CN116384732A - Intelligent assessment method, system, storage medium and computing device for station pipeline risk - Google Patents
Intelligent assessment method, system, storage medium and computing device for station pipeline risk Download PDFInfo
- Publication number
- CN116384732A CN116384732A CN202310203577.1A CN202310203577A CN116384732A CN 116384732 A CN116384732 A CN 116384732A CN 202310203577 A CN202310203577 A CN 202310203577A CN 116384732 A CN116384732 A CN 116384732A
- Authority
- CN
- China
- Prior art keywords
- station pipeline
- failure
- risk
- area
- station
- 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
- 238000000034 method Methods 0.000 title claims abstract description 69
- 238000003860 storage Methods 0.000 title claims abstract description 12
- 238000012549 training Methods 0.000 claims abstract description 37
- 238000012706 support-vector machine Methods 0.000 claims abstract description 27
- 238000004364 calculation method Methods 0.000 claims abstract description 17
- 230000008569 process Effects 0.000 claims abstract description 15
- 238000005457 optimization Methods 0.000 claims abstract description 13
- 238000013210 evaluation model Methods 0.000 claims abstract description 12
- 238000012502 risk assessment Methods 0.000 claims description 35
- 230000006378 damage Effects 0.000 claims description 29
- 238000011156 evaluation Methods 0.000 claims description 16
- 238000001514 detection method Methods 0.000 claims description 15
- 208000027418 Wounds and injury Diseases 0.000 claims description 14
- 208000014674 injury Diseases 0.000 claims description 14
- 238000012360 testing method Methods 0.000 claims description 13
- 238000004458 analytical method Methods 0.000 claims description 7
- 238000012937 correction Methods 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 7
- 230000009467 reduction Effects 0.000 claims description 7
- 229910018503 SF6 Inorganic materials 0.000 claims description 6
- 238000002955 isolation Methods 0.000 claims description 6
- SFZCNBIFKDRMGX-UHFFFAOYSA-N sulfur hexafluoride Chemical compound FS(F)(F)(F)(F)F SFZCNBIFKDRMGX-UHFFFAOYSA-N 0.000 claims description 6
- 229960000909 sulfur hexafluoride Drugs 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 4
- 238000010801 machine learning Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 claims description 3
- 238000010561 standard procedure Methods 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 2
- 230000007613 environmental effect Effects 0.000 claims description 2
- 230000000704 physical effect Effects 0.000 claims description 2
- 208000033999 Device damage Diseases 0.000 claims 1
- 238000003745 diagnosis Methods 0.000 description 8
- 238000010219 correlation analysis Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 239000010779 crude oil Substances 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 239000000203 mixture Substances 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 239000003208 petroleum Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009835 boiling Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000005336 cracking Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 239000006247 magnetic powder Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000013077 scoring method Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000011179 visual inspection 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
- 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
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a station pipeline risk intelligent assessment method, a system, a storage medium and a computing device, wherein the method comprises the following steps: collecting operation data of a station pipeline and determining a station pipeline risk level; identifying key influence parameters in the field station pipeline risk level influence parameters; forming a sample set according to the key influence parameters and the corresponding station pipeline risk levels, and establishing a related database of the key influence factors, the failure possibility and the failure results of the station pipeline by using a training sample through a support vector machine, wherein the related database is used for model training and optimization of a station pipeline risk intelligent assessment model; based on the detected station pipeline operation parameters, predicting the failure possibility and failure result of the station pipeline through the station pipeline risk intelligent evaluation model, so as to determine the risk level of the detected station pipeline. The invention can directly obtain two indexes of failure possibility and failure result, only needs a small amount of parameters in the calculation process, and has simple calculation flow and convenient engineering practice application.
Description
Technical Field
The invention relates to the technical field of risk assessment, in particular to a station pipeline risk intelligent assessment method, a system, a storage medium and computing equipment.
Background
Along with the development of national economy, the demand for crude oil transportation of pipelines is continuously increased, meanwhile, the safety of the society on petroleum transportation pipelines is particularly concerned, and the safety of the petroleum transportation pipelines is ensured to have important roles in the development of the crude oil storage and transportation industry and the stability of the society. The station pipeline is a transfer station for crude oil transportation, and has complex structure, harsh working conditions and critical safety guarantee.
The risk analysis and evaluation are important components of risk engineering, are used for qualitatively or quantitatively evaluating the possibility of failure of a specific dangerous source, the severity of possible consequences, the range of harm and the like, and are widely applied to petrochemical industry.
The traditional risk analysis method has the defects of numerous considered parameters, complex calculation flow and difficulty in engineering practice application, so that the risk analysis method based on intelligent learning is to be developed in combination with the requirements of field station pipeline engineering practice.
Disclosure of Invention
Aiming at the problems existing in the prior art, the invention provides a station pipeline risk intelligent assessment method, a system, a storage medium and computing equipment.
In order to solve the above technical problems, an embodiment of the present invention provides an intelligent assessment method for risk of a station pipeline, including: collecting operation data of a station pipeline, and determining the risk level of the station pipeline according to the operation data; identifying key influence parameters in the risk level influence parameters of the station pipeline by adopting a gray correlation method; forming a sample set according to the key influence parameters and the corresponding station pipeline risk levels, and establishing a related database of the key influence factors, the failure possibility and the failure results of the station pipeline through support vector machine learning, wherein the related database is used for model training of a station pipeline risk intelligent evaluation model; performing model optimization on the intelligent station pipeline risk assessment model by using a test sample; based on the detected station pipeline operation parameters, predicting the failure possibility and failure result of the station pipeline through the station pipeline risk intelligent evaluation model, so as to determine the risk level of the detected station pipeline.
In order to solve the technical problem, the invention also provides an intelligent field station pipeline risk assessment system, which comprises: the system comprises a data acquisition module, a key influence parameter identification module, a model training module, a model optimization module and a risk assessment module;
the data acquisition module is used for acquiring the operation data of the station pipeline and determining the risk level of the station pipeline according to the operation data; the key influence parameter identification module is used for identifying key influence parameters in the field station pipeline risk level influence parameters by adopting a gray correlation method; the model training and optimizing module is used for forming a sample set according to the key influence parameters and the corresponding station pipeline risk levels, establishing a related database of the failure possibility and failure results of the key influence factors and the station pipeline through support vector machine learning, and used for model training of the station pipeline risk intelligent evaluation model; performing model optimization on the intelligent station pipeline risk assessment model by using a test sample; the risk assessment module is used for predicting failure possibility and failure result of the station pipeline through the station pipeline risk intelligent assessment model based on the detected station pipeline operation parameters, so that the risk level of the detected station pipeline is determined.
In order to solve the technical problem, the invention also provides a computer readable storage medium, which comprises instructions, when the instructions run on a computer, the computer is caused to execute the intelligent assessment method for the risk of the station pipeline provided by the technical scheme.
In order to solve the technical problems, the invention also provides a computing device which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the intelligent assessment method for the station pipeline risk provided by the technical scheme is realized when the processor executes the program.
The beneficial effects of the invention are as follows: the method comprises the steps of determining key influence parameters in the station pipeline risk assessment influence parameters through a gray association degree method, forming a sample set according to the key influence parameters and corresponding station pipeline risk grades, establishing an association database of the key influence factors, the failure probability of the station pipeline and failure results through support vector machine learning by using training samples, training and optimizing a model of a station pipeline risk intelligent assessment model, directly evaluating and obtaining two indexes of the failure probability and the failure results of the station pipeline through the station pipeline risk intelligent diagnosis model, wherein the failure probability is used for determining the occurrence probability of a failure event, the failure results are used for measuring the severity and the loss size of the result after the failure event occurs, only a small amount of parameters are needed in the calculation process, and the calculation flow is simple and engineering practice application is facilitated.
Additional aspects of the invention and advantages thereof will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
Fig. 1 is a flowchart of a station pipeline risk intelligent assessment method according to an embodiment of the present invention.
FIG. 2 is a block diagram of a failure probability calculation according to an embodiment of the present invention;
FIG. 3 is a flowchart of failure outcome calculation provided by an embodiment of the present invention;
fig. 4 is a Matlab operation flow of the support vector machine provided by the embodiment of the invention.
Detailed Description
Other advantages and effects of the present disclosure will become readily apparent to those skilled in the art from the following disclosure, which describes embodiments of the present disclosure by way of specific examples. It will be apparent that the described embodiments are only some, but not all, of the embodiments of the present disclosure. The disclosure may be embodied or practiced in other different specific embodiments, and details within the subject specification may be modified or changed from various points of view and applications without departing from the spirit of the disclosure. It should be noted that the following embodiments and features in the embodiments may be combined with each other without conflict. All other embodiments, which can be made by one of ordinary skill in the art without inventive effort, based on the embodiments in this disclosure are intended to be within the scope of this disclosure.
It is noted that various aspects of the embodiments are described below within the scope of the following claims. It should be apparent that the aspects described herein may be embodied in a wide variety of forms and that any specific structure and/or function described herein is merely illustrative. Based on the present disclosure, one skilled in the art will appreciate that one aspect described herein may be implemented independently of any other aspect, and that two or more of these aspects may be combined in various ways. For example, an apparatus may be implemented and/or a method practiced using any number of the aspects set forth herein. In addition, such apparatus may be implemented and/or such methods practiced using other structure and/or functionality in addition to one or more of the aspects set forth herein.
As shown in fig. 1, the intelligent assessment method for risk of a station pipeline provided by an embodiment of the invention includes the following steps:
and step 1, collecting operation data of the station pipeline, and determining the risk level of the station pipeline according to the operation data.
Through station pipeline detection, operation data of the station pipeline are collected, station pipeline operation ledgers are established, station pipeline risk grades are calculated, and training samples and test samples for intelligent analysis of the station pipeline are divided. Specifically, the diameter and length dimensions of the station pipeline, the physical parameters and flow of the medium in the pipeline, the complex structure state information, the construction specification condition, the operation period, the operation condition, the process continuity and stability condition, the safety valve state and the like are obtained through the collection of the station pipeline design parameters and the operation parameter data. And obtaining the damage state of the station pipeline and the residual wall thickness by adopting a station pipeline nondestructive detection method such as wall thickness ultrasonic detection, magnetic powder nondestructive detection and the like. The method comprises the steps of obtaining station conditions, climate cold states and earthquake activity states of a pipeline through investigation of the running environment of the station pipeline; and evaluating the enterprise management system through questionnaires of site management personnel.
In the embodiment of the invention, the failure possibility and the failure area of the station pipeline are respectively calculated by using the operation data of the station pipeline, and the risk level is determined according to the failure possibility and the failure area.
And 2, identifying key influence parameters in the risk level influence parameters of the station pipeline by adopting a gray correlation method.
The station pipeline risk assessment relates to a plurality of influence parameters, and the influence degree of each parameter on the station pipeline failure possibility and the failure result is required to be judged to determine key influence parameters to be considered in the station pipeline risk intelligent assessment method. The gray correlation analysis can obtain the correlation degree of each influence parameter, the failure possibility and the failure result of the station pipeline, the parameter with large correlation degree can be called as a key parameter to be considered in risk assessment, and the parameter with small correlation can be called as a non-key parameter to be ignored in risk assessment, so that the risk assessment flow is simplified, and the accuracy of the assessment result is not affected.
In the embodiment, gray correlation degree analysis is performed on station pipeline risk influence factors of a single station, and invariant in the single station is ignored, so that key influence factors of station pipeline failure possibility can be obtained, wherein the key influence factors are as follows: planned parking factors, detection periods, management system evaluation probabilities, unplanned parking factors, remaining life, service life, operating pressure, design pressure, measured wall thickness, raw wall thickness, pipe length; key influencing factors of the failure result of the station pipeline are as follows: operating pressure. It should be noted that the different station key influencing factors are different and need to be analyzed separately.
And 3, forming a sample set according to the key influence parameters and the corresponding station pipeline risk level, and establishing a related database of the failure possibility and the failure result of the key influence factors and the station pipeline through support vector machine learning for model training of the station pipeline risk intelligent assessment model.
The probability of failure is used to determine the probability of failure event occurrence, and the consequences of failure are used to measure the severity and loss magnitude of the consequences of failure event occurrence.
The support vector machine is a machine learning algorithm, i.e. the class of training points is known, and the corresponding relation between training points and classes is calculated so as to separate training sets according to the classes or predict the class corresponding to new training points. The theoretical basis of the support vector machine is statistical learning theory, and is an approximate implementation of structural risk minimization. The error rate of the learning machine on the test data is bounded by the sum of the training error rate and a term dependent on the VC dimension, the value of the support vector machine for the previous term is zero in separable mode, and the second term is minimized.
By considering key influence parameters of the station pipeline risk, a support vector machine learning method is adopted to obtain the relation between the key parameters and the station pipeline failure possibility and failure results, so that intelligent diagnosis of the station pipeline failure possibility and failure results is realized. The Matlab programming is used for calling the calculation of the support vector machine, and fig. 4 is a Matlab operation flow of the support vector machine. And selecting the data in the detection process as a training set to carry out learning training of the support vector machine.
And 4, performing model optimization on the intelligent field station pipeline risk assessment model by using a sample.
Specifically, the test sample is used for verifying the intelligent diagnosis program of the station pipeline, if the prediction accuracy requirement is not met, the training sample is added, the machine learning of the support vector machine is continued, and if the prediction accuracy requirement is met, the intelligent prediction method can be used for intelligent prediction of the station pipeline risk.
And 5, based on the detected station pipeline operation parameters, predicting failure possibility and failure results of the station pipeline through the station pipeline risk intelligent evaluation model, so as to determine the risk level of the detected station pipeline.
Inputting station pipeline data required to be subjected to risk analysis by a station into an intelligent prediction program of the station pipeline risk failure possibility by means of Matlab software, so as to realize intelligent diagnosis of the station pipeline failure possibility; inputting station pipeline data required to be subjected to risk analysis by a station into an intelligent prediction program of the station pipeline risk failure result by means of Matlab software, so as to realize intelligent diagnosis of the station pipeline failure result; the detected risk level of the station pipe is determined based on the predicted failure probability and the resultant area of the station pipe by the support vector machine program.
According to the embodiment of the invention, the unique application scene of the station pipeline is fully researched, the unique key influence factors are extracted, and the failure possibility and failure result prediction model which meet the actual application scene of the station pipeline are established. And through the station pipeline failure possibility and the result area prediction model, the station pipeline risk intelligent assessment model in the station pipeline application scene is further developed by combining the special acceptable risk level determined by the station pipeline use unit because of the application scene. By combining the past inspection and evaluation data and the results of analysis and evaluation of the intelligent station pipeline risk evaluation model in the application scene of the station pipeline, the embodiment of the invention establishes a special risk database for the station pipeline, reserves a data exchange port and lays a foundation for subsequent research and development. The embodiment of the invention provides an algorithm of a station pipeline risk intelligent assessment model based on a station pipeline special risk database and a station pipeline risk intelligent assessment model, and the algorithm further optimizes the effectiveness of database data and the simulation of an analysis model.
The embodiment of the invention determines key influence parameters in the risk assessment influence parameters of the station pipeline by a gray correlation method; according to the key influence parameters and the corresponding station pipeline risk levels, a sample set is formed, a related database of failure possibility and failure results of the key influence factors and the station pipeline is established through support vector machine learning, the model training and optimization of the station pipeline risk intelligent assessment model are used, the station pipeline risk intelligent diagnosis model can be used for directly assessing and obtaining two indexes of the failure possibility and the failure results of the station pipeline, only a small amount of parameters are needed in the calculation process, the calculation flow is simple, and engineering practice application is facilitated.
Optionally, determining the station pipeline risk level according to the operation data includes:
and step 11, determining the average failure possibility of the station pipeline, the station pipeline correction coefficient and the management system evaluation coefficient according to the operation data.
Specifically, by establishing running ledger information of the station pipeline, average failure probability FG of the station pipeline, station pipeline correction coefficient FE (comprising thinning factors, stress corrosion cracking factors, general condition factors, mechanical factors and process factors), management system evaluation coefficient FM and superscale defect influence coefficient are obtained.
And step 12, determining the failure possibility of the station pipeline according to the average failure possibility of the station pipeline, the station pipeline correction coefficient and the management system evaluation coefficient.
The failure probability of the station pipe is calculated according to the failure probability calculation block diagram of fig. 2. The failure probability calculation formula is:
F＝F G F E F M (1)
F E ＝DF+SF 1 +SF 2 +SF 3 (2)
wherein DF is the injury cofactor; SF (sulfur hexafluoride) 1 Taking the factors of factory conditions, climate conditions and earthquake activities into account as general secondary factors; SF (sulfur hexafluoride) 2 Taking the equipment complexity coefficient, the standard condition coefficient, the life cycle coefficient and the safety condition coefficient into consideration as mechanical secondary factors; SF (sulfur hexafluoride) 3 As process cofactors, process continuity coefficients, process stability coefficients and safety protection device condition coefficients are considered.
F G The average failure probability of the station pipelines refers to the average failure probability of the same type of pipelines, and is mainly confirmed through failure conditions of the same type of pipelines at home and abroad and expert scoring methods in related fields.
F M Is an evaluation of the management level of the station pipeline usage unit, and is a determination coefficient of objective existence of scores of a plurality of problems in a plurality of aspects. The embodiment of the invention can select 14 aspects, such as safety production responsibility system, operation rules, emergency measures, subcontracting management and the like100 problems, such as whether to establish a safety production responsibility system, whether the operation procedure is scientific and reasonable, whether the emergency measures are targeted and effective, whether the subcontractor makes qualified supplier evaluation, and the like.
The factors are algebraic sums of all assignments obtained by carrying out expert assignment on all damage factors (including damage factors, general factors, mechanical factors and process factors) and combining different influence degrees.
And step 13, determining the area result and the economic result caused by the failure event according to the operation data, and determining the failure result of the station pipeline according to the area result and the economic result.
FIG. 3 is a flow chart of the result of calculating station pipe failure. The detailed implementation flow of calculating the failure result of the station pipeline is as follows:
1. selecting leakage representative media and physical parameters thereof: for single-component media, a representative medium closest to the actual medium in the pressure-bearing equipment system to be evaluated can be selected from table 2 in GB/T26610.5; for multicomponent mixture media, the relative physical properties of the representative media corresponding to the mixture media should be determined according to the molar Mass (MW), density, normal Boiling Point (NBP), and auto-ignition temperature of the various media in the mixture.
2. Selecting a leakage diameter: for each leakage hole, its leakage area An is calculated as follows:
where d represents the leakage hole diameter.
3. Calculating a theoretical leak rate: for each leakage hole, the theoretical leakage rate Wn of the medium is calculated as follows:
wherein C is d Represents the leakage coefficient, the leakage coefficient of turbulent medium through the sharp edge holes is [0.60,0.65 ]]A conservative value of 0.61 is recommended, ρ representing the medium density.
4. Evaluation of the influence of the detection and isolation system on the leakage quantity:
1) The detection system can be divided into three stages:
first-order: a detection system for detecting loss of medium based on changes in operating conditions.
And (2) second-stage: and a detection system capable of directly detecting the medium leakage.
Three stages: visual inspection, photography, or detection systems with limited detection range.
2) The isolation system can be divided into three stages:
first-order: directly by the process meter or detector without the need for an isolation or shut-off system for operator intervention.
And (2) second-stage: isolation or shut-off systems activated by operators in the control room or other remote from the leak.
Three stages: an isolation system relying on manual valves.
5. Determining an actual leak rate:
the actual leak rate is calculated by the formula:
r n ＝W n (1-f)
where f represents the leak rate reduction coefficient, and the detailed values are shown in the following table:
6. calculating area and economic consequences:
6.1, taking larger values in the equipment damage result area and the personnel injury result area according to a formula:
CA＝max(CA c ，CA i )
in the formula, CA c Indicating the consequences of the area of destruction of the apparatus, CA i Indicating the consequences of personnel injury.
Wherein, the area of the equipment damage result is calculated according to the formula:
CA c ＝ar n b (1-f)；
wherein a and b are constants, and the value of table 13 is taken according to GB/T26610.5;
wherein, personnel injury result area calculates according to the formula:
wherein c and d are constants and are valued according to Table 14 in GB/T26610.5;
6.2, the economic result is the sum of five economic costs, and the sum is calculated according to the formula:
FC＝FC c +FC a +FC p +FC i +FC e ；
in FC, FC c Indicating equipment maintenance or replacement costs, FC a Representing the cost of destruction of other devices in the device failure impact area, FC p Indicating media leakage and downtime due to equipment servicing or replacement, FC i Indicating personnel injury costs due to equipment failure, FC e Representing an environmental cleaning cost;
6.3, total failure result, according to the formula:
C z ＝CA+FC。
and step 14, determining the risk level of the station pipeline based on the risk level matrix according to the failure possibility and the failure result of the station pipeline.
Specifically, the risk level matrix divides the failure possibility into M levels according to the magnitude of the numerical value, divides the failure result into N levels according to the severity, and combines the failure possibility and the failure result to obtain M rows and N columns of matrixes; wherein M and N are constants. In the embodiment of the invention, the failure possibility is divided into 5 stages according to the magnitude of the numerical value, and is represented by 1, 2, 3, 4 and 5, wherein 1 represents the minimum failure possibility and 5 represents the maximum failure possibility. The consequences of the failure are also classified into 5 classes according to severity, A, B, C, D, E respectively, where a indicates that the consequences of the failure are least severe and E indicates that the consequences of the failure are most severe. And combining the failure result with 5 grades of failure possibility to obtain 5 rows and 5 columns of risk matrixes.
The embodiment of the invention determines the failure possibility and the failure result of the station pipeline, and can evaluate the risk level of the station pipeline according to the risk matrix diagram, wherein the risk level gradually rises along the diagonal line from the lower left to the upper right and is divided into 4 levels which are sequentially as follows: low risk, medium high risk and high risk. And combining failure possibility and failure result of the station pipeline, and determining the risk level of the station pipeline according to the risk level matrix.
According to the embodiment of the invention, part of the detected pipeline information and the corresponding risk level result are selected as training samples, the rest of the detected pipeline information and the corresponding risk level result are used as test samples, the training samples are used for intelligent diagnosis learning training, and the test samples are used for judging the effectiveness of the intelligent diagnosis result of the station pipeline.
Optionally, determining a key impact parameter of the station pipeline risk assessment impact parameters according to the gray correlation method includes:
and 21, carrying out gray correlation analysis on parameters required by the risk assessment of the station pipeline, failure possibility and failure results, and carrying out gray correlation coefficients of the failure possibility and failure results of the station pipeline and each influence parameter obtained by the gray correlation analysis.
The station pipeline risk assessment relates to a plurality of influence parameters, and the influence degree of each parameter on the station pipeline failure possibility and the failure result is required to be judged to determine key influence parameters to be considered in the station pipeline risk intelligent assessment method. The gray correlation analysis can obtain the correlation degree of each influence parameter, the failure possibility and the failure result of the station pipeline, the parameter with large correlation degree can be called as a key parameter to be considered in risk assessment, and the parameter with small correlation can be called as a non-key parameter to be ignored in risk assessment, so that the risk assessment flow is simplified, and the accuracy of the assessment result is not affected. Calculating gray correlation coefficients:
wherein: i represents the ith column data; k represents the kth data in a certain column; minimink|x0 (k) -xi (k) | represents the value on the ith column parent-to-child difference and takes the minimum of the absolute values. maximaxk|x0 (k) -xi (k) | denotes that the value on the parent column of the ith column is different from each value on the child column, and takes the maximum value of the absolute value. The value of the parent row is different from the value of the child row by the value of the parent row, and the absolute value is taken. ρ represents an adjustment coefficient for adjusting the difference between different coefficients, the value range of the adjustment coefficient is (0, 1), and the larger ρ is, the smaller the difference between the coefficients is; conversely, the larger the difference between the coefficients.
And step 22, sorting gray correlation coefficients of failure possibility and failure result influence parameters of the station pipeline respectively, and selecting key influence parameters of the failure possibility and key influence parameters of the failure result according to the sorting result.
According to the embodiment of the invention, gray correlation degree analysis is carried out on the station pipeline risk influence factors of the single station, and invariant in the single station is ignored, so that the key influence factors of the station pipeline failure possibility can be obtained as follows: planned parking factors, detection periods, management system evaluation probabilities, unplanned parking factors, remaining life, service life, operating pressure, design pressure, measured wall thickness, raw wall thickness, pipe length; key influencing factors of the failure result of the station pipeline are as follows: operating pressure. It should be noted that the different station key influencing factors are different and need to be analyzed separately.
Optionally, establishing a database of associations of the key influencing factors with failure possibilities and failure results of the station pipeline through support vector machine learning, including:
step 31, learning training samples according to the key influence parameters of the failure possibility, and constructing an association relation between the key parameters and the failure possibility of the station pipeline;
and step 32, learning training samples according to the key influence parameters of the failure results, and constructing the association relation between the key parameters and the station pipeline failure results.
Optionally, performing model optimization on the station pipeline risk intelligent assessment model by using a sample, including:
and step 41, inputting key influence parameters of the test sample into a station pipeline risk intelligent evaluation model to obtain failure possibility and failure result of the test sample.
Step 42, performing error analysis according to the failure possibility and the failure result obtained through evaluation and the failure possibility and the failure result obtained through a standard method; the standard method is guided by the standard of GB/T26610 'inspection implementation rules for pressure equipment system based on risks'.
And 43, if the error does not meet the prediction accuracy requirement, adding a training sample, and continuing to perform machine learning of the support vector machine until the error meets the prediction accuracy requirement.
And taking the data of the residual pipelines as a test set, and verifying the prediction accuracy of the trained support vector machine station pipeline risk intelligent assessment model. Thereby detecting the effectiveness of the intelligent risk assessment model of the station pipeline.
By considering key influence parameters of the station pipeline risk, a support vector machine learning method is adopted to obtain the relation between the key parameters and the station pipeline failure possibility and failure result area, so that intelligent diagnosis of the station pipeline failure possibility and failure result is realized. The Matlab programming is used for calling the calculation of the support vector machine, and fig. 4 is a Matlab operation flow of the support vector machine. And selecting the data in the detection process as a training set to carry out learning training of the support vector machine.
The embodiment of the invention also provides an intelligent assessment system for the risk of the station pipeline, which comprises the following steps: the system comprises a data acquisition module, a key influence parameter identification module, a model training module, a model optimization module and a risk assessment module.
The data acquisition module is used for acquiring the operation data of the station pipeline and determining the risk level of the station pipeline according to the operation data; the key influence parameter identification module is used for identifying key influence parameters in the field station pipeline risk level influence parameters by adopting a gray correlation method; the model training and optimizing module is used for forming a sample set according to the key influence parameters and the corresponding station pipeline risk levels, establishing a related database of the failure possibility and failure results of the key influence factors and the station pipeline through support vector machine learning, and used for model training of the station pipeline risk intelligent evaluation model; performing model optimization on the intelligent station pipeline risk assessment model by using a test sample; the risk assessment module is used for predicting failure possibility and failure result of the station pipeline through the station pipeline risk intelligent assessment model based on the detected station pipeline operation parameters, so that the risk level of the detected station pipeline is determined.
The embodiment of the invention also provides a computer readable storage medium, which comprises instructions, when the instructions run on a computer, the computer is caused to execute the station pipeline risk intelligent assessment method provided by the embodiment.
The embodiment of the invention also provides a computing device which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the intelligent assessment method for the station pipeline risk provided by the embodiment is realized when the processor executes the program.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the apparatus and units described above may refer to corresponding procedures in the foregoing method embodiments, which are not described herein again.
In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of elements is merely a logical functional division, and there may be additional divisions of actual implementation, e.g., multiple elements or components may be combined or integrated into another system, or some features may be omitted, or not performed.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiment of the present invention.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention is essentially or a part contributing to the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the invention are intended to be included within the scope of the invention.
Claims (14)
1. The intelligent station pipeline risk assessment method is characterized by comprising the following steps of:
collecting operation data of a station pipeline, and determining the risk level of the station pipeline according to the operation data;
identifying key influence parameters in the risk level influence parameters of the station pipeline by adopting a gray correlation method;
forming a sample set according to the key influence parameters and the corresponding station pipeline risk levels, and establishing a related database of failure possibility and failure results of the key influence factors and the station pipeline by using training samples through support vector machine learning, wherein the related database is used for model training of a station pipeline risk intelligent evaluation model;
performing model optimization on the intelligent station pipeline risk assessment model by using a sample to be tested;
based on the detected station pipeline operation parameters, predicting the failure possibility and failure result of the station pipeline through the station pipeline risk intelligent evaluation model, so as to determine the risk level of the detected station pipeline.
2. The intelligent assessment method for risk of a station pipeline according to claim 1, wherein determining the risk level of the station pipeline according to the operation data comprises:
determining the average failure possibility of the station pipeline, the station pipeline correction coefficient and the management system evaluation coefficient according to the operation data;
determining the failure probability of the station pipeline according to the average failure probability of the station pipeline, the station pipeline correction coefficient and the management system evaluation coefficient;
determining area results and economic results caused by failure events according to the operation data, and determining the failure results of the station pipeline according to the area results and the economic results;
and determining the risk level of the station pipeline based on the risk level matrix according to the failure possibility and the failure result of the station pipeline.
3. The intelligent assessment method for the risk of the station pipeline according to claim 2, wherein the station pipeline failure probability is determined according to the station pipeline average failure probability, the station pipeline correction coefficient and the management system evaluation coefficient, and the calculation formula is as follows:
F＝F G F E F M
F E ＝DF+SF 1 +SF 2 +SF 3
wherein F is G For average failure probability of station pipeline, F E Correction coefficient for station pipeline, F M Evaluating coefficients for a management system; DF is the injury subfactor; SF (sulfur hexafluoride) 1 The method comprises the steps of determining a common secondary factor according to a factory condition coefficient, a climate condition coefficient and an earthquake activity coefficient; SF (sulfur hexafluoride) 2 Determining the mechanical secondary factor according to the complexity coefficient, the standard condition coefficient, the life cycle coefficient and the safety condition coefficient of the equipment; SF (sulfur hexafluoride) 3 And determining the process sub-factor according to the process continuous coefficient, the process stability coefficient and the safety protection device condition coefficient.
4. The intelligent assessment method for risk of a station pipeline according to claim 2, wherein determining the area consequences and the economic consequences caused by the failure event according to the operation data, and determining the failure consequences of the station pipeline according to the area consequences and the economic consequences, comprises:
selecting leakage representative medium and physical parameters thereof;
selecting leakage diameters and calculating leakage areas of each leakage hole;
calculating a theoretical leakage rate of the medium according to the physical property parameters and the leakage area of the selected leakage representative medium for each leakage hole;
determining an actual leakage rate according to the theoretical leakage rate of the medium and a leakage amount reduction coefficient, wherein the leakage amount reduction coefficient is determined according to the influence of a detection and isolation system on the leakage amount;
determining the area of the equipment damage result and the area of the personnel injury result according to the actual leakage rate, and determining the area result according to the area of the equipment damage result and the area of the personnel injury result;
determining economic consequences according to the sum of equipment maintenance or replacement cost in the operation data, damage cost of other equipment in an equipment failure influence area, medium leakage, downtime cost caused by equipment maintenance or replacement, personnel injury cost caused by equipment failure and environmental cleaning cost;
and determining the failure result of the station pipeline according to the sum of the area result and the economic result.
5. The intelligent assessment method for risk of station pipeline according to claim 4, wherein the leakage area A of each leakage hole is calculated n The calculation formula is as follows:
where d represents the leakage hole diameter.
6. The intelligent assessment method for risk of station pipeline according to claim 4, wherein the theoretical leakage rate W of the medium is calculated according to the selected physical parameters and leakage area of the leakage representative medium n The calculation formula is as follows:
wherein C is d Represents the leakage coefficient, and the leakage coefficient of turbulent medium passing through the sharp edge hole has the value range of [0.60,0.65 ]]The method comprises the steps of carrying out a first treatment on the surface of the ρ represents the medium density, A n Representing the leakage area.
7. The intelligent assessment method for risk of station pipeline according to claim 4, wherein the actual leakage rate r is determined according to the theoretical leakage rate of medium and the leakage amount reduction coefficient n The calculation formula is as follows:
r n ＝W n (1-f)
wherein f represents a leakage rate reduction coefficient, W n Representing the theoretical leakage rate of the medium.
8. The intelligent assessment method for risk of a station pipeline according to claim 4, wherein the determining the equipment damage outcome area and the personnel injury outcome area according to the actual leakage rate, determining the area outcome according to the equipment damage outcome area and the personnel injury outcome area, comprises:
the area of the damage result of the device is calculated as follows:
CA c ＝ar n b (1-f)
in the formula, CA c Representing the area of the damage result of the equipment, wherein a and b are constants, and the values are taken according to a table 13 in GB/T26610.5; f represents a leak rate reduction coefficient;
the area of the injury result of the personnel is calculated, and the formula is as follows:
in the formula, CA i Representing the area of the injury result of personnel, c and d are constants, the value of table 14 is taken according to GB/T26610.5, and f represents the leakage rate reduction coefficient;
the larger of the area of the device damage result and the area of the person injury result is taken as the area result.
9. The intelligent assessment method for the risk of the station pipeline according to claim 2, wherein the risk level matrix is: dividing the failure possibility into M levels according to the magnitude of the numerical value, dividing the failure result into N levels according to the severity, and combining the failure possibility and the failure result to obtain an M-row and N-column matrix; wherein M and N are constants.
10. The intelligent assessment method for risk of a station pipeline according to any one of claims 1 to 9, wherein the establishing, by support vector machine learning, an association database of the key influencing factors with failure possibilities and failure results of the station pipeline comprises:
learning training samples according to the key influence parameters of the failure possibility, and constructing an association relation between the key parameters and the failure possibility of the station pipeline;
and learning the training samples according to the key influence parameters of the failure results, and constructing the association relation between the key parameters and the station pipeline failure results.
11. The intelligent terminal pipeline risk assessment method according to any one of claims 1 to 9, wherein the model optimization of the intelligent terminal pipeline risk assessment model using a sample specimen, comprises:
inputting key influence parameters of the test sample into a station pipeline risk intelligent evaluation model to obtain failure possibility and failure results of the test sample;
performing error analysis according to the failure possibility and the failure result obtained through evaluation and the failure possibility and the failure result obtained through a standard method;
if the error does not meet the prediction precision requirement, training samples are added, and machine learning of the support vector machine is continued until the prediction precision requirement is met.
12. A station pipeline risk intelligent assessment system, comprising:
the data acquisition module is used for acquiring the operation data of the station pipeline and determining the risk level of the station pipeline according to the operation data;
the key influence parameter identification module is used for identifying key influence parameters in the field station pipeline risk level influence parameters by adopting a gray correlation method;
the model training module is used for forming a sample set according to the key influence parameters and the corresponding station pipeline risk levels, establishing a related database of failure possibility and failure results of the key influence factors and the station pipeline through support vector machine learning, and used for model training of the station pipeline risk intelligent evaluation model;
the model optimization module is used for carrying out model optimization on the intelligent field station pipeline risk assessment model by using a sample to be tested;
and the risk assessment module is used for predicting the failure possibility and the failure result of the station pipeline through the station pipeline risk intelligent assessment model based on the detected station pipeline operation parameters so as to determine the risk level of the detected station pipeline.
13. A computer readable storage medium comprising instructions which, when run on a computer, cause the computer to perform the intelligent substation pipeline risk assessment method according to any one of claims 1 to 11.
14. A computing device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the intelligent assessment method of site conduit risk of any one of claims 1 to 11 when the program is executed by the processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310203577.1A CN116384732A (en) | 2023-03-06 | 2023-03-06 | Intelligent assessment method, system, storage medium and computing device for station pipeline risk |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310203577.1A CN116384732A (en) | 2023-03-06 | 2023-03-06 | Intelligent assessment method, system, storage medium and computing device for station pipeline risk |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116384732A true CN116384732A (en) | 2023-07-04 |
Family
ID=86968382
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310203577.1A Pending CN116384732A (en) | 2023-03-06 | 2023-03-06 | Intelligent assessment method, system, storage medium and computing device for station pipeline risk |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116384732A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117094565A (en) * | 2023-10-19 | 2023-11-21 | 赛飞特工程技术集团有限公司 | Main responsibility implementation grading evaluation system for national group enterprises |
-
2023
- 2023-03-06 CN CN202310203577.1A patent/CN116384732A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117094565A (en) * | 2023-10-19 | 2023-11-21 | 赛飞特工程技术集团有限公司 | Main responsibility implementation grading evaluation system for national group enterprises |
| CN117094565B (en) * | 2023-10-19 | 2024-01-12 | 赛飞特工程技术集团有限公司 | Main responsibility implementation grading evaluation system for national group enterprises |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20180046155A1 (en) | Identifying and implementing refinery or petrochemical plant process performance improvements | |
| US20220057367A1 (en) | Method for evaluating pipe condition | |
| CN109522962B (en) | Chemical plant safety quantitative evaluation method | |
| CN108508863A (en) | A kind of electromechanical equipment method for diagnosing faults based on gray model | |
| CN115994248B (en) | Data detection method and system for valve faults | |
| CN116777223A (en) | Urban underground pipe network safety comprehensive risk assessment method and system | |
| CN111104989A (en) | Gas pipeline corrosion prediction method and device | |
| Song et al. | Multifractional and long-range dependent characteristics for remaining useful life prediction of cracking gas compressor | |
| CN116384732A (en) | Intelligent assessment method, system, storage medium and computing device for station pipeline risk | |
| CN117029968A (en) | Traffic data diagnosis method, system, storage medium and electronic equipment | |
| Defteraios et al. | Hydrogen explosion incident mitigation in steam reforming units through enhanced inspection and forecasting corrosion tools implementation | |
| CN117575027B (en) | Sensor fault diagnosis method for enhancing space-time causality by using knowledge | |
| Pinciroli et al. | A semi-supervised method for the characterization of degradation of nuclear power plants steam generators | |
| CN117312972A (en) | Method for identifying health state of scraper conveyor speed reducer | |
| Roh et al. | Steam trap maintenance-prioritizing model based on big data | |
| CN103406364B (en) | Method for predicting thickness of hot-rolled strip steel on basis of improved partial robust M-regression algorithm | |
| Sharma | Application of support vector machines for damage detection in structures | |
| CN111341396A (en) | Method and system for evaluating material corrosion safety in atmospheric environment | |
| CN106250993A (en) | A kind of measurement equipment metering cycle method of adjustment based on warship maintenance section | |
| CN110083933A (en) | A kind of corrosion pipeline Bayes's degradation analysis method considering stochastic effects | |
| AU2021101888A4 (en) | System and method for corrosion prediction in oil and gas pipeline | |
| Lu et al. | Integration of wavelet decomposition and artificial neural network for failure prognosis of reciprocating compressors | |
| JP2004302709A (en) | Maintenance management method for valve and support system therefor | |
| CN115330177A (en) | Urban public facility safety risk assessment method based on causal learning | |
| CN113836488A (en) | Method and device for online data processing and state evaluation of steam turbine |
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 |