CN110705176A - Method and device for predicting residual life of gas pipeline - Google Patents
Method and device for predicting residual life of gas pipeline Download PDFInfo
- Publication number
- CN110705176A CN110705176A CN201910823075.2A CN201910823075A CN110705176A CN 110705176 A CN110705176 A CN 110705176A CN 201910823075 A CN201910823075 A CN 201910823075A CN 110705176 A CN110705176 A CN 110705176A
- Authority
- CN
- China
- Prior art keywords
- gas pipeline
- residual life
- life
- residual
- predicted
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- 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"
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Biomedical Technology (AREA)
- Game Theory and Decision Science (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Pipeline Systems (AREA)
Abstract
The invention provides a method and a device for predicting the residual life of a gas pipeline, wherein the method comprises the following steps: obtaining residual life influencing factors of a plurality of gas pipelines and corresponding residual life classifications as training samples; training the artificial neural network through a training sample to obtain a residual life prediction model of the gas pipeline; detecting the influence factors of the residual service life of the gas pipeline to be predicted; and inputting the residual life influence factors of the gas pipeline to be predicted into the residual life prediction model of the gas pipeline to obtain the residual life classification of the gas pipeline to be predicted. The invention can conveniently and effectively predict the residual service life of the gas pipeline, thereby reducing the manpower and material resources for overhauling the gas pipeline and reducing the potential safety hazard of the gas pipeline.
Description
Technical Field
The invention relates to the technical field of gas pipeline management, in particular to a method and a device for predicting the residual life of a gas pipeline.
Background
The gas pipeline management organization needs to invest capital to technically transform a batch of hidden danger pipelines with higher aging degree or increased accident frequency every year. The hidden danger pipelines are generally judged whether to be modified or not only by the service life of the pipelines, the leakage times and other factors. But after the pipeline excavation of partial transformation, the discovery does not reach the degree that needs the transformation, consequently can cause the waste of resource, manpower, material resources, more probably makes the pipeline that should reform transform not reform transform, leaves the potential safety hazard.
Disclosure of Invention
The invention aims to solve the technical problems and provides a method and a device for predicting the residual life of a gas pipeline, which can conveniently and effectively predict the residual life of the gas pipeline, thereby reducing manpower and material resources for overhauling the gas pipeline and reducing the potential safety hazard of the gas pipeline.
The technical scheme adopted by the invention is as follows:
a method for predicting the residual life of a gas pipeline comprises the following steps: obtaining residual life influencing factors of a plurality of gas pipelines and corresponding residual life classifications as training samples; training the artificial neural network through the training sample to obtain a residual life prediction model of the gas pipeline; detecting the influence factors of the residual service life of the gas pipeline to be predicted; and inputting the residual life influence factors of the gas pipeline to be predicted into the residual life prediction model of the gas pipeline to obtain the residual life classification of the gas pipeline to be predicted.
The artificial neural network is a BP neural network.
The remaining life influencing factors comprise the number of air leakage points, the distance between the air leakage points, the commissioning age, the pipe diameter, the operation pressure, the length, the number of the leakage points of the anticorrosive coating, the grade of the anticorrosive coating and the grade of a pipeline.
The residual service life is classified into immediate overall modification, temporary overall modification, local pipe replacement, operation enhancement, correct situation, ground detection or excavation detection.
A gas pipeline remaining life prediction device includes: the acquisition module is used for acquiring the residual life influencing factors of the plurality of gas pipelines and the corresponding residual life classifications as training samples; the training module is used for training the artificial neural network through the training sample to obtain a residual life prediction model of the gas pipeline; the detection module is used for detecting the influence factors of the residual service life of the gas pipeline to be predicted; and the prediction module is used for inputting the residual life influence factors of the gas pipeline to be predicted into the gas pipeline residual life prediction model so as to obtain the residual life classification of the gas pipeline to be predicted.
The artificial neural network is a BP neural network.
The remaining life influencing factors comprise the number of air leakage points, the distance between the air leakage points, the commissioning age, the pipe diameter, the operation pressure, the length, the number of the leakage points of the anticorrosive coating, the grade of the anticorrosive coating and the grade of a pipeline.
The residual service life is classified into immediate overall modification, temporary overall modification, local pipe replacement, operation enhancement, correct situation, ground detection or excavation detection.
The invention has the beneficial effects that:
according to the invention, the training sample is obtained, the artificial neural network is trained through the training sample to obtain the residual life prediction model of the gas pipeline, then the residual life influence factor of the gas pipeline to be predicted is detected, and the residual life influence factor of the gas pipeline to be predicted is input into the residual life prediction model of the gas pipeline to obtain the residual life classification of the gas pipeline to be predicted, so that the residual life of the gas pipeline can be conveniently and effectively predicted, the manpower and material resources for overhauling the gas pipeline can be reduced, and the potential safety hazard of the gas pipeline can be reduced.
Drawings
FIG. 1 is a flowchart of a method for predicting the remaining life of a gas pipeline according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a structure of a neuron in an artificial neural network;
FIG. 3 is a graph of two Sigmoid functions;
FIG. 4 is a schematic structural diagram of a multi-layer forward network;
fig. 5 is a block diagram of a residual life prediction device for a gas pipeline according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, the method for predicting the remaining life of a gas pipeline according to the embodiment of the present invention includes the following steps:
and S1, acquiring the residual life influencing factors of the plurality of gas pipelines and the corresponding residual life classifications as training samples.
In one embodiment of the invention, the remaining life influencing factors may include the number of leak points, the distance between leak points, the operational age, the pipe diameter, the operating pressure, the length, the number of leak points of the anticorrosive layer, the grade of the anticorrosive layer and the rating of the pipe. The remaining life classification can be immediate overall reconstruction, temporary overall reconstruction, local pipe replacement, operation enhancement, condition improvement, ground detection or excavation detection.
Specifically, the artificial classification can be carried out according to the residual life influencing factors of the plurality of gas pipelines under the experimental condition initially, and each gas pipeline has a corresponding pipeline number. It should be understood that the more training samples, the higher the prediction accuracy of the residual life prediction model of the gas pipeline obtained by subsequent training, so that the number of the gas pipelines in the training samples of the embodiment of the present invention is as large as possible, for example, may be 200. Data for a portion of the training samples are shown in table 1.
TABLE 1
| Pipeline Numbering | Air leakage Counting number | Air leakage Between points Distance between | Put into operation Age limit | Pipe diameter | Operation of Pressure of | Long and long Degree of rotation | Others Description of the invention | Anticorrosive coating Number of leakage points | Preservation of corrosion Hierarchy level Clip for fixing | Pipeline Rating | Evaluation results |
| 1013 | 1 | 0 | 1981 /1/1 | DN200 | Low pressure | 1.5 | Is free of | 0 | Difference (D) | Is free of | Immediate integral improvement Make |
| 6014 | 0 | 0 | 1981 /1/1 | DN500 | High pressure A | 0.2 | Is free of | 0 | Good wine | Is free of | Temporary integrated modification Make |
| 1015 | 0 | 0 | 1988 /1/1 | DN500 | Medium pressure | 1 | Is free of | 0 | Bad quality | Is free of | Local repair |
| 1016 | 1 | 0 | 1988 /1/1 | DN300 | Medium pressure | 4.7 | Is free of | 3 | Difference (D) | Is free of | Local tube replacement |
| 3017 | 1 | 0 | 1975 /1/1 | DN300 | Medium pressure | 1 | Is free of | 1 | Difference (D) | Is free of | Immediate integral improvement Make |
| 2018 | 1 | 0 | 1975 /1/1 | DN300 | Low pressure | 0.5 | Is free of | 0 | Difference (D) | Is free of | Immediate integral improvement Make |
| 2019 | 1 | 0 | 1975 /1/1 | DN300 | Low pressure | 0.8 | Is free of | 0 | Difference (D) | Is free of | Immediate integral improvement Make |
| 5020 | 1 | 0 | 1985 /1/1 | Multiple kinds of Pipe diameter | Low pressure | 1.2 | Is free of | 2 | Difference (D) | Is free of | Local tube replacement |
| 5021 | 8 | 105 | 1990 /1/1 | Multiple kinds of Pipe diameter | Low pressure | 1 | Is free of | 20 | Difference (D) | Is free of | Please proceed excavation Detecting and updating |
| 2022 | 0 | 0 | 1975 /1/1 | Multiple kinds of Pipe diameter | Medium pressure | 0.1 | Is free of | 0 | Difference (D) | Is free of | Immediate integral improvement Make |
| 5023 | 5 | 300 | 1983 /1/1 | Multiple kinds of Pipe diameter | Low pressure | 7.4 | Is free of | 3 | Difference (D) | Is free of | Immediate integral improvement Make |
| 2024 | 9 | 200 | 1979 /1/1 | DN300 | Medium pressure | 4.9 4 | Is free of | 8 | Difference (D) | Is free of | Immediate integral improvement Make |
| 3025 | 7 | 700 | 1988 /1/1 | DN300 | Medium pressure | 4 | Is free of | 0 | In | Is free of | Local repair |
| 5026 | 15 | 180 | 1987 /1/1 | Multiple kinds of Pipe diameter | Low pressure | 8 | Is free of | 12 | Difference (D) | Is free of | Please proceed excavation Detecting and updating |
| 2027 | 1 | 0 | 1980 /1/1 | DN300 | Low pressure | 1.5 | Is free of | 2 | Difference (D) | Is free of | Immediate integral improvement Make |
| 5028 | 6 | 100 | 1980 /1/1 | Multiple kinds of Pipe diameter | Low pressure | 7.1 | Is free of | 8 | Difference (D) | Is free of | Immediate integral improvement Make |
| 5029 | 5 | 150 | 1989 /1/1 | DN500 | Medium pressure | 0.8 | Is free of | 12 | Difference (D) | Is free of | Please proceed excavation Detecting and updating |
| 1004 | 1 | 0 | 1980 /1/1 | Multiple kinds of Pipe diameter | Medium pressure | 0.3 | Is free of | 0 | Bad quality | Is free of | Immediate integral improvement Make |
| 1005 | 3 | 500 | 1982 /1/1 | Multiple kinds of Pipe diameter | Medium pressure | 0.1 | Is free of | 0 | Difference (D) | Is free of | Immediate integral improvement Make |
| 1006 | 0 | 0 | 1980 /1/1 | Multiple kinds of Pipe diameter | Multiple kinds of Pressure of | 2 | Is free of | 2 | Difference (D) | Is free of | Immediate integral improvement Make |
| 2007 | 0 | 0 | 1979 /1/1 | Multiple kinds of Pipe diameter | Medium pressure | 0.7 | Is free of | 0 | In | Is free of | Temporary integrated modification Make |
| 2008 | 5 | 400 | 1983 /1/1 | Multiple kinds of Pipe diameter | Low pressure | 12. 05 | Is free of | 1 | Difference (D) | Is free of | Immediate integral improvement Make |
| 3009 | 0 | 0 | 1993 /1/1 | Multiple kinds of Pipe diameter | Medium pressure | 1.6 | Is free of | 0 | Bad quality | Is free of | Local repair |
| 1010 | 0 | 0 | 1980 /1/1 | DN250 | Low pressure | 4.5 | Is free of | 0 | Difference (D) | Is free of | Immediate integral improvement Make |
| 1011 | 1 | 0 | 1984 /1/1 | Multiple kinds of Pipe diameter | Low pressure | 2 | Is free of | 0 | Difference (D) | Is free of | Local tube replacement |
| 1012 | 0 | 0 | 1993 /1/1 | Multiple kinds of Pipe diameter | Low pressure | 4.5 | Is free of | 0 | Difference (D) | Is free of | Local repair |
| 1030 | 1 | 0 | 1984 /1/1 | Multiple kinds of Pipe diameter | Low pressure | 2 | Is free of | 9 | In | Is free of | Local tube replacement |
And S2, training the artificial neural network through the training samples to obtain a residual life prediction model of the gas pipeline.
The artificial neural network is composed of a large number of neurons, and the composition of the neurons is shown in fig. 2.
The input-output relationship of a neuron can be expressed as:
ui＝∑jwjixj,vi＝ui+θi,yi＝f(vi)
wherein x isjIs an input signal of a neuron, wijAs a connection right, uiOutput of linearly combined input signals (net input to neuron i), θiIs a threshold value, viFor the offset-adjusted value, f () is the excitation function, yiIs the output of neuron i.
The excitation function f () may take different functions, and commonly used excitation functions include a threshold function, a piecewise linear function, and a Sigmoid function, wherein Sigmoid is most commonly used, and function curves of two Sigmoid functions f (v) ═ 1/[1+ exp (-av) ] and f (v) ═ 1/[1+ exp (-av) ] are shown in fig. 3.
In one embodiment of the present invention, the artificial neural network may be a bp (back propagation) neural network.
As shown in fig. 4, a multi-layer forward network includes an input layer, an output layer and a number of hidden layers.
At the input xjWithout change, output yiThe size depends on wijBy changing wijA value of (a) may beiClose to the ideal output. If a large number of corresponding x's are knownj、yiAnd x isj、yiContaining typical characteristics of the system, by training of the neural network, wijThe characteristics of the system can be reflected, so that when the input is not in the training sample, the corresponding output can be obtained through the trained neural network. So determine w that implies the system characteristicsijIs a key step for establishing the neural network, and the process is a learning rule of the neural network. The BP neural network can approximate functions with any precision and has an autonomous learning ability. The method has the advantages of good nonlinear mapping capability, simple structure, good performance and better durability and predictability compared with other traditional models. The BP neural network consists of an input layer, a hidden layer (also called an intermediate layer) and an output layer.
The BP neural network can be seen as a highly non-linear mapping from input to output, i.e., f (x) y, f: Rn→Rm. The BP neural network has a flexible form in structure, and no fixed mode canFollow. A 3-layer BP neural network can implement arbitrary n-dimensional to m-dimensional mapping. The number of input and output layer neurons of the network is completely determined by the problem being solved.
The self-learning of the BP algorithm is to continuously correct the network weight and the threshold in the network training process, and the error function E is reduced along the negative gradient direction. Using a three-layer BP network model structure, where xjIs the input of the jth input node, yiIs the output of the ith hidden node, OlIs the output of the ith output node. w is aijIs the network weight, θ, between the input node and the hidden nodeiIs the threshold value of the ith hidden node, thetalIs the threshold of the ith output node.
When the desired output of the output node is tlIn time, the output of the BP model due to the nodes is:
yi＝f(∑wijxj-θi)＝f(neti)
therein neti＝∑wij-θi. The computational output of the output node is:
therein netl＝∑Tliyi-θl. The error at the output node is:
the steepest descent algorithm of the forward three-layer neural network of the S-shaped function can be adopted to correct the weight.
The gradient of the output layer node weight is:
the gradient of the weight of the hidden layer node is as follows:
error of setting hidden node
Then
△ T due to weight correctionli,△wijDecreases along the gradient in proportion to the error function, so:
wij(k+1)＝wij(k)+η′δixj
wherein eta, eta' is the learning rate, and is generally a small positive number.
The derivation of the formula shows that the hidden layer error delta is calculatediError delta required to use the output layerl. The derivation of the error function is therefore a back-propagation recursive process starting from the output layer, i.e. the weight coefficients are modified by back-propagation of the error function.
After repeated training of a plurality of samples, the weight is corrected along the direction of reducing the error, and finally, a prediction model for predicting the result can be obtained.
And S3, detecting the influence factors of the residual service life of the gas pipeline to be predicted.
In one embodiment of the invention, the relevant pipeline data may be obtained by micro-via excavation or field testing. For example, the number of gas leakage points and the distance between the gas leakage points of a certain gas pipeline to be predicted can be detected through a gas detector arranged at the gas pipeline through micropore excavation, the running pressure is detected through a pressure detector arranged at the gas pipeline through micropore excavation, the pipe diameter, the number of leakage points of an anticorrosive coating, the grade and the length of the anticorrosive coating and the like are obtained through field micropore excavation detection or calling of a pipeline database, and the commissioning life and the like are obtained through calling of a pipeline database.
And S4, inputting the residual life influence factors of the gas pipeline to be predicted into the residual life prediction model of the gas pipeline to obtain the residual life classification of the gas pipeline to be predicted.
In an embodiment of the present invention, a partial result of the classification of the remaining life of the gas pipeline to be predicted according to the input influence factors of the remaining life of the gas pipeline to be predicted is shown in table 2.
TABLE 2
After obtaining the remaining life classification of the gas pipeline to be predicted, the gas pipeline management mechanism can directly take corresponding measures according to the remaining life classification, for example, when the remaining life classification of a certain gas pipeline to be predicted is immediately transformed integrally, the gas pipeline can be integrally excavated, maintained or replaced.
In addition, after the residual life classification of the gas pipeline to be predicted is obtained, the prediction result can be added into the training sample, and the artificial neural network is retrained again by combining the training sample obtained in the previous experiment. The training samples can be updated through the prediction results, so that the residual life prediction model of the gas pipeline is updated through continuous training, and the prediction accuracy is continuously improved.
According to the method for predicting the residual life of the gas pipeline, the training sample is obtained, the artificial neural network is trained through the training sample to obtain a prediction model of the residual life of the gas pipeline, then the influence factors of the residual life of the gas pipeline to be predicted are detected, and the influence factors of the residual life of the gas pipeline to be predicted are input into the prediction model of the residual life of the gas pipeline to be predicted to obtain the classification of the residual life of the gas pipeline to be predicted.
In order to realize the method for predicting the residual life of the gas pipeline in the embodiment, the invention further provides a device for predicting the residual life of the gas pipeline.
As shown in fig. 5, the device for predicting the remaining life of a gas pipeline according to the embodiment of the present invention includes an obtaining module 10, a training module 20, a detecting module 30, and a predicting module 40. The obtaining module 10 is configured to obtain remaining life influencing factors of the plurality of gas pipelines and corresponding remaining life classifications as training samples; the training module 20 is used for training the artificial neural network through a training sample to obtain a residual life prediction model of the gas pipeline; the detection module 30 is used for detecting the influence factors of the residual service life of the gas pipeline to be predicted; the prediction module 40 is configured to input the remaining life influence factors of the gas pipeline to be predicted into the gas pipeline remaining life prediction model, so as to obtain a remaining life classification of the gas pipeline to be predicted.
In one embodiment of the invention, the remaining life influencing factors may include the number of leak points, the distance between leak points, the operational age, the pipe diameter, the operating pressure, the length, the number of leak points of the anticorrosive layer, the grade of the anticorrosive layer and the rating of the pipe. The remaining life classification can be immediate overall reconstruction, temporary overall reconstruction, local pipe replacement, operation enhancement, condition improvement, ground detection or excavation detection.
The data of the part of the training sample acquired by the acquisition module 10 is shown in table 1.
In one embodiment of the invention, the artificial neural network may be a BP neural network.
In one embodiment of the present invention, the detection module 30 may include an on-site detection device for the micro-hole excavation, i.e., related pipeline data can be obtained through micro-hole excavation or on-site testing. For example, the number of gas leakage points and the distance between the gas leakage points of a certain gas pipeline to be predicted can be detected through a gas detector arranged at the gas pipeline through micropore excavation, the running pressure is detected through a pressure detector arranged at the gas pipeline through micropore excavation, the pipe diameter, the number of leakage points of an anticorrosive coating, the grade and the length of the anticorrosive coating and the like are obtained through field micropore excavation detection or calling of a pipeline database, and the commissioning life and the like are obtained through calling of a pipeline database.
In an embodiment of the present invention, the prediction module 40 obtains partial results of the classification of the remaining life of the gas pipeline to be predicted according to the input influence factors of the remaining life of the gas pipeline to be predicted, as shown in table 2.
After obtaining the remaining life classification of the gas pipeline to be predicted, the gas pipeline management mechanism can directly take corresponding measures according to the remaining life classification, for example, when the remaining life classification of a certain gas pipeline to be predicted is immediately transformed integrally, the gas pipeline can be integrally excavated, maintained or replaced.
In addition, after obtaining the remaining life classification of the gas pipeline to be predicted, the prediction module 40 may input the prediction result into the training module 20 to supplement the training sample, and the training module 20 may train the artificial neural network again by combining the training sample obtained by the previous obtaining module 10. The training samples can be updated through the prediction results, so that the residual life prediction model of the gas pipeline is updated through continuous training, and the prediction accuracy is continuously improved.
According to the device for predicting the residual life of the gas pipeline, the training sample is obtained through the obtaining module, the training module trains the artificial neural network through the training sample to obtain the residual life prediction model of the gas pipeline, the residual life influence factor of the gas pipeline to be predicted is detected through the detecting module, and finally the residual life influence factor of the gas pipeline to be predicted is input into the residual life prediction model of the gas pipeline through the predicting module to obtain the residual life classification of the gas pipeline to be predicted.
In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (8)
1. A method for predicting the residual life of a gas pipeline is characterized by comprising the following steps:
obtaining residual life influencing factors of a plurality of gas pipelines and corresponding residual life classifications as training samples;
training the artificial neural network through the training sample to obtain a residual life prediction model of the gas pipeline;
detecting the influence factors of the residual service life of the gas pipeline to be predicted;
and inputting the residual life influence factors of the gas pipeline to be predicted into the residual life prediction model of the gas pipeline to obtain the residual life classification of the gas pipeline to be predicted.
2. The method for predicting the residual life of a gas pipeline according to claim 1, wherein the artificial neural network is a BP neural network.
3. The method for predicting the remaining life of a gas pipeline according to claim 1 or 2, wherein the remaining life influencing factors include the number of air leakage points, the distance between the air leakage points, the operational life, the pipe diameter, the operating pressure, the length, the number of anticorrosive layer leakage points, the grade of anticorrosive layer and the rating of the pipeline.
4. The method for predicting the remaining life of a gas pipeline according to claim 3, wherein the remaining life is classified into immediate overall modification, temporary overall modification, local pipe replacement, enhanced operation, situation-friendly performance, ground detection or excavation detection.
5. A gas pipeline remaining life prediction device is characterized by comprising:
the acquisition module is used for acquiring the residual life influencing factors of the plurality of gas pipelines and the corresponding residual life classifications as training samples;
the training module is used for training the artificial neural network through the training sample to obtain a residual life prediction model of the gas pipeline;
the detection module is used for detecting the influence factors of the residual service life of the gas pipeline to be predicted;
and the prediction module is used for inputting the residual life influence factors of the gas pipeline to be predicted into the gas pipeline residual life prediction model so as to obtain the residual life classification of the gas pipeline to be predicted.
6. The gas pipeline residual life prediction device of claim 5, wherein the artificial neural network is a BP neural network.
7. The gas pipeline residual life prediction device according to claim 5 or 6, wherein the residual life influencing factors include the number of air leakage points, the distance between air leakage points, the operational life span, the pipe diameter, the operating pressure, the length, the number of anticorrosive layer leakage points, the grade of anticorrosive layer, and the rating of pipeline.
8. The gas pipeline residual life prediction device according to claim 7, wherein the residual life is classified as immediate overall reconstruction, temporary overall reconstruction, local pipe replacement, enhanced operation, situation-friendly, ground detection, or excavation detection.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910823075.2A CN110705176A (en) | 2019-09-02 | 2019-09-02 | Method and device for predicting residual life of gas pipeline |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910823075.2A CN110705176A (en) | 2019-09-02 | 2019-09-02 | Method and device for predicting residual life of gas pipeline |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110705176A true CN110705176A (en) | 2020-01-17 |
Family
ID=69193717
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910823075.2A Pending CN110705176A (en) | 2019-09-02 | 2019-09-02 | Method and device for predicting residual life of gas pipeline |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110705176A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111881619A (en) * | 2020-07-13 | 2020-11-03 | 成都鹦鹉螺大数据科技有限公司 | Prediction method for realizing pipe erosion defect based on BP neural network of MATLAB tool box |
| CN113090959A (en) * | 2021-03-31 | 2021-07-09 | 杨大松 | Wisdom gas monitoring system |
| CN115330094A (en) * | 2022-10-14 | 2022-11-11 | 成都秦川物联网科技股份有限公司 | Intelligent gas pipeline service life prediction method, internet of things system, device and medium |
| CN115879913A (en) * | 2023-02-13 | 2023-03-31 | 成都秦川物联网科技股份有限公司 | Intelligent gas pipe network maintenance material prediction method, internet of things system and medium |
| CN115899595A (en) * | 2023-03-08 | 2023-04-04 | 成都秦川物联网科技股份有限公司 | Intelligent gas pipeline corrosion prevention optimization method, internet of things system and storage medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2002121962A (en) * | 2002-08-19 | 2004-03-20 | к Богдан Владимирович Будзул | METHOD FOR DETERMINING THE RESIDUAL RESOURCE OF METAL OF PIPES OF THE MAIN PIPELINE INTENDED FOR RE-USE |
| CN101915728A (en) * | 2010-07-27 | 2010-12-15 | 沈阳建筑大学 | Testing method for predicting residual service life of buried metal water supply pipeline |
| CN104063588A (en) * | 2014-06-12 | 2014-09-24 | 东北大学 | Multi-source data fusion-based system and method for predicting pipeline corrosion defect size |
| WO2018191730A1 (en) * | 2017-04-13 | 2018-10-18 | Texas Tech University System | System and method for automated prediction and detection of component and system failures |
| CN109190749A (en) * | 2018-06-25 | 2019-01-11 | 中国电力科学研究院有限公司 | A kind of prediction technique and device for the intelligent electric meter service life |
| CN109559046A (en) * | 2018-11-30 | 2019-04-02 | 北京市燃气集团有限责任公司 | A kind of natural gas development influence factor appraisal procedure and assessment system |
| US20190138995A1 (en) * | 2016-03-29 | 2019-05-09 | t4 Spatial, LLC | Advanced infrastructure management |
| CN109977511A (en) * | 2019-03-18 | 2019-07-05 | 四川轻化工大学 | Method for predicting long-term service life of plastic pressure pipeline based on artificial intelligence big data |
| CN110110804A (en) * | 2019-05-15 | 2019-08-09 | 上海飞机客户服务有限公司 | Flight control system method for predicting residual useful life based on CNN and LSTM |
| CN110175369A (en) * | 2019-04-30 | 2019-08-27 | 南京邮电大学 | A kind of gear method for predicting residual useful life based on two-dimensional convolution neural network |
-
2019
- 2019-09-02 CN CN201910823075.2A patent/CN110705176A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2002121962A (en) * | 2002-08-19 | 2004-03-20 | к Богдан Владимирович Будзул | METHOD FOR DETERMINING THE RESIDUAL RESOURCE OF METAL OF PIPES OF THE MAIN PIPELINE INTENDED FOR RE-USE |
| CN101915728A (en) * | 2010-07-27 | 2010-12-15 | 沈阳建筑大学 | Testing method for predicting residual service life of buried metal water supply pipeline |
| CN104063588A (en) * | 2014-06-12 | 2014-09-24 | 东北大学 | Multi-source data fusion-based system and method for predicting pipeline corrosion defect size |
| US20190138995A1 (en) * | 2016-03-29 | 2019-05-09 | t4 Spatial, LLC | Advanced infrastructure management |
| WO2018191730A1 (en) * | 2017-04-13 | 2018-10-18 | Texas Tech University System | System and method for automated prediction and detection of component and system failures |
| CN109190749A (en) * | 2018-06-25 | 2019-01-11 | 中国电力科学研究院有限公司 | A kind of prediction technique and device for the intelligent electric meter service life |
| CN109559046A (en) * | 2018-11-30 | 2019-04-02 | 北京市燃气集团有限责任公司 | A kind of natural gas development influence factor appraisal procedure and assessment system |
| CN109977511A (en) * | 2019-03-18 | 2019-07-05 | 四川轻化工大学 | Method for predicting long-term service life of plastic pressure pipeline based on artificial intelligence big data |
| CN110175369A (en) * | 2019-04-30 | 2019-08-27 | 南京邮电大学 | A kind of gear method for predicting residual useful life based on two-dimensional convolution neural network |
| CN110110804A (en) * | 2019-05-15 | 2019-08-09 | 上海飞机客户服务有限公司 | Flight control system method for predicting residual useful life based on CNN and LSTM |
Non-Patent Citations (8)
| Title |
|---|
| FUREN ZHANG .ETAL: "The application of the Synchronous improved grey-neural network model in predicting of oil-gas pipeline corrosion rate", 《IEEE》 * |
| 崔勃 等: "《压力容器安全操作600问》", 31 October 2013, 中国质检出版社 * |
| 广州年鉴编纂委员会 编: "《广州年鉴 2016版》", 31 October 2016, 广州年鉴社 * |
| 张若愚: "量子BP神经网络在燃气管网泄漏诊断的应用", 《煤气与热力》 * |
| 沈松泉 等编著: "《压力管道安全技术》", 30 April 2000, 东南大学出版社 * |
| 王琬 等: "基于BP人工神经网络理论对埋地燃气管线腐蚀剩余寿命研究", 《现代机械》 * |
| 管锡珺 等: "《市政公用工程新技术概论》", 30 April 2008, 中国海洋大学出版社 * |
| 魏碧霞 等: "基于神经网络的模糊风险评价技术的应用", 《油气储运》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111881619A (en) * | 2020-07-13 | 2020-11-03 | 成都鹦鹉螺大数据科技有限公司 | Prediction method for realizing pipe erosion defect based on BP neural network of MATLAB tool box |
| CN113090959A (en) * | 2021-03-31 | 2021-07-09 | 杨大松 | Wisdom gas monitoring system |
| CN115330094A (en) * | 2022-10-14 | 2022-11-11 | 成都秦川物联网科技股份有限公司 | Intelligent gas pipeline service life prediction method, internet of things system, device and medium |
| US11898704B2 (en) | 2022-10-14 | 2024-02-13 | Chengdu Qinchuan Iot Technology Co., Ltd. | Methods and Internet of Things systems for smart gas pipeline life prediction based on safety |
| CN115879913A (en) * | 2023-02-13 | 2023-03-31 | 成都秦川物联网科技股份有限公司 | Intelligent gas pipe network maintenance material prediction method, internet of things system and medium |
| CN115879913B (en) * | 2023-02-13 | 2023-05-05 | 成都秦川物联网科技股份有限公司 | Intelligent gas pipe network maintenance material prediction method, internet of things system and medium |
| US11966885B2 (en) | 2023-02-13 | 2024-04-23 | Chengdu Qinchuan Iot Technology Co., Ltd. | Methods and Internet of Things (IoT) systems for predicting maintenance materials of smart gas pipeline networks |
| CN115899595A (en) * | 2023-03-08 | 2023-04-04 | 成都秦川物联网科技股份有限公司 | Intelligent gas pipeline corrosion prevention optimization method, internet of things system and storage medium |
| CN115899595B (en) * | 2023-03-08 | 2023-05-23 | 成都秦川物联网科技股份有限公司 | Intelligent gas pipeline corrosion prevention optimization method, internet of things system and storage medium |
| US11982613B2 (en) | 2023-03-08 | 2024-05-14 | Chengdu Qinchuan Iot Technology Co., Ltd. | Methods and internet of things (IOT) systems for corrosion protection optimization of pipeline of smart gas |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110705176A (en) | Method and device for predicting residual life of gas pipeline | |
| Zhang et al. | Accurate prediction of water quality in urban drainage network with integrated EMD-LSTM model | |
| Zhou et al. | A sequential learning algorithm for online constructing belief-rule-based systems | |
| Tiwari et al. | Performance evaluation of two ANFIS models for predicting water quality index of River Satluj (India) | |
| CN109472110B (en) | Method for predicting residual service life of aeroengine based on LSTM network and ARIMA model | |
| CN107153874B (en) | Water quality prediction method and system | |
| CN111539515B (en) | Complex equipment maintenance decision method based on fault prediction | |
| Talebizadeh et al. | Uncertainty analysis for the forecast of lake level fluctuations using ensembles of ANN and ANFIS models | |
| Adamowski et al. | Development of a coupled wavelet transform and neural network method for flow forecasting of non-perennial rivers in semi-arid watersheds | |
| Ghalkhani et al. | Application of surrogate artificial intelligent models for real‐time flood routing | |
| Rajaee | Wavelet and Neuro‐fuzzy Conjunction Approach for Suspended Sediment Prediction | |
| Afshin et al. | Long term rainfall forecasting by integrated artificial neural network-fuzzy logic-wavelet model in Karoon basin | |
| Byakatonda et al. | Modeling dryness severity using artificial neural network at the Okavango Delta, Botswana | |
| Firat et al. | Monthly total sediment forecasting using adaptive neuro fuzzy inference system | |
| CN106874686A (en) | Index network of personal connections construction method | |
| CN115147645A (en) | Membrane module membrane pollution detection method based on multi-feature information fusion | |
| Reddy et al. | A concise neural network model for estimating software effort | |
| CN114925723A (en) | Method for predicting residual service life of rolling bearing by adopting encoder and decoder | |
| KR101585545B1 (en) | A method of Wavelet-based autoregressive fuzzy modeling for forecasting algal blooms | |
| Kishikawa et al. | Prediction of stock trends by using the wavelet transform and the multi-stage fuzzy inference system optimized by the GA | |
| CN111061708A (en) | Electric energy prediction and restoration method based on LSTM neural network | |
| CN114267422B (en) | Method and system for predicting surface water quality parameters, computer equipment and storage medium | |
| Kakati et al. | Remaining useful life predictions for turbofan engine degradation using online long short-term memory network | |
| CN114692729A (en) | New energy station bad data identification and correction method based on deep learning | |
| Yılmaz et al. | RECURRENT NEURAL NETWORKS FOR PEAK FLOW ESTIMATION. |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200117 |