CN109102149A - A kind of prediction technique of city gas buried pipeline third party breakage in installation risk - Google Patents
A kind of prediction technique of city gas buried pipeline third party breakage in installation risk Download PDFInfo
- Publication number
- CN109102149A CN109102149A CN201810708001.XA CN201810708001A CN109102149A CN 109102149 A CN109102149 A CN 109102149A CN 201810708001 A CN201810708001 A CN 201810708001A CN 109102149 A CN109102149 A CN 109102149A
- Authority
- CN
- China
- Prior art keywords
- party
- breakage
- information
- installation
- city gas
- 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
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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
Abstract
The invention discloses a kind of prediction technique of city gas buried pipeline third party breakage in installation risk, which includes the following steps: step 1, establishes the prediction model of city gas buried pipeline third party's breakage in installation risk；Step 2, at least one of weather characteristics information, environmental characteristic information, red-letter day characteristic information, conference features information characteristic information are input in prediction model；Step 3, a possibility that third party's breakage in installation occurs information is exported by prediction model.The present invention establishes objective and practical city gas buried pipeline third party's breakage in installation possibility prediction model, provides decision assistant for combustion gas relevant enterprise；So that combustion gas relevant enterprise can accomplish the risk for identifying third party's breakage in installation in advance according to prediction result, so as to prevent, cut down harm in advance and control risk, the generation of third party's breakage in installation event is directly reduced.
Description
Technical field
The present invention relates to city gas buried pipelines to destroy risk profile technical field, and specifically, the present invention is one kind
The prediction technique of city gas buried pipeline third party's breakage in installation risk.
Background technique
Currently, town gas pipe evaluation method for failure mainly includes Field Using Fuzzy Comprehensive Assessment, Mu Shi method and expert analysis mode
Method etc., these conventional methods often take into account various gas pipeline risk factors, for example, burn into maloperation, design are lacked
The factors such as sunken, damage from third-party are taken into account, then determine a set of risk factors and marking rule, carry out from each factor to pipeline
Marking, then determines the weight of each factor again, is finally commented according to the risk that the marking of each factor and weight calculation go out pipeline
Valuation.Conventional method is seemed to consider a problem from multiple angles, although conventional method is also to carry out risk from multiple angles to comment
Estimate, but since correlative factor is too many and the experience difference of expert, causes risk evaluation result to have heterogeneous and uncertain
Property, and then causing the accuracy of pipe risk relatively low, concrete reason is as follows.
(1) conventional method is influenced vulnerable to subjective factor: in risk of selection factor, formulate marking rule and calculate each risk because
When the weight of element, the experience and knowledge of designer is relied on larger；Even for comprehensive domain knowledge and rich experiences
Designer, still will appear the objective problem of subjective impact.
(2) all risk factors comprehensively considered excessively idealize: a risk factors usually contain many sub- factors,
For example corrosion factor includes three atmospheric corrosion, pipeline corrosion and corrosion of buried metal factors, and corrosion of buried metal
Include more than ten sub- factors such as cathodic protection, cladding layer status, soil corrosion and the system operation time limit；In reality, have
A little factor relevant informations are not record or lose, and acquire and arrange all factors and need very high cost.
(3) importance of key factor is lowered: will lead to certain key factors during comprehensively considering all factors
Importance be lowered, and then final risk assessment value is made to be likely to be at average value, loses the meaning of risk assessment.
Therefore, in view of existing town gas pipe evaluation method for failure exist vulnerable to subjective factor influence, consider risk because
How accurately, objectively the problems such as element excessively idealizes, the importance of key factor is lowered carry out risk to gas pipeline
Assessment becomes the emphasis of those skilled in the art's research.
Summary of the invention
To solve the risk for influencing, considering vulnerable to subjective factor existing for existing city gas buried pipeline appraisal procedure
Factor is excessively idealized, can be reduced the problems such as key factor importance, and present invention innovation provides a kind of city gas underground pipe
The prediction technique of road third party's breakage in installation risk, using weather, festivals or holidays, environment and great meeting as third party's breakage in installation
Objective influence factor, to establish accurate, reliable prediction model, and then effectively realize to city gas buried pipeline
Tripartite's breakage in installation risk carries out objective prediction.
To realize above-mentioned technical purpose, the invention discloses a kind of city gas buried pipeline third party breakage in installation wind
The prediction technique of danger, the prediction technique include the following steps；
Step 1, establish the prediction model of city gas buried pipeline third party's breakage in installation risk, the prediction model it is defeated
Enter to be characterized a possibility that is third party's breakage in installation occurs for information, output information；
Step 2, by least one in weather characteristics information, environmental characteristic information, red-letter day characteristic information, conference features information
Kind characteristic information is input in the prediction model；
Step 3, a possibility that third party's breakage in installation occurs information is exported by prediction model, is believed using the possibility
Breath predicts city gas buried pipeline third party's breakage in installation risk.
Based on above-mentioned technical solution, the present invention can innovatively be applied third party by characteristic informations such as weather, red-letter days
Work is destroyed risk and rationally effectively predict, so that the risk of look-ahead third party's breakage in installation, reaches and reduce in advance
Harm even thoroughly avoids third party's breakage in installation event from occurring.
Further, in step 1, city gas buried pipeline third party's breakage in installation risk is established in the following way
Prediction model；
Step 1a, in preset time section, acquisition characteristics information, and acquire third party corresponding with the characteristic information
Breakage in installation incident report information；Wherein, the characteristic information includes weather characteristics information, environmental characteristic information, red-letter day feature
Information and conference features information；
Step 1b extracts subcharacter information from each characteristic information of acquisition respectively, constructs all subcharacter information
With the mapping relations of third party's breakage in installation incident report information, using the mapping relations as raw data set；
The raw data set is divided into two parts at random by step 1c, and a part is used as training set, and another part is as survey
Examination collection；
Step 1d selects a model as initial model from multiple pre-selection models, and by the training set to first
Beginning model is trained, and to obtain the first process model, then is tested first process model by the test set,
To obtain the second process model；
Step 1e, judges whether the test result obtained when testing first process model reaches expected essence
Degree: if it is, using second process model as prediction model；If it is not, then returning again to step 1d.
Based on above-mentioned improved technical solution, the present invention can objectively for third party's breakage in installation risk provide it is accurate and
The prediction model of science, to greatly improve the accuracy rate and reliability of third party's breakage in installation risk profile.
Further, in step 1b, subcharacter information is indicated by characteristic value, passes through third party's breakage in installation event number
Indicate third party's breakage in installation incident report information；The mapping relations are relational matrix, and a column of the relational matrix are
Other column of third party's breakage in installation event number, the relational matrix are characteristic value.
Based on above-mentioned improved technical solution, the present invention further improves the accurate of third party's breakage in installation risk profile
Rate and reliability.
Further, it is m equal portions by the raw data set random division in step 1c, takes and be wherein used as test for 1 part
Collection is used as training set for remaining m-1 parts.
Further, in step 1c, using nearest 1 year raw data set as test set, the initial data in remaining time
Collection is used as training set.
Further, in step 1d, the pre-selection model is regression model.
Further, in step 1d, the regression model is linear regression model (LRM), SVM model, random forest
One of model.
Further, in step 1e, during judging test result, by way of mean absolute error
The error between test result and actual result is measured, if the error is less than or equal to error expected, illustrates test knot
Fruit reaches expected precision；If the error is greater than error expected, illustrate the not up to expected precision of test result.
Further, the error expected is 0.42.
Further, the weather characteristics information includes sleet information, temperature information；The environmental characteristic information includes mist
Haze information, the red-letter day characteristic information include holiday information, month information and week information, and the conference features information includes
Great conferencing information.
The invention has the benefit that the present invention establishes objective and practical city gas buried pipeline third party construction
Possibility prediction model is destroyed, by features such as weather, festivals or holidays on the day of inputting some area, output occurs on the day of this area
A possibility that third party's breakage in installation, provides decision assistant for combustion gas relevant enterprise；So that combustion gas relevant enterprise can root
It is predicted that as a result, accomplishing the risk of look-ahead third party's breakage in installation, so as to prevent, cut down harm and control wind in advance
The generation of third party's breakage in installation event is directly reduced in danger；In addition, the present invention also has, implementation cost is low, is suitable for popularization and application
Outstanding advantages of.
Detailed description of the invention
Fig. 1 is a kind of stream of the prediction technique of city gas buried pipeline third party breakage in installation risk of the present invention
Journey schematic diagram.
Fig. 2 is the stream of the prediction model of the present invention for establishing city gas buried pipeline third party's breakage in installation risk
Journey schematic diagram.
Fig. 3 is the schematic diagram of somewhere true value and predicted value in 2017 in implementation process.
Specific embodiment
With reference to the accompanying drawings of the specification to a kind of city gas buried pipeline third party breakage in installation wind of the present invention
The prediction technique of danger carries out detailed explanation and illustration.
The present embodiment will innovatively have very strong paroxysmal third party's breakage in installation as the core of pipe risk
Factor, the characteristics of for third party's breakage in installation and existing data extract associated risk factors, and it is objective and practical to establish
City gas buried pipeline third party's breakage in installation possibility prediction model, so that it is pre- effectively to carry out science to pipeline risk
It surveys.The present embodiment is analyzed data with existing with data digging method, and be extracted from time dimension using data as driving
Risk factors (25) relevant with third party's breakage in installation, and modeled using the method for machine learning, propose one kind
New city gas buried pipeline third party's breakage in installation possibility prediction technique.
As shown in Figures 1 to 3, present embodiment discloses a kind of the pre- of city gas buried pipeline third party breakage in installation risk
Survey method is a kind of side predicted using data-driven version city gas buried pipeline third party's breakage in installation risk
Method；The prediction technique specifically comprises the following steps.
Step 1, establish the prediction model of city gas buried pipeline third party's breakage in installation risk, the prediction model it is defeated
Enter to be characterized a possibility that is third party's breakage in installation occurs for information, output information；In the present embodiment, a city gas is established
Buried pipeline third party's breakage in installation possibility prediction model, input are the weather on the same day in some area, festivals or holidays, great meeting
A possibility that characteristic informations such as view and haze early warning, on the day of being this area third party's breakage in installation occurs for output (is same day hair
Raw third party's breakage in installation event number), the prior art can effectively obtain the information such as the following festivals or holidays, weather, great meeting, from
And following third party's breakage in installation information can be effectively predicted in the present invention；In this step, built by following mode
The prediction model of vertical city gas buried pipeline third party breakage in installation risk；It is described as follows, as shown in Figure 2.
Step 1a, in preset time section, acquisition characteristics information, and acquire third party's construction corresponding with characteristic information
Destructive insident report information；Acquire data procedures；Wherein, characteristic information includes weather characteristics information, environmental characteristic information, section
Day characteristic information and conference features information；In the present embodiment, the data of acquisition can be divided into internal data and external data: needs
The internal data of acquisition mainly includes the report of history third party's breakage in installation event, and the external data for needing to acquire mainly includes section
Holiday Dates arrangement data, great meeting date data, Weather information data and haze warning information etc..In general, it adopts
The more the data of collection the newer, and the accuracy of final mask can be higher.
Step 1b extracts subcharacter information from each characteristic information of acquisition respectively, constructs all subcharacter information
With the mapping relations of third party's breakage in installation incident report information, using mapping relations as raw data set；In the present embodiment, lead to
Crossing characteristic value indicates subcharacter information, indicates third party's breakage in installation event report letter by third party's breakage in installation event number
Breath；The mapping relations of the present embodiment are relational matrix, and as shown in the table, a column of relational matrix are third party's breakage in installation thing
Other column of number of packages amount, relational matrix are characteristic value, wherein the corresponding sample of a line, i.e., one day data, it is assumed that have n days
Historical data, then the data set matrix of n × 26 can be obtained.Wherein, y indicates the third occurred on the day of this area
Square breakage in installation event number.
| x1 | x2 | x3 | … | x25 | y |
| 1 | 0 | 0 | … | 0 | 0 |
| 0 | 0 | 0 | … | 0 | 1 |
| … | … | … | … | … | … |
| 0 | 1 | 0 | … | 0 | 0 |
Influence for above-mentioned subcharacter information to breakage in installation, in general follows following rule.
1) had during festivals or holidays part construction stop work, so during festivals or holidays occur breakage in installation a possibility that compared with
It is low；2) in the great session, largely construction is stopped work, so the great session is lower a possibility that breakage in installation occurs；3)
Largely construction is stopped work during haze early warning, so a possibility that breakage in installation occurs during haze early warning is lower；4) exist
Part construction is stopped work during raining and snowing, so a possibility that breakage in installation occurs during raining and snowing is lower；5) in the winter
Largely construction is stopped work during season frozen soil, so a possibility that breakage in installation occurs during winter frozen soil is lower；6) freeze in winter
Native front and back will appear the phenomenon that works to tight deadlines, so a possibility that breakage in installation occurs before and after frozen soil in winter is higher.
As shown in the table, the present embodiment is extracted following 25 from time dimension and applies with city gas buried pipeline third party
Work destroys relevant feature.On the basis of the present embodiment disclosure, can according to the actual conditions of collectable data,
Suitably increase some features, for example, the quantity etc. of this area's same day Large Construction, to improve the accuracy rate of model.
Raw data set is divided into two parts at random by step 1c, and a part is used as training set, and another part is as test
Collection；It is m equal portions by raw data set random division in the present embodiment, takes and be wherein used as test set for 1 part, remaining m-1 parts is made
For training set；For example, the raw data set in remaining time is as training using nearest 1 year raw data set as test set
Collection.
Step 1d selects a model as initial model from multiple pre-selection models, and by training set to introductory die
Type is trained, and to obtain the first process model, then is tested the first process model by test set, to obtain the second mistake
Journey model；In the present embodiment, used pre-selection model be regression model, specifically, regression model be linear regression model (LRM),
One of SVM model, Random Forest model, for example, linear regression is come using regression analysis in mathematical statistics
Determine a kind of statistical analysis technique of complementary quantitative relationship between two or more variable.
Step 1e, judges whether the test result obtained when testing the first process model reaches expected precision: such as
Fruit is then to model the second process model as prediction model, end；If it is not, then returning again to step 1d, model or tune are replaced
Mould preparation shape parameter.In the present embodiment, during judging test result, it can be weighed by way of mean absolute error
The error between test result and actual result is measured, if the error is less than or equal to error expected, illustrates that test result reaches
To expected precision；If the error is greater than error expected, illustrates that test result is not up to and be expected precision, in the present embodiment, in advance
Period error is 0.42.The mean absolute error (mean absolute error, MAE) being directed to: for measuring predicted value
With the error of true value；Its calculation formula is:Wherein, yiIt indicates true value (actual result), y 'iIt indicates
Predicted value (test result).
The present embodiment indicates above-mentioned prediction model using following mathematical form:
F (X)=y
Wherein, f indicates prediction model, X={ xi| i=1,2,3 ..., n indicate the model input (n indicate input
Feature quantity), y indicates the output of the model, is third party's breakage in installation event number that this area occurs on the day of.Assuming that L
Indicate the error between predicted value and true value, the present embodiment makes L (f*) small as far as possible, f*=argminL (f).
Step 2, by least one in weather characteristics information, environmental characteristic information, red-letter day characteristic information, conference features information
Kind characteristic information is input in prediction model；In the present embodiment, above-mentioned weather characteristics information includes sleet information, temperature letter
Breath；Environmental characteristic information includes haze information, and red-letter day characteristic information includes holiday information, month information and week information, meeting
Discussing characteristic information includes great conferencing information；It is specific as shown above.
Step 3, a possibility that third party's breakage in installation occurs information is exported by prediction model, utilizes possibility information pair
City gas buried pipeline third party's breakage in installation risk is predicted.
As shown in figure 3, making test process of the invention: using 2015 and 2016 data in somewhere, using machine
Linear regression method training in study obtains combustion gas buried pipeline third party's breakage in installation possibility prediction mould of this area
Type reuses third party's breakage in installation possibility of the model prediction this area in January, 2017 to October.Specifically, scheme
Be the comparison of true value and predicted value shown in 3: Fig. 3 longitudinal axis indicates the third party's breakage in installation event number occurred daily, horizontal axis
Indicate exact date.It can be seen that the overall condition of true value in 2017 is that the January is relatively high, February drop to it is minimum, from
March, the event number monthly occurred gradually rise, and highest is reached to June, is then gradually decreased again.Predicted value is whole
It is shown on body and the consistent trend of true value；Again from the point of view of details, festivals or holidays (Spring Festival, Clear and Bright, May Day, the Dragon Boat Festival, mid-autumn and
National Day) during predicted value obviously than low before and after festivals or holidays, the predicted value of great session is also before obvious specific gravity Great Council
Afterwards low, this all meets practical rule.Predicted value and the mean absolute error of true value are 0.42, i.e. the model prediction
Third party's breakage in installation event number and the mean error of true value be 0.42, this precision is for sudden extremely strong the
It is acceptable for tripartite's breakage in installation, so the present invention can provide good decision assistant for combustion gas relevant enterprise.
In the description of this specification, reference term " the present embodiment ", " one embodiment ", " some embodiments ", " show
The description of example ", " specific example " or " some examples " etc. mean specific features described in conjunction with this embodiment or example, structure,
Material or feature are included at least one embodiment or example of the invention.In the present specification, above-mentioned term is shown
The statement of meaning property is necessarily directed to identical embodiment or example.Moreover, specific features, structure, material or the spy of description
Point may be combined in any suitable manner in any one or more of the embodiments or examples.In addition, without conflicting with each other,
Those skilled in the art can be by different embodiments or examples described in this specification and different embodiments or examples
Feature is combined.
In addition, term " first ", " second " are used for descriptive purposes only and cannot be understood as indicating or suggesting relative importance
Or implicitly indicate the quantity of indicated technical characteristic.Define " first " as a result, the feature of " second " can be expressed or
Implicitly include at least one this feature.In the description of the present invention, the meaning of " plurality " is at least two, such as two, three
It is a etc., unless otherwise specifically defined.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Made any modification, equivalent replacement and simple modifications etc., should all be included in the protection scope of the present invention in content.
Claims (10)
1. a kind of prediction technique of city gas buried pipeline third party breakage in installation risk, it is characterised in that: the prediction technique
Include the following steps；
Step 1, the prediction model of city gas buried pipeline third party's breakage in installation risk is established, the input of the prediction model is
A possibility that is third party's breakage in installation occurs for characteristic information, output information；
Step 2, by least one of weather characteristics information, environmental characteristic information, red-letter day characteristic information, conference features information spy
Reference breath is input in the prediction model；
Step 3, a possibility that third party's breakage in installation occurs information is exported by prediction model, utilizes the possibility information pair
City gas buried pipeline third party's breakage in installation risk is predicted.
2. the prediction technique of city gas buried pipeline third party breakage in installation risk according to claim 1, feature
It is: in step 1, establishes the prediction model of city gas buried pipeline third party's breakage in installation risk in the following way；
Step 1a, in preset time section, acquisition characteristics information, and acquire third party's construction corresponding with the characteristic information
Destructive insident report information；Wherein, the characteristic information includes weather characteristics information, environmental characteristic information, red-letter day characteristic information
And conference features information；
Step 1b extracts subcharacter information from each characteristic information of acquisition respectively, constructs all subcharacter information and the
The mapping relations of tripartite's breakage in installation incident report information, using the mapping relations as raw data set；
The raw data set is divided into two parts at random by step 1c, and a part is used as training set, and another part is as test
Collection；
Step 1d selects a model as initial model from multiple pre-selection models, and by the training set to introductory die
Type is trained, and to obtain the first process model, then is tested first process model by the test set, with
To the second process model；
Step 1e, judges whether the test result obtained when testing first process model reaches expected precision: such as
Fruit is, then using second process model as prediction model；If it is not, then returning again to step 1d.
3. the prediction technique of city gas buried pipeline third party breakage in installation risk according to claim 2, feature
It is:
In step 1b, subcharacter information is indicated by characteristic value, indicates that third party applies by third party's breakage in installation event number
Work destructive insident report information；The mapping relations are relational matrix, and a column of the relational matrix are that third party's construction is broken
Other column of bad event number, the relational matrix are characteristic value.
4. the prediction technique of city gas buried pipeline third party breakage in installation risk according to claim 3, feature
It is:
It is m equal portions by the raw data set random division in step 1c, takes and be wherein used as test set for 1 part, by remaining m-1
Part is used as training set.
5. the prediction technique of city gas buried pipeline third party breakage in installation risk according to claim 4, feature
It is:
In step 1c, using nearest 1 year raw data set as test set, the raw data set in remaining time is as training set.
6. the prediction technique of city gas buried pipeline third party breakage in installation risk according to claim 5, feature
It is:
In step 1d, the pre-selection model is regression model.
7. the prediction technique of city gas buried pipeline third party breakage in installation risk according to claim 6, feature
It is:
In step 1d, the regression model is one of linear regression model (LRM), SVM model, Random Forest model.
8. the prediction technique of city gas buried pipeline third party breakage in installation risk according to claim 7, feature
It is:
In step 1e, during judging test result, test result is measured by way of mean absolute error
Error between actual result illustrates that test result reaches expected essence if the error is less than or equal to error expected
Degree；If the error is greater than error expected, illustrate the not up to expected precision of test result.
9. the prediction technique of city gas buried pipeline third party breakage in installation risk according to claim 8, feature
Be: the error expected is 0.42.
10. according to claim 1 or the prediction technique of city gas buried pipeline third party breakage in installation risk described in 9,
Be characterized in that: the weather characteristics information includes sleet information, temperature information；The environmental characteristic information includes haze information,
The red-letter day characteristic information includes holiday information, month information and week information, and the conference features information includes great meeting
Discuss information.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810573765 | 2018-06-06 | ||
| CN2018105737652 | 2018-06-06 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109102149A true CN109102149A (en) | 2018-12-28 |
Family
ID=64845344
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810708001.XA Pending CN109102149A (en) | 2018-06-06 | 2018-07-02 | A kind of prediction technique of city gas buried pipeline third party breakage in installation risk |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109102149A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111539394A (en) * | 2020-07-08 | 2020-08-14 | 浙江浙能天然气运行有限公司 | Pipeline along-line third-party construction early warning method based on time domain characteristics and space-time information |
| CN111768073A (en) * | 2020-05-20 | 2020-10-13 | 深圳市燃气集团股份有限公司 | Pipeline protection method based on intelligent identification |
| CN111859779A (en) * | 2020-06-05 | 2020-10-30 | 北京市燃气集团有限责任公司 | Early warning method and device for preventing third-party construction damage risk of gas pipe network |
| CN112529376A (en) * | 2020-11-27 | 2021-03-19 | 合肥泽众城市智能科技有限公司 | Gas pipeline-third party construction coupling hidden danger identification and management system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106503925A (en) * | 2016-11-16 | 2017-03-15 | 深圳市燃气集团股份有限公司 | A kind of city gas polyethylene pipe failure accidents analyze realization method and system |
| CN106779320A (en) * | 2016-11-28 | 2017-05-31 | 成都千嘉科技有限公司 | A kind of gas pipeline damage from third-party methods of risk assessment based on fuzzy mathematics |
| CN108053075A (en) * | 2017-12-27 | 2018-05-18 | 北京中交兴路车联网科技有限公司 | A kind of scrap-car Forecasting Methodology and system |
-
2018
- 2018-07-02 CN CN201810708001.XA patent/CN109102149A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106503925A (en) * | 2016-11-16 | 2017-03-15 | 深圳市燃气集团股份有限公司 | A kind of city gas polyethylene pipe failure accidents analyze realization method and system |
| CN106779320A (en) * | 2016-11-28 | 2017-05-31 | 成都千嘉科技有限公司 | A kind of gas pipeline damage from third-party methods of risk assessment based on fuzzy mathematics |
| CN108053075A (en) * | 2017-12-27 | 2018-05-18 | 北京中交兴路车联网科技有限公司 | A kind of scrap-car Forecasting Methodology and system |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111768073A (en) * | 2020-05-20 | 2020-10-13 | 深圳市燃气集团股份有限公司 | Pipeline protection method based on intelligent identification |
| CN111768073B (en) * | 2020-05-20 | 2024-03-22 | 深圳市燃气集团股份有限公司 | Pipeline protection method based on intelligent identification |
| CN111859779A (en) * | 2020-06-05 | 2020-10-30 | 北京市燃气集团有限责任公司 | Early warning method and device for preventing third-party construction damage risk of gas pipe network |
| CN111859779B (en) * | 2020-06-05 | 2024-04-12 | 北京市燃气集团有限责任公司 | Method and device for early warning of third party construction damage risk of gas pipe network |
| CN111539394A (en) * | 2020-07-08 | 2020-08-14 | 浙江浙能天然气运行有限公司 | Pipeline along-line third-party construction early warning method based on time domain characteristics and space-time information |
| CN112529376A (en) * | 2020-11-27 | 2021-03-19 | 合肥泽众城市智能科技有限公司 | Gas pipeline-third party construction coupling hidden danger identification and management system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109102149A (en) | A kind of prediction technique of city gas buried pipeline third party breakage in installation risk | |
| Najafi et al. | Pipeline condition prediction using neural network models | |
| Piechota et al. | Development of exceedance probability streamflow forecast | |
| Tabesh et al. | Assessing pipe failure rate and mechanical reliability of water distribution networks using data-driven modeling | |
| US20040199410A1 (en) | Method for evaluating flood plain risks | |
| CN104764868B (en) | A kind of soil organic matter Forecasting Methodology based on Geographical Weighted Regression | |
| Xu et al. | Condition evaluation of suspension bridges for maintenance, repair and rehabilitation: A comprehensive framework | |
| US20170206510A1 (en) | Spatially-keyed, consolidated-data-controlled apparatus and method | |
| Coll et al. | Application of homogenization methods for Ireland's monthly precipitation records: Comparison of break detection results | |
| US20220057367A1 (en) | Method for evaluating pipe condition | |
| Moomen et al. | Bridge deterioration models to support Indiana’s bridge management system | |
| US8682623B1 (en) | Electric power distribution interruption risk assessment calculator | |
| CN101853320A (en) | Fuzzy comprehensive evaluation method suitable for aircraft structure corrosion damage | |
| Robbins et al. | Pavement ME design–A summary of local calibration efforts for flexible pavements | |
| CN103257000B (en) | Temperature extreme-value prediction method for bridge structure sunshine effect analysis | |
| Andersen et al. | Ranking procedure on maintenance tasks for monitoring of embankment dams | |
| CN113191582A (en) | Road torrential flood vulnerability evaluation method based on GIS and machine learning | |
| Bean et al. | Predicting Utah ground snow loads with PRISM | |
| CN110502526A (en) | A method of the data series interpolation suitable for icing phenomenon | |
| CN113779760B (en) | Power-statistics combined season climate prediction method based on predictable climate mode | |
| Brown et al. | Use of expert opinion elicitation to quantify the internal erosion process in dams | |
| Heyer | Reliability assessment of levees based on failure investigations | |
| Yamijala | Statistical estimation of water distribution system pipe break risk | |
| Spławińska | Development of models for determining the traffic volume for the analysis of roads efficiency | |
| Desjardins | Corrosion rate and severity results from in-line inspection data |
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 |
Application publication date: 20181228 |
|
| RJ01 | Rejection of invention patent application after publication |