be detected according to the gas pipeline leakage identifying model;
the training data set construction module is specifically configured to:
acquiring two groups of first sequences of adjacent positions, and determining time sequence data corresponding to two gas pipeline sensors of the adjacent positions at each moment;
scoring the time sequence data according to a preset expert scoring model, and determining a gas leakage scoring result;
determining a training sample according to the time sequence data, and determining a label of the training sample according to the gas leakage scoring result;
constructing a training data set according to the training sample and the label;
the expert scoring model is as follows:
where l denotes the gas leakage level, l=1, 2,3,4,5, l=1 corresponds to an uncontrollable leakage, l=2 corresponds to a severe leakage, l=3 corresponds to a general leakage, l=4 corresponds to a slight leakage, l=5 corresponds to no leakage occurring,representation ofPosition S m+1 At t n Pipe pressure at time,/>Representing the position S m At t n Pipeline pressure, delta at time 2l And delta 1l Respectively represent the upper and lower limits of the pipeline pressure when the gas leakage level is l,/>Representing the position S m+1 At t n Gas flow at time,/->Representing the position S m At t n Gas flow at time epsilon 2l And epsilon 1l Respectively represent the upper and lower limits of the gas flow when the gas leakage level is l,/for the gas leakage level>Representing the position S m+1 At t n Gas concentration at time->Representing the position S m At t n Gas concentration, delta at time 2l And delta 1l Respectively representing the upper limit and the lower limit of the gas concentration when the gas leakage level is l;
the step of inputting the training data set into a pre-constructed cyclic neural network for training to obtain a trained gas pipeline leakage identification model comprises the following steps:
inputting the training data set into the cyclic neural network to obtain a prediction classification result;
determining a loss value of the recurrent neural network according to the prediction classification result and the label;
updating parameters of the recurrent neural network through a back propagation algorithm according to the loss value;
and stopping training when the loss value reaches a preset first threshold value or the iteration number reaches a preset second threshold value or the test precision reaches a preset third threshold value, and obtaining a trained gas pipeline leakage identification model.
6. A gas pipeline leak detection apparatus, comprising:
at least one processor;
at least one memory for storing at least one program;
when said at least one program is executed by said at least one processor, said at least one processor is caused to implement a gas pipeline leak detection method as claimed in any one of claims 1 to 4.
7. A computer-readable storage medium in which a processor-executable program is stored, characterized in that the processor-executable program, when executed by a processor, is for performing a gas pipe leakage detection method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111494477.6A CN114352947B (en) | 2021-12-08 | 2021-12-08 | Gas pipeline leakage detection method, system, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111494477.6A CN114352947B (en) | 2021-12-08 | 2021-12-08 | Gas pipeline leakage detection method, system, device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114352947A CN114352947A (en) | 2022-04-15 |
| CN114352947B true CN114352947B (en) | 2024-03-12 |
Family
ID=81097115
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111494477.6A Active CN114352947B (en) | 2021-12-08 | 2021-12-08 | Gas pipeline leakage detection method, system, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114352947B (en) |
Families Citing this family (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115063950B (en) * | 2022-05-20 | 2024-04-05 | 南通中油燃气有限责任公司 | Intelligent monitoring method and system for open space gas leakage of station |
| CN114777030B (en) * | 2022-05-23 | 2023-09-05 | 中用科技有限公司 | Dangerous chemical gas monitoring method based on NB-IOT technology |
| CN115127036B (en) * | 2022-09-01 | 2022-11-08 | 北京云庐科技有限公司 | Municipal gas pipe network leakage positioning method and system |
| CN115330094B (en) * | 2022-10-14 | 2023-04-07 | 成都秦川物联网科技股份有限公司 | Intelligent gas pipeline service life prediction method, internet of things system, device and medium |
| CN115330361B (en) | 2022-10-14 | 2023-01-13 | 成都秦川物联网科技股份有限公司 | Indoor safety-based gas leakage prediction method and intelligent gas Internet of things system |
| CN116055514B (en) * | 2022-11-08 | 2024-06-14 | 成都秦川物联网科技股份有限公司 | Natural gas synergistic control method, intelligent gas Internet of things system, device and medium |
| CN115681821B (en) | 2022-12-13 | 2023-04-07 | 成都秦川物联网科技股份有限公司 | Automatic odorizing control method for intelligent gas equipment management and Internet of things system |
| CN116164243A (en) * | 2023-04-26 | 2023-05-26 | 北京理工大学 | Hydrogen leakage detection positioning system and method |
| CN116336400B (en) * | 2023-05-30 | 2023-08-04 | 克拉玛依市百事达技术开发有限公司 | Baseline detection method for oil and gas gathering and transportation pipeline |
| CN116625438B (en) * | 2023-07-25 | 2023-12-01 | 克拉玛依市燃气有限责任公司 | Gas pipe network safety on-line monitoring system and method thereof |
| CN116781430B (en) * | 2023-08-24 | 2023-12-01 | 克拉玛依市燃气有限责任公司 | Network information security system and method for gas pipe network |
| 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 |
| CN117114369B (en) * | 2023-10-23 | 2024-01-02 | 成都秦川物联网科技股份有限公司 | Intelligent gas emergency gas supply disposal method, internet of things system, device and medium |
| CN118517643A (en) * | 2024-07-25 | 2024-08-20 | 海纳云物联科技有限公司 | Method and apparatus for gas leak location, and computer readable storage medium |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DD226371A1 (en) * | 1984-05-14 | 1985-08-21 | Zentrales Entwurfs U Konstrukt | METHOD FOR THE EXPERIMENTAL MATHEMATICAL GUIDANCE FOR HOUSEHOLD EXTRACTION TESTS |
| RU2279140C1 (en) * | 2005-04-06 | 2006-06-27 | Сергей Яковлевич Барбулев | Device for training specialists in removal of gas leaks from gas pipelines |
| CN108167653A (en) * | 2017-12-23 | 2018-06-15 | 浙江大学 | Public supply mains booster detection method based on dynamic neural network prediction |
| CN109308494A (en) * | 2018-09-27 | 2019-02-05 | 厦门服云信息科技有限公司 | LSTM Recognition with Recurrent Neural Network model and network attack identification method based on this model |
| CN109359698A (en) * | 2018-10-30 | 2019-02-19 | 清华大学 | Leakage loss recognition methods based on long Memory Neural Networks model in short-term |
| KR20190018293A (en) * | 2017-08-14 | 2019-02-22 | 오토시맨틱스 주식회사 | Diagnosis method for Detecting Leak of Water Supply Pipe using Deep Learning by Acoustic Signature |
| CN110242865A (en) * | 2019-07-09 | 2019-09-17 | 北京讯腾智慧科技股份有限公司 | A kind of gas leakage detection determination method and system being easy to Continuous optimization |
| CN111783945A (en) * | 2020-06-22 | 2020-10-16 | 东北石油大学 | Long oil transmission pipeline leakage real-time detection system based on transfer learning LSTM |
| CN111950693A (en) * | 2019-05-14 | 2020-11-17 | 辉达公司 | Neural network inference using attenuation parameters |
| CN112149750A (en) * | 2020-09-29 | 2020-12-29 | 浙江大学 | Water supply network pipe burst identification data driving method |
| CN112332444A (en) * | 2020-09-14 | 2021-02-05 | 华北电力大学（保定） | Microgrid energy management system based on digital twins |
| KR20210048100A (en) * | 2019-10-23 | 2021-05-03 | 서울대학교산학협력단 | Condition monitoring data generating apparatus and method using generative adversarial network |
| CN112749761A (en) * | 2021-01-22 | 2021-05-04 | 上海机电工程研究所 | Enemy combat intention identification method and system based on attention mechanism and recurrent neural network |
| CN112836758A (en) * | 2021-02-08 | 2021-05-25 | 浙江工业大学 | Independent metering area pipe network leakage detection method based on double-layer circulating neural network |
| CN112903211A (en) * | 2021-03-29 | 2021-06-04 | 广州燃气集团有限公司 | Equipment and method for detecting tightness of gas pipeline |
| CN113364751A (en) * | 2021-05-26 | 2021-09-07 | 北京电子科技职业学院 | Network attack prediction method, computer-readable storage medium, and electronic device |
| CN113642023A (en) * | 2021-08-25 | 2021-11-12 | 北京恒安嘉新安全技术有限公司 | Data security detection model training method, data security detection device and equipment |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10948132B2 (en) * | 2017-05-08 | 2021-03-16 | 64Seconds, Inc. | Integrity assessment of a pipeline network |
| WO2020033316A1 (en) * | 2018-08-09 | 2020-02-13 | Bridger Pipeline Llc | Leak detection with artificial intelligence |
| US11401801B2 (en) * | 2019-09-25 | 2022-08-02 | Halliburton Energy Services, Inc. | Systems and methods for real-time hydraulic fracture control |
-
2021
- 2021-12-08 CN CN202111494477.6A patent/CN114352947B/en active Active
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DD226371A1 (en) * | 1984-05-14 | 1985-08-21 | Zentrales Entwurfs U Konstrukt | METHOD FOR THE EXPERIMENTAL MATHEMATICAL GUIDANCE FOR HOUSEHOLD EXTRACTION TESTS |
| RU2279140C1 (en) * | 2005-04-06 | 2006-06-27 | Сергей Яковлевич Барбулев | Device for training specialists in removal of gas leaks from gas pipelines |
| KR20190018293A (en) * | 2017-08-14 | 2019-02-22 | 오토시맨틱스 주식회사 | Diagnosis method for Detecting Leak of Water Supply Pipe using Deep Learning by Acoustic Signature |
| CN108167653A (en) * | 2017-12-23 | 2018-06-15 | 浙江大学 | Public supply mains booster detection method based on dynamic neural network prediction |
| CN109308494A (en) * | 2018-09-27 | 2019-02-05 | 厦门服云信息科技有限公司 | LSTM Recognition with Recurrent Neural Network model and network attack identification method based on this model |
| CN109359698A (en) * | 2018-10-30 | 2019-02-19 | 清华大学 | Leakage loss recognition methods based on long Memory Neural Networks model in short-term |
| CN111950693A (en) * | 2019-05-14 | 2020-11-17 | 辉达公司 | Neural network inference using attenuation parameters |
| CN110242865A (en) * | 2019-07-09 | 2019-09-17 | 北京讯腾智慧科技股份有限公司 | A kind of gas leakage detection determination method and system being easy to Continuous optimization |
| KR20210048100A (en) * | 2019-10-23 | 2021-05-03 | 서울대학교산학협력단 | Condition monitoring data generating apparatus and method using generative adversarial network |
| CN111783945A (en) * | 2020-06-22 | 2020-10-16 | 东北石油大学 | Long oil transmission pipeline leakage real-time detection system based on transfer learning LSTM |
| CN112332444A (en) * | 2020-09-14 | 2021-02-05 | 华北电力大学（保定） | Microgrid energy management system based on digital twins |
| CN112149750A (en) * | 2020-09-29 | 2020-12-29 | 浙江大学 | Water supply network pipe burst identification data driving method |
| CN112749761A (en) * | 2021-01-22 | 2021-05-04 | 上海机电工程研究所 | Enemy combat intention identification method and system based on attention mechanism and recurrent neural network |
| CN112836758A (en) * | 2021-02-08 | 2021-05-25 | 浙江工业大学 | Independent metering area pipe network leakage detection method based on double-layer circulating neural network |
| CN112903211A (en) * | 2021-03-29 | 2021-06-04 | 广州燃气集团有限公司 | Equipment and method for detecting tightness of gas pipeline |
| CN113364751A (en) * | 2021-05-26 | 2021-09-07 | 北京电子科技职业学院 | Network attack prediction method, computer-readable storage medium, and electronic device |
| CN113642023A (en) * | 2021-08-25 | 2021-11-12 | 北京恒安嘉新安全技术有限公司 | Data security detection model training method, data security detection device and equipment |
Non-Patent Citations (1)
| Title |
|---|
| 长输油气管道大数据挖掘与应用;于涛;刘丽君;陈泓君;于瑶;;物联网学报(第03期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114352947A (en) | 2022-04-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114352947B (en) | Gas pipeline leakage detection method, system, device and storage medium | |
| Romano et al. | Automated detection of pipe bursts and other events in water distribution systems | |
| CN107949812A (en) | Combined method for detecting anomalies in a water distribution system | |
| CN107480705A (en) | A kind of running water pipe leakage detection method | |
| US20230221207A1 (en) | Methods and internet of things systems for determining gas leakages based on smart gas | |
| CN115022187B (en) | Situation awareness method and device for electric-gas comprehensive energy system | |
| CN115935241B (en) | Multi-parameter mutually-fused pipe cleaner real-time positioning method and device | |
| CN117540329B (en) | Online early warning method and system for defects of drainage pipe network based on machine learning | |
| CN116245412A (en) | On-spot safety monitoring management system of building engineering | |
| CN111191855B (en) | Water quality abnormal event identification and early warning method based on pipe network multi-element water quality time sequence data | |
| CN118413265B (en) | Satellite online state monitoring system and method | |
| CN117191147A (en) | Flood discharge dam water level monitoring and early warning method and system | |
| Mitoma et al. | Fault diagnosis and condition surveillance for plant rotating machinery using partially-linearized neural network | |
| CN116382100A (en) | Oil and gas pipeline detection control system and control method | |
| CN106706119B (en) | Vibration source identification method and system based on signal frequency domain characteristics | |
| CN118224552A (en) | Outdoor pipeline heat preservation effect monitoring system in job site | |
| CN115063337A (en) | Intelligent maintenance decision-making method and device for buried pipeline | |
| CN117150445B (en) | Settlement monitoring and evaluating method for section tunnel short-distance downward river | |
| CN104317778A (en) | Massive monitoring data based substation equipment fault diagnosis method | |
| CN117554000A (en) | Intelligent detection method and system for leakage of tailing conveying pipeline | |
| CN116754022A (en) | On-line detection emergency early warning method and system for cable tunnel | |
| CN116186642A (en) | Distributed optical fiber sensing event early warning method based on multidimensional feature fusion | |
| CN115356400B (en) | BiLSTM-based ultrasonic wood nondestructive testing method and BiLSTM-based ultrasonic wood nondestructive testing system | |
| CN116306262A (en) | Galvanized steel corrosion prediction method based on ensemble learning algorithm | |
| CN115081741A (en) | Natural gas metrological verification intelligent prediction method based on neural network |
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 |