CN115481940A - Oil and gas pipeline area risk monitoring system based on big data - Google Patents
Oil and gas pipeline area risk monitoring system based on big data Download PDFInfo
- Publication number
- CN115481940A CN115481940A CN202211341263.XA CN202211341263A CN115481940A CN 115481940 A CN115481940 A CN 115481940A CN 202211341263 A CN202211341263 A CN 202211341263A CN 115481940 A CN115481940 A CN 115481940A
- Authority
- CN
- China
- Prior art keywords
- oil
- risk
- gas pipeline
- data
- pipeline
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 85
- 238000010276 construction Methods 0.000 claims abstract description 37
- 238000013528 artificial neural network Methods 0.000 claims abstract description 23
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 12
- 238000000034 method Methods 0.000 claims description 26
- 238000012502 risk assessment Methods 0.000 claims description 23
- 210000002569 neuron Anatomy 0.000 claims description 15
- 230000008569 process Effects 0.000 claims description 9
- 230000007613 environmental effect Effects 0.000 claims description 6
- 238000012423 maintenance Methods 0.000 claims description 6
- 238000009826 distribution Methods 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 abstract description 7
- 230000000694 effects Effects 0.000 abstract description 7
- 238000011156 evaluation Methods 0.000 abstract 1
- 239000007789 gas Substances 0.000 description 129
- 239000010410 layer Substances 0.000 description 21
- 238000010586 diagram Methods 0.000 description 8
- 230000008859 change Effects 0.000 description 5
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 239000000126 substance Substances 0.000 description 5
- 238000004590 computer program Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 239000003208 petroleum Substances 0.000 description 2
- 239000002356 single layer Substances 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005315 distribution function Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 239000003345 natural gas Substances 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- General Health & Medical Sciences (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Biophysics (AREA)
- Water Supply & Treatment (AREA)
- Educational Administration (AREA)
- Public Health (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Primary Health Care (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Pipeline Systems (AREA)
Abstract
The invention relates to the technical field of risk monitoring of oil and gas pipeline regions, and discloses an oil and gas pipeline region risk monitoring system based on big data. Acquiring risk monitoring data and construction data of the oil and gas pipeline, calculating a basic risk factor of the oil and gas pipeline, and performing basic risk evaluation; and judging whether the risk exists in the oil and gas pipeline or not by combining basic risk factors based on the operation data and the environment data of the oil and gas pipeline, constructing an oil and gas pipeline risk identification model, and identifying the risk type by adopting a deep neural network algorithm. The invention solves the problems that in the prior art, the problems of oil and gas pipelines in various regions cannot be accurately analyzed, the initial construction condition of the oil and gas pipelines is not considered, so that the analysis dimension is not comprehensive enough, and the risk identification accuracy and the monitoring effect need to be improved.
Description
Technical Field
The invention relates to the technical field of risk monitoring of oil and gas pipeline regions, in particular to an oil and gas pipeline region risk monitoring system based on big data.
Background
The long-distance pipeline for energy sources such as petroleum, natural gas and the like is the infrastructure for ensuring the development of China, so that the risk analysis of the oil and gas transportation pipeline in China is highly emphasized, and the risk is reduced to the minimum. The long-distance pipeline is mainly used for transporting and storing petroleum, and transporting energy sources in places where oil and gas are stored abundantly to the places where users are located, so that the requirements of industrial production, people's life and enterprise development are met. However, the long-distance oil and gas pipeline is affected by factors such as external environment, internal flowing substances and the like in the actual transportation process, so that a high risk coefficient exists, and once danger occurs, great harm is generated. In order to ensure the safety of oil and gas transportation, the risk monitoring of an oil and gas pipeline is forced to be enhanced, reasonable solution measures are made in combination with reality, and the probability of dangerous accidents is reduced.
However, in the prior art, in the risk monitoring process of the oil and gas pipeline, the oil and gas pipeline in each region cannot be accurately analyzed, so that the working strength, the environmental influence degree and the fault influence degree of the oil and gas pipeline cannot be accurately judged, and therefore, the matched management measures cannot be implemented when risk monitoring is performed on the corresponding region, the management measures lack pertinence, and the working efficiency of management is directly reduced.
Chinese patent application No.: CN202210365941, published: 2022.07.05, which discloses a large data-based risk monitoring system for a long oil and gas pipeline region, solves the technical problem that matched management measures cannot be implemented when risk monitoring is performed on the region in the prior art, and judges the influence caused by the occurrence of a conveying fault of each sub-region, so that judgment basis is provided for risk management and control, fault maintenance of each sub-region can be performed in a targeted manner, and reasonable fault emergency measures can be performed on the sub-region according to the fault influence, so that the excessive influence on the sub-region caused by improper emergency measures is prevented; the influence of the change of the external environment of the pipe section on the inside of the pipe section is judged, so that the risk possibility of the corresponding subarea is judged, the management strength and efficiency of the pipeline risk are improved, and the risk occurrence frequency in the oil-gas pipeline operation process is reduced; the accuracy of regional risk monitoring is improved, simultaneously can carry out oil gas pipeline's working strength to each region.
However, in the process of implementing the technical solution in the embodiment, it is found that the above-mentioned technology has at least the following problems: the problem that the oil gas pipeline in each region exists can not be accurately analyzed in the prior art, the initial construction condition of the oil gas pipeline is not considered, the analysis dimension is not comprehensive enough, and the risk identification accuracy and the monitoring effect are to be improved.
Disclosure of Invention
By providing the oil-gas pipeline regional risk monitoring system based on the big data, the problems that in the prior art, the problems of oil-gas pipelines in various regions cannot be accurately analyzed, the initial construction condition of the oil-gas pipelines is not considered, the analysis dimension is not comprehensive enough, the risk identification accuracy and the monitoring effect need to be improved are solved, the construction condition of the oil-gas pipelines is comprehensively considered, the regional risk monitoring accuracy is improved, the management intensity of the oil-gas pipeline risks is enhanced, the occurrence rate of high-risk risks is reduced, and the economic loss is avoided.
The invention specifically comprises the following technical scheme:
a big data based risk monitoring system for an oil and gas pipeline area comprises the following parts:
the system comprises a data acquisition module, a data application module, a basic risk assessment module, a range setting module, a risk judgment module, a risk identification module, an early warning module and a risk monitoring database;
the basic risk assessment module is used for performing basic risk assessment on the oil and gas pipeline according to building data of the oil and gas pipeline, acquiring the number of main pipe sections and branch pipe sections in a sub-region and the number of multi-crossing points at the connection part of the main pipe sections and the branch pipe sections, calculating a basic risk factor of the oil and gas pipeline of the current sub-region based on the geographical data of the geographical position of the sub-region and a construction acceptance report, representing the risk level of the oil and gas pipeline during initial construction through the basic risk factor, wherein different basic risk levels have different influences on the oil and gas pipeline in the using process; the basic risk assessment module is connected with the risk judgment module in a data connection mode;
the risk identification module is used for constructing an oil and gas pipeline risk identification model, inputting risk monitoring data into a deep neural network by adopting a deep neural network algorithm and outputting an identified risk type, and the risk identification module is connected with the early warning module and the risk monitoring database in a data connection mode;
the implementation method of the oil and gas pipeline region risk monitoring system based on big data comprises the following steps:
s1, acquiring risk monitoring data and construction data of an oil-gas pipeline, calculating a foundation risk factor of the oil-gas pipeline according to the construction data, and performing foundation risk assessment on the oil-gas pipeline;
and S2, judging whether the oil and gas pipeline has risks or not based on the operation data and the environment data of the oil and gas pipeline and combining with the basic risk factors, constructing an oil and gas pipeline risk identification model, and identifying the risk type by adopting a deep neural network algorithm.
Further, the step S1 specifically includes:
the method comprises the steps of carrying out basic risk assessment on an oil-gas pipeline according to building data of the oil-gas pipeline, wherein the oil-gas pipeline is formed by connecting a plurality of pipeline sections, each pipeline section comprises a main pipeline section and a branch pipeline section, the main pipeline section is a pipeline section on a main trunk pipeline of the oil-gas pipeline, and the branch pipeline section is a pipeline section on a branch trunk pipeline branched from the main trunk pipeline.
Further, the step S1 specifically includes:
the method comprises the steps of collecting the number of main pipe sections and branch pipe sections in a sub-region and the number of multi-intersection points at the connection part of the main pipe sections and the branch pipe sections, and calculating the basic risk factor of the oil and gas pipeline of the current sub-region based on the geographic data of the geographic position of the sub-region and a construction acceptance report.
Further, the step S2 specifically includes:
based on the operating data and the environmental data of the oil and gas pipeline, the risk of the oil and gas pipeline area is intelligently monitored by combining with basic risk factors.
Further, the step S2 specifically includes:
judging the current oil and gas pipeline operation data according to the numerical value threshold range and the numerical value variation range, and determining whether the current oil and gas pipeline operation data conforms to the two ranges; if the oil gas pipeline is in accordance with the preset condition, the oil gas pipeline is temporarily free of risk and continues to be monitored; otherwise, the risk type of the oil and gas pipeline needs to be confirmed, and maintenance personnel are informed to come for maintenance in time.
Further, the step S2 specifically includes:
and constructing an oil and gas pipeline risk identification model, acquiring historical risk monitoring data and corresponding risk types from an oil and gas pipeline risk monitoring database to form a data sample set, and inputting the data sample into a deep neural network for supervised learning by adopting a deep neural network algorithm until outputting the risk types according with preset precision.
Further, the step S2 specifically includes:
and optimizing the weight of the neuron in each hidden layer by the deep neural network algorithm according to the distribution of the neuron in the first hidden layer, the state of the hidden layer and the characteristic expression of the hidden layer.
The invention has at least the following technical effects or advantages:
1. multi-dimensional monitoring data are collected, and comprehensiveness of safety protection early warning is improved; the method comprises the steps of obtaining construction data of the oil-gas pipeline, evaluating basic risks of the pipeline based on the connection condition of the intersection and the quality of the pipe section pipe body, providing basis for regional risk monitoring, comprehensively considering the construction condition of the oil-gas pipeline, and improving the accuracy of regional risk monitoring.
2. Through the learning idea of the deep neural network, potential rules and values are searched from massive pipeline data, so that different types of risks are identified, the risk types of oil and gas pipelines in each region are identified according to risk monitoring data, the influence caused by risks in each region is determined, the accuracy of regional risk monitoring is improved, reasonable fault emergency measures can be performed on the risks in each region, the management strength and efficiency of the risks in the oil and gas pipelines are improved, the occurrence rate of high-risk risks is reduced, and economic loss is avoided.
3. The technical scheme of the invention can effectively solve the problems that the prior art can not accurately analyze the problems of the oil-gas pipelines in each area, the initial construction condition of the oil-gas pipelines is not considered, the analysis dimension is not comprehensive enough, the risk identification accuracy and the monitoring effect need to be improved, the construction condition of the oil-gas pipelines can be comprehensively considered, the accuracy of area risk monitoring is improved, the management strength of the oil-gas pipeline risks is enhanced, the occurrence rate of high-risk risks is reduced, and the economic loss is avoided.
Drawings
FIG. 1 is a block diagram of a big data based risk monitoring system for an oil and gas pipeline region according to the present invention;
FIG. 2 is a flow chart of a method for implementing a big data based risk monitoring system for an oil and gas pipeline region according to the present invention.
Detailed Description
The embodiment of the application provides an oil gas pipeline regional risk monitoring system based on big data, has solved prior art and can't carry out accurate analysis to the problem that the oil gas pipeline in each region exists, does not consider the oil gas pipeline initial construction condition, leads to the analysis dimension comprehensive inadequately, and risk identification correct rate and monitoring effect remain the problem that improves.
In order to solve the above problems, the technical solution in the embodiment of the present application has the following general idea:
multi-dimensional monitoring data are collected, and comprehensiveness of safety protection early warning is improved; acquiring oil and gas pipeline construction data, evaluating the basic risk of the pipeline based on the connection condition at the intersection and the quality of the pipe section pipe body, providing a basis for regional risk monitoring, comprehensively considering the construction condition of the oil and gas pipeline, and improving the accuracy of regional risk monitoring; through the learning idea of the deep neural network, potential rules and values are searched from massive pipeline data, so that different types of risks are identified, the risk types of oil and gas pipelines in each region are identified according to risk monitoring data, the influence caused by risks in each region is determined, the accuracy of regional risk monitoring is improved, reasonable fault emergency measures can be performed on the risks in each region, the management strength and efficiency of the risks in the oil and gas pipelines are improved, the occurrence rate of high-risk risks is reduced, and economic loss is avoided.
In order to better understand the technical scheme, the technical scheme is described in detail in the following with reference to the attached drawings of the specification and specific embodiments.
Referring to the attached figure 1, the oil and gas pipeline region risk monitoring system based on big data comprises the following parts:
the system comprises a data acquisition module 10, a data application module 20, a basic risk assessment module 30, a range setting module 40, a risk judgment module 50, a risk identification module 60, an early warning module 70 and a risk monitoring database 80.
The data acquisition module 10 is used for acquiring risk monitoring data of different types based on a multi-dimensional oil and gas pipeline monitoring mode, and the data acquisition module 10 is connected with the risk judgment module 50 and the risk monitoring database 80 in a data connection mode;
the data application module 20 is used for applying for obtaining construction data of oil and gas pipelines in the sub-area from related systems or departments, and the data application module 20 is connected with the basic risk assessment module 30 in a data connection mode;
the basic risk assessment module 30 is used for performing basic risk assessment on the oil and gas pipeline according to building data of the oil and gas pipeline, acquiring the number of main pipe sections and branch pipe sections in a sub-region and the number of multi-intersection points at the connection positions of the main pipe sections and the branch pipe sections, calculating basic risk factors of the oil and gas pipeline in the current sub-region based on geographic data of the geographical positions of the sub-region, construction acceptance reports and other data, representing the risk level of the oil and gas pipeline during initial construction through the basic risk factors, wherein different basic risk levels have different influences on the use process of the oil and gas pipeline; the basic risk assessment module 30 is connected with the risk judgment module 50 through a data connection mode;
the range setting module 40 is used for setting a numerical threshold range and a numerical variation range of each attribute in the pipeline operation data based on an expert experience method, and the range setting module 40 is connected with the risk judgment module 50 in a data connection mode;
the risk judgment module 50 is used for determining whether the current oil and gas pipeline operation data meet the two ranges according to the numerical threshold range and the numerical variation range; if the oil gas pipeline is in accordance with the preset condition, the oil gas pipeline is temporarily free of risk and continues to be monitored; otherwise, judging that the oil and gas pipeline has risks; the risk judgment module 50 is connected with the risk identification module 60 in a data connection manner;
the risk identification module 60 is used for constructing an oil and gas pipeline risk identification model, inputting risk monitoring data into a deep neural network by adopting a deep neural network algorithm and outputting identified risk types, and the risk identification module 60 is connected with the early warning module 70 and the risk monitoring database 80 in a data connection mode;
the early warning module 70 is used for displaying the positioning and risk types of the oil and gas pipelines with risks and sending out an alarm;
and a risk monitoring database 80 for storing the risk monitoring data and the corresponding risk types.
The implementation method of the oil and gas pipeline region risk monitoring system based on big data comprises the following steps:
s1, acquiring risk monitoring data and construction data of the oil and gas pipeline, calculating a foundation risk factor of the oil and gas pipeline according to the construction data, and performing foundation risk assessment on the oil and gas pipeline.
The method comprises the following steps of carrying out regional division on an oil and gas transmission pipeline, dividing the oil and gas transmission pipeline into N sub-regions, setting a multi-dimensional oil and gas pipeline monitoring mode in each sub-region, and acquiring risk monitoring data of different types by a data acquisition module 10; the multi-dimensional oil and gas pipeline monitoring mode includes but is not limited to: physical property type optical fiber sensors, grating pressure sensors, video monitoring and other modes; the risk monitoring data comprises oil and gas pipeline operation data and environmental data.
The data application module 20 acquires construction data of the oil and gas pipelines in the sub-area and carries out basic risk assessment on the oil and gas pipelines; and evaluating the operation risk of the oil and gas pipeline in real time based on the oil and gas pipeline operation data and the environment data. The basic data, i.e. the relevant data of the pipeline at the time of initial construction, may include: pipeline design data, geographic data, construction data, test data, and the like; the operation data mainly refers to dynamic data generated by the pipeline wall in the operation process of the oil and gas pipeline, and can comprise detection data, monitoring data and the like; the environmental data comprise vehicle stop conditions, personnel stop conditions, firework information, meteorological data and the like in the oil and gas pipeline sub-region.
The risk monitoring database 80 of the oil and gas pipeline is constructed according to the building data, the operation data and the environment data of the oil and gas pipeline, the risk monitoring database 80 covers main risk elements of the pipeline area, and risks can be intelligently predicted and identified.
Further, the basic risk assessment module 30 performs basic risk assessment on the oil and gas pipeline according to the building data of the oil and gas pipeline, the oil and gas pipeline is formed by connecting a plurality of pipe sections, each pipe section comprises a main pipe section and a branch pipe section, the main pipe section is a pipe section on a main trunk of the oil and gas pipeline, and the branch pipe section is a pipe section on a branch trunk which branches from the main trunk. And marking the joint between the pipe sections as an intersection point, and evaluating the basic risk of the pipeline based on the connection condition at the intersection point and the quality of the pipe body of the pipe section. The specific implementation manner of the basic risk assessment method is as follows:
the method comprises the following steps of collecting the number of main pipe sections and branch pipe sections in a sub-area and the number of multi-intersection points at the connection part of the main pipe sections and the branch pipe sections, and calculating the basic risk factor of the oil and gas pipeline of the current sub-area based on the geographic data of the geographical position of the sub-area, the construction acceptance report and other data, wherein the calculation formula is as follows:
wherein the content of the first and second substances,
which is indicative of the correction factor(s),
represents the risk factor of the oil and gas pipeline foundation,
which represents the number of main tube segments,
the number of branch pipe sections is indicated,
and
respectively is a preset ratio coefficient of a main pipe section and a branch pipe section,
the number of multiple intersection points is shown,
the ratio coefficient of the multiple cross points is shown,
the quality of construction acceptance is shown,
the percentage coefficient of construction acceptance quality is shown,
representing a geographic data impact factor. The risk level of the oil and gas pipeline during initial construction is represented through basic risk factors, and the oil and gas pipeline is used when the basic risk levels are differentThe resulting effect is also different.
The beneficial effects of the step S1 are as follows: multi-dimensional monitoring data are collected, and comprehensiveness of safety protection early warning is improved; the method has the advantages that the construction data of the oil and gas pipeline are obtained, the basic risk of the pipeline is evaluated based on the connection condition of the intersection and the quality of the pipe section pipe body, the basis is provided for regional risk monitoring, the construction condition of the oil and gas pipeline is comprehensively considered, and the accuracy of regional risk monitoring is improved.
And S2, judging whether the oil and gas pipeline has risks or not based on the operation data and the environment data of the oil and gas pipeline and combining with the basic risk factors, constructing an oil and gas pipeline risk identification model, and identifying the risk type by adopting a deep neural network algorithm.
Based on the operating data and the environmental data of the oil and gas pipeline, the risk of the oil and gas pipeline area is intelligently monitored by combining with basic risk factors. Aiming at the operation data of the oil and gas pipeline, the vibration, strain and integrity conditions of the inner wall and the outer wall of the pipeline are mainly considered, and whether leakage occurs or not is judged.
Further, the range setting module 40 sets a numerical threshold range and a numerical variation range of each attribute in the pipeline operation data based on an expert experience method. The numerical threshold range is used for representing a standard numerical interval of the pipeline operation data, and if the pipeline operation data are located in the numerical threshold range, no risk exists temporarily; otherwise, further analysis is needed to be carried out on the operation data of the pipeline, and the type of the risk existing in the oil and gas pipeline is confirmed. The numerical value change range is a standard range of data change of the oil and gas pipeline from construction to the present based on the oil and gas pipeline basic risk factors, and if the difference value of the pipeline data change exceeds the numerical value change range, the pipeline is indicated to have risks.
First, the risk judgment module 50 judges the current oil and gas pipeline operation data according to the numerical threshold range and the numerical variation range, and determines whether the current oil and gas pipeline operation data meets the two ranges. If the oil gas pipeline is in accordance with the preset condition, the oil gas pipeline is temporarily free of risk and continues to be monitored; otherwise, the risk type of the oil and gas pipeline needs to be confirmed, and maintenance personnel are informed to maintain in time. The method for identifying the risk type of the oil and gas pipeline comprises the following steps:
the risk identification module 60 constructs an oil and gas pipeline risk identification model, acquires historical risk monitoring data and corresponding risk types from the oil and gas pipeline risk monitoring database 80 to form a data sample set, and performs normalization processing on the data sample set. And inputting the processed data sample into the deep neural network for supervised learning by adopting a deep neural network algorithm until the output of a risk type which accords with preset precision. The specific process of the deep neural network for supervised learning is as follows:
first, single-layer neurons are constructed layer by layer, so that each time a single-layer network is trained. After all layers are trained, the training is carried out, and the data characteristics of each layer learned from the input are expressed as
The learned characteristics of each hidden layer neuron are expressed as
，
Indicating the second in the hidden layer
And (4) a neuron. The distribution of the first hidden layer neurons is represented as:
wherein the content of the first and second substances,
representing a first hidden layer
The distribution function of the individual neurons is,
is shown as
The deviation of the individual neurons is determined by the deviation,
is shown as
The weight of each of the individual neurons is,
，
representing the number of first hidden layer neurons. The distribution of the first hidden layer neurons is
。
Similarly, the neurons in each underlying hidden layer are distributed as if they were
Then the state of the layer is hidden
Expressed as:
the characteristics of the hidden layer are expressed as:
wherein the content of the first and second substances,
a feature expression representing the hidden layer,
representing inputThe sample data is then sampled at a time,
representing the hidden layer state under given conditions.
Optimizing the weights of the neurons in each hidden layer:
wherein the content of the first and second substances,
the weight after the optimization is represented by the weight,
an optimization factor is represented. By adjusting the weight, the generated topmost hidden layer can restore the bottom nodes at the maximum accuracy rate, so that the learning of the deep neural network is completed. And inputting the current risk monitoring data into the risk identification model of the oil and gas pipeline, and automatically outputting the identified risk types. The early warning module 70 displays the location and risk type of the oil and gas pipeline with risk and gives an alarm to inform maintenance personnel to maintain as soon as possible.
The beneficial effects of the step S2 are as follows: through the learning idea of the deep neural network, potential rules and values are searched from massive pipeline data, so that different types of risks are identified, the risk types of oil and gas pipelines in each region are identified according to risk monitoring data, the influence caused by risks in each region is determined, the accuracy of regional risk monitoring is improved, reasonable fault emergency measures can be performed on the risks in each region, the management strength and efficiency of the risks in the oil and gas pipelines are improved, the occurrence rate of high-risk risks is reduced, and economic loss is avoided.
In conclusion, the oil and gas pipeline region risk monitoring system based on the big data is completed.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (7)
1. A big data based risk monitoring system for an oil and gas pipeline area is characterized by comprising the following parts:
the system comprises a data acquisition module, a data application module, a basic risk assessment module, a range setting module, a risk judgment module, a risk identification module, an early warning module and a risk monitoring database;
the basic risk assessment module is used for performing basic risk assessment on the oil and gas pipeline according to building data of the oil and gas pipeline, acquiring the number of main pipe sections and branch pipe sections in a subregion and the number of multi-intersection points at the joint of the main pipe sections and the branch pipe sections, calculating a basic risk factor of the oil and gas pipeline of the current subregion based on geographic data of the geographic position of the subregion and a construction acceptance report, representing the risk level of the oil and gas pipeline during initial construction through the basic risk factor, wherein different basic risk levels have different influences on the use process of the oil and gas pipeline; the basic risk assessment module is connected with the risk judgment module in a data connection mode;
the risk identification module is used for constructing an oil and gas pipeline risk identification model, inputting risk monitoring data into a deep neural network by adopting a deep neural network algorithm and outputting identified risk types, and is connected with the early warning module and the risk monitoring database in a data connection mode;
the implementation method of the oil and gas pipeline region risk monitoring system based on big data comprises the following steps:
s1, acquiring risk monitoring data and construction data of an oil and gas pipeline, calculating a basic risk factor of the oil and gas pipeline according to the construction data, and performing basic risk assessment on the oil and gas pipeline;
and S2, judging whether the risk exists in the oil and gas pipeline based on the operation data and the environment data of the oil and gas pipeline and combining with the basic risk factor, constructing an oil and gas pipeline risk identification model, and identifying the risk type by adopting a deep neural network algorithm.
2. The big-data-based risk monitoring system for the oil and gas pipeline area according to claim 1, wherein the step S1 specifically comprises:
the method comprises the steps of carrying out basic risk assessment on an oil-gas pipeline according to building data of the oil-gas pipeline, wherein the oil-gas pipeline is formed by connecting a plurality of pipeline sections, each pipeline section comprises a main pipeline section and a branch pipeline section, the main pipeline section is a pipeline section on a main trunk pipeline of the oil-gas pipeline, and the branch pipeline section is a pipeline section on a branch trunk pipeline branched from the main trunk pipeline.
3. The big-data-based risk monitoring system for the oil and gas pipeline area according to claim 1, wherein the step S1 specifically comprises:
the method comprises the steps of collecting the number of main pipe sections and branch pipe sections in a sub-region and the number of multi-intersection points at the connection part of the main pipe sections and the branch pipe sections, and calculating the basic risk factor of the oil and gas pipeline of the current sub-region based on the geographic data of the geographic position of the sub-region and a construction acceptance report.
4. The big-data-based risk monitoring system for the oil and gas pipeline region as claimed in claim 1, wherein the step S2 specifically comprises:
based on the operating data and the environmental data of the oil and gas pipeline, the risk of the oil and gas pipeline area is intelligently monitored by combining with basic risk factors.
5. The big-data-based risk monitoring system for the oil and gas pipeline region as claimed in claim 1, wherein the step S2 specifically comprises:
judging the current oil and gas pipeline operation data according to the numerical value threshold range and the numerical value variation range, and confirming whether the current oil and gas pipeline operation data meet the two ranges; if the oil gas pipeline is in accordance with the preset condition, the oil gas pipeline is not in risk temporarily, and monitoring is continued; otherwise, the risk type of the oil and gas pipeline needs to be confirmed, and maintenance personnel are informed to maintain in time.
6. The big-data-based risk monitoring system for the oil and gas pipeline region as claimed in claim 1, wherein the step S2 specifically comprises:
and constructing an oil and gas pipeline risk identification model, acquiring historical risk monitoring data and corresponding risk types from an oil and gas pipeline risk monitoring database to form a data sample set, and inputting the data sample into a deep neural network for supervised learning by adopting a deep neural network algorithm until outputting the risk types according with preset precision.
7. The big-data-based risk monitoring system for oil and gas pipeline regions according to claim 1, wherein the step S2 specifically comprises:
and optimizing the weight of the neuron in each hidden layer by the deep neural network algorithm according to the distribution of the neuron in the first hidden layer, the state of the hidden layer and the characteristic expression of the hidden layer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211341263.XA CN115481940A (en) | 2022-10-31 | 2022-10-31 | Oil and gas pipeline area risk monitoring system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211341263.XA CN115481940A (en) | 2022-10-31 | 2022-10-31 | Oil and gas pipeline area risk monitoring system based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115481940A true CN115481940A (en) | 2022-12-16 |
Family
ID=84395942
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211341263.XA Pending CN115481940A (en) | 2022-10-31 | 2022-10-31 | Oil and gas pipeline area risk monitoring system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115481940A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116295442A (en) * | 2023-05-11 | 2023-06-23 | 国网浙江宁波市鄞州区供电有限公司 | Anti-drop control method, device and equipment for pipeline operation equipment and storage medium |
| CN116558574A (en) * | 2023-06-29 | 2023-08-08 | 深圳市秒加能源科技有限公司 | Big data-based gas station safety monitoring method and device |
| CN117875721A (en) * | 2024-03-12 | 2024-04-12 | 山东港源管道物流有限公司 | System and method for managing engineering construction progress of oil depot |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109978374A (en) * | 2019-03-27 | 2019-07-05 | 中国环境科学研究院 | Oil-gas pipeline system risk appraisal procedure |
| US20200041305A1 (en) * | 2018-08-03 | 2020-02-06 | Environmental Protection Administration. R.O.C. | Method for sorting unsystematic environment risk of underground storage tank systems |
| CN113128803A (en) * | 2019-12-30 | 2021-07-16 | 中国石油天然气股份有限公司 | Oil and gas pipeline risk determination method and device and computer equipment |
| CN113705609A (en) * | 2021-07-26 | 2021-11-26 | 天津中油能源科技股份有限公司 | Method and device for constructing risk judgment model of oil and gas pipeline |
| CN114707862A (en) * | 2022-04-08 | 2022-07-05 | 淮阴师范学院 | Long oil and gas pipeline area risk supervision system based on big data |
-
2022
- 2022-10-31 CN CN202211341263.XA patent/CN115481940A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200041305A1 (en) * | 2018-08-03 | 2020-02-06 | Environmental Protection Administration. R.O.C. | Method for sorting unsystematic environment risk of underground storage tank systems |
| CN109978374A (en) * | 2019-03-27 | 2019-07-05 | 中国环境科学研究院 | Oil-gas pipeline system risk appraisal procedure |
| CN113128803A (en) * | 2019-12-30 | 2021-07-16 | 中国石油天然气股份有限公司 | Oil and gas pipeline risk determination method and device and computer equipment |
| CN113705609A (en) * | 2021-07-26 | 2021-11-26 | 天津中油能源科技股份有限公司 | Method and device for constructing risk judgment model of oil and gas pipeline |
| CN114707862A (en) * | 2022-04-08 | 2022-07-05 | 淮阴师范学院 | Long oil and gas pipeline area risk supervision system based on big data |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116295442A (en) * | 2023-05-11 | 2023-06-23 | 国网浙江宁波市鄞州区供电有限公司 | Anti-drop control method, device and equipment for pipeline operation equipment and storage medium |
| CN116295442B (en) * | 2023-05-11 | 2023-10-13 | 国网浙江宁波市鄞州区供电有限公司 | Anti-drop control method, device and equipment for pipeline operation equipment and storage medium |
| CN116558574A (en) * | 2023-06-29 | 2023-08-08 | 深圳市秒加能源科技有限公司 | Big data-based gas station safety monitoring method and device |
| CN116558574B (en) * | 2023-06-29 | 2023-09-26 | 深圳市秒加能源科技有限公司 | Big data-based gas station safety monitoring method and device |
| CN117875721A (en) * | 2024-03-12 | 2024-04-12 | 山东港源管道物流有限公司 | System and method for managing engineering construction progress of oil depot |
| CN117875721B (en) * | 2024-03-12 | 2024-06-07 | 山东港源管道物流有限公司 | System and method for managing engineering construction progress of oil depot |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115481940A (en) | Oil and gas pipeline area risk monitoring system based on big data | |
| US20220205956A1 (en) | Detection of structural anomalies in a pipeline network | |
| CN114626615B (en) | Production process monitoring and management method and system | |
| US20230221207A1 (en) | Methods and internet of things systems for determining gas leakages based on smart gas | |
| CN116503975B (en) | Intelligent gas GIS-based potential safety hazard disposal method and Internet of things system | |
| CN104456092A (en) | Multidimensional assessment method of petroleum and natural gas pipeline warning priority | |
| CN115270527B (en) | Real-time assessment method, equipment and storage medium for road collapse risk | |
| CN116006908A (en) | Intelligent gas pipe network reliability monitoring method and Internet of things system | |
| KR20110086530A (en) | Management system for water distribution network employing bayes technology | |
| CN113705609A (en) | Method and device for constructing risk judgment model of oil and gas pipeline | |
| CN116739352B (en) | Gas pipeline safety evaluation early warning system, method and storage medium | |
| CN117570381A (en) | Pipe network leakage early warning method based on online prediction and data fusion | |
| CN115063337A (en) | Intelligent maintenance decision-making method and device for buried pipeline | |
| CN113128803B (en) | Oil and gas pipeline risk determination method and device and computer equipment | |
| CN117128459A (en) | Urban water supply network pipe explosion prediction method and system based on real-time monitoring data | |
| CN114445041B (en) | Method and system for emergency treatment of in-transit accidents of hazardous chemical substances | |
| CN115906663A (en) | Building safety evaluation model establishing method, evaluation method, server and system | |
| CN114519248B (en) | Method and system for processing leakage behavior of natural gas long-distance pipeline based on digital twin | |
| CN114510994A (en) | Training method and device for urban underground gas leakage recognition model | |
| KR20110086528A (en) | Management system for water distribution network employing electre technology | |
| CN116906837B (en) | State monitoring system and monitoring method for underground pipeline | |
| KR20030067305A (en) | Method of risk assessment for buried gas pipelines | |
| KR102615082B1 (en) | A monitoring system using a buried complex IoT sensor device for reservoir and embankment management, and its execution method | |
| CN116451885B (en) | Water supply network health degree prediction method and device and computing equipment | |
| CN117314705B (en) | Environment comprehensive evaluation prediction method based on remote sensing image |
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: 20221216 |