CN114399113A - Natural gas pipe network management method and system - Google Patents
Natural gas pipe network management method and system Download PDFInfo
- Publication number
- CN114399113A CN114399113A CN202210045160.2A CN202210045160A CN114399113A CN 114399113 A CN114399113 A CN 114399113A CN 202210045160 A CN202210045160 A CN 202210045160A CN 114399113 A CN114399113 A CN 114399113A
- Authority
- CN
- China
- Prior art keywords
- pipe network
- maintenance
- information
- natural gas
- time
- 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
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 title claims abstract description 168
- 239000003345 natural gas Substances 0.000 title claims abstract description 84
- 238000007726 management method Methods 0.000 title claims abstract description 39
- 238000012423 maintenance Methods 0.000 claims abstract description 162
- 238000000034 method Methods 0.000 claims description 36
- 238000003860 storage Methods 0.000 claims description 21
- 238000001514 detection method Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 8
- 238000012549 training Methods 0.000 description 32
- 239000007789 gas Substances 0.000 description 21
- 230000006870 function Effects 0.000 description 14
- 239000000463 material Substances 0.000 description 14
- 230000008569 process Effects 0.000 description 14
- 238000010586 diagram Methods 0.000 description 10
- 238000012545 processing Methods 0.000 description 8
- 239000013598 vector Substances 0.000 description 8
- 238000010801 machine learning Methods 0.000 description 7
- 230000002123 temporal effect Effects 0.000 description 7
- 230000005540 biological transmission Effects 0.000 description 5
- 230000007613 environmental effect Effects 0.000 description 5
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 238000006243 chemical reaction Methods 0.000 description 4
- 238000009792 diffusion process Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 230000008439 repair process Effects 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 230000003042 antagnostic effect Effects 0.000 description 2
- 238000012512 characterization method Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000000712 assembly Effects 0.000 description 1
- 238000000429 assembly Methods 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 210000002310 elbow joint Anatomy 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000003607 modifier Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000009423 ventilation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
An embodiment of the present specification provides a natural gas pipeline network management method, including: acquiring natural gas pipe network information of at least one region, wherein the pipe network information comprises the running time of a natural gas management system and pipe network air leakage information; extracting feature information based on the running time and the air leakage information; and inputting the characteristic information into a maintenance time prediction model to predict the maintenance time of the pipe network.
Description
Technical Field
The specification relates to the field of natural gas pipe network management, in particular to a natural gas pipe network management method and system.
Background
The natural gas pipe network carries important tasks such as natural gas transmission, energy transportation and the like day and night, and is an indispensable important component of natural gas transmission. The life cycle management and control of the natural gas pipe network is effective management and control over infrastructure of natural gas equipment, the existing natural gas pipe network management mainly depends on personnel self-checking, but because the natural gas pipe network is long in line length, multiple in points, wide in range, scattered by personnel and other factors, personnel self-checking hardly finds the pipe network problem in time, and the maintenance is carried out before the pipe network is damaged, so that the management efficiency of the pipe network is lower.
Therefore, it is desirable to provide a method for managing a natural gas pipe network, which predicts the maintenance time of the pipe network by obtaining information of the natural gas pipe network, realizes the full life cycle intelligent management of the natural gas pipe network, prevents the natural gas pipe network from being used normally due to the full life cycle, and avoids causing serious loss.
Disclosure of Invention
One embodiment of the present specification provides a method for managing a natural gas pipeline network. The method comprises the following steps: acquiring natural gas pipe network information of at least one region, wherein the pipe network information comprises the running time of a natural gas management system and pipe network air leakage information; extracting feature information based on the running time and the air leakage information; and inputting the characteristic information into a maintenance time prediction model to predict the maintenance time of the pipe network.
One embodiment of the present description provides a natural gas pipeline network management system. The system comprises: the information acquisition module is used for acquiring natural gas pipe network information of at least one region, wherein the pipe network information comprises the running time of a natural gas management system and pipe network air leakage information; the characteristic extraction module is used for extracting characteristic information based on the running time and the air leakage information; and the time prediction module is used for inputting the characteristic information into a maintenance time prediction model and predicting the maintenance time of the pipe network.
One of the embodiments of the present specification provides a natural gas pipeline network management device, which includes at least one processor and at least one memory; the at least one memory is for storing computer instructions; the at least one processor is configured to execute at least a portion of the computer instructions to implement the above-described natural gas pipeline network management method.
One of the embodiments of the present disclosure provides a computer-readable storage medium, where the storage medium stores computer instructions, and when the computer reads the computer instructions in the storage medium, the computer executes the above-mentioned natural gas pipeline network management method.
Drawings
The present description will be further explained by way of exemplary embodiments, which will be described in detail by way of the accompanying drawings. These embodiments are not intended to be limiting, and in these embodiments like numerals are used to indicate like structures, wherein:
fig. 1 is a schematic diagram of an application scenario of a natural gas pipeline management system according to some embodiments of the present description;
FIG. 2 is an exemplary flow diagram of a natural gas pipeline network management method according to some embodiments described herein;
FIG. 3 is an exemplary diagram of a method of maintaining temporal prediction, according to some embodiments herein;
FIG. 4 is an exemplary diagram of a maintenance value prediction method according to some embodiments described herein;
fig. 5 is an exemplary block diagram of a natural gas pipeline network management system according to some embodiments described herein.
Detailed Description
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings used in the description of the embodiments will be briefly described below. It is obvious that the drawings in the following description are only examples or embodiments of the present description, and that for a person skilled in the art, the present description can also be applied to other similar scenarios on the basis of these drawings without inventive effort. Unless otherwise apparent from the context, or otherwise indicated, like reference numbers in the figures refer to the same structure or operation.
It should be understood that "system", "apparatus", "unit" and/or "module" as used herein is a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, other words may be substituted by other expressions if they accomplish the same purpose.
As used in this specification and the appended claims, the terms "a," "an," "the," and/or "the" are not intended to be inclusive in the singular, but rather are intended to be inclusive in the plural, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that steps and elements are included which are explicitly identified, that the steps and elements do not form an exclusive list, and that a method or apparatus may include other steps or elements.
Flow charts are used in this description to illustrate operations performed by a system according to embodiments of the present description. It should be understood that the preceding or following operations are not necessarily performed in the exact order in which they are performed. Rather, the various steps may be processed in reverse order or simultaneously. Meanwhile, other operations may be added to the processes, or a certain step or several steps of operations may be removed from the processes.
Fig. 1 is a schematic diagram of an application scenario of a natural gas pipeline management system 100 according to some embodiments of the present description. The application scenario may include a server 110, a processor 112, a storage device 120, a user terminal 130, a network 140, and a natural gas pipeline network 150.
The natural gas pipe network management system can be used for a service platform for natural gas pipe network management, and the purpose of natural gas pipe network management can be achieved by implementing the method and/or the process disclosed in the application.
The server 110 may communicate with the processor 112, the storage device 120, and the user terminal 130 through the network 140 to provide various functions of natural gas pipeline network management, and the storage device 120 may store all information of the operation process of the natural gas pipeline network. In some embodiments, the user terminal 130 may send a natural gas pipeline network information acquisition request to the server 110 and receive feedback information of the server 110. The above information transfer relationship between the devices is merely an example, and the present application is not limited thereto.
In some embodiments, storage device 120 may be included in server 110, user terminal 130, and possibly other components.
In some embodiments, processor 112 may be included in server 110, user terminal 130, and possibly other components.
The server 110 may be used to manage resources and process data and/or information from at least one component of the present system or an external data source (e.g., a cloud data center). In some embodiments, the server 110 may be a single server or a group of servers. The set of servers can be centralized or distributed (e.g., the servers 110 can be a distributed system), can be dedicated, or can be serviced by other devices or systems at the same time. In some embodiments, the server 110 may be regional or remote. In some embodiments, the server 110 may be implemented on a cloud platform, or provided in a virtual manner.
The above examples are intended only to illustrate the broad scope of the user terminal 130 device and not to limit its scope.
Natural gas pipeline network 150 refers to a network of pipelines that transport natural gas from a production site or processing plant to a municipal distribution center or customer. In some embodiments, the natural gas pipeline network 150 may include gas collection pipelines, gas transmission pipelines, gas distribution pipelines, and the like. Gas collection piping refers to piping from a gas field wellhead through a gas collection station to a gas treatment plant or a start-point gas station for collecting untreated natural gas produced from a formation. The gas transmission pipeline refers to a pipeline from a gas treatment plant or a starting point gas pressing station of a gas source to a gas distribution center, a large-scale user or a gas storage warehouse of each large city, and pipelines which are mutually communicated among the gas sources and used for transmitting natural gas which is processed and meets the pipeline transmission quality standard. The distribution pipeline is a pipeline from the urban pressure regulating metering station to the user branch line. In some embodiments, the natural gas pipeline network 150 may be assembled from individual pipes connected one by one.
It should be noted that the above description of the application scenario of the natural gas pipeline network management system is only for convenience of description, and the description is not limited to the scope of the illustrated embodiments. It will be understood by those skilled in the art that, having the benefit of the teachings of this system, various components may be combined in any combination or sub-components may be connected to other components without departing from such teachings. In some embodiments, the server, processor and memory disclosed in fig. 1 may be separate units in one component, or may be a single component that performs the functions of two or more of the above described components. For example, the components may share one storage unit, or each component may have a storage unit. Such variations are within the scope of the present disclosure.
Fig. 2 is an exemplary flow diagram of a natural gas pipeline network management method according to some embodiments described herein. As shown in fig. 2, the process 200 may include the following steps. In some embodiments, the process 200 may be performed by the processor 112.
And step 210, acquiring the natural gas pipe network information of at least one region. In some embodiments, the information acquisition module 510 performs step 210.
The area may be a cell, a school, a city, or a specific area defined, and may be determined according to actual management requirements.
In some embodiments, the natural gas pipeline network information may include runtime of the natural gas management system and pipeline network leakage information.
The running time of the system is the time that the natural gas pipe network system runs from the system starting (which may include the first starting or maintenance restarting) to the current running time information collection, or the time that the natural gas pipe network system has run since the last maintenance. For example, if the natural gas pipeline system is operated for the first time in 2021 year, 1 month and 1 day, and is not maintained in 2021 year, 2 months and 1 day today, the operation time of the system is 31 days. For another example, if the last time of the maintenance restart of the natural gas pipe network system is 2021, 3 and 1 days, and the natural gas pipe network system is not maintained by 2021, 4 and 1 days, the operation time of the system is 31 days.
The pipe network leakage information is information related to natural gas leakage. In some embodiments, the grid leak information may include gas concentration, diffusion rate, leak time, duration of leak, location of leak, etc. of the leaked natural gas.
In some embodiments, the processor 112 may obtain the runtime of the system based on historical information. Historical information may refer to various types of information collected and recorded in the past, including the runtime of the system. In some embodiments, the processor 112 may obtain the gas concentration, diffusion rate, leak time, and elapsed time of the leaked natural gas via a gas detector. In some embodiments, the processor 112 may obtain the leak location of the leaked natural gas by detecting a record of the leak information. In some embodiments, the processor 112 may integrate information on gas concentration, diffusion rate, leakage time, duration of leakage, leakage location, etc. of the leaked natural gas to obtain the pipe network leakage information.
And step 220, extracting characteristic information based on the running time and the air leakage information. In some embodiments, the feature extraction module 520 performs step 220.
The characteristic information can be abstract expression obtained by characteristic extraction of the running time of the system and the characteristics of the pipe network air leakage information. In some embodiments, the feature information may be in the form of a feature vector or matrix.
In some embodiments, the extracted feature information may be obtained by a conversion algorithm, a model process, or the like.
In some embodiments, the runtime and network leakage information may be vectorized to obtain the characterization information. Specifically, a vector corresponding to the running time and the pipe network air leakage information can be determined by using a conversion algorithm. The conversion algorithm may include a one-hot encoding algorithm, a collinear vector algorithm, a Glove algorithm, and the like. Illustratively, the running time and pipe network air leakage information can be converted into vector representation by adopting a one-hot coding algorithm. one-hot encoding, also known as one-bit-efficient encoding or one-hot encoding, mainly uses an N-bit status register to encode N states, each state having an independent register bit and only one bit being efficient at any time. One-Hot encoding is the representation of classification variables as binary vectors. For example, assuming that the tag type includes run time and air leakage information, the principle of encoding N states according to an N-bit state register, where N is 2, is that after encoding: the label corresponding to the run time may be represented as [1, 0], and the label corresponding to the air leakage information may be represented as [0, 1 ].
In some embodiments, the vectors corresponding to the running time and the pipe network air leakage information may be spliced or superimposed to obtain a feature vector or a matrix.
In some embodiments, the runtime and grid leak information may be processed using a first model to obtain characterization information. For example, runtime and grid leak information may be input into a first model, from which characteristic information is output. The first model may be a Word2Vec model, a BERT model, a CNN model, a DNN model, or the like. The first model may be trained using the historical run-time and historical leak information as training data such that the first model is able to output its corresponding vector or matrix representation based on the run-time and leak information. The label to which the training data corresponds may be determined by a conversion algorithm, manual input, or historical data.
And 230, inputting the characteristic information into a maintenance time prediction model to predict the maintenance time of the pipe network. In some embodiments, the prediction module 530 performs step 230.
The predicted pipe network maintenance time is a time point for maintaining the pipe network, which is obtained through prediction of the maintenance time prediction model. For example, today is 1/2022, and the maintenance time of the pipe network predicted by the maintenance time prediction model may be 6/30/2022.
In some embodiments, after the characteristic information is input into the maintenance time prediction model, the maintenance time prediction model can output the predicted pipe network maintenance time.
In some embodiments, the maintenance time prediction model may be constructed based on a deep learning neural network model. Exemplary deep learning neural network models can include convolutional network models (CNNs), fully convolutional neural network (FCN) models, Generative Antagonistic Networks (GANs), Back Propagation (BP) machine learning models, Radial Basis Function (RBF) machine learning models, Deep Belief Networks (DBNs), Elman machine learning models, and the like, or combinations thereof.
For more details on maintaining the temporal prediction model, reference may be made to other parts of this specification (for example, fig. 3 and the related description thereof), and details are not repeated here.
Through predicting the maintenance time of the pipe network, the natural gas pipe network can be maintained before being damaged, and the problem that the underground pipe network cannot be normally used due to the fact that the underground pipe network reaches the full life cycle is avoided, so that serious loss is avoided. In addition, the system operation time and the pipe network air leakage information are jointly used as the input of a pipe network maintenance time prediction model, and the accuracy of the pipe network maintenance time prediction can be improved by adopting a mode of comprehensively judging the system operation time and the air leakage information.
FIG. 3 is an exemplary diagram of a method of maintaining temporal prediction, according to some embodiments described herein. As shown in FIG. 3, the method 300 includes a running time 310-1, pipe network air leakage information 310-2, characteristic information 320-1, a pipe network maintenance value 320-2, a pipe network vibration fatigue factor 320-3, a maintenance time prediction model 330, a pipe network maintenance time 340, an initial maintenance time prediction model 350, and a first training sample 360.
In some embodiments, as shown in FIG. 3, the input to maintain the temporal prediction model 330 may be feature information 320-1. The characteristic information 320-1 may be obtained based on the runtime 310-1 and the air leak information 310-2. For more about the extraction of the feature information 320-1, reference may be made to other parts of this specification (e.g., fig. 2 and the related description thereof), and details are not repeated here.
In some embodiments, the inputs to the maintenance time prediction model 330 may also include a pipe network maintenance value 320-2. The dashed boxes in fig. 3 indicate alternatives.
The pipe network maintenance value may be a numeric value or a letter or the like that can reflect the priority of the maintenance process. For example, a pipe network maintenance value may be represented by a number between 1 and 10, or the letters a-f, or a star rating, with a larger value, a larger dictionary order, or a higher star rating indicating a higher priority for maintenance processing.
In some embodiments, the pipe network maintenance value may be obtained based on pipe network maintenance information and pipe network environment information. In some embodiments, the pipe network maintenance value may be obtained by a maintenance value prediction model. For more details about the pipe network maintenance value, reference may be made to other parts of this specification (for example, fig. 4 and the related description thereof), and details are not described herein again.
In some embodiments, the inputs to the maintenance time prediction model 330 may also include a pipe network vibration fatigue factor 320-3.
The pipe network vibration fatigue factor can be used for reflecting the strength of vibration fatigue generated by vibration of the pipeline. For example, the pipe network vibration fatigue factor can be expressed by a value between 1 and 10, and a larger value indicates a greater strength of the pipe fatigue due to vibration.
In some embodiments, the pipe network vibration fatigue factor may be obtained based on a pipe network vibration frequency and a pipe network vibration time. In some embodiments, the pipe network vibration fatigue factor may be calculated directly based on the pipe network vibration frequency and the pipe network vibration time. In some embodiments, the pipe network vibration fatigue factor may be obtained by inputting the pipe network vibration frequency and the pipe network vibration time into the second model, and outputting the pipe network vibration fatigue factor in the second mode.
In some embodiments, the processor 112 may obtain the pipe network vibration time by detecting with a sensor. For example, the processor 112 may detect that the pipe network vibrates for a certain time period of a certain day via the sensors and determine the vibration time of the pipe network. In some embodiments, the processor 112 may obtain the vibration frequency of the pipe network through periodic detection by the sensor. For more details on the vibration frequency of the pipe network, reference may be made to other parts of this specification (for example, fig. 4 and the related description thereof), and details are not repeated here.
In some embodiments, the process of calculating the pipe network vibration fatigue factor may be expressed as: the pipe network vibration fatigue factor is pipe network vibration frequency and pipe network vibration time/pipe material strength.
The larger the pipe network vibration frequency and the pipe network vibration time are, the more easily the pipeline is fatigued, and the larger the corresponding pipe network vibration fatigue factor is. By acquiring the pipe network vibration frequency and the pipe network vibration time, a foundation can be laid for accurately calculating the pipe network vibration fatigue factors subsequently. The strength of a pipe material is the ability of the pipe material to resist failure under an external force. In some embodiments, the pipe material strength may include tensile strength, compressive strength, shear strength, bending strength, and the like. The smaller the strength of the pipeline material is, the more easily the pipeline is fatigued, and the larger the corresponding vibration fatigue factor of the pipe network is. Through setting up pipeline material intensity, can consider comprehensively that different materials produce tired difficult and easy degree's influence to the pipeline to can promote the accuracy of confirming pipe network vibration fatigue factor.
In some embodiments, the pipe network vibration frequency and the pipe network vibration time may be input into the second model to obtain the pipe network vibration fatigue factor. The second model may be a CNN model, DNN model, or the like. The historical pipe network vibration frequency and the historical pipe network vibration time can be used as training data to train the second model, so that the second model can output pipe network vibration fatigue factors based on the pipe network vibration frequency and the pipe network vibration time. The label of the training data can be a manually labeled pipe network vibration fatigue factor.
In some embodiments, the input of the maintenance time prediction model 330 may be a combination of the characteristic information and a pipe network maintenance value and a pipe network vibration fatigue factor, and the output of the maintenance time prediction model 330 is the pipe network maintenance time 340.
In some embodiments, as shown in FIG. 3, the model parameters that maintain the temporal prediction model 330 may be trained using a plurality of labeled first training samples 360. In some embodiments, multiple sets of first training samples 360 may be obtained based on the historical data, and each set of first training samples 360 may include multiple training data and labels corresponding to the training data. Taking the input of the maintenance time prediction model 330 as the feature information 320-1 as an example, the training data may include feature information corresponding to historical operating time and historical air leakage information, and the label of the training data may be manually labeled maintenance time of the pipe network. Taking the input of the maintenance time prediction model 330 as the characteristic information 320-1 and the pipe network maintenance value 320-2 as an example, the training data may include characteristic information corresponding to historical operating time and historical gas leakage information, and a pipe network maintenance value obtained based on historical pipe network maintenance information and historical pipe network environment information, and the label of the training data may be manually labeled pipe network maintenance time. Taking the input of the maintenance time prediction model 330 as the characteristic information 320-1, the pipe network maintenance value 320-2 and the pipe network vibration fatigue factor 320-3 as an example, the training data may include characteristic information corresponding to the historical operating time and the historical air leakage information, a historical pipe network maintenance value and a pipe network vibration fatigue factor calculated based on the historical pipe network vibration frequency and the historical pipe network vibration time, and the label of the training data may be the manually labeled pipe network maintenance time.
Parameters of the initial maintenance time prediction model 350 can be updated through multiple sets of the first training samples 360, so that the trained initial maintenance time prediction model 350 is obtained. The parameters of the maintenance time prediction model 330 are derived from the trained initial maintenance time prediction model 350. Wherein the parameters may be communicated in any common manner.
In some embodiments, the parameters of the initial maintenance temporal prediction model 350 may be iteratively updated based on a plurality of first training samples such that the loss function of the model satisfies a preset condition. For example, the loss function converges, or the loss function value is smaller than a preset value. When the loss function meets the preset condition, the model training is completed, and a trained initial maintenance time prediction model 350 is obtained. The maintenance time prediction model 330 and the trained initial maintenance time prediction model 350 have the same model structure.
The maintenance time of the pipe network is predicted through the maintenance time prediction model, the natural gas pipe network can be maintained before being damaged, and the problem that the underground pipe network cannot be normally used due to the fact that the underground pipe network reaches the full life cycle is avoided, so that serious loss is avoided. The pipe network maintenance value or the pipe network vibration fatigue factor is used as the input of the maintenance time prediction model to obtain the prediction result combining the characteristic information obtained based on the operation time and the air leakage information and the pipe network maintenance value or the correlation between the characteristic information obtained based on the operation time and the air leakage information and the pipe network vibration fatigue factor, so that the maintenance time prediction model can predict the pipe network maintenance time more accurately.
It should be noted that the above description of the method for predicting the flow maintenance time is only for illustration and description, and does not limit the application scope of the present specification. Various modifications and changes to the flow maintenance time prediction method will be apparent to those skilled in the art in light of this disclosure. However, such modifications and variations are intended to be within the scope of the present description. For example, the input to the second model may also include the pipe material strength. The pipe network vibration frequency, the pipe network vibration time and the pipeline material strength can be input into the second model to obtain the pipe network vibration fatigue factor. The second model may be a CNN model, DNN model, or the like. The historical pipe network vibration frequency, the historical pipe network vibration time and the historical pipeline material strength can be used as training data to train the second model, so that the second model can output pipe network vibration fatigue factors based on the pipe network vibration frequency, the pipe network vibration time and the pipeline material strength. The labels of the training data can be artificially labeled pipe network vibration fatigue factors.
FIG. 4 is an exemplary diagram of a maintenance value prediction method according to some embodiments described herein. As shown in fig. 4, the method 400 includes pipe network maintenance information 410, pipe network environment information 420, a maintenance value prediction model 430, and pipe network maintenance values 440, and further includes an initial maintenance value prediction model 450 and a second training sample 460.
The maintenance value prediction model can be used for predicting the maintenance value of the pipe network. In some embodiments, the pipe network maintenance value may be obtained based on the pipe network maintenance information and the pipe network environment information via a maintenance value prediction model.
In some embodiments, the maintenance value prediction model may be a convolutional machine learning model (CNN), a fully convolutional neural network (FCN) model, a Generative Antagonistic Network (GAN), a Back Propagation (BP) machine learning model, a Radial Basis Function (RBF) machine learning model, a Deep Belief Network (DBN), an Elman machine learning model, or the like, or a combination thereof.
In some embodiments, the maintenance value prediction model may be a Graph Neural Network (GNN) model. The nodes of the GNN model are historical pipe network maintenance locations and pipe network environment information, and corresponding pipe connections are used at the same time.
In some embodiments, as shown in fig. 4, the inputs to maintenance value prediction model 430 may include pipe network maintenance information 410 and pipe network environment information 420, and the output is pipe network maintenance value 440. In some embodiments, the inputs to the maintenance value prediction model 430 may include historical data over a period of time in the past (e.g., within one month, within 2 months, within 3 months, etc.).
In some embodiments, the pipe network maintenance information may include at least one of replacement pipes, time of repair, specific locations of repair (e.g., joints, elbows, branches, etc.), post-repair air leaks, and vibration detection results. In some embodiments, processor 112 may obtain pipe network maintenance information based on historical service records.
In some embodiments, the pipe network environmental information may include pipe network vibration frequency and natural gas usage environmental information.
In some embodiments, the natural gas usage environment information may include an average ventilation rate of natural gas within the cell. The processor 112 may obtain the natural gas usage environment information through sensor detection.
In some embodiments, the pipe network vibration frequency may include the pipe natural frequency as well as the external vibration frequency. The natural frequency of a pipeline is the frequency of vibrations due to changes in the bends, diameters, etc. of the pipeline, and due to natural gas flow. The external vibration frequency may be a frequency of vibration due to surrounding construction of a construction site, traffic, design instability of a pipe bracket, and the like.
In some embodiments, processor 112 may derive the pipe network vibration frequency through periodic detection of sensor timing. The detected history data may be stored in the storage device 120. When the maintenance value of the pipe network is predicted through the maintenance value prediction model, data in a certain past time period (for example, 1 week, 1 month, 2 months, 3 months and the like) is selected as model input.
In some embodiments, the corresponding time period duration of the selection data is inversely related to the pipe network maintenance value within a certain range. For example, the maintenance value of the pipe network is large, the priority of the maintenance processing is high, and the selection of the time period can be relatively small, so as to accelerate the prediction speed or avoid the interference of irrelevant data. For another example, the maintenance value of the pipe network is small, the priority of maintenance processing is low, and the selection of the time period can be relatively large, so as to ensure the prediction effect.
In some embodiments, the GNN model may process graph data constructed based on relationships between historical pipe network repair locations and historical pipe network environmental information to determine pipe network maintenance values. In some embodiments, the graph may include a plurality of nodes and a plurality of edges, the nodes corresponding to historical pipe network maintenance locations and pipe network environment information, the edges corresponding to relationships between pipe connections. In some embodiments, the edge corresponds to a spatial position relationship between the historical pipe network maintenance location and the pipe network environment information, and the spatial position relationship may be a relative position relationship, a distance relationship, or the like. In some embodiments, the nodes and edges each contain a respective characteristic. In some embodiments, the characteristics of the node may include replacement of tubing, maintenance time, specific location of maintenance, post-maintenance gas leakage, vibration detection results, pipe network vibration frequency, and natural gas usage environment information, among others. The characteristics of the edges may include pipe material, diameter, connection, and relationship of pipe network environmental information to the pipe network service location (e.g., correspondence between a service point and pipe network environmental information).
In some embodiments, as shown in FIG. 4, the output of the maintenance value prediction model 430 is a pipe network maintenance value 440.
In some embodiments, as shown in FIG. 4, the parameters of the maintenance value prediction model 430 may be trained using a plurality of labeled second training samples 460. In some embodiments, multiple sets of second training samples 460 may be obtained, each set of second training samples 460 may include multiple training data and tags corresponding to the training data, and the training data may include historical pipe network maintenance information and historical pipe network environment information, where the historical pipe network maintenance information and the historical pipe network environment information are pipe network maintenance information and pipe network environment information in a historical time period, and the tags of the training data may be pipe network maintenance values directly labeled manually according to maintenance records.
The parameters of the initial maintenance value prediction model 450 may be updated through multiple sets of second training samples 460, resulting in a trained maintenance value prediction model 450.
In some embodiments, the parameters of the initial maintenance value prediction model 450 may be iteratively updated based on a plurality of second training samples such that the loss function of the model satisfies the preset condition. For example, the loss function converges, or the loss function value is smaller than a preset value. And when the loss function meets the preset condition, the model training is completed, and a trained initial maintenance value prediction model 450 is obtained. The maintenance value prediction model 430 and the trained initial maintenance value prediction model 450 have the same model structure.
The maintenance value of the pipe network is predicted through the maintenance value prediction model, and the maintenance value of the pipe network can be used as the input of the maintenance time prediction model to obtain a prediction result combining the characteristic information obtained based on the running time and the air leakage information and the correlation of the maintenance value of the pipe network, so that the maintenance time of the pipe network is more accurately predicted through the maintenance time prediction model.
Fig. 5 is an exemplary block diagram of a natural gas pipeline network management system according to some embodiments described herein. As shown in fig. 5, the natural gas pipeline network management system 500 may include at least an information acquisition module 510, a feature extraction module 520, and a prediction module 530.
The information obtaining module 510 may be configured to obtain information about a natural gas pipeline network of at least one region, where the information about the pipeline network includes operation time of a natural gas management system and pipeline network leakage information. For more details on the information of the natural gas pipeline network, refer to fig. 2 and the related description thereof, which are not described herein again.
The feature extraction module 520 may be configured to extract feature information based on the run-time and leak information. For more details on the feature information, refer to fig. 2 and the related description thereof, which are not repeated herein.
The time prediction module 530 may be configured to input the feature information into the maintenance time prediction model to predict the maintenance time of the pipe network. In some embodiments, the inputs to the maintenance time prediction model of the time prediction module 530 further include a pipe network maintenance value; and the pipe network maintenance value is obtained based on the pipe network maintenance information and the pipe network environment information through a maintenance value prediction model. In some embodiments, the pipe network environment information of the time prediction module 530 includes pipe network vibration frequency and natural gas usage environment information; the maintenance information of the pipe network comprises at least one of pipe replacement, maintenance time, specific maintenance position, air leakage after maintenance and vibration detection results. In some embodiments, the inputs to the maintenance time prediction model of the time prediction module 530 further include a pipe network vibration fatigue factor, which is calculated based on the pipe network vibration frequency and the pipe network vibration time. For more details on maintaining the temporal prediction model, refer to fig. 3 and its related description, which are not repeated herein.
It should be noted that the above description of the system and its modules is for convenience only and should not limit the present disclosure to the illustrated embodiments. It will be appreciated by those skilled in the art that, given the teachings of the present system, any combination of modules or sub-system configurations may be used to connect to other modules without departing from such teachings. In some embodiments, the information acquisition module 510, the feature extraction module 520, and the prediction module 530 disclosed in fig. 1 may be different modules in a system, or may be a module that implements the functions of two or more modules described above. For example, each module may share one memory module, and each module may have its own memory module. Such variations are within the scope of the present disclosure.
Having thus described the basic concept, it will be apparent to those skilled in the art that the foregoing detailed disclosure is to be regarded as illustrative only and not as limiting the present specification. Various modifications, improvements and adaptations to the present description may occur to those skilled in the art, although not explicitly described herein. Such modifications, improvements and adaptations are proposed in the present specification and thus fall within the spirit and scope of the exemplary embodiments of the present specification.
Also, the description uses specific words to describe embodiments of the description. Reference throughout this specification to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic described in connection with at least one embodiment of the specification is included. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, some features, structures, or characteristics of one or more embodiments of the specification may be combined as appropriate.
Additionally, the order in which the elements and sequences of the process are recited in the specification, the use of alphanumeric characters, or other designations, is not intended to limit the order in which the processes and methods of the specification occur, unless otherwise specified in the claims. While various presently contemplated embodiments of the invention have been discussed in the foregoing disclosure by way of example, it is to be understood that such detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the embodiments herein. For example, although the system components described above may be implemented by hardware devices, they may also be implemented by software-only solutions, such as installing the described system on an existing server or mobile device.
Similarly, it should be noted that in the preceding description of embodiments of the present specification, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of one or more of the embodiments. This method of disclosure, however, is not intended to imply that more features than are expressly recited in a claim. Indeed, the embodiments may be characterized as having less than all of the features of a single embodiment disclosed above.
Numerals describing the number of components, attributes, etc. are used in some embodiments, it being understood that such numerals used in the description of the embodiments are modified in some instances by the use of the modifier "about", "approximately" or "substantially". Unless otherwise indicated, "about", "approximately" or "substantially" indicates that the number allows a variation of ± 20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximations that may vary depending upon the desired properties of the individual embodiments. In some embodiments, the numerical parameter should take into account the specified significant digits and employ a general digit preserving approach. Notwithstanding that the numerical ranges and parameters setting forth the broad scope of the range are approximations, in the specific examples, such numerical values are set forth as precisely as possible within the scope of the application.
For each patent, patent application publication, and other material, such as articles, books, specifications, publications, documents, etc., cited in this specification, the entire contents of each are hereby incorporated by reference into this specification. Except where the application history document does not conform to or conflict with the contents of the present specification, it is to be understood that the application history document, as used herein in the present specification or appended claims, is intended to define the broadest scope of the present specification (whether presently or later in the specification) rather than the broadest scope of the present specification. It is to be understood that the descriptions, definitions and/or uses of terms in the accompanying materials of this specification shall control if they are inconsistent or contrary to the descriptions and/or uses of terms in this specification.
Finally, it should be understood that the embodiments described herein are merely illustrative of the principles of the embodiments of the present disclosure. Other variations are also possible within the scope of the present description. Thus, by way of example, and not limitation, alternative configurations of the embodiments of the specification can be considered consistent with the teachings of the specification. Accordingly, the embodiments of the present description are not limited to only those embodiments explicitly described and depicted herein.
Claims (10)
1. A natural gas pipe network management method comprises the following steps:
acquiring natural gas pipe network information of at least one region, wherein the pipe network information comprises the running time of a natural gas management system and pipe network air leakage information;
extracting feature information based on the running time and the air leakage information;
and inputting the characteristic information into a maintenance time prediction model to predict the maintenance time of the pipe network.
2. The method of claim 1, the inputs to the maintenance time prediction model further comprising a pipe network maintenance value; and the pipe network maintenance value is obtained based on the pipe network maintenance information and the pipe network environment information through a maintenance value prediction model.
3. The method of claim 2, wherein the pipe network environment information comprises pipe network vibration frequency and natural gas use environment information; the pipe network maintenance information comprises at least one of pipe replacement, maintenance time, specific maintenance position, air leakage after maintenance and vibration detection results.
4. The method of claim 1, wherein the inputs to the maintenance time prediction model further comprise a pipe network vibration fatigue factor; and the pipe network vibration fatigue factor is obtained by calculation based on the pipe network vibration frequency and the pipe network vibration time.
5. A natural gas pipeline network management system comprising:
the information acquisition module is used for acquiring natural gas pipe network information of at least one region, wherein the pipe network information comprises the running time of a natural gas management system and pipe network air leakage information;
the characteristic extraction module is used for extracting characteristic information based on the running time and the air leakage information;
and the time prediction module is used for inputting the characteristic information into a maintenance time prediction model and predicting the maintenance time of the pipe network.
6. The system of claim 5, the inputs to the maintenance time prediction model further comprising a pipe network maintenance value; and the pipe network maintenance value is obtained based on the pipe network maintenance information and the pipe network environment information through a maintenance value prediction model.
7. The method of claim 6, wherein the pipe network environment information comprises pipe network vibration frequency and natural gas use environment information; the pipe network maintenance information comprises at least one of pipe replacement, maintenance time, specific maintenance position, air leakage after maintenance and vibration detection results.
8. The method of claim 5, wherein the inputs to the maintenance time prediction model further comprise a pipe network vibration fatigue factor, wherein the pipe network vibration fatigue factor is calculated based on pipe network vibration frequency and pipe network vibration time.
9. A natural gas pipeline network management device comprises at least one processor and at least one memory;
the at least one memory is for storing computer instructions;
the at least one processor is configured to execute at least a portion of the computer instructions to implement the method of any one of claims 1-4.
10. A computer-readable storage medium storing computer instructions, wherein when the computer instructions in the storage medium are read by a computer, the computer executes the natural gas pipeline network management method according to any one of claims 1 to 4.
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210045160.2A CN114399113B (en) | 2022-01-14 | 2022-01-14 | Natural gas pipe management method and system |
| US17/649,190 US11822325B2 (en) | 2021-02-04 | 2022-01-27 | Methods and systems for managing a pipe network of natural gas |
| US18/485,307 US20240036563A1 (en) | 2021-02-04 | 2023-10-11 | Method and system for determining maintenance time of pipe networks of natural gas |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210045160.2A CN114399113B (en) | 2022-01-14 | 2022-01-14 | Natural gas pipe management method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114399113A true CN114399113A (en) | 2022-04-26 |
| CN114399113B CN114399113B (en) | 2024-07-09 |
Family
ID=81231034
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210045160.2A Active CN114399113B (en) | 2021-02-04 | 2022-01-14 | Natural gas pipe management method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114399113B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116596512A (en) * | 2023-05-22 | 2023-08-15 | 湖北华中电力科技开发有限责任公司 | Electric power operation and maintenance safety strengthening method and system based on information system |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5333240A (en) * | 1989-04-14 | 1994-07-26 | Hitachi, Ltd. | Neural network state diagnostic system for equipment |
| US20020046048A1 (en) * | 2000-07-11 | 2002-04-18 | Hidetada Fukushima | System, method, computer program, and recording medium for machine-management |
| JP2010048680A (en) * | 2008-08-22 | 2010-03-04 | Jtekt Corp | Vibration test method and apparatus |
| CN102866071A (en) * | 2012-10-23 | 2013-01-09 | 朱占元 | Building method of ice layer dynamic settlement prediction model |
| KR101283828B1 (en) * | 2012-04-04 | 2013-07-15 | 한국수자원공사 | System for diagnosing performance of water supply network |
| CN104050541A (en) * | 2014-06-27 | 2014-09-17 | 国家电网公司 | Maintenance cycle management system for grid equipment |
| CN108645615A (en) * | 2018-04-08 | 2018-10-12 | 太原科技大学 | A kind of Adaptive Fuzzy Neural-network gear method for predicting residual useful life |
| CN109630902A (en) * | 2018-12-07 | 2019-04-16 | 深圳市燃气集团股份有限公司 | A kind of gas distributing system leak detection method, storage medium and terminal device |
| CN109858126A (en) * | 2019-01-23 | 2019-06-07 | 北京市燃气集团有限责任公司 | Pipeline network of fuel gas in city safety monitoring method for early warning and system based on settlement monitoring |
| US20190257700A1 (en) * | 2018-02-21 | 2019-08-22 | Miqrotech, Inc. | Apparatus, system, and method for monitoring a member |
| WO2020020088A1 (en) * | 2018-07-23 | 2020-01-30 | 第四范式（北京）技术有限公司 | Neural network model training method and system, and prediction method and system |
| CN111798089A (en) * | 2020-05-25 | 2020-10-20 | 成都华润燃气设计有限公司 | Urban natural gas high-pressure pipe network operation state risk evaluation method |
| CN112163722A (en) * | 2020-10-30 | 2021-01-01 | 中国石油大学(北京) | Method and device for predicting gas supply state of natural gas pipe network |
| KR102226687B1 (en) * | 2019-11-20 | 2021-03-11 | (주)위세아이텍 | Apparatus and method of remaining maintenance cycle prediction based on times series prediction using deep learning |
-
2022
- 2022-01-14 CN CN202210045160.2A patent/CN114399113B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5333240A (en) * | 1989-04-14 | 1994-07-26 | Hitachi, Ltd. | Neural network state diagnostic system for equipment |
| US20020046048A1 (en) * | 2000-07-11 | 2002-04-18 | Hidetada Fukushima | System, method, computer program, and recording medium for machine-management |
| JP2010048680A (en) * | 2008-08-22 | 2010-03-04 | Jtekt Corp | Vibration test method and apparatus |
| KR101283828B1 (en) * | 2012-04-04 | 2013-07-15 | 한국수자원공사 | System for diagnosing performance of water supply network |
| CN102866071A (en) * | 2012-10-23 | 2013-01-09 | 朱占元 | Building method of ice layer dynamic settlement prediction model |
| CN104050541A (en) * | 2014-06-27 | 2014-09-17 | 国家电网公司 | Maintenance cycle management system for grid equipment |
| US20190257700A1 (en) * | 2018-02-21 | 2019-08-22 | Miqrotech, Inc. | Apparatus, system, and method for monitoring a member |
| CN108645615A (en) * | 2018-04-08 | 2018-10-12 | 太原科技大学 | A kind of Adaptive Fuzzy Neural-network gear method for predicting residual useful life |
| WO2020020088A1 (en) * | 2018-07-23 | 2020-01-30 | 第四范式（北京）技术有限公司 | Neural network model training method and system, and prediction method and system |
| CN109630902A (en) * | 2018-12-07 | 2019-04-16 | 深圳市燃气集团股份有限公司 | A kind of gas distributing system leak detection method, storage medium and terminal device |
| CN109858126A (en) * | 2019-01-23 | 2019-06-07 | 北京市燃气集团有限责任公司 | Pipeline network of fuel gas in city safety monitoring method for early warning and system based on settlement monitoring |
| KR102226687B1 (en) * | 2019-11-20 | 2021-03-11 | (주)위세아이텍 | Apparatus and method of remaining maintenance cycle prediction based on times series prediction using deep learning |
| CN111798089A (en) * | 2020-05-25 | 2020-10-20 | 成都华润燃气设计有限公司 | Urban natural gas high-pressure pipe network operation state risk evaluation method |
| CN112163722A (en) * | 2020-10-30 | 2021-01-01 | 中国石油大学(北京) | Method and device for predicting gas supply state of natural gas pipe network |
Non-Patent Citations (2)
| Title |
|---|
| 丁鹏: "海底管线安全可靠性及风险评价技术研究", 《中国博士学位论文全文数据库工程科技Ⅰ辑》, no. 06, 15 June 2009 (2009-06-15), pages 019 - 26 * |
| 王爱芳: "穿越河流输油管道的安全性评估", 《中国优秀博硕士学位论文全文数据库 (硕士) 工程科技Ⅰ辑》, no. 03, 15 March 2006 (2006-03-15), pages 019 - 78 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116596512A (en) * | 2023-05-22 | 2023-08-15 | 湖北华中电力科技开发有限责任公司 | Electric power operation and maintenance safety strengthening method and system based on information system |
| CN116596512B (en) * | 2023-05-22 | 2024-05-10 | 湖北华中电力科技开发有限责任公司 | Electric power operation and maintenance safety strengthening method and system based on information system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114399113B (en) | 2024-07-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Rinaldi et al. | Current status and future trends in the operation and maintenance of offshore wind turbines: A review | |
| Shao et al. | Digital manufacturing: Requirements and challenges for implementing digital surrogates | |
| CN113935497B (en) | Intelligent operation and maintenance fault processing method, device, equipment and storage medium thereof | |
| CN104794578A (en) | Could computing based smart water affair management system | |
| US11822325B2 (en) | Methods and systems for managing a pipe network of natural gas | |
| US11561950B2 (en) | System and method for facilitating an objective-oriented data structure and an objective via the data structure | |
| CN112700131B (en) | AB test method and device based on artificial intelligence, computer equipment and medium | |
| CN115587640A (en) | Intelligent gas pipeline pigging safety management method, internet of things system and medium | |
| CN117114369B (en) | Intelligent gas emergency gas supply disposal method, internet of things system, device and medium | |
| Alabi et al. | Water 4.0: An integrated business model from an industry 4.0 approach | |
| CN114970926A (en) | Model training method, enterprise operation risk prediction method and device | |
| CN114399113B (en) | Natural gas pipe management method and system | |
| Parto et al. | Cyber-physical system implementation for manufacturing with analytics in the cloud layer | |
| Ilkhani et al. | Extraction test cases by using data mining; reducing the cost of testing | |
| Eklund et al. | Using a digital twin as the objective function for evolutionary algorithm applications in large scale industrial processes | |
| CN108023740A (en) | The indicating risk method and apparatus of exception information in monitoring | |
| Tello et al. | Digital twins: An enabler for digital transformation | |
| Wu et al. | A distributed real-time data prediction framework for large-scale time-series data using stream processing | |
| Ni | A Digitalization Framework for Smart Maintenance of Historic Buildings | |
| Wang | Reliability detection method of online education resource sharing based on blockchain | |
| Hood et al. | Industrial Internet of Things: An Analysis of Emergence, Component and Challenges | |
| Saari et al. | Framework and Development Process for IoT Data Gathering | |
| CN113487085B (en) | Method and device for predicting service life of equipment based on joint learning framework, computer equipment and computer readable storage medium | |
| RUG et al. | Digital Twins | |
| Behrendt et al. | Meeting the Complexity of Industrial Requirements-Digital Learning Platform for Innovative Application Domains |
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 |