CN105653791A - Data mining based corrosion failure prediction system for on-service oil pipe column - Google Patents
Data mining based corrosion failure prediction system for on-service oil pipe column Download PDFInfo
- Publication number
- CN105653791A CN105653791A CN201511018634.0A CN201511018634A CN105653791A CN 105653791 A CN105653791 A CN 105653791A CN 201511018634 A CN201511018634 A CN 201511018634A CN 105653791 A CN105653791 A CN 105653791A
- Authority
- CN
- China
- Prior art keywords
- data
- oil pipe
- predictor
- prediction
- precursor
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/30—Circuit design
- G06F30/36—Circuit design at the analogue level
- G06F30/367—Design verification, e.g. using simulation, simulation program with integrated circuit emphasis [SPICE], direct methods or relaxation methods
Abstract
The invention discloses a data mining based corrosion failure prediction system for an on-service oil pipe column. The system comprises an oil pipe working environment, a training data source, an oil pipe failure predictor and a user. The training data source obtains training data in a manner of connecting a database or accessing to an arff file; the obtained training data is preprocessed to form a training data set; the oil pipe failure predictor calls a required predictor model to refresh a prediction model in the oil pipe failure predictor; and when new prediction data is input, the oil pipe failure predictor receives the data, calls the model to perform prediction and gives out a prediction result. The oil pipe failure predictor can call one or more predictor models to give out the prediction result. According to the system, the degree of influence of a current environment on the corrosion rate of an oil pipe can be accurately predicted and the service life of the oil pipe can be predicted, so that the use safety of the oil pipe column can be greatly improved, the leakage accidents of the pipe column can be greatly reduced, the enterprise and user costs can be reduced, and the environmental pollution can be avoided.
Description
Technical field
The invention belongs to a kind of DSS, relate to artificial intelligence and data base's area research, this invention is capable of disclosing information that is implicit, not previously known and that have potential value from a large amount of historical datas, can be used for maintainer and predict the current environment influence degree to tube corrosion speed, and its physical life is predicted.
Background technology
Exploitation along with oil gas field, the media such as hydrogen sulfide, carbon dioxide, chloride ion, water and the microorganism that the High Temperature High Pressure multiphase flow environment under Oil/gas Well contains can occur as attendants, make down-hole oil tube too corroded, not only have impact on the normal production of Oil/gas Well, and bring many difficulties to examination workover treatment.
The factor affecting Oil Tube Steel corrosion can be divided into material factor, environmental factors and mechanics factor etc. Steel material factor includes chemical composition (mainly alloying element) and the condition of heat treatment (microscopic structures of steel) thereof of steel. Environmental factors includes temperature, partial pressure, corrosion products film, pH value, flow velocity, flow pattern, solution degree of supersaturation, antibacterial etc. Mechanics factor includes magnitude of load, direction and the distribution situation etc. that tubing bears. The above factor affects the corrosion of oil pipe to some extent, therefore obtains tube corrosion degree and mainly sets about from this several respects factor, thus the service life of in-service oil pipe is carried out preliminary grading forewarning system.
Data mining (DataMining, DM) also known as the Knowledge Discovery (KnowledgeDiscoverinDatabase in data base, KDD), being current artificial intelligence and the hot issue of data base's area research, so-called data mining refers to the non-trivial process disclosing information that is implicit, not previously known and that have potential value from the mass data of data base. Data mining is a kind of decision support processes, it is based primarily upon artificial intelligence, machine learning, pattern recognition, statistics, data base, visualization technique etc., analyze the data of enterprise increasingly automatedly, make the reasoning of inductive, therefrom excavate potential pattern, aid decision making person adjusts market strategy, reduces risks, and makes correct decision-making.
Data mining is by analyzing each data, finds the technology of its rule from mass data, mainly has data preparation, rule to find and rule represents 3 steps.It is choose required data from relevant data source and be integrated into the data set for data mining that data prepare; It is with the rule contained by data set being found out someway that rule is found; Rule represents it is the rule found out showed in the intelligible mode of user (such as visualization) as far as possible.
Prediction is worked by classification or valuation, say, that draw model by classification or valuation, and this model is for the prophesy to known variables. In this sense, prophesy there is no need to be divided into an independent class in fact. Prophesy its objective is the prediction to following known variables, and this prediction requires time for verifying, after namely having to pass through certain time, just knows that prophesy accuracy is how many.
The step of data mining can be varied from the application of different field, and each data mining technology also has respective characteristic and uses step, and the data mining process formulated for different problems and demand also can there are differences. Additionally, the degree etc. of the integrated degree of data, professional's support all can affect setting up data mining process to some extent. These factors cause data mining utilization in variant field, planning, and the diversity of flow process, even if same industry, as analytical technology is different with the degree that involves in of Professional knowledge and different, therefore the systematization of data mining process, standardization are just seemed increasingly important. Consequently, it is possible to be possible not only to cross-cutting application relatively easily, it is also possible in conjunction with different Professional knowledges, play the true spirit of data mining. The complete step of data mining is as follows:
1. the source (understanding) of data and data is understood.
2. relevant knowledge and technology (acquisition) are obtained.
3. integrate and check data (integrationandchecking).
4. wrong or inconsistent data (datacleaning) are removed.
5. set up model and assume (modelandhypothesisdevelopment).
6. real data excacation (datamining).
7. test and checking Result (testingandverification).
8. explain and application (interpretationanduse).
Be can be seen that by above-mentioned steps, data mining has involved substantial amounts of preparation and planning, in fact many experts all think a whole set of data mining process in, the time and efforts having 80% is to spend in data preprocessing phase, integrate including the purification of data, Data Format Transform, variable, and the link of tables of data. Visible, before carrying out the analysis of data mining technology, also have many preparations to complete.
Composite pattern is the hierarchical structure that object composition becomes tree structure to represent " part is overall ". Composite makes user that single Object Operations and operating with of compound object are had concordance. Expect that Composite is just it should be appreciated that tree structure figure. In assembly, these objects have common interface, and when the called execution of the method for one object of assembly, Composite will travel through whole tree structure, find the object comprising this method equally and execution is called in realization.
Composite benefit: first, makes client call simple, use combinative structure that client can be consistent or wherein single object, and user just need not be concerned about that what oneself process is single object or whole combinative structure, which simplifies client code. Second, it is easier to adding object Part in assembly, client need not change code because adding new object Part.
The full name of WEKA is Waikato intellectual analysis environment (WaikatoEnvironmentforKnowledgeAnalysis), it is a free, non-commercialization, based on the machine learning increased income under JAVA environment and data mining software, it is described as data mining and the historical milestone of machine learning, is one of the most complete now Data Mining Tools.WEKA, as a disclosed data mining work platforms, has gathered a large amount of machine learning algorithm that can undertake data mining task, carries out pretreatment including to data, classification, recurrence, cluster, correlation rule and the visualization on new interactive interface.
At present, domestic maintenance data excavates the research carrying out tubing string corrosion failure prediction and compares shortcoming, working site is typically all the experience by technical staff and estimation carries out early warning, lacks credibility and degree of safety, so the research and development of this respect have good engineer applied and are worth.
Summary of the invention
It is an object of the invention to for prior art Problems existing, in conjunction with data mining technology, it is provided that a kind of early warning system to tube corrosion speed, be used for prediction oil pipe service life exactly, and produce the life-span warning of different stage.
For solving above-mentioned technical problem, the technical solution of the present invention is:
A kind of in-service tubing string corrosion failure prognoses system based on data mining, including the training data source being associated with oil pipe working environment, oil pipe inefficacy precursor and user;
Described oil pipe working environment, including affecting the environmental factors of Oil Tube Steel corrosion, material factor and mechanics factor;
Described training data source, obtains training data by two ways: one is by connecting data base, obtains the data being stored in data base; Two is by accessing arff file, obtains with the data of arff document form storage;
Described oil pipe inefficacy precursor, with reference to Composite pattern, is one and refreshes forecast model and be predicted, and the prediction data of reception user's input calls predictor model and output predicts the outcome, the interface exchanged with user;
Described user, it is possible to input prediction data also obtain accurately believable predicting the outcome by this system;
Described training data source and user connected pipes working environment and oil pipe inefficacy precursor respectively, oil pipe inefficacy precursor obtains training data by training data source, forms training dataset through data prediction; The training dataset then passing through acquisition calls required predictor model, refreshes the forecast model in oil pipe inefficacy precursor; When user has new prediction data to input, oil pipe inefficacy precursor receives data, calls required forecast model and is predicted, and provides and predict the outcome.
Further, described tubing material factor includes chemical composition and the condition of heat treatment (microscopic structures of steel) thereof of steel alloying element; Described environmental factors includes temperature, partial pressure, pH value, flow velocity, flow pattern, solution degree of supersaturation and antibacterial; Described mechanics factor includes the stress intensity under tubing carrying, direction and distribution situation.
Further, by the training data that described training data source obtains, to choose whether as required to carry out data prediction, training dataset could be formed.
Further, described data prediction includes the purification of data, Data Format Transform and variable integration.
Further, described oil pipe inefficacy precursor, with reference to Composite pattern, its forecast model combination include: the predictor based on random tree algorithm, the predictor based on renewable NB Algorithm, the predictor based on LWL algorithm, the predictor based on IBk algorithm, based on the predictor of SMO regression algorithm, the predictor based on addicted regression algorithm and the predictor based on neural network algorithm.
Further, described oil pipe inefficacy precursor uses a predictor to be predicted, or uses multiple predictor to be predicted, and namely uses combined method to call multiple predictor and is predicted.Oil pipe inefficacy precursor can call a predictor model and provide and predict the outcome when giving a forecast, it is also possible to predicting the outcome of comprehensive multiple predictor models provides higher predicting the outcome of credibility.
Further, it was predicted that device is referred in Weka software to provide include data prediction, set up forecast model and carry out data prediction.
Present invention is characterized in that
(1) present invention is based on data mining technology, relates to artificial intelligence and data base's area research, it is provided that a kind of DSS.
(2) oil pipe inefficacy precursor of the present invention, with reference to Composite pattern, a predictor model can be called provide predict the outcome when giving a forecast, it is also possible to predicting the outcome of comprehensive multiple predictor models provides higher predicting the outcome of credibility.
(3) present invention can obtain training data by two ways. One is by connecting data base, obtains the data being stored in data base; Two is by accessing arff file, obtains with the data of arff document form storage;
(4) present invention is capable of disclosing information that is implicit, not previously known and that have potential value from a large amount of historical datas, can be used for maintainer and predicts the current environment influence degree to tube corrosion speed, and its physical life is predicted.
Accompanying drawing explanation
Fig. 1 is present system composition diagram.
Detailed description of the invention
Below in conjunction with accompanying drawing, the specific embodiment of the present invention is described in detail.
As it is shown in figure 1, the system of the present invention is made up of oil pipe working environment, training data source, oil pipe inefficacy precursor and user four part. Oil pipe working environment is connected with training data source and user respectively, and training data source and user are connected with connected pipes inefficacy precursor respectively. Oil pipe inefficacy precursor obtains training data by training data source, forms training dataset through data prediction; The training dataset then passing through acquisition calls required predictor model, refreshes the forecast model in oil pipe inefficacy precursor; When user has new prediction data to input, oil pipe inefficacy precursor receives data, calls appropriate forecast model and is predicted, and provides and predict the outcome.
Wherein, oil pipe working environment includes affecting the material factor of Oil Tube Steel corrosion, environmental factors and mechanics factor etc., and material factor includes chemical composition (mainly alloying element) and the condition of heat treatment (microscopic structures of steel) thereof of steel; Environmental factors includes temperature, partial pressure, pH value, flow velocity, flow pattern, solution degree of supersaturation, antibacterial etc.; Mechanics factor includes the stress intensity under tubing carrying, direction and distribution situation etc. These factors will be recorded in the form of data, as the data foundation of data digging system.
Training data source can obtain training data by two ways. One is by connecting data base, obtains the data being stored in data base; Two is by accessing arff file, obtains with the data of arff document form storage. The training data obtained, will choose whether as required to carry out data prediction, could form training dataset. Data prediction includes the purification of data, Data Format Transform and variable integration etc.
Oil pipe inefficacy precursor, with reference to Composite pattern, its forecast model combination include: the predictor based on random tree algorithm, the predictor based on renewable NB Algorithm, the predictor based on LWL algorithm, the predictor based on IBk algorithm, based on the predictor of SMO regression algorithm, the predictor based on addicted regression algorithm and the predictor etc. based on neural network algorithm.Oil pipe inefficacy precursor is one and refreshes forecast model and be predicted, and the prediction data of reception user's input calls predictor model and output predicts the outcome, the interface exchanged with user.
Oil pipe inefficacy precursor uses a predictor to be predicted when giving a forecast, or uses multiple predictor to be predicted, and namely uses combined method to call multiple predictor and is predicted. A predictor model can be called provide and predict the outcome, it is also possible to predicting the outcome of comprehensive multiple predictor models provides higher predicting the outcome of credibility. Method that predictor is referred in Weka software to provide and thought, including data prediction, set up forecast model and carry out data prediction.
Comprehensive multiple predictor model, refer to the following calculating process that predicts the outcome: combined method is randomly drawed some data from training data source and used as checking data set, remaining training data source is trained as each predictor of training data set pair, generate model, and the condition of each predictor input validation data set is predicted. Combined method, by predicting the outcome and verifying that the result of data set compares, calculates the error of each predictor. Combined method ignores the predictor that error is maximum, and the predictor input calling other needs the condition of prediction to calculate predicting the outcome of other each predictor, and predicting the outcome of other each predictor is taken the mean, predicting the outcome as combined method.
The energy Accurate Prediction current environment of the present invention influence degree to tube corrosion speed, and its physical life is predicted, provide one DSS accurately, the safety that tubing string uses and the generation reducing oil and gas leakage accident can be greatly improved, save enterprise customer's cost.
Claims (7)
1. the in-service tubing string corrosion failure prognoses system based on data mining, it is characterised in that include the training data source, oil pipe inefficacy precursor and the user that are associated with oil pipe working environment;
Described oil pipe working environment, including affecting the environmental factors of Oil Tube Steel corrosion, material factor and mechanics factor;
Described training data source, obtains training data by two ways: one is by connecting data base, obtains the data being stored in data base; Two is by accessing arff file, obtains with the data of arff document form storage;
Described oil pipe inefficacy precursor, with reference to Composite pattern, is one and refreshes forecast model and be predicted, and the prediction data of reception user's input calls predictor model and output predicts the outcome, the interface exchanged with user;
Described user, it is possible to input prediction data also obtain accurately believable predicting the outcome by this system;
Described training data source and user connected pipes working environment and oil pipe inefficacy precursor respectively, oil pipe inefficacy precursor obtains training data by training data source, forms training dataset through data prediction; The training dataset then passing through acquisition calls required predictor model, refreshes the forecast model in oil pipe inefficacy precursor; When user has new prediction data to input, oil pipe inefficacy precursor receives data, calls required forecast model and is predicted, and provides and predict the outcome.
2. a kind of in-service tubing string corrosion failure prognoses system based on data mining according to claim 1, it is characterised in that described tubing material factor includes chemical composition and the condition of heat treatment thereof of steel alloying element;Described environmental factors includes temperature, partial pressure, pH value, flow velocity, flow pattern, solution degree of supersaturation and antibacterial; Described mechanics factor includes the stress intensity under tubing carrying, direction and distribution situation.
3. a kind of in-service tubing string corrosion failure prognoses system based on data mining according to claim 1, it is characterized in that, by the training data that described training data source obtains, to choose whether as required to carry out data prediction, training dataset could be formed.
4. a kind of in-service tubing string corrosion failure prognoses system based on data mining according to claim 3, it is characterised in that described data prediction includes the purification of data, Data Format Transform and variable and integrates.
5. a kind of in-service tubing string corrosion failure prognoses system based on data mining according to claim 1, it is characterized in that, described oil pipe inefficacy precursor, with reference to Composite pattern, its forecast model combination include: the predictor based on random tree algorithm, the predictor based on renewable NB Algorithm, the predictor based on LWL algorithm, the predictor based on IBk algorithm, based on the predictor of SMO regression algorithm, the predictor based on addicted regression algorithm and the predictor based on neural network algorithm.
6. a kind of in-service tubing string corrosion failure prognoses system based on data mining according to claim 4, it is characterized in that, described oil pipe inefficacy precursor uses a predictor to be predicted, or use multiple predictor to be predicted, namely use combined method to call multiple predictor and be predicted.
7. a kind of in-service tubing string corrosion failure prognoses system based on data mining according to claim 1 or 4, it is characterised in that described predictor includes data prediction with reference to providing in Weka software, sets up forecast model and carry out data prediction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511018634.0A CN105653791A (en) | 2015-12-29 | 2015-12-29 | Data mining based corrosion failure prediction system for on-service oil pipe column |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511018634.0A CN105653791A (en) | 2015-12-29 | 2015-12-29 | Data mining based corrosion failure prediction system for on-service oil pipe column |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105653791A true CN105653791A (en) | 2016-06-08 |
Family
ID=56477459
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201511018634.0A Pending CN105653791A (en) | 2015-12-29 | 2015-12-29 | Data mining based corrosion failure prediction system for on-service oil pipe column |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105653791A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106442291A (en) * | 2016-09-30 | 2017-02-22 | 中国石油大学(华东) | Corrosion fatigue life prediction method based on BP neural network and application |
| CN106503176A (en) * | 2016-10-25 | 2017-03-15 | 英业达科技有限公司 | Solution hunting system and the operational approach of solution hunting system |
| CN106503177A (en) * | 2016-10-25 | 2017-03-15 | 英业达科技有限公司 | Solution hunting system and the operational approach of solution hunting system |
| CN107063991A (en) * | 2017-04-14 | 2017-08-18 | 中国石油天然气股份有限公司 | A kind of conveyance conduit internal corrosion defect dynamic security assessment method and device |
| CN109977511A (en) * | 2019-03-18 | 2019-07-05 | 四川轻化工大学 | Method based on artificial intelligence big data prediction Pressurized Plastic Pipes long term life |
| CN111062625A (en) * | 2019-12-19 | 2020-04-24 | 中国特种设备检测研究院 | Method and device for establishing residual oil hydrogenation device failure prediction model |
| CN111190885A (en) * | 2019-12-19 | 2020-05-22 | 中国特种设备检测研究院 | Method and device for establishing oil refining device data management platform |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101807254A (en) * | 2009-02-13 | 2010-08-18 | 烟台海岸带可持续发展研究所 | Implementation method for data characteristic-oriented synthetic kernel support vector machine |
| CN103455682A (en) * | 2013-09-12 | 2013-12-18 | 西南石油大学 | Method for predicting residual life of corroded casing of high-temperature and high-pressure well |
| CN103870670A (en) * | 2012-12-17 | 2014-06-18 | 中国石油天然气集团公司 | Oil pipe corrosion degree forecasting method and device |
| CN105069486A (en) * | 2015-09-09 | 2015-11-18 | 西安石油大学 | Extreme learning machine-based petrochemical equipment corrosion prediction method |
-
2015
- 2015-12-29 CN CN201511018634.0A patent/CN105653791A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101807254A (en) * | 2009-02-13 | 2010-08-18 | 烟台海岸带可持续发展研究所 | Implementation method for data characteristic-oriented synthetic kernel support vector machine |
| CN103870670A (en) * | 2012-12-17 | 2014-06-18 | 中国石油天然气集团公司 | Oil pipe corrosion degree forecasting method and device |
| CN103455682A (en) * | 2013-09-12 | 2013-12-18 | 西南石油大学 | Method for predicting residual life of corroded casing of high-temperature and high-pressure well |
| CN105069486A (en) * | 2015-09-09 | 2015-11-18 | 西安石油大学 | Extreme learning machine-based petrochemical equipment corrosion prediction method |
Non-Patent Citations (3)
| Title |
|---|
| 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 《中国优秀硕士学位论文全文数据库 工程科技Ⅰ辑》 * |
| 《科技创业月刊》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106442291A (en) * | 2016-09-30 | 2017-02-22 | 中国石油大学(华东) | Corrosion fatigue life prediction method based on BP neural network and application |
| CN106503176A (en) * | 2016-10-25 | 2017-03-15 | 英业达科技有限公司 | Solution hunting system and the operational approach of solution hunting system |
| CN106503177A (en) * | 2016-10-25 | 2017-03-15 | 英业达科技有限公司 | Solution hunting system and the operational approach of solution hunting system |
| CN106503176B (en) * | 2016-10-25 | 2019-12-24 | 英业达科技有限公司 | Solution searching system and operation method thereof |
| CN107063991A (en) * | 2017-04-14 | 2017-08-18 | 中国石油天然气股份有限公司 | A kind of conveyance conduit internal corrosion defect dynamic security assessment method and device |
| CN109977511A (en) * | 2019-03-18 | 2019-07-05 | 四川轻化工大学 | Method based on artificial intelligence big data prediction Pressurized Plastic Pipes long term life |
| CN111062625A (en) * | 2019-12-19 | 2020-04-24 | 中国特种设备检测研究院 | Method and device for establishing residual oil hydrogenation device failure prediction model |
| CN111190885A (en) * | 2019-12-19 | 2020-05-22 | 中国特种设备检测研究院 | Method and device for establishing oil refining device data management platform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105653791A (en) | Data mining based corrosion failure prediction system for on-service oil pipe column | |
| Zhang et al. | Towards a fuzzy Bayesian network based approach for safety risk analysis of tunnel‐induced pipeline damage | |
| Gao et al. | Digital twin and its application in transportation infrastructure | |
| CN111724126B (en) | Accurate tracing method and system for quality abnormality of process flow | |
| CN102520697B (en) | Onsite information preprocessing method of remote cooperative diagnosis | |
| CN101950382B (en) | Method for optimal maintenance decision-making of hydraulic equipment with risk control | |
| CN108877223A (en) | A kind of Short-time Traffic Flow Forecasting Methods based on temporal correlation | |
| CN106161138A (en) | A kind of intelligence automatic gauge method and device | |
| CN104156422A (en) | Gas concentration real-time prediction method based on dynamic neural network | |
| CN103577676A (en) | Grey weighting method for sewage treatment process comprehensive evaluation | |
| CN108615098B (en) | Bayesian survival analysis-based water supply network pipeline pipe burst risk prediction method | |
| CN109522962B (en) | Chemical plant safety quantitative evaluation method | |
| CN107862324A (en) | A kind of CBR forecast model intellectuality method for early warning based on MWSPCA | |
| CN109886506A (en) | A kind of water supply network booster risk analysis method | |
| Li et al. | Risk probability predictions for coal enterprise infrastructure projects in countries along the Belt and Road Initiative | |
| Xu et al. | A hybrid approach for dynamic simulation of safety risks in mega construction projects | |
| Mohsenijam et al. | Framework for developing labour-hour prediction models from project design features: case study in structural steel fabrication | |
| CN105678053A (en) | Method for predicting corrosion and invalidity of in-service tubing strings based on data mining | |
| Dawood et al. | Watermain's failure index modeling via Monte Carlo simulation and fuzzy inference system | |
| Wu et al. | Evaluating the economic and social benefits of multiutility tunnels with an agent-based simulation approach | |
| CN106844861B (en) | Orthotropic Steel Bridge Deck welding node measured stress width dynamic probability modeling method | |
| CN111852466B (en) | Method for shale gas well scale production allocation and pipe network operation optimization | |
| Li et al. | Domain knowledge in predictive maintenance for water pipe failures | |
| Pouri et al. | Spatial analysis and failure management in water distribution networks using fuzzy inference system | |
| CN109558615B (en) | Oil-gas exploration decision tree analysis method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160608 |