CN116557787A - Intelligent evaluation system and method for pipe network state - Google Patents
Intelligent evaluation system and method for pipe network state Download PDFInfo
- Publication number
- CN116557787A CN116557787A CN202310844253.6A CN202310844253A CN116557787A CN 116557787 A CN116557787 A CN 116557787A CN 202310844253 A CN202310844253 A CN 202310844253A CN 116557787 A CN116557787 A CN 116557787A
- Authority
- CN
- China
- Prior art keywords
- matrix
- feature
- flow
- pressure
- pipe
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000011156 evaluation Methods 0.000 title claims abstract description 28
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 75
- 239000011159 matrix material Substances 0.000 claims description 149
- 239000013598 vector Substances 0.000 claims description 123
- 230000004927 fusion Effects 0.000 claims description 65
- 238000009826 distribution Methods 0.000 claims description 27
- 238000013527 convolutional neural network Methods 0.000 claims description 21
- 238000004891 communication Methods 0.000 claims description 13
- 230000002159 abnormal effect Effects 0.000 claims description 12
- 238000005457 optimization Methods 0.000 claims description 11
- 238000012795 verification Methods 0.000 claims description 9
- 230000005856 abnormality Effects 0.000 claims description 2
- 238000007689 inspection Methods 0.000 abstract description 10
- 238000013473 artificial intelligence Methods 0.000 abstract description 4
- 238000012545 processing Methods 0.000 description 9
- 238000000605 extraction Methods 0.000 description 8
- 238000012544 monitoring process Methods 0.000 description 8
- 238000011176 pooling Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000003062 neural network model Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 238000013507 mapping Methods 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000012550 audit Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000011426 transformation method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17D—PIPE-LINE SYSTEMS; PIPE-LINES
- F17D5/00—Protection or supervision of installations
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A20/00—Water conservation; Efficient water supply; Efficient water use
- Y02A20/152—Water filtration
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Mathematical Optimization (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Mechanical Engineering (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The utility model relates to an intelligent evaluation field, it specifically discloses a pipe network state intelligent evaluation system and method thereof, and its comprehensive utilization pipe network a plurality of pipe section's pressure value and flow value to combine degree of depth study and artificial intelligence technique to come the real-time supervision and the evaluation to water supply pipe network state now, in order to optimize the operational mode of water supply pipe network, improve water supply efficiency. Meanwhile, the dependence on traditional manual inspection can be reduced, the working efficiency is improved, and the inspection cost is reduced.
Description
Technical Field
The present application relates to the field of intelligent assessment, and more particularly, to an intelligent assessment system for pipe network status and a method thereof.
Background
Along with the continuous acceleration of the urban process, the scale and complexity of the water supply network are continuously increased, and the traditional manual inspection method cannot meet the requirements for monitoring and evaluating the state of the water supply network in real time.
Thus, an optimized pipe network state assessment scheme is desired.
Disclosure of Invention
The present application has been made in order to solve the above technical problems. The embodiment of the application provides an intelligent evaluation system and method for a pipe network state, which comprehensively utilizes pressure values and flow values of a plurality of pipe sections in the pipe network, and combines deep learning and artificial intelligence technology to realize real-time monitoring and evaluation of the water supply pipe network state so as to optimize the operation mode of the water supply pipe network and improve the water supply efficiency. Meanwhile, the dependence on traditional manual inspection can be reduced, the working efficiency is improved, and the inspection cost is reduced.
According to one aspect of the present application, there is provided a method for intelligently evaluating a pipe network state, including: installing a plurality of pressure sensors and a plurality of flow sensors at proper positions of a water supply network to be evaluated; receiving pressure values and flow values of a plurality of pipe sections in the water supply network to be evaluated, which are acquired by the plurality of pressure sensors and the plurality of flow sensors; extracting a multi-mode association feature matrix based on the pressure values and the flow values of the pipe sections and the communication relation between the pipe sections; and determining whether the running state of the water supply network to be evaluated is abnormal or not based on the multi-mode association characteristic matrix.
According to another aspect of the present application, there is provided a pipe network state intelligent evaluation system, which includes: the information acquisition module is used for installing a plurality of pressure sensors and a plurality of flow sensors at proper positions of the water supply network to be evaluated; the information receiving module is used for receiving pressure values and flow values of a plurality of pipe sections in the water supply network to be evaluated, which are acquired by the plurality of pressure sensors and the plurality of flow sensors; the correlation characteristic extraction module is used for extracting a multi-mode correlation characteristic matrix based on the communication relation between the pressure values and the flow values of the pipe sections and the pipe sections; and the state evaluation module is used for determining whether the running state of the water supply network to be evaluated is abnormal or not based on the multi-mode association characteristic matrix.
Compared with the prior art, the intelligent evaluation system and the intelligent evaluation method for the pipe network state comprehensively utilize the pressure values and the flow values of a plurality of pipe sections in the pipe network, and realize real-time monitoring and evaluation of the water supply pipe network state by combining deep learning and artificial intelligence technology so as to optimize the operation mode of the water supply pipe network and improve the water supply efficiency. Meanwhile, the dependence on traditional manual inspection can be reduced, the working efficiency is improved, and the inspection cost is reduced.
Drawings
The foregoing and other objects, features and advantages of the present application will become more apparent from the following more particular description of embodiments of the present application, as illustrated in the accompanying drawings. The accompanying drawings are included to provide a further understanding of embodiments of the application and are incorporated in and constitute a part of this specification, illustrate the application and not constitute a limitation to the application. In the drawings, like reference numerals generally refer to like parts or steps.
Fig. 1 is a flowchart of a pipe network state intelligent evaluation method according to an embodiment of the present application.
Fig. 2 is a system architecture diagram of a pipe network state intelligent evaluation method according to an embodiment of the present application.
Fig. 3 is a flowchart of substep S3 of the intelligent pipe network state assessment method according to an embodiment of the present application.
Fig. 4 is a flowchart of substep S31 of the pipe network state intelligent assessment method according to an embodiment of the present application.
Fig. 5 is a block diagram of a pipe network state intelligent assessment system according to an embodiment of the present application.
Fig. 6 is a schematic view of a scenario of a pipe network state intelligent assessment method according to an embodiment of the present application.
Detailed Description
Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application and not all of the embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.
As used in this application and in the claims, the terms "a," "an," "the," and/or "the" are not specific to the singular, but may include the plural, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.
Although the present application makes various references to certain modules in a system according to embodiments of the present application, any number of different modules may be used and run on a user terminal and/or server. The modules are merely illustrative, and different aspects of the systems and methods may use different modules.
Flowcharts are used in this application to describe the operations performed by systems according to embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in order precisely. Rather, the various steps may be processed in reverse order or simultaneously, as desired. Also, other operations may be added to or removed from these processes.
Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application and not all of the embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.
Along with the continuous acceleration of the urban process, the scale and complexity of the water supply network are continuously increased, and the traditional manual inspection method cannot meet the requirements for monitoring and evaluating the state of the water supply network in real time. Thus, an optimized pipe network state assessment scheme is desired.
In the technical scheme of the application, an intelligent pipe network state assessment method is provided. Fig. 1 is a flowchart of a pipe network state intelligent evaluation method according to an embodiment of the present application. Fig. 2 is a system architecture diagram of a pipe network state intelligent evaluation method according to an embodiment of the present application. As shown in fig. 1 and fig. 2, the intelligent pipe network state assessment method according to the embodiment of the present application includes the steps of: s1, installing a plurality of pressure sensors and a plurality of flow sensors at proper positions of a water supply network to be evaluated; s2, receiving pressure values and flow values of a plurality of pipe sections in the water supply network to be evaluated, which are acquired by the plurality of pressure sensors and the plurality of flow sensors; s3, extracting a multi-mode association feature matrix based on the pressure values and the flow values of the pipe sections and the communication relation among the pipe sections; and S4, determining whether the running state of the water supply network to be evaluated is abnormal or not based on the multi-mode association characteristic matrix.
Specifically, in step S1, a plurality of pressure sensors and a plurality of flow sensors are installed at appropriate positions of the water supply network to be evaluated. The water supply network is a set of system consisting of a water source, a water pipeline, a water distribution pipeline, a fire-fighting water source, a water pool, a water tower, a water pump room, a water meter and the like, and is used for conveying water of the water source to places such as cities, villages and the like for people to live, produce industrially, use water for fire fighting and the like. The main functions of the water supply network are to convey, store, distribute and adjust water resources, ensure the water resource supply in cities, villages and other places, and meet the demands of people for life, industrial production, fire water and the like.
A pressure sensor is a sensor that measures pressure and converts the pressure into an electrical signal for output. Pressure sensors are typically composed of two parts, a sensing element and a signal processing circuit. The sensing element can convert pressure into an electric signal, and the signal processing circuit can amplify, filter, linearize and the like the electric signal output by the sensing element so as to be convenient for a user to read and analyze. The pressure sensor is widely applied to the fields of industrial automation, automobiles, medical equipment, weather, environmental protection and the like.
A flow sensor is a sensor for measuring the flow of a fluid or gas. They may be measured in a variety of ways, including by measuring pressure differentials, heat conduction or acoustic wave sensors, and the like. Flow sensors are commonly used to monitor and control flow in industrial processes.
According to an embodiment of the present application, a plurality of pressure sensors and a plurality of flow sensors are respectively placed at specific positions of the pipe to acquire pressure values and flow values of the plurality of pipe sections. It is worth mentioning that in order to make the process of data acquisition and transmission more automatic, technologies such as internet of things can be used to transmit data to data management systems such as cloud platform, so as to realize complete management of water network data. In particular, in determining the location where the sensor needs to be installed, a field survey and analysis is performed. When selecting the sensor installation position, the structure and the characteristics of the water supply network and the parameter range to be monitored need to be considered.
Specifically, in step S2, pressure values and flow values of a plurality of pipe sections in the water supply network to be evaluated acquired by the plurality of pressure sensors and the plurality of flow sensors are received. Namely, the pressure values and the data information received by the flow values of the pipe sections in the water supply network to be evaluated, which are acquired by the pressure sensors and the flow sensors, are collated.
Accordingly, in one possible implementation, the pressure values and flow values of a plurality of pipe sections in the water supply network to be evaluated acquired by the plurality of pressure sensors and the plurality of flow sensors may be received, for example: installing a plurality of pressure sensors and a plurality of flow sensors to collect pressure values and flow values of a plurality of pipe sections in the water supply network to be evaluated; transmitting the data acquired by the sensor to a data acquisition system; processing and cleaning the transmitted data to remove noise and invalid data; time synchronizing the data collected by the pressure sensor and the flow sensor to ensure that they collect data at the same point in time; calculating the average pressure and flow value of each pipe section by using the data acquired by the pressure sensor and the flow sensor; storing the calculated average pressure and flow values in a database for subsequent evaluation and analysis; analyzing and modeling the data by using a statistical method and a machine learning algorithm to evaluate the performance of the water supply network and predict the pipeline faults; and according to the analysis result, timely taking measures to repair the pipeline faults and improve the performance of the water supply network.
Specifically, in step S3, a multi-modal correlation feature matrix is extracted based on the pressure values and flow values of the plurality of pipe segments and the communication relationship between the plurality of pipe segments. In particular, in one specific example of the present application, as shown in fig. 3, the step S3 includes: s31, carrying out parameter association and fusion on the pressure values and the flow values of the pipe sections based on a deep convolutional neural network model to obtain a multi-parameter fusion feature matrix; s32, extracting a connected logic topology feature matrix based on the connected relation among the pipe sections; and S33, fusing the multi-parameter fusion feature matrix and the connected logic topology feature matrix to obtain the multi-mode association feature matrix.
More specifically, the step S31 is to perform parameter association and fusion on the pressure values and the flow values of the plurality of pipe segments based on a deep convolutional neural network model to obtain a multi-parameter fusion feature matrix. In particular, in one specific example of the present application, as shown in fig. 4, the S31 includes: s311, arranging the pressure values and the flow values of the pipe sections into pressure input vectors and flow input vectors according to the dimensions of the pipe section samples; s312, the pressure input vector and the flow input vector are respectively passed through an inter-pipe parameter correlation feature extractor comprising a first convolution layer and a second convolution layer to obtain a pressure correlation feature vector and a flow correlation feature vector; and S313, fusing the pressure correlation feature vector and the flow correlation feature vector by using a Gaussian density map to obtain the multi-parameter fusion feature matrix.
Accordingly, the step S311 is to arrange the pressure values and the flow values of the pipe segments into a pressure input vector and a flow input vector according to the sample dimensions of the pipe segments. Wherein the pressure values and flow values of the plurality of pipe segments are then arranged in a pipe segment sample dimension into a pressure input vector and a flow input vector. Wherein each sample corresponds to a pipe segment. In this way, various types of data for each pipe segment are converted into structured data, so that machine learning algorithms can be effectively applied for modeling.
Accordingly, in one possible implementation, the pressure values and flow values of the plurality of pipe segments may be arranged in pipe segment sample dimensions into pressure input vectors and flow input vectors, for example, by: collecting pressure value and flow value data of a plurality of pipe sections; arranging the pressure value and the flow value of each pipe section according to a time sequence to form a two-dimensional matrix; arranging the two-dimensional matrix of each pipe section according to the pipe section sequence to form a three-dimensional tensor; for the three-dimensional tensor of each pipe section, arranging each two-dimensional matrix according to the dimension of the sample to form a two-dimensional matrix; arranging the two-dimensional matrix of each pipe section according to the pipe section sequence to form a new three-dimensional tensor; arranging the three-dimensional tensors of each pipe section according to a time sequence to form a four-dimensional tensor; for the pressure input vector, arranging all row vectors of each two-dimensional matrix in the four-dimensional tensor according to a time sequence to form a one-dimensional row vector; for the flow input vector, arranging all column vectors of each two-dimensional matrix in the four-dimensional tensor according to a time sequence to form a one-dimensional column vector; and taking the pressure input vector and the flow input vector as the input of the model, and carrying out subsequent analysis and processing.
Accordingly, the step S312 is to pass the pressure input vector and the flow input vector through an inter-pipe parameter correlation feature extractor including a first convolution layer and a second convolution layer, respectively, to obtain a pressure correlation feature vector and a flow correlation feature vector. In the technical scheme of the application, because the spatial positions of the pressure and flow input vectors in the pipeline network have correlation, and the spatial correlation presents different characteristics in different areas, in the technical scheme of the application, the pressure input vector and the flow input vector are expected to be respectively subjected to multi-scale convolution coding by using one-dimensional convolution kernels with different scales to extract the multi-scale space implicit correlation characteristic distribution contained in the pressure input vector and the flow input vector. That is, the pressure input vector and the flow input vector are passed through an inter-pipe parameter correlation feature extractor comprising a first convolution layer and a second convolution layer, respectively, to obtain a pressure correlation feature vector and a flow correlation feature vector.
In one specific example of the present application, passing the pressure input vector and the flow input vector through an inter-pipe parameter correlation feature extractor comprising a first convolution layer and a second convolution layer, respectively, to obtain a pressure correlation feature vector and a flow correlation feature vector, includes: respectively inputting the pressure input vector and the flow input vector into a first convolution layer of the inter-pipe parameter correlation feature extractor to obtain the first neighborhood scale pressure correlation feature vector and the first neighborhood scale flow correlation feature vector, wherein the first convolution layer is provided with a first one-dimensional convolution kernel with a first length; respectively inputting the pressure input vector and the flow input vector into a second convolution layer of the inter-pipe section parameter correlation feature extractor to obtain the second neighborhood scale pressure correlation feature vector and the second neighborhood scale flow correlation feature vector, wherein the second convolution layer is provided with a second one-dimensional convolution kernel with a second length, and the first length is different from the second length; and cascading the first neighborhood scale pressure correlation feature vector and the first neighborhood scale flow correlation feature vector with the second neighborhood scale pressure correlation feature vector and the second neighborhood scale flow correlation feature vector respectively to obtain the pressure correlation feature vector and the flow correlation feature vector.
It should be noted that, in other specific examples of the present application, the pressure input vector and the flow input vector may also be passed through an inter-pipe parameter correlation feature extractor including a first convolution layer and a second convolution layer, respectively, to obtain a pressure correlation feature vector and a flow correlation feature vector, for example: for the pressure input vector, firstly inputting the pressure input vector into an inter-pipe parameter correlation feature extractor comprising a first convolution layer and a second convolution layer; in the first convolution layer, performing convolution operation on the input pressure vector by using a group of convolution checks to obtain a group of convolution feature graphs; inputting the convolution feature map into a second convolution layer, and carrying out convolution operation again by using a group of convolution checks to obtain a group of convolution feature maps with higher level; for the flow input vector, the flow input vector is also input into an inter-pipe parameter correlation feature extractor comprising a first convolution layer and a second convolution layer; in the first convolution layer, carrying out convolution operation on the input flow vector by using a group of convolution checks to obtain a group of convolution characteristic diagrams; inputting the convolution feature map into a second convolution layer, and carrying out convolution operation again by using a group of convolution checks to obtain a group of convolution feature maps with higher level; splicing the high-level convolution feature graphs of the pressure and the flow to obtain a comprehensive feature vector; and finally, processing the comprehensive feature vector by using the full connection layer to obtain a pressure-related feature vector and a flow-related feature vector.
Correspondingly, the step S313 of fusing the pressure-related feature vector and the flow-related feature vector by using a gaussian density map to obtain the multi-parameter fusion feature matrix. It is considered that in a real scenario, pressure data and flow data are related to each other, and influence each other. In order to construct the association relationship between the pressure association feature vector and the flow association feature vector, a Gaussian density chart is used for fusing the pressure association feature vector and the flow association feature vector to obtain a multi-parameter fusion feature matrix. Wherein the gaussian density map can effectively describe the relationships between features in the dataset and their dependencies. Here, the pressure and the flow rate are physical quantities that affect each other, and the gaussian density map can well capture the correlation between the pressure characteristic and the flow rate characteristic.
In particular, in one specific example of the present application, the S313 includes fusing the pressure-related feature vector and the flow-related feature vector using a gaussian density map to obtain an initial multi-parameter fusion feature matrix; and performing spatial multi-source fusion pre-verification information distribution optimization on the characteristic value of each position of the initial multi-parameter fusion characteristic matrix to obtain the multi-parameter fusion characteristic matrix.
According to an embodiment of the present application, fusing the pressure-related feature vector and the flow-related feature vector using a gaussian density map to obtain an initial multi-parameter fusion feature matrix includes: high useThe density chart fuses the pressure-related feature vector and the flow-related feature vector to obtain the initial multi-parameter fusion feature matrix by the following formula; wherein, the formula is:wherein->Mean vector representing the initial multi-parameter fusion feature matrix,/->A covariance matrix representing the initial multi-parameter fusion feature matrix,representing the pressure-related feature vector, +.>Representing the flow associated feature vector.
A gaussian density map is a graph, also known as a thermodynamic diagram or density map, used to visualize two-dimensional data distributions. It shows the distribution of data by plotting the density distribution of a set of points on a two-dimensional plane. In a gaussian density map, each data point is considered a gaussian distribution, and then all the gaussian distributions are superimposed together to form a smooth density distribution curve. The shade of each point on this surface represents the density value of the data points around that point, with darker colors representing greater density and lighter colors representing less density.
According to the embodiment of the application, the spatial multi-source fusion pre-verification information distribution optimization is carried out on the characteristic value of each position of the initial multi-parameter fusion characteristic matrix so as to obtain the multi-parameter fusion characteristic matrix. It should be appreciated that when the pressure-related feature vector and the flow-related feature vector are fused using a gaussian density map to obtain the multi-parameter fusion feature matrix, the multi-parameter fusion feature matrix is based on the mean feature vector of the pressure-related feature vector and the flow-related feature vectorThe multi-parameter fusion feature matrix is obtained by expanding row variance distribution through the position-by-position variance matrix of the pressure-related feature vector and the flow-related feature vector, so that the multi-parameter fusion feature matrix can be regarded as a global feature set formed by local feature sets of the row feature vectors. And, the mean feature vector also has a parameter timing correlation distribution relationship considering that the feature value of each position of the pressure correlation feature vector and the flow correlation feature vector expresses a specific local timing feature within the overall timing distribution of the pressure values and the flow values of the plurality of pipe sections. In this way, the multi-parameter fusion feature matrix can be regarded as a multi-source information association relationship between each row of feature vectors, which has the expressed parameter time sequence distribution information corresponding to the mean feature vector, in addition to the neighborhood distribution relationship which is associated with each other. Therefore, in order to promote the overall associative distribution expression effect of the multi-parameter fusion feature matrix, the applicant of the present application performs feature value for each position of the multi-parameter fusion feature matrixOptimizing the spatial multisource fusion pre-verification information distribution to obtain optimized characteristic values +.>The method is specifically expressed as follows: />Wherein->Is the eigenvalue of each position of the initial multi-parameter fusion eigenvector matrix,/for each position of the initial multi-parameter fusion eigenvector matrix>Is a mean feature matrix, < >>Represents a logarithmic function value based on 2, < +.>And->Setting up superparameters for a neighborhood->Is the eigenvalue of each position of the multi-parameter fusion eigenvalue matrix. The spatial multi-source fusion pre-verification information distribution optimization can be based on robustness class maximum likelihood estimation of feature spatial distribution fusion, the multi-parameter fusion feature matrix is used as a feature global set formed by feature local sets corresponding to a plurality of inter-related neighborhood parts, effective folding of the multi-source pre-verification information of each feature local set to the feature global set is achieved, and an optimization paradigm which can be used for evaluating standard expectations between internal spatial association and spatial information fusion change relations of the feature matrix is obtained through pre-verification information distribution construction under the multi-source condition, so that the information expression effect of the multi-parameter fusion feature matrix based on multi-source information spatial distribution association fusion is improved, and the integral association distribution expression effect of the multi-parameter fusion feature matrix is improved.
It should be noted that, in other specific examples of the present application, the pressure values and the flow values of the multiple pipe sections may be associated and fused by other ways to obtain a multi-parameter fusion feature matrix based on a deep convolutional neural network model, for example: normalizing the original pressure value and flow value data to ensure that the numerical range is between 0 and 1 so as to facilitate the training and optimization of the neural network model; and (3) data structuring: the normalized pressure value and flow value data are arranged according to the time sequence, and are formed into a multidimensional input vector, so that the neural network model can perform time sequence coding and feature extraction on the pressure value and the flow value data; and designing a deep convolutional neural network model, wherein the deep convolutional neural network model comprises a plurality of convolutional layers, a pooling layer and a full-connection layer and is used for carrying out time sequence coding and feature extraction on input pressure value and flow value data. The convolution layer is used for extracting local features, the pooling layer is used for reducing feature dimensions, and the full-connection layer is used for mapping the features to an output space; training the neural network model by using the marked pressure value and flow value data set to optimize model parameters and improve generalization capability of the model; after the neural network model is trained, the model can be used for predicting the pressure value and the flow value, and the prediction result is compared with the original data, so that the parameter association relation between the pressure value and the flow value is obtained. Then, the association relation can be applied to fusion of the pressure value and the flow value to obtain a multi-parameter fusion feature matrix; the multi-parameter fusion feature matrix is applied to monitoring and controlling the flow state of the pipeline, so that the real-time monitoring and controlling of a plurality of parameters such as the flow and the pressure of the pipeline can be realized, and the safety and the efficiency of the pipeline are improved.
More specifically, the S32 extracts a connected logical topology feature matrix based on the connected relation between the plurality of pipe segments. In particular, in one specific example of the present application, the S32 includes: constructing a connected logic topology matrix of the plurality of pipe sections, wherein the characteristic values of each position on the non-diagonal positions in the connected logic topology matrix are used for indicating whether the corresponding two pipe sections are connected or not; and the connected logic topology matrix passes through a topology feature extractor based on a convolutional neural network model to obtain the connected logic topology feature matrix.
According to the embodiment of the application, a connected logic topology matrix of the plurality of pipe sections is constructed, wherein the characteristic value of each position on the non-diagonal position in the connected logic topology matrix is used for indicating whether the corresponding two pipe sections are connected or not. In the process of evaluating the running state of the pipe network, the communication relation among the pipe sections is important to the running state analysis of the whole pipe network. For this purpose, in the technical solution of the present application, a connected logical topology matrix of the plurality of pipe segments is first constructed, where a feature value of each position on a non-diagonal position in the connected logical topology matrix is used to indicate whether or not the corresponding two pipe segments are connected. That is, the physical structural characteristics of the pipe network are better presented by constructing the connected logical topology matrix.
Topology location refers to the location of a node or element in a topology. The topological locations are typically relative, i.e., the location of a certain node or element is relative to other nodes or elements.
According to the embodiment of the application, the connected logic topology matrix is obtained through a topology feature extractor based on a convolutional neural network model. And the connected logic topology matrix passes through a topology feature extractor based on a convolutional neural network model to obtain a connected logic topology feature matrix. Among them, convolutional neural networks are a widely used neural network model, which is good at processing high-dimensional data such as images. In the application of state evaluation of water supply network, in order to capture the space topology characteristics between the network so as to better analyze the running state and characteristics, a topology characteristic extractor is constructed by using a convolutional neural network model, so as to convolve the connected logic topology matrix and extract the topology characteristics from the connected logic topology matrix.
More specifically, passing the connected logical topology matrix through a topology feature extractor based on a convolutional neural network model to obtain the connected logical topology feature matrix, including: each layer of the convolutional neural network model used as the filter performs the following steps on input data in forward transfer of the layer: carrying out convolution processing on input data to obtain a convolution characteristic diagram; pooling the convolution feature map along a channel dimension to obtain a pooled feature map; performing nonlinear activation on the pooled feature map to obtain an activated feature map; the output of the last layer of the convolutional neural network serving as the filter is the connected logic topology feature matrix, and the input of the first layer of the convolutional neural network serving as the filter is the connected logic topology matrix.
The convolutional neural network model comprises an input layer, a convolutional layer, an activation layer, a pooling layer and an output layer. Wherein the convolution layer extracts features on the input layer by sliding a convolution kernel (also called a filter) to form a Feature Map. A convolutional layer typically needs to specify parameters such as the number, size, step size, and fill pattern of the convolutional kernels. For example, two convolution kernels may be defined, 3x3 in size, 1 in step size, with zero padding. The active layer is used to introduce nonlinearities in the results of the convolutional layer output. In general, the ReLU function is widely used in convolutional neural networks, and its mathematical expression is: f (x) =max (0, x). The Pooling layer is used for reducing the dimension of data, and a common Pooling method is Max-Pooling (Max-Pooling), i.e. selecting a region with a fixed size from the feature map, and taking the largest value as the feature of the region. Notably, in the convolutional neural network model of the present application, the last pooling layer performs global mean pooling operation along the channel dimension on the input feature map, and the final output result is the connected logic topology feature matrix.
It should be noted that, in other specific examples of the present application, the connected logical topology feature matrix may also be extracted based on the connected relationships among the plurality of pipe segments in other manners, for example: determining the communication relation between pipe sections, which can be determined by the layout of the pipeline or the actual pipeline connection condition; establishing a topological relation matrix between pipe sections according to the communication relation, wherein each element represents whether two pipe sections are adjacent or communicated; and processing the topological relation matrix to obtain a connected logic topological feature matrix. This matrix describes the connectivity between pipe segments and can be used for subsequent analysis and modeling; some graph theory algorithms may be used to analyze the connected logical topology feature matrix, such as shortest path algorithms, maximum flow algorithms, etc.; finally, optimization and adjustment of the pipeline system can be performed according to the connected logic topology feature matrix, so that the efficiency and stability of the system are improved.
More specifically, the step S33 fuses the multi-parameter fusion feature matrix and the connected logic topology feature matrix to obtain the multi-mode association feature matrix. That is, the multi-parameter fusion feature matrix and the connected logic topology feature matrix are fused to obtain a multi-mode association feature matrix. Therefore, the multi-mode association characteristic matrix simultaneously contains association characteristic distribution modes among parameters and spatial topology characteristic distribution information of the pipe network, and has more excellent characteristic characterization capability.
Accordingly, in one possible implementation, the multi-modal associated feature matrix may be obtained by fusing the multi-parameter fusion feature matrix and the connected logical topology feature matrix by, for example: firstly, splicing a multi-parameter fusion feature matrix and a connected logic topology feature matrix to obtain a large feature matrix; then, the feature matrix is normalized so that the weights between different features can be equally considered; then, mapping the feature matrix into a higher dimensional space using linear transformation or non-linear transformation methods to enhance the correlation between features; then, using convolutional neural network or cyclic neural network to code the time sequence of the characteristic matrix to capture the time sequence relation between the characteristics; and finally, splicing the characteristic matrix after time sequence coding with the original characteristic matrix, and training the characteristic matrix by using a neural network model to obtain a final multi-mode associated characteristic matrix.
It should be noted that, in other specific examples of the present application, the multi-modal correlation feature matrix may also be extracted by other manners based on the pressure values and the flow values of the plurality of pipe segments and the communication relationship between the plurality of pipe segments, for example: pressure and flow data for a plurality of pipe segments are collected and a communication relationship between them is recorded. Such data may be collected and recorded by sensors or other devices; preprocessing the collected data, including data cleaning, denoising, normalization and the like, so as to ensure the quality and reliability of the data; suitable feature extraction methods are determined as needed for the particular problem. For example, a local neighborhood time sequence associated feature extraction method can be used for extracting time sequence feature vectors, and the expression mode and some optimization methods of text semantic associated features are used for improving the expression effect and generalization capability of a semantic matching feature matrix; according to the selected feature extraction method, extracting the features of the pressure value and the flow value of each pipe section, and combining the pressure value and the flow value into a feature vector; the extracted feature vectors are formed into a matrix, wherein each row represents a feature vector of a pipe segment and each column represents a feature dimension. Then, constructing an association matrix according to the communication relation between the pipelines, wherein each element represents the association degree between two pipeline sections; multiplying the constructed correlation matrix with the feature matrix to obtain a multi-modal correlation feature matrix, wherein each row represents a multi-modal correlation feature vector of a pipe section, and each column represents a correlation dimension; the obtained multi-mode correlation feature matrix is applied to specific problems, and can be used for monitoring and predicting the state of a pipeline or solving the multi-scale electric audit problem.
Specifically, in step S4, it is determined whether there is an abnormality in the operation state of the water supply network to be evaluated based on the multi-modal correlation feature matrix. In particular, in one specific example of the application, the multi-modal associated feature matrix is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the running state of the water supply network to be evaluated is abnormal, and more particularly, the multi-modal associated feature matrix is expanded into a classification feature vector based on a row vector or a column vector; 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. The method comprises the steps of determining a multi-mode correlation characteristic matrix according to a classification label, namely, performing classification processing by using a soft maximum function in the classifier, and mapping the multi-mode correlation characteristic matrix into the corresponding classification label, namely, whether the running state of the water supply network to be evaluated is abnormal or not. In practical application, the classification result can be used for prompting pipe network management personnel to timely carry out pipeline maintenance and management decision, and improving the reliability and management efficiency of the pipe network.
A classifier is a machine learning algorithm that is used to divide input data into different categories. The goal of the classifier is to learn a mapping function from input to output so that the input data can be correctly classified into known classes. Common classifiers include decision trees, naive bayes, support vector machines, logistic regression, etc.
It should be noted that, in other specific examples of the present application, whether the operation state of the water supply network to be evaluated is abnormal may be determined based on the multi-mode association feature matrix in other manners, for example: collecting various data of a water supply network, including a plurality of indexes such as water supply flow, water pressure, water temperature and the like, and converting the data into a numerical vector form; for each index, extracting the characteristics by using a corresponding model to obtain a characteristic vector; splicing the feature vectors of all indexes into a multi-mode feature matrix; for each time segment, a multi-mode association feature extraction method is used to obtain a feature vector of the time segment; forming a feature matrix by the feature vectors of all the time segments; for the water supply pipe network to be evaluated, the same method is used for obtaining a characteristic matrix of the water supply pipe network; calculating the similarity between the characteristic matrix of the water supply network to be evaluated and the characteristic matrix of the historical data, and using cosine similarity or other similarity measurement methods; and judging whether the running state of the water supply network to be evaluated is abnormal or not according to the similarity. And if the similarity is lower, indicating that the running state of the water supply network to be evaluated is abnormal.
In summary, the intelligent evaluation method for the pipe network state according to the embodiment of the application is explained, which comprehensively utilizes the pressure values and the flow values of a plurality of pipe sections in the pipe network, and combines deep learning and artificial intelligence technology to realize real-time monitoring and evaluation of the water supply pipe network state so as to optimize the operation mode of the water supply pipe network and improve the water supply efficiency. Meanwhile, the dependence on traditional manual inspection can be reduced, the working efficiency is improved, and the inspection cost is reduced.
According to the embodiment of the application, an intelligent pipe network state evaluation system is also provided.
Fig. 5 is a block diagram of a pipe network state intelligent assessment system according to an embodiment of the present application. As shown in fig. 5, the intelligent pipe network state evaluation system 300 according to the embodiment of the present application includes: the information acquisition module 310 is used for installing a plurality of pressure sensors and a plurality of flow sensors at proper positions of the water supply network to be evaluated; the information receiving module 320 is configured to receive pressure values and flow values of a plurality of pipe sections in the water supply network to be evaluated, which are acquired by the plurality of pressure sensors and the plurality of flow sensors; an associated feature extraction module 330, configured to extract a multi-mode associated feature matrix based on the pressure values and the flow values of the plurality of pipe segments and the communication relationship between the plurality of pipe segments; and a state evaluation module 340, configured to determine whether an abnormal operation state exists in the water supply network to be evaluated based on the multi-mode correlation feature matrix.
As described above, the pipe network state intelligent assessment system 300 according to the embodiment of the present application may be implemented in various wireless terminals, for example, a server or the like having a pipe network state intelligent assessment algorithm. In one possible implementation, the intelligent pipe network state assessment system 300 according to embodiments of the present application may be integrated into a wireless terminal as a software module and/or hardware module. For example, the pipe network state intelligent assessment system 300 can be a software module in the operating system of the wireless terminal, or can be an application developed for the wireless terminal; of course, the intelligent assessment system 300 can also be one of many hardware modules of the wireless terminal.
Alternatively, in another example, the intelligent pipe network state assessment system 300 and the wireless terminal may be separate devices, and the intelligent pipe network state assessment system 300 may be connected to the wireless terminal through a wired and/or wireless network and transmit interactive information in a agreed data format.
Fig. 6 is a schematic view of a scenario of a pipe network state intelligent assessment method according to an embodiment of the present application. As shown in fig. 6, in this application scenario, pressure values of a plurality of pipe sections in the water supply network to be evaluated are acquired by a plurality of pressure sensors (e.g., va, vb,..vc as illustrated in fig. 6); and obtaining flow values for a plurality of pipe segments in the water supply network under evaluation by a plurality of flow sensors (e.g., V1, V2, vn as illustrated in fig. 6). Then, the data are input into a server (for example, S in fig. 6) deployed with an intelligent evaluation algorithm for pipe network status, wherein the server can process the input data with the intelligent evaluation algorithm for pipe network status to generate a classification result for indicating whether the operation status of the water supply pipe network to be evaluated is abnormal.
The foregoing description of the embodiments of the present disclosure has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the various embodiments described. The terminology used herein was chosen in order to best explain the principles of the embodiments, the practical application, or the improvement of technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (7)
1. The intelligent pipe network state evaluation method is characterized by comprising the following steps of: installing a plurality of pressure sensors and a plurality of flow sensors at proper positions of a water supply network to be evaluated; receiving pressure values and flow values of a plurality of pipe sections in the water supply network to be evaluated, which are acquired by the plurality of pressure sensors and the plurality of flow sensors; extracting a multi-mode association feature matrix based on the pressure values and the flow values of the pipe sections and the communication relation between the pipe sections; and determining whether the running state of the water supply network to be evaluated is abnormal or not based on the multi-mode association characteristic matrix.
2. The intelligent pipe network state assessment method according to claim 1, wherein extracting the multi-modal correlation feature matrix based on the pressure values and the flow values of the plurality of pipe segments and the communication relation between the plurality of pipe segments comprises: performing parameter association and fusion on the pressure values and the flow values of the pipe sections based on the deep convolutional neural network model to obtain a multi-parameter fusion feature matrix; extracting a connected logic topology feature matrix based on the connected relation among the pipe sections; and fusing the multi-parameter fusion feature matrix and the connected logic topology feature matrix to obtain the multi-mode association feature matrix.
3. The intelligent pipe network state assessment method according to claim 2, wherein performing parameter association and fusion on the pressure values and the flow values of the plurality of pipe segments based on a deep convolutional neural network model to obtain a multi-parameter fusion feature matrix comprises: arranging the pressure values and the flow values of the pipe sections into pressure input vectors and flow input vectors according to the dimensions of pipe section samples; respectively passing the pressure input vector and the flow input vector through an inter-pipe section parameter correlation feature extractor comprising a first convolution layer and a second convolution layer to obtain a pressure correlation feature vector and a flow correlation feature vector; and fusing the pressure-related feature vector and the flow-related feature vector by using a Gaussian density map to obtain the multi-parameter fusion feature matrix.
4. The intelligent pipe network state assessment method according to claim 3, wherein fusing the pressure-related feature vector and the flow-related feature vector to obtain the multi-parameter fusion feature matrix using a gaussian density map comprises: fusing the pressure-related feature vector and the flow-related feature vector by using a Gaussian density map to obtain an initial multi-parameter fusion feature matrix; and performing spatial multi-source fusion pre-verification information distribution optimization on the characteristic value of each position of the initial multi-parameter fusion characteristic matrix to obtain the multi-parameter fusion characteristic matrix.
5. The intelligent pipe network state assessment method according to claim 4, wherein performing spatial multi-source fusion pre-verification information distribution optimization on the feature value of each position of the initial multi-parameter fusion feature matrix to obtain the multi-parameter fusion feature matrix comprises: carrying out spatial multi-source fusion pre-verification information distribution optimization on the characteristic value of each position of the initial multi-parameter fusion characteristic matrix by using the following optimization formula to obtain the multi-parameter fusion characteristic matrix; wherein, the formula is:wherein->Is the eigenvalue of each position of the initial multi-parameter fusion eigenvector matrix,/for each position of the initial multi-parameter fusion eigenvector matrix>Is a mean feature matrix, < >>Represents a logarithmic function value based on 2, < +.>And->Setting up superparameters for a neighborhood->Is the eigenvalue of each position of the multi-parameter fusion eigenvalue matrix.
6. The intelligent pipe network state assessment method according to claim 5, wherein extracting the connected logical topology feature matrix based on the connected relation between the pipe segments comprises: constructing a connected logic topology matrix of the plurality of pipe sections, wherein the characteristic values of each position on the non-diagonal positions in the connected logic topology matrix are used for indicating whether the corresponding two pipe sections are connected or not; and the connected logic topology matrix passes through a topology feature extractor based on a convolutional neural network model to obtain the connected logic topology feature matrix.
7. The intelligent pipe network state evaluation method according to claim 6, wherein determining whether an abnormality exists in the operation state of the water supply network to be evaluated based on the multi-modal correlation feature matrix comprises: and the multi-mode association characteristic matrix passes through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the running state of the water supply network to be evaluated is abnormal or not.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310844253.6A CN116557787B (en) | 2023-07-11 | 2023-07-11 | Intelligent evaluation system and method for pipe network state |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310844253.6A CN116557787B (en) | 2023-07-11 | 2023-07-11 | Intelligent evaluation system and method for pipe network state |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116557787A true CN116557787A (en) | 2023-08-08 |
| CN116557787B CN116557787B (en) | 2023-09-15 |
Family
ID=87486580
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310844253.6A Active CN116557787B (en) | 2023-07-11 | 2023-07-11 | Intelligent evaluation system and method for pipe network state |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116557787B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117151649A (en) * | 2023-09-15 | 2023-12-01 | 浙江蓝城萧立建设管理有限公司 | Construction method management and control system and method based on big data analysis |
| CN117370818A (en) * | 2023-12-05 | 2024-01-09 | 四川发展环境科学技术研究院有限公司 | Intelligent diagnosis method and intelligent environment-friendly system for water supply and drainage pipe network based on artificial intelligence |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013040667A1 (en) * | 2011-09-19 | 2013-03-28 | Universidade Estadual De Campinas . Unicamp | Gas leak detection system and method, method for determining the importance and location of a gas leak by means of neural networks, and use in rigid and/or flexible pipes |
| CN103939750A (en) * | 2014-05-05 | 2014-07-23 | 重庆大学 | Detecting identifying and positioning method for fire-fighting water pipe network leakage |
| CN112610903A (en) * | 2020-12-10 | 2021-04-06 | 合肥学院 | Water supply pipe network leakage positioning method based on deep neural network model |
| CN115493093A (en) * | 2022-09-01 | 2022-12-20 | 北京云庐科技有限公司 | Steam heating pipe network leakage positioning method and system based on mechanical simulation |
| KR102504054B1 (en) * | 2022-10-14 | 2023-02-28 | 주식회사 아라아이티이엔지 | Multifunctional pipe chamber and air ventilation system using thereof |
| CN116182089A (en) * | 2023-02-24 | 2023-05-30 | 宿迁莱卓网络科技有限公司 | Long-distance conveying pipeline leakage detection method and system |
| CN116228014A (en) * | 2023-02-24 | 2023-06-06 | 国网安徽省电力有限公司经济技术研究院 | DC power distribution network benefit evaluation system and method for infrastructure network access |
| CN116336400A (en) * | 2023-05-30 | 2023-06-27 | 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 |
-
2023
- 2023-07-11 CN CN202310844253.6A patent/CN116557787B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013040667A1 (en) * | 2011-09-19 | 2013-03-28 | Universidade Estadual De Campinas . Unicamp | Gas leak detection system and method, method for determining the importance and location of a gas leak by means of neural networks, and use in rigid and/or flexible pipes |
| CN103939750A (en) * | 2014-05-05 | 2014-07-23 | 重庆大学 | Detecting identifying and positioning method for fire-fighting water pipe network leakage |
| CN112610903A (en) * | 2020-12-10 | 2021-04-06 | 合肥学院 | Water supply pipe network leakage positioning method based on deep neural network model |
| CN115493093A (en) * | 2022-09-01 | 2022-12-20 | 北京云庐科技有限公司 | Steam heating pipe network leakage positioning method and system based on mechanical simulation |
| KR102504054B1 (en) * | 2022-10-14 | 2023-02-28 | 주식회사 아라아이티이엔지 | Multifunctional pipe chamber and air ventilation system using thereof |
| CN116182089A (en) * | 2023-02-24 | 2023-05-30 | 宿迁莱卓网络科技有限公司 | Long-distance conveying pipeline leakage detection method and system |
| CN116228014A (en) * | 2023-02-24 | 2023-06-06 | 国网安徽省电力有限公司经济技术研究院 | DC power distribution network benefit evaluation system and method for infrastructure network access |
| CN116336400A (en) * | 2023-05-30 | 2023-06-27 | 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 |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117151649A (en) * | 2023-09-15 | 2023-12-01 | 浙江蓝城萧立建设管理有限公司 | Construction method management and control system and method based on big data analysis |
| CN117151649B (en) * | 2023-09-15 | 2024-02-23 | 浙江蓝城萧立建设管理有限公司 | Construction method management and control system and method based on big data analysis |
| CN117370818A (en) * | 2023-12-05 | 2024-01-09 | 四川发展环境科学技术研究院有限公司 | Intelligent diagnosis method and intelligent environment-friendly system for water supply and drainage pipe network based on artificial intelligence |
| CN117370818B (en) * | 2023-12-05 | 2024-02-09 | 四川发展环境科学技术研究院有限公司 | Intelligent diagnosis method and intelligent environment-friendly system for water supply and drainage pipe network based on artificial intelligence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116557787B (en) | 2023-09-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116557787B (en) | Intelligent evaluation system and method for pipe network state | |
| CN108921051B (en) | Pedestrian attribute identification network and technology based on cyclic neural network attention model | |
| CN111694879B (en) | Multielement time sequence abnormal mode prediction method and data acquisition monitoring device | |
| CN112101480B (en) | Multivariate clustering and fused time sequence combined prediction method | |
| Che et al. | Hybrid multimodal fusion with deep learning for rolling bearing fault diagnosis | |
| CN116625438A (en) | Gas pipe network safety on-line monitoring system and method thereof | |
| CN112132430B (en) | Reliability evaluation method and system for distributed state sensor of power distribution main equipment | |
| CN115618296A (en) | Dam monitoring time sequence data anomaly detection method based on graph attention network | |
| CN116684878B (en) | 5G information transmission data safety monitoring system | |
| CN117041017B (en) | Intelligent operation and maintenance management method and system for data center | |
| CN114266301A (en) | Intelligent power equipment fault prediction method based on graph convolution neural network | |
| CN114265913A (en) | Space-time prediction algorithm based on federal learning on industrial Internet of things edge equipment | |
| CN116307152A (en) | Traffic prediction method for space-time interactive dynamic graph attention network | |
| CN114048546B (en) | Method for predicting residual service life of aeroengine based on graph convolution network and unsupervised domain self-adaption | |
| CN117156442A (en) | Cloud data security protection method and system based on 5G network | |
| CN114897085A (en) | Clustering method based on closed subgraph link prediction and computer equipment | |
| Zhao et al. | Research on digital twin driven rolling bearing model-data fusion life prediction method | |
| CN111126477A (en) | Learning and reasoning method of hybrid Bayesian network | |
| CN117388893B (en) | Multi-device positioning system based on GPS | |
| Zhang et al. | Spatial-temporal dual-channel adaptive graph convolutional network for remaining useful life prediction with multi-sensor information fusion | |
| CN117072891B (en) | Real-time intelligent leakage monitoring and positioning method for hydrogen conveying pipe network under abnormal sample-free condition | |
| CN114399066A (en) | Mechanical equipment predictability maintenance system and maintenance method based on weak supervision learning | |
| CN114169091A (en) | Method for establishing prediction model of residual life of engineering mechanical part and prediction method | |
| CN116402777B (en) | Power equipment detection method and system based on machine vision | |
| CN116599857B (en) | Digital twin application system suitable for multiple scenes of Internet of things |
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 |