CN112001545B - Digital twin-driven marine oil underwater production system fault prediction method and system - Google Patents
Digital twin-driven marine oil underwater production system fault prediction method and system Download PDFInfo
- Publication number
- CN112001545B CN112001545B CN202010856388.0A CN202010856388A CN112001545B CN 112001545 B CN112001545 B CN 112001545B CN 202010856388 A CN202010856388 A CN 202010856388A CN 112001545 B CN112001545 B CN 112001545B
- Authority
- CN
- China
- Prior art keywords
- underwater
- unit
- control module
- module
- reliability
- 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.)
- Active
Links
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 179
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000006731 degradation reaction Methods 0.000 claims abstract description 138
- 230000015556 catabolic process Effects 0.000 claims abstract description 125
- 241000191291 Abies alba Species 0.000 claims abstract description 68
- 238000012545 processing Methods 0.000 claims abstract description 57
- 238000004364 calculation method Methods 0.000 claims abstract description 45
- 238000012544 monitoring process Methods 0.000 claims abstract description 30
- 230000003068 static effect Effects 0.000 claims description 55
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 42
- 238000004891 communication Methods 0.000 claims description 26
- 238000009826 distribution Methods 0.000 claims description 26
- 238000004458 analytical method Methods 0.000 claims description 15
- 238000005516 engineering process Methods 0.000 claims description 12
- 238000013507 mapping Methods 0.000 claims description 10
- 238000001514 detection method Methods 0.000 claims description 9
- 230000010354 integration Effects 0.000 claims description 9
- 230000001186 cumulative effect Effects 0.000 claims description 8
- 238000011156 evaluation Methods 0.000 claims description 7
- 238000004088 simulation Methods 0.000 claims description 7
- 238000005457 optimization Methods 0.000 claims description 6
- 238000012351 Integrated analysis Methods 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 5
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 230000001364 causal effect Effects 0.000 claims description 4
- 230000007423 decrease Effects 0.000 claims description 4
- 238000013461 design Methods 0.000 claims description 4
- 238000005315 distribution function Methods 0.000 claims description 4
- 238000005070 sampling Methods 0.000 claims description 4
- 238000007476 Maximum Likelihood Methods 0.000 claims description 2
- 238000013459 approach Methods 0.000 claims description 2
- 238000000556 factor analysis Methods 0.000 claims description 2
- 230000001502 supplementing effect Effects 0.000 claims description 2
- 230000000007 visual effect Effects 0.000 claims description 2
- 239000003208 petroleum Substances 0.000 abstract description 9
- 238000010586 diagram Methods 0.000 description 7
- 230000005540 biological transmission Effects 0.000 description 4
- 230000008054 signal transmission Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 239000007788 liquid Substances 0.000 description 2
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000593 degrading effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000001131 transforming effect Effects 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- 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
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Computing Systems (AREA)
- Game Theory and Decision Science (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Algebra (AREA)
- Probability & Statistics with Applications (AREA)
- Life Sciences & Earth Sciences (AREA)
- Agronomy & Crop Science (AREA)
- Animal Husbandry (AREA)
- Marine Sciences & Fisheries (AREA)
- Mining & Mineral Resources (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention belongs to the field of petroleum engineering, and particularly relates to a method and a system for predicting faults of a digital twin-driven marine petroleum underwater production system. The method for predicting the fault of the marine oil underwater production system driven by the digital twin comprises five major steps: determining degradation modes of all modules, dynamic Bayesian network modeling of a performance degradation process, dynamic reliability calculation, residual life calculation and life information management and updating based on digital twins. The digital twin-driven marine petroleum underwater production system fault prediction system comprises an overwater control module data acquisition and processing subsystem, a hydraulic power unit data acquisition and processing subsystem, an electric power unit data acquisition and processing subsystem, an underwater control module data acquisition and processing subsystem, an underwater Christmas tree data acquisition and processing subsystem and a digital twin life monitoring control system.
Description
Technical Field
The invention belongs to the field of petroleum engineering, and particularly relates to a method and a system for predicting faults of a digital twin-driven marine petroleum underwater production system.
Background
Underwater production systems have become an important component of deep sea marine engineering technology as an important medium for completing marine oil production. Failure of any component can result in failure of the entire system due to its system integrity and structural complexity, which can lead to serious accidents if not cleared in time, resulting in significant personal injury and loss of property. The main equipment of the underwater production system comprises an underwater well head, an underwater Christmas tree, a manifold, a cross-boundary pipe, a pipeline terminal, an umbilical cable, a control system, a distribution system and the like.
The traditional fault prediction method is based on historical life data, and determines the occurrence time of equipment faults through statistical analysis of the life data, but for some large-scale equipment, the life data often cannot reflect the fault condition and the life information of each component, so that the problems of incomplete subsequent maintenance information and the like are caused. The digital twin technology can synchronize the module states of the underwater equipment and carry out remote fault prediction, can greatly shorten the time spent on fault prediction and improve the efficiency of fault prediction. Therefore, it is necessary to provide a method and a system for predicting the failure of the marine oil underwater production system driven by the digital twin.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides a method and a system for predicting the fault of a digital twin-driven marine oil underwater production system.
To achieve the above object, according to one aspect of the present invention, a method for predicting a failure of a digital twin driven offshore oil subsea production system comprises five major steps:
s1: determining degradation modes of the modules. The method comprises the steps of dividing an underwater production system into an electric control module, a hydraulic module and a mechanical part for degradation analysis, acquiring state monitoring data of the underwater production system in operation for parameter estimation, and performing uncertain analysis and probability distribution correction of parameters in each degradation model by combining with field expert experience.
S2: and (3) dynamic Bayesian network modeling is carried out in the performance degradation process. The method comprises the steps of establishing a static Bayesian network for performance degradation of each module of the underwater production system, inputting a degradation model of each module of the underwater production system into the static Bayesian network for performance degradation of each module, establishing the static Bayesian network for performance degradation of the underwater production system, determining nodes which change along with time in the static Bayesian network for performance degradation of the underwater production system, and expanding the static Bayesian network for performance degradation of the underwater production system into a dynamic Bayesian network for performance degradation of the underwater production system.
S3: and calculating the dynamic reliability. By time expansion of the dynamic Bayesian network in the performance degradation process of the underwater production system and taking years as time units, the reliability of each module of the underwater production system in the next years from the current moment is calculated, and the reliability of each module of the underwater production system is integrated to obtain the overall reliability of the underwater production system.
S4: and calculating the residual life. When the system degrades for a period of time under internal factors and external influences, the performance gradually degrades, and when the performance is below a failure threshold, the system will not perform properly. And calculating the time period from the moment of the detection point to the end of the failure point based on the integral dynamic reliability of the underwater production system, and acquiring the residual service life of the underwater production system.
S5: and managing and updating the service life information based on the digital twin. A digital twin fault prediction system is built by utilizing sensor data of the physical world, an integrated analysis technology and a continuously updated digital twin application program, and the full-cycle life management in the working process of the digital mirror image of the underwater production system is realized.
According to another aspect of the invention, the digital twin-driven offshore oil underwater production system fault prediction system comprises an overwater control module data acquisition and processing subsystem installed on an overwater control module, a hydraulic power unit data acquisition and processing subsystem installed on a hydraulic power unit, an electric power unit data acquisition and processing subsystem installed on an electric power unit, an underwater control module data acquisition and processing subsystem installed on an underwater control module, an underwater Christmas tree data acquisition and processing subsystem installed on an underwater Christmas tree, and a digital twin life monitoring and controlling system installed on an overwater control station.
The water control module data acquisition and processing subsystem comprises a water control module data acquisition unit, a water control module reliability calculation unit and a first sonar signal emission unit.
The hydraulic power unit data acquisition and processing subsystem comprises a hydraulic power unit electronic control module data acquisition unit, a hydraulic power unit hydraulic module data acquisition unit, a hydraulic power unit reliability calculation unit and a second sonar signal emission unit.
The electric power unit data acquisition and processing subsystem comprises an electric power unit electric control module data acquisition unit, an electric power unit reliability calculation unit and a third sonar signal emission unit.
The underwater control module data acquisition and processing subsystem comprises an underwater control module electric control module data acquisition unit, an underwater control module hydraulic module data acquisition unit, an underwater control module reliability calculation unit and a fourth sonar signal emission unit.
The underwater Christmas tree data acquisition and processing subsystem comprises an underwater Christmas tree hydraulic module data acquisition unit, an underwater Christmas tree mechanical part data acquisition unit, an underwater Christmas tree reliability calculation unit and a fifth sonar signal transmitting unit.
Digital twin life monitoring control system contains first sonar signal receiving unit, second sonar signal receiving unit, third sonar signal receiving unit, fourth sonar signal receiving unit, fifth sonar signal receiving unit, the whole reliability integration of system and computational element, the remaining life computational element of system, high in the clouds data acquisition unit and performance feedback unit.
Compared with the prior art, the invention has the beneficial results that: the digital twin-driven marine oil underwater production system fault prediction method is used for respectively monitoring states and evaluating performances of different modules of an underwater production system, and is matched with a digital twin technology to realize the performance management of the whole life cycle of the underwater production system, so that the method has more accurate residual life analysis capability.
Drawings
FIG. 1 is a flow chart of a digital twin driven marine oil subsea production system fault prediction;
FIG. 2 is a schematic diagram of a static Bayesian network for reliability assessment of an electrical control module of a subsea production system;
FIG. 3 is a schematic diagram of a static Bayesian network for reliability assessment of a hydraulic module of a subsea production system;
FIG. 4 is a schematic diagram of a static Bayesian network for reliability evaluation of mechanical portions of a subsea production system;
FIG. 5 is a schematic diagram of a subsea production system performance degrading static Bayesian network;
FIG. 6 is a schematic diagram of a dynamic Bayesian network of subsea production system performance degradation;
FIG. 7 is a schematic diagram of a method for calculating the remaining life of a subsea production system;
FIG. 8 is a flow chart of the construction of a fault prediction system of the marine oil underwater production system driven by a digital twin;
FIG. 9 is a schematic view of a subsea production system;
FIG. 10 is a schematic diagram of a digital twin driven marine oil subsea production system failure prediction system.
In the figure, 101, an above-water control module, 102, an uninterruptible power supply, 103, a master control station, 104, an electric power unit, 105, a communication unit, 106, a hydraulic power unit, 107, a first hydraulic module of the hydraulic power unit, 108, a second hydraulic module of the hydraulic power unit, 109, an electric control module of the hydraulic power unit, 110, a third hydraulic module of the hydraulic power unit, 111, a fourth hydraulic module of the hydraulic power unit, 112, the electric power unit, 113, a second communication modem, 114, a first communication modem, 115, a second filter, 116, a first filter, 117, a second electric coupler, 118, a first electric coupler, 119, an underwater control module, 120, an underwater control module reversing valve group, 121, a first reversing valve, 122, a second reversing valve, 123, a third reversing valve, 124, a fourth reversing valve, 125, a fifth reversing valve, 126, an underwater control module electric module group, 127. a third underwater electronic module, 128, a second underwater electronic module, 129, a first underwater electronic module, 130, an underwater Christmas tree, 131, an underwater Christmas tree hydraulic valve group, 132, a first hydraulic valve, 133, a second hydraulic valve, 134, a third hydraulic valve, 135, a fourth hydraulic valve, 136, a fifth hydraulic valve, 137, an underwater Christmas tree mechanical part group, 138, a Christmas tree cap, 139, a Christmas tree body, 201, a digital twin life monitoring control system, 202, a first sonar signal receiving unit, 203, a second sonar signal receiving unit, 204, a third sonar signal receiving unit, 205, a fourth sonar signal receiving unit, 206, a fifth sonar signal receiving unit, 207, a system integral reliability integration and calculation unit, 208, a performance feedback unit, 209, a system residual life calculation unit, 210, a cloud data acquisition unit, 211, a hydraulic power unit data acquisition and processing subsystem, 212. a second sonar signal transmitting unit, 213, a hydraulic power unit reliability calculating unit, 214, a hydraulic power unit electronic control module data collecting unit, 215, a hydraulic power unit hydraulic module data collecting unit, 216, an above-water control module data collecting and processing subsystem, 217, a first sonar signal transmitting unit, 218, an above-water control module reliability calculating unit, 219, an above-water control module electronic control module data collecting unit, 220, an electric power unit data collecting and processing subsystem, 221, a third sonar signal transmitting unit, 222, an electric power unit reliability calculating unit, 223, an electric power unit electronic control module data collecting unit, 224, an underwater Christmas tree data collecting and processing subsystem, 225, an underwater Christmas tree mechanical part data collecting unit, 226, an underwater Christmas tree liquid pressure module data collecting unit, 227, a hydraulic power unit electronic control module data collecting unit, 215, an above-water control module data collecting unit, 220, an electric power unit data collecting and processing subsystem, an underwater Christmas tree mechanical part data collecting unit, a hydraulic power unit, a hydraulic, The underwater Christmas tree reliability calculating unit comprises an underwater Christmas tree reliability calculating unit, a 228 fifth sonar signal transmitting unit, a 229 underwater control module data acquisition and processing subsystem, a 230 underwater control module hydraulic module data acquisition unit, a 231 underwater control module electric control module data acquisition unit, a 232 underwater control module reliability calculating unit, and a 233 fourth sonar signal transmitting unit.
Detailed Description
As shown in fig. 1, a method for predicting the failure of a digital twin-driven marine petroleum underwater production system comprises five major steps:
s1: determining degradation modes of the modules. The method comprises the steps of dividing an underwater production system into an electric control module, a hydraulic module and a mechanical part for degradation analysis, acquiring state monitoring data of the underwater production system in operation for parameter estimation, and performing uncertain analysis and probability distribution correction of parameters in each degradation model by combining with field expert experience.
S101: and determining degradation models of the electric control module, the hydraulic module and the mechanical part.
(1) For an electric control module in an underwater production system, a reliability degradation model is an exponential degradation model:
Re＝e-at (1)
wherein, Re is the reliability of the electric control module; a is the failure rate of the electronic component; t is the degradation time.
(2) For a hydraulic module in an underwater production system, the probability density function of a reliability degradation model of the hydraulic module, which is a Weibull degradation model, is as follows:
the cumulative distribution function, i.e. the cumulative failure rate function, of the weibull degradation model is as follows:
the reliability of the subsea production system hydraulic module can be expressed as:
Rh＝1-Fh(t,k,λ) (4)
wherein W is a probability density function in the Weibull degradation model, Fh is a cumulative distribution function in the Weibull degradation model and is also a cumulative failure rate function of the hydraulic module, Rh is the reliability of the hydraulic module, k is a shape parameter in the Weibull model, and λ is a scale parameter in the Weibull model.
(3) For a mechanical part in a subsea production system, the reliability degradation model is a gamma degradation process:
Rm(τ)-Rm(t)～Ga[α(τ)-α(t),β] (5)
wherein Rm (τ) and Rm (t) represent the degradation states at time τ and time t, Ga [ ] represents the gamma distribution, α is the shape parameter in the gamma distribution, and β is the scale parameter in the gamma distribution.
S102: and extracting state monitoring data in the underwater production system to carry out parameter estimation, and finishing the correction of probability distribution by combining with a field expert database.
And (3) performing parameter estimation by adopting a maximum likelihood estimation method:
wherein x is an estimated parameter; z is a radical ofiThe condition monitoring data, i.e. the sample.
S2: and (3) dynamic Bayesian network modeling is carried out in the performance degradation process. The method comprises the steps of establishing a static Bayesian network for performance degradation of each module of the underwater production system, inputting a degradation model of each module of the underwater production system into the static Bayesian network for performance degradation of each module, establishing the static Bayesian network for performance degradation of the underwater production system, determining nodes which change along with time in the static Bayesian network for performance degradation of the underwater production system, and expanding the static Bayesian network for performance degradation of the underwater production system into a dynamic Bayesian network for performance degradation of the underwater production system.
S201: and establishing a static Bayesian network of each degradation process. And mapping each parameter in the formula to each parameter node in the Bayesian network, and mapping the logical relationship in the formula to a conditional probability table in the Bayesian network in a sampling analog calculation mode.
And (3) mapping the formula (1) to the reliability evaluation static Bayesian network of the underwater production system electric control module as shown in FIG. 2 to obtain the reliability degradation distribution and probability of the underwater production system electric control module. The static Bayesian network is divided into three layers, wherein the first layer is a state monitoring layer and comprises two sensor data monitoring nodes S1 and S2; the second layer is a parameter estimation layer and comprises a node of failure rate a in the degradation of the electric control module; the third layer is a result layer and comprises a node of the reliability Re of the electric control module. The operation result of the static Bayesian network shows the reliability distribution and probability information of the electric control module.
And (3) mapping the formulas (2), (3) and (4) to the reliability evaluation static Bayesian network of the hydraulic module of the underwater production system shown in FIG. 3 to obtain the reliability degradation distribution and probability of the hydraulic module of the underwater production system. The static Bayesian network is divided into four layers, wherein the first layer is a state monitoring layer and comprises four sensor data monitoring nodes S3, S4, S5 and S6; the second layer is a parameter estimation layer and comprises two nodes of a shape parameter k and a scale parameter lambda in the degradation of the hydraulic module; the third layer is a middle result layer and comprises a node of the cumulative failure rate Fh of the hydraulic module; the fourth layer is the result layer and contains the reliability Rh of the hydraulic module, one node. The operation result of the static Bayesian network represents the reliability distribution and probability information of the hydraulic module.
And (3) mapping the formula (5) to the reliability evaluation static Bayesian network of the mechanical part of the underwater production system as shown in FIG. 4 to obtain the reliability degradation distribution and probability of the mechanical part of the underwater production system. The static Bayesian network is divided into three layers, wherein the first layer is a state monitoring layer and comprises four sensor data monitoring nodes S7, S8, S9 and S10; the third layer is a result layer, which contains a node of reliability Rm of the mechanical part. The operation result of the static Bayesian network represents the reliability distribution and probability information of the mechanical part.
And establishing the performance degradation static Bayesian network of the underwater production system as shown in FIG. 5 according to the serial-parallel structural relationship among the degradation modules and the causal relationship among the modules, wherein the network comprises a structural model of the performance degradation static Bayesian network of the underwater production system and a parameter model of the performance degradation static Bayesian network of the underwater production system. The structural model of the static Bayesian network for the performance degradation of the underwater production system is constructed according to the parameter relationship among degradation models on one hand and the causal relationship among division modules on the other hand; in the parameter model of the static Bayesian network for the performance degradation of the underwater production system, the prior probability is extracted through a database associated with the underwater production system, and the conditional probability table is obtained by converting a formula in the degradation model. The performance degradation static Bayesian network of the underwater production system is divided into six layers, the first layer is an above-water control module layer and comprises five nodes of an electric control module M1, an electric control module M2, an electric control module M3, an electric control module M4 and an above-water control module reliability RM; the second layer is a hydraulic power unit layer and comprises six nodes of an electric control module H1, a hydraulic module H2, a hydraulic module H3, a hydraulic module H4, a hydraulic module H5 and hydraulic power unit reliability RH; the third layer is an electric power unit layer and comprises seven nodes of an electric control module E1, an electric control module E2, an electric control module E3, an electric control module E4, an electric control module E5, an electric control module E6 and the reliability RE of an electric power unit; the fourth layer is an underwater control module layer and comprises nine nodes including a hydraulic module S1, a hydraulic module S2, a hydraulic module S3, a hydraulic module S4, a hydraulic module S5, an electric control module S6, an electric control module S7, an electric control module S8 and an underwater control module reliability RE; the fifth layer is an underwater Christmas tree layer and comprises eight nodes of a hydraulic module T1, a hydraulic module T2, a hydraulic module T3, a hydraulic module T4, a hydraulic module T5, a mechanical part T6, a mechanical part T7 and underwater Christmas tree reliability RT; and the sixth layer is a reliability evaluation layer and comprises a node of the integral reliability R of the underwater production system. The operation result of the static Bayesian network represents the reliability distribution and probability information of the underwater production system.
S202: and transforming a dynamic Bayesian network time slice and a conditional probability table among time slices according to each module degradation formula, and establishing the underwater production system performance degradation dynamic Bayesian network shown in FIG. 6. Each layer of nodes in the underwater production system performance degradation dynamic bayesian network is the same as the underwater production system performance degradation static bayesian network of fig. 5, and shows performance degradation and life change from time t to time t + 1.
S3: and calculating the dynamic reliability. By time expansion of the dynamic Bayesian network in the performance degradation process of the underwater production system and year as a time unit, the reliability of each module of the underwater production system in the next years from the current moment is calculated, and the reliability of each module of the underwater production system is integrated to obtain the overall reliability of the underwater production system.
The reliability of each module approaches infinity along with the sampling times of the Bayesian network, and the arithmetic mean of the reliability converges to an expected value:
the overall reliability of the system is:
where RM, RH, RE, RS and RT are calculated from the series-parallel relationship of the components of each layer, when the components are in series relationship, the reliability can be expressed as:
when the components are in a parallel relationship, the reliability can be expressed as:
and calculating the reliability R (t is 1), R (t is 2), R (t is 3) and … of each module of the underwater production system in the coming years from the first year by taking the year as a time unit.
S4: and calculating the residual life. When the system degrades for a period of time under internal factors and external influences, the performance gradually decreases, and when the performance is below a failure threshold, the system will not perform as normal. And calculating the time period from the moment of the detection point to the end of the failure point based on the integral dynamic reliability of the underwater production system, and acquiring the residual service life of the underwater production system.
The method for calculating the residual life of the underwater production system is shown in fig. 7, wherein the residual life refers to the estimated continuous normal working time from the current detection moment to the fault occurrence of the system. At time t1, the point of detection, a life prediction for the subsea production system is made, from which point the life of the system begins to gradually decrease; the point t2 is the time when the system performance first reaches the failure threshold, i.e., the failure point. When the system degrades for a period of time under internal factors and external influences and the performance gradually falls below the failure threshold, the system will not complete normal work, and the remaining life of the subsea production system is the period of time from the point of detection to the point of failure.
S5: and managing and updating the service life information based on the digital twin. A digital twin fault prediction system is built by utilizing sensor data of the physical world, an integrated analysis technology and a continuously updated digital twin application program, and the full-cycle life management in the working process of the digital mirror image of the underwater production system is realized.
A flow chart for building a digital twin-driven marine petroleum underwater production system fault prediction system is shown in fig. 8, a digital twin model of an underwater production system is built according to a physical model of the underwater production system, a fault prediction system is built by using sensor data of a physical world, an integrated analysis technology and a continuously updated digital twin application program, a residual life calculation algorithm of the underwater production system is stored in the system, full-period life management in a working process of a digital mirror image of the underwater production system is realized, and the step for building the digital twin-driven marine petroleum underwater production system fault prediction system is as follows:
(1) the method comprises the steps of conducting modularization processing on the underwater production system, defining each module subsystem, establishing internal relation among modules aiming at hardware analysis, architecture function and working process of the underwater production system, constructing an actual physical model of the underwater production system, and conducting reliability degradation analysis according to each module degradation model of the underwater production system.
(2) Defining the function of a digital twin system, constructing the digital twin model of the underwater production system according to the actual physical model of the underwater production system, designing the system according to the function of the system, and finally, carrying out hardware analysis and software design on the digital twin system according to the requirement of life prediction.
(3) Carrying out internal data acquisition and external environment simulation of digital twin driving, wherein the internal data acquisition comprises the model selection and design of sensors of each module, and the arrangement optimization of the sensors is carried out; the external environment simulation comprises external influence factor analysis, sensor selection and design and arrangement optimization of the sensors.
(4) The method comprises the steps of obtaining the residual life prediction method of the underwater production system based on a Bayesian network and a reliability degradation process, analyzing sensor information installed in production equipment, obtaining operation and environment data related to an actual process, connecting the data with a cloud database of the underwater production system, providing the data to a residual life prediction program stored in a digital twin system through a data processing and interface technology, analyzing the data and calculating the residual life by utilizing an analysis technology, an algorithm simulation and a visual program, continuously inputting real-time sensor information and fault rate information to realize continuous updating of the life information, simultaneously carrying out optimization control on the underwater production system according to a life prediction result, achieving the relation between a physical world and the digital world, and establishing a real-time digital model of a physical entity and a process.
As shown in fig. 9, the subsea production system comprises a topside control module 101, a hydraulic power unit 106, an electric power unit 112, a subsea control module 119, and a subsea tree 130; wherein, control module 101 on water is located control platform on water, includes: an uninterruptible power supply 102, a master control station 103, a power unit 104, and a communication unit 105; the uninterruptible power supply 102, the power unit 104 and the communication unit 105 are connected with the master control station 103 through cables and are used for carrying out power and communication transmission on the master control station 103; the hydraulic power unit 106 is located within the marine control platform and includes: a first hydraulic module 107 of the hydraulic power unit, a second hydraulic module 108 of the hydraulic power unit, an electronic control module 109 of the hydraulic power unit, a third hydraulic module 110 of the hydraulic power unit and a fourth hydraulic module 111 of the hydraulic power unit; the hydraulic power unit electronic control module 109 is connected with the first hydraulic module 107, the second hydraulic module 108, the third hydraulic module 110 and the fourth hydraulic module 111 of the hydraulic power unit through cables and is used for controlling the four hydraulic modules; the electric power unit 112 is located within the marine control platform and includes: a first communication modem 114, a second communication modem 113, a first filter 116, a second filter 115, a first power coupler 118, and a second power coupler 117; the first communication modem 114 is connected to the first filter 116 through a cable, and is used for filtering the electric signals of the unwanted frequencies; the first communication modem 114 and the first filter 116 are connected to the first power coupler 118 by a cable for coupling electrical signals and communication information; the second communication modem 113 is connected to the second filter 115 through a cable, and is configured to filter out an electrical signal of an unwanted frequency; the second communication modem 113 and the second filter 115 are connected to the second power coupler 117 through a cable for coupling of electric signals and communication information; subsea control module 119 is located within a subsea control pod and includes: an underwater control module reversing valve group 120 and an underwater control module electronic module group 126; the subsea control module diverter valve block 120 includes: a first direction valve 121, a second direction valve 122, a third direction valve 123, a fourth direction valve 124, and a fifth direction valve 125; the subsea control module electronics module set 126 includes: a first subsea electronics module 129, a second subsea electronics module 128, and a third subsea electronics module 127; subsea tree 130 is located in a subsea field and includes: subsea tree hydraulic valve block 131 and subsea tree mechanical section block 137; the subsea tree hydraulic valve block 131 includes: a first hydraulic valve 132, a second hydraulic valve 133, a third hydraulic valve 134, a fourth hydraulic valve 135, and a fifth hydraulic valve 136; subsea tree mechanical section group 137 includes: a tree cap 138 and tree body 139; the uninterruptible power supply 102 is connected with the hydraulic power unit 106 and the electric power unit 112 through cables and is used for providing electric power required by hydraulic transmission and signal transmission; the main control station 103 is connected with the hydraulic power unit 106 and the electric power unit 112 through cables and is used for controlling hydraulic transmission and signal transmission in oil and gas production; the first hydraulic module 107, the second hydraulic module 108, the third hydraulic module 110 and the fourth hydraulic module 111 are connected with a first reversing valve 121, a second reversing valve 122, a third reversing valve 123, a fourth reversing valve 124 and a fifth reversing valve 125 through cables for transmission of hydraulic liquid; the first power coupler 118 and the second power coupler 117 are connected with the first underwater electronic module 129, the second underwater electronic module 128 and the third underwater electronic module 127 through cables for controlling the transmission of signals; the subsea control module electronic module set 126 is connected to the subsea control module reversing valve set 120 by a cable, and is configured to control a flow direction of the hydraulic circuit.
As shown in fig. 10, the digital twin-driven marine petroleum underwater production system fault prediction system includes an above-water control module data acquisition and processing subsystem 216 installed in the above-water control module 101, a hydraulic power unit data acquisition and processing subsystem 211 installed in the hydraulic power unit 106, an electric power unit data acquisition and processing subsystem 220 installed in the electric power unit 112, a subsea control module data acquisition and processing subsystem 229 installed in the subsea control module 119, a subsea tree data acquisition and processing subsystem 224 installed in the subsea tree 130, and a digital twin life monitoring and controlling system 201 installed in the above-water control station.
The water control module data acquisition and processing subsystem 216 comprises a water control module data acquisition unit 219, a water control module reliability calculation unit 218 and a first sonar signal transmitting unit 217; the data acquisition unit 219 of the electric control module of the water control module is connected with the uninterruptible power supply 102, the main control station 103, the power unit 104 and the communication unit 105 in the water control module 101 through cables, and is used for acquiring sensor information of the uninterruptible power supply 102, the main control station 103, the power unit 104 and the communication unit 105 in the water control module 101 and acquiring degradation data of each module; the overwater control module reliability calculating unit 218 is connected with the overwater control module electric control module data acquisition unit 219 through a cable and is used for integrating the degradation data of each module in the overwater control module 101 and calculating the overall reliability of the module; the first sonar signal emitting unit 217 is connected with the overwater control module reliability calculating unit 218 through a cable and used for transmitting reliability data of the overwater control module 101 in the overwater control module reliability calculating unit 218.
The hydraulic power unit data acquisition and processing subsystem 211 comprises a hydraulic power unit electronic control module data acquisition unit 214, a hydraulic power unit hydraulic module data acquisition unit 215, a hydraulic power unit reliability calculation unit 213 and a second sonar signal emission unit 212; the data acquisition unit 214 of the hydraulic power unit electronic control module is connected with the hydraulic power unit electronic control module 109 through a cable and is used for acquiring the sensor information of the hydraulic power unit electronic control module 109 and acquiring the degradation data of the module; the hydraulic power unit hydraulic module data acquisition unit 215 is connected with the hydraulic power unit first hydraulic module 107, the hydraulic power unit second hydraulic module 108, the hydraulic power unit third hydraulic module 110 and the hydraulic power unit fourth hydraulic module 111 through cables, and is used for acquiring sensor information of the hydraulic power unit first hydraulic module 107, the hydraulic power unit second hydraulic module 108, the hydraulic power unit third hydraulic module 110 and the hydraulic power unit fourth hydraulic module 111 and acquiring degradation data of each module; the hydraulic power unit reliability calculation unit 213 is connected with the hydraulic power unit electronic control module data acquisition unit 214 and the hydraulic power unit hydraulic module data acquisition unit 215 through cables, and is used for integrating degradation data of each module in the hydraulic power unit 106 and calculating the overall reliability of the module; the second sonar signal emitting unit 212 is connected with the hydraulic power unit reliability calculating unit 213 through a cable, and is used for transmitting reliability data of the hydraulic power unit 106 in the hydraulic power unit reliability calculating unit 213.
The electric power unit data acquisition and processing subsystem 220 comprises an electric power unit electric control module data acquisition unit 223, an electric power unit reliability calculation unit 222 and a third sonar signal emission unit 221; the electric power unit electric control module data acquisition unit 223 is connected with the first communication modem 114, the second communication modem 113, the first filter 116, the second filter 115, the first electric coupler 118 and the second electric coupler 117 through cables, and is used for acquiring sensor information of the first communication modem 114, the second communication modem 113, the first filter 116, the second filter 115, the first electric coupler 118 and the second electric coupler 117 in the electric power unit 112 and acquiring degradation data of each module; the electric power unit reliability calculating unit 222 is connected with the electric power unit electronic control module data acquisition unit 223 through a cable, and is used for integrating degradation data of each module in the electric power unit 112 and calculating the overall reliability of the module; the third sonar signal emitting unit 221 is connected to the electric power unit reliability calculating unit 222 through a cable, and is used for transmitting reliability data of the electric power unit 112 in the electric power unit reliability calculating unit 222.
An underwater control module data acquisition and processing subsystem 229, which comprises an underwater control module electric control module data acquisition unit 231, an underwater control module hydraulic module data acquisition unit 230, an underwater control module reliability calculation unit 232 and a fourth sonar signal emission unit 233; the underwater control module electric control module data acquisition unit 231 is connected with the first underwater electronic module 129, the second underwater electronic module 128 and the third underwater electronic module 127 through cables and is used for acquiring sensor information of the first underwater electronic module 129, the second underwater electronic module 128 and the third underwater electronic module 127 in the underwater control module 119 and acquiring degradation data of each module; the underwater control module hydraulic module data acquisition unit 230 is connected with the first reversing valve 121, the second reversing valve 122, the third reversing valve 123, the fourth reversing valve 124 and the fifth reversing valve 125 through cables, and is used for acquiring sensor information of the first reversing valve 121, the second reversing valve 122, the third reversing valve 123, the fourth reversing valve 124 and the fifth reversing valve 125 in the underwater control module 119 and acquiring degradation data of each module; the underwater control module reliability calculating unit 232 is connected with the underwater control module electric control module data collecting unit 231 and the underwater control module hydraulic module data collecting unit 230 through cables and is used for integrating degradation data of all modules in the underwater control module 119 and calculating the integral reliability of the modules; the fourth sonar signal emitting unit 233 is connected to the underwater control module reliability calculating unit 232 through a cable, and is configured to transmit reliability data of the underwater control module 119 in the underwater control module reliability calculating unit 232.
An underwater Christmas tree data acquisition and processing subsystem 224, which comprises an underwater Christmas tree hydraulic module data acquisition unit 226, an underwater Christmas tree mechanical part data acquisition unit 225, an underwater Christmas tree reliability calculation unit 227 and a fifth sonar signal emission unit 228; the underwater Christmas tree hydraulic module data acquisition unit 226 is connected with the first hydraulic valve 132, the second hydraulic valve 133, the third hydraulic valve 134, the fourth hydraulic valve 135 and the fifth hydraulic valve 136 through cables and is used for acquiring sensor information of the first hydraulic valve 132, the second hydraulic valve 133, the third hydraulic valve 134, the fourth hydraulic valve 135 and the fifth hydraulic valve 136 in the underwater Christmas tree 130 and acquiring degradation data of each module; the data acquisition unit 225 of the mechanical part of the underwater Christmas tree is connected with the Christmas tree cap 138 and the Christmas tree body 139 through cables and is used for acquiring the sensor information of the Christmas tree cap 138 and the Christmas tree body 139 in the underwater Christmas tree 130 and acquiring the degradation data of each module; the underwater Christmas tree reliability calculating unit 227 is connected with the underwater Christmas tree hydraulic module data collecting unit 226 and the underwater Christmas tree mechanical part data collecting unit 225 through cables and is used for integrating degradation data of each module in the underwater Christmas tree 130 and calculating the integral reliability of the module; the fifth sonar signal transmitting unit 228 is connected to the subsea tree reliability calculating unit 227 through a cable, and is configured to transmit reliability data of the subsea tree 130 in the subsea tree reliability calculating unit 227.
A digital twin life monitoring and controlling system 201, which comprises a first sonar signal receiving unit 202, a second sonar signal receiving unit 203, a third sonar signal receiving unit 204, a fourth sonar signal receiving unit 205, a fifth sonar signal receiving unit 206, a system overall reliability integration and calculation unit 207, a system residual life calculation unit 209, a cloud data acquisition unit 210 and a performance feedback unit 208; the first sonar signal receiving unit 202 is communicated with the first sonar signal emitting unit 217 through sonar and is used for receiving reliability data of the water control module 101 transmitted by the first sonar signal emitting unit 217; the second sonar signal receiving unit 203 is communicated with the second sonar signal emitting unit 212 through sonar and is used for receiving reliability data of the hydraulic power unit 106 transmitted by the second sonar signal emitting unit 212; the third sonar signal receiving unit 204 communicates with the third sonar signal emitting unit 221 through sonar, and is used for receiving reliability data of the electric power unit 112 transmitted by the third sonar signal emitting unit 221; fourth sonar signal receiving unit 205 communicates with fourth sonar signal emitting unit 233 through sonar for receiving the reliability data of underwater control module 119 transmitted by fourth sonar signal emitting unit 233; the fifth sonar signal receiving unit 206 communicates with the fifth sonar signal emitting unit 228 through sonar, and is configured to receive reliability data of the underwater Christmas tree 130 transmitted by the fifth sonar signal emitting unit 228; the system overall reliability integration and calculation unit 207 is connected with the first sonar signal receiving unit 202, the second sonar signal receiving unit 203, the third sonar signal receiving unit 204, the fourth sonar signal receiving unit 205 and the fifth sonar signal receiving unit 206 through cables, and is used for integrating the degradation data received by the first sonar signal receiving unit 202, the second sonar signal receiving unit 203, the third sonar signal receiving unit 204, the fourth sonar signal receiving unit 205 and the fifth sonar signal receiving unit 206 and calculating the overall reliability of the underwater production system; the system residual life calculating unit 209 is connected with the system integral reliability integration and calculation unit 207 through a cable and is used for calculating the residual life of the underwater production system; the cloud data acquisition unit 210 is connected with the system residual life calculation unit 209 through a cable and is used for supplementing incomplete degradation data and correcting the residual life of the underwater production system; the performance feedback unit 208 is connected with the system residual life calculation unit 209 and the main control station 103 in the water control module through cables, and is used for extracting the life data in the system residual life calculation unit 209, feeding the data back to the main control station 103, analyzing the residual life information, and realizing the optimal control of the underwater production system.
In the working process of the underwater production system, the water control module data acquisition and processing subsystem 216, the hydraulic power unit data acquisition and processing subsystem 211, the electric power unit data acquisition and processing subsystem 220 and the underwater Christmas tree data acquisition and processing subsystem 224 respectively extract state data of the water control module 101, the hydraulic power unit 106, the electric power unit 112, the underwater control module 119 and the underwater Christmas tree 130 in real time, calculate the real-time reliability of the corresponding modules, transmit reliability information to the digital twin life monitoring and control system 201 through a sonar, calculate the residual life of the underwater production system through the system residual life calculation unit 209, feed the life information back to the main control station 103, extract information and optimize a control scheme by related personnel, and ensure the safety of oil and gas production.
Claims (7)
1. A digital twin driven marine oil underwater production system fault prediction method is characterized by comprising the following steps:
s1: determining degradation modes of the modules: dividing the underwater production system into an electric control module, a hydraulic module and a mechanical part for degradation analysis, acquiring state monitoring data in the operation of the underwater production system for parameter estimation, and performing uncertain analysis and probability distribution correction of parameters in each degradation model by combining with field expert experience;
s101: determining a degradation model of the electric control module, the hydraulic module and the mechanical part;
(1) for an electric control module in an underwater production system, a reliability degradation model is an exponential degradation model:
Re＝e-at (1)
wherein, Re is the reliability of the electric control module; a is the failure rate of the electronic component; t is the degradation time;
(2) for a hydraulic module in an underwater production system, the probability density function of a reliability degradation model of the hydraulic module, which is a Weibull degradation model, is as follows:
the cumulative distribution function, i.e. the cumulative failure rate function, of the weibull degradation model is as follows:
the reliability of the subsea production system hydraulic module can be expressed as:
Rh＝1-Fh(t,k,λ) (4)
wherein W is a probability density function in the Weibull degradation model, Fh is an accumulated distribution function in the Weibull degradation model and is also an accumulated failure rate function of the hydraulic module, Rh is the reliability of the hydraulic module, k is a shape parameter in the Weibull model, and lambda is a scale parameter in the Weibull model;
(3) for a mechanical part in a subsea production system, the reliability degradation model is a gamma degradation process:
Rm(τ)-Rm(t)～Ga[α(τ)-α(t),β] (5)
wherein Rm (τ) and Rm (t) represent the degradation states at the time τ and the time t, Ga [ ] represents the gamma distribution, α is the shape parameter in the gamma distribution, and β is the scale parameter in the gamma distribution;
s102: extracting state monitoring data in the underwater production system for parameter estimation, and finishing the correction of probability distribution by combining with a field expert database;
and (3) performing parameter estimation by adopting a maximum likelihood estimation method:
whereinX is an estimated parameter; z is a radical ofiIs the condition monitoring data, i.e. the sample;
s2: dynamic Bayesian network modeling of the performance degradation process: establishing a static Bayesian network for performance degradation of each module of the underwater production system, inputting a degradation model of each module of the underwater production system into the static Bayesian network for performance degradation of each module, establishing the static Bayesian network for performance degradation of the underwater production system, determining nodes which change along with time in the static Bayesian network for performance degradation of the underwater production system, and expanding the static Bayesian network for performance degradation of the underwater production system into a dynamic Bayesian network for performance degradation of the underwater production system;
s201: establishing a static Bayesian network of each degradation process, mapping each parameter in the formula to each parameter node in the Bayesian network, and mapping the logical relationship in the formula to a conditional probability table in the Bayesian network in a sampling simulation calculation mode;
mapping the formula (1) into a static Bayesian network for evaluating the reliability of the electric control module of the underwater production system to obtain reliability degradation distribution and probability of the electric control module of the underwater production system; the static Bayesian network is divided into three layers, wherein the first layer is a state monitoring layer and comprises two sensor data monitoring nodes S1 and S2; the second layer is a parameter estimation layer and comprises a node of failure rate a in the degradation of the electric control module; the third layer is a result layer and comprises a node of the reliability Re of the electric control module; the operation result of the static Bayesian network shows the reliability distribution and probability information of the electric control module;
mapping the formulas (2), (3) and (4) to a static Bayesian network for evaluating the reliability of the hydraulic module of the underwater production system to obtain the reliability degradation distribution and probability of the hydraulic module of the underwater production system; the static Bayesian network is divided into four layers, wherein the first layer is a state monitoring layer and comprises four sensor data monitoring nodes S3, S4, S5 and S6; the second layer is a parameter estimation layer and comprises two nodes of a shape parameter k and a scale parameter lambda in the degradation of the hydraulic module; the third layer is a middle result layer and comprises a node of the cumulative failure rate Fh of the hydraulic module; the fourth layer is a result layer and comprises a node of the reliability Rh of the hydraulic module; the operation result of the static Bayesian network shows the reliability distribution and probability information of the hydraulic module;
mapping the formula (5) to a reliability evaluation static Bayesian network of the mechanical part of the underwater production system to obtain reliability degradation distribution and probability of the mechanical part of the underwater production system; the static Bayesian network is divided into three layers, wherein the first layer is a state monitoring layer and comprises four sensor data monitoring nodes S7, S8, S9 and S10; the third layer is a result layer and comprises a node of reliability Rm of the mechanical part; the operation result of the static Bayesian network represents the reliability distribution and probability information of the mechanical part;
establishing a performance degradation static Bayesian network of the underwater production system according to the serial-parallel structural relationship among the degradation modules and the causal relationship among the modules, wherein the network comprises a structural model of the performance degradation static Bayesian network of the underwater production system and a parameter model of the performance degradation static Bayesian network of the underwater production system; the structural model of the static Bayesian network for the performance degradation of the underwater production system is constructed according to the parameter relationship among degradation models on one hand and the causal relationship among division modules on the other hand; in a parameter model of a static Bayesian network for performance degradation of an underwater production system, prior probability is extracted through a database associated with the underwater production system, and a conditional probability table is obtained by converting a formula in a degradation model; the performance degradation static Bayesian network of the underwater production system is divided into six layers, the first layer is an above-water control module layer and comprises five nodes of an electric control module M1, an electric control module M2, an electric control module M3, an electric control module M4 and an above-water control module reliability RM; the second layer is a hydraulic power unit layer and comprises six nodes of an electric control module H1, a hydraulic module H2, a hydraulic module H3, a hydraulic module H4, a hydraulic module H5 and hydraulic power unit reliability RH; the third layer is an electric power unit layer and comprises seven nodes of an electric control module E1, an electric control module E2, an electric control module E3, an electric control module E4, an electric control module E5, an electric control module E6 and the reliability RE of an electric power unit; the fourth layer is an underwater control module layer and comprises nine nodes including a hydraulic module S1, a hydraulic module S2, a hydraulic module S3, a hydraulic module S4, a hydraulic module S5, an electric control module S6, an electric control module S7, an electric control module S8 and an underwater control module reliability RE; the fifth layer is an underwater Christmas tree layer and comprises eight nodes of a hydraulic module T1, a hydraulic module T2, a hydraulic module T3, a hydraulic module T4, a hydraulic module T5, a mechanical part T6, a mechanical part T7 and underwater Christmas tree reliability RT; the sixth layer is a reliability evaluation layer and comprises a node of the integral reliability R of the underwater production system; the operation result of the static Bayesian network shows the reliability distribution and probability information of the underwater production system;
s202: converting a dynamic Bayesian network time slice and a conditional probability table among time slices according to each module degradation formula, and establishing a dynamic Bayesian network with degraded performance of the underwater production system; each layer of nodes in the dynamic Bayesian network for the performance degradation of the underwater production system are the same as the static Bayesian network for the performance degradation of the underwater production system, and represent the performance degradation and the service life change from the time t to the time t + 1;
s3: and (3) calculating the dynamic reliability: calculating the reliability of each module of the underwater production system in the next years from the current moment by using the time extension of the dynamic Bayesian network in the performance degradation process of the underwater production system and taking the year as a time unit, and integrating the reliability of each module of the underwater production system to obtain the integral reliability of the underwater production system;
the reliability of each module approaches infinity along with the sampling times of the Bayesian network, and the arithmetic mean of the reliability converges to an expected value:
the overall reliability of the system is:
where RM, RH, RE, RS and RT are calculated from the series-parallel relationship of the components of each layer, when the components are in series relationship, the reliability can be expressed as:
when the components are in a parallel relationship, the reliability can be expressed as:
calculating the reliability R (t is 1), R (t is 2), R (t is 3) and … of each module of the underwater production system in the coming years from the first year by taking the year as a time unit;
s4: calculating the residual life: when the system degrades for a period of time under the influence of internal factors and external factors, the performance gradually decreases, and when the performance is lower than a failure threshold value, the system cannot complete normal work; calculating the time period from the moment of the detection point to the end of the failure point based on the integral dynamic reliability of the underwater production system, and acquiring the residual service life of the underwater production system;
the residual life refers to the estimated continuous normal working time from the current detection moment to the fault occurrence of the system; at time t1, the point of detection, a life prediction for the subsea production system is made, from which point the life of the system begins to gradually decrease; a point t2 is a point when the system performance reaches a failure threshold for the first time, namely a failure point; when the system degrades for a period of time under the influence of internal factors and external factors and the performance is gradually lower than the failure threshold value, the system cannot complete normal work, and the residual life of the underwater production system is a time period from the moment of the detection point to the moment of the failure point;
s5: life information management and updating based on digital twinning: a digital twin fault prediction system is built by utilizing sensor data of the physical world, an integrated analysis technology and a continuously updated digital twin application program, so that the full-cycle life management in the working process of the digital mirror image of the underwater production system is realized;
the method comprises the following steps of constructing a digital twin model of the underwater production system according to a physical model of the underwater production system, constructing a digital twin fault prediction system by utilizing sensor data of a physical world, an integrated analysis technology and a continuously updated digital twin application program, storing a residual life calculation algorithm of the underwater production system in the system, realizing full-cycle life management in a working process of a digital mirror image of the underwater production system, and constructing the digital twin-driven underwater production system fault prediction system:
(1) modularizing the underwater production system, defining each module subsystem, establishing the internal relation among the modules aiming at the hardware analysis, the architecture function and the working process of the underwater production system, constructing an actual physical model of the underwater production system, and performing reliability degradation analysis according to the established degradation model of each module of the underwater production system;
(2) defining a digital twin system function, constructing a digital twin model of the underwater production system according to an actual physical model of the underwater production system, designing the system according to the system function, and finally performing hardware analysis and software design of the digital twin system according to the requirement of life prediction;
(3) carrying out internal data acquisition and external environment simulation of digital twin driving, wherein the internal data acquisition comprises the model selection and design of sensors of each module, and the arrangement optimization of the sensors is carried out; the external environment simulation comprises external influence factor analysis, sensor model selection and design and sensor arrangement optimization;
(4) the method comprises the steps of obtaining a residual life prediction method of the underwater production system based on a Bayesian network and a reliability degradation process, analyzing sensor information installed in production equipment, obtaining operation and environment data related to an actual process, connecting the data with a cloud database of the underwater production system, providing the data to a residual life prediction program stored in a digital twin system through a data processing and interface technology, analyzing the data and calculating the residual life by utilizing an analysis technology, an algorithm simulation and a visual program, continuously inputting real-time sensor information and fault rate information to realize continuous updating of the life information, simultaneously carrying out optimization control on the underwater production system according to a life prediction result, achieving the relation between a physical world and the digital world, and establishing a real-time digital model of a physical entity and a process;
the digital twin-driven offshore oil underwater production system fault prediction method is applied to a digital twin-driven offshore oil underwater production system fault prediction system, and the system comprises an overwater control module data acquisition and processing subsystem installed on an overwater control module, a hydraulic power unit data acquisition and processing subsystem installed on a hydraulic power unit, an electric power unit data acquisition and processing subsystem installed on an electric power unit, an underwater control module data acquisition and processing subsystem installed on an underwater control module, an underwater Christmas tree data acquisition and processing subsystem installed on an underwater Christmas tree, and a digital twin life monitoring and controlling system installed on an overwater control station;
the system comprises a water control module data acquisition and processing subsystem, a water control module data acquisition and processing subsystem and a first sonar signal transmitting unit, wherein the water control module data acquisition and processing subsystem comprises a water control module data acquisition unit, a water control module reliability calculation unit and a first sonar signal transmitting unit;
the hydraulic power unit data acquisition and processing subsystem comprises a hydraulic power unit electronic control module data acquisition unit, a hydraulic power unit hydraulic module data acquisition unit, a hydraulic power unit reliability calculation unit and a second sonar signal emission unit;
the electric power unit data acquisition and processing subsystem comprises an electric power unit electric control module data acquisition unit, an electric power unit reliability calculation unit and a third sonar signal emission unit;
the underwater control module data acquisition and processing subsystem comprises an underwater control module electric control module data acquisition unit, an underwater control module hydraulic module data acquisition unit, an underwater control module reliability calculation unit and a fourth sonar signal emission unit;
the underwater Christmas tree data acquisition and processing subsystem comprises an underwater Christmas tree hydraulic module data acquisition unit, an underwater Christmas tree mechanical part data acquisition unit, an underwater Christmas tree reliability calculation unit and a fifth sonar signal transmitting unit;
digital twin life monitoring control system contains first sonar signal receiving unit, second sonar signal receiving unit, third sonar signal receiving unit, fourth sonar signal receiving unit, fifth sonar signal receiving unit, the whole reliability integration of system and computational element, the remaining life computational element of system, high in the clouds data acquisition unit and performance feedback unit.
2. The method of predicting a failure of a digital twin driven offshore oil subsea production system according to claim 1, wherein: the system comprises a water control module data acquisition and processing subsystem, a water control module data acquisition and processing subsystem and a first sonar signal transmitting unit, wherein the water control module data acquisition and processing subsystem comprises a water control module data acquisition unit, a water control module reliability calculation unit and a first sonar signal transmitting unit; the data acquisition unit of the electric control module of the water control module is connected with the uninterrupted power supply, the master control station, the power unit and the communication unit in the water control module through cables and is used for acquiring the sensor information of the uninterrupted power supply, the master control station, the power unit and the communication unit in the water control module and acquiring the degradation data of each module; the overwater control module reliability calculation unit is connected with the overwater control module electric control module data acquisition unit through a cable and is used for integrating the degradation data of each module in the overwater control module and calculating the integral reliability of the module; the first sonar signal transmitting unit is connected with the overwater control module reliability calculating unit through a cable and used for transmitting reliability data of the overwater control module in the overwater control module reliability calculating unit.
3. The method of predicting a failure of a digital twin driven offshore oil subsea production system according to claim 1, wherein: the hydraulic power unit data acquisition and processing subsystem comprises a hydraulic power unit electronic control module data acquisition unit, a hydraulic power unit hydraulic module data acquisition unit, a hydraulic power unit reliability calculation unit and a second sonar signal emission unit; the hydraulic power unit electronic control module data acquisition unit is connected with the hydraulic power unit electronic control module through a cable and is used for acquiring sensor information of the hydraulic power unit electronic control module and acquiring degradation data of the module; the hydraulic power unit hydraulic module data acquisition unit is connected with the hydraulic power unit first hydraulic module, the hydraulic power unit second hydraulic module, the hydraulic power unit third hydraulic module and the hydraulic power unit fourth hydraulic module through cables and is used for acquiring sensor information of the hydraulic power unit first hydraulic module, the hydraulic power unit second hydraulic module, the hydraulic power unit third hydraulic module and the hydraulic power unit fourth hydraulic module and acquiring degradation data of each module; the hydraulic power unit reliability calculation unit is connected with the hydraulic power unit electronic control module data acquisition unit and the hydraulic power unit hydraulic module data acquisition unit through cables and is used for integrating degradation data of all modules in the hydraulic power unit and calculating the overall reliability of the modules; and the second sonar signal transmitting unit is connected with the hydraulic power unit reliability calculating unit through a cable and is used for transmitting the reliability data of the hydraulic power unit in the hydraulic power unit reliability calculating unit.
4. The method of predicting a failure of a digital twin driven offshore oil subsea production system according to claim 1, wherein: the electric power unit data acquisition and processing subsystem comprises an electric power unit electric control module data acquisition unit, an electric power unit reliability calculation unit and a third sonar signal emission unit; the electric power unit electric control module data acquisition unit is connected with the first communication modem, the second communication modem, the first filter, the second filter, the first electric coupler and the second electric coupler through cables and is used for acquiring sensor information of the first communication modem, the second communication modem, the first filter, the second filter, the first electric coupler and the second electric coupler in the electric power unit and acquiring degradation data of each module; the electric power unit reliability calculation unit is connected with the electric control module data acquisition unit of the electric power unit through a cable and is used for integrating the degradation data of each module in the electric power unit and calculating the integral reliability of the module; the third sonar signal transmitting unit is connected with the electric power unit reliability calculating unit through a cable and used for transmitting reliability data of the electric power unit in the electric power unit reliability calculating unit.
5. The method of predicting a failure of a digital twin driven offshore oil subsea production system according to claim 1, wherein: the underwater control module data acquisition and processing subsystem comprises an underwater control module electric control module data acquisition unit, an underwater control module hydraulic module data acquisition unit, an underwater control module reliability calculation unit and a fourth sonar signal emission unit; the underwater control module electric control module data acquisition unit is connected with the first underwater electronic module, the second underwater electronic module and the third underwater electronic module through cables and is used for acquiring sensor information of the first underwater electronic module, the second underwater electronic module and the third underwater electronic module in the underwater control module and acquiring degradation data of each module; the underwater control module hydraulic module data acquisition unit is connected with the first reversing valve, the second reversing valve, the third reversing valve, the fourth reversing valve and the fifth reversing valve through cables and is used for acquiring sensor information of the first reversing valve, the second reversing valve, the third reversing valve, the fourth reversing valve and the fifth reversing valve in the underwater control module and acquiring degradation data of each module; the underwater control module reliability calculation unit is connected with the underwater control module electric control module data acquisition unit and the underwater control module hydraulic module data acquisition unit through cables and is used for integrating degradation data of all modules in the underwater control module and calculating the integral reliability of the module; and the fourth sonar signal transmitting unit is connected with the underwater control module reliability calculating unit through a cable and is used for transmitting the reliability data of the underwater control module in the underwater control module reliability calculating unit.
6. The method of predicting a failure of a digital twin driven offshore oil subsea production system according to claim 1, wherein: the underwater Christmas tree data acquisition and processing subsystem comprises an underwater Christmas tree hydraulic module data acquisition unit, an underwater Christmas tree mechanical part data acquisition unit, an underwater Christmas tree reliability calculation unit and a fifth sonar signal transmitting unit; the underwater Christmas tree hydraulic module data acquisition unit is connected with a first hydraulic valve, a second hydraulic valve, a third hydraulic valve, a fourth hydraulic valve and a fifth hydraulic valve through cables and is used for acquiring sensor information of the first hydraulic valve, the second hydraulic valve, the third hydraulic valve, the fourth hydraulic valve and the fifth hydraulic valve in the underwater Christmas tree and acquiring degradation data of each module; the data acquisition unit of the mechanical part of the underwater Christmas tree is connected with the Christmas tree cap and the Christmas tree body through cables and is used for acquiring sensor information of the Christmas tree cap and the Christmas tree body in the underwater Christmas tree and acquiring degradation data of each module; the underwater Christmas tree reliability calculating unit is connected with the underwater Christmas tree hydraulic module data acquisition unit and the underwater Christmas tree mechanical part data acquisition unit through cables and is used for integrating degradation data of each module in the underwater Christmas tree and calculating the integral reliability of the module; and the fifth sonar signal transmitting unit is connected with the underwater Christmas tree reliability calculating unit through a cable and is used for transmitting reliability data of the underwater Christmas tree in the underwater Christmas tree reliability calculating unit.
7. The method of predicting a failure of a digital twin driven offshore oil subsea production system according to claim 1, wherein: the digital twin life monitoring and controlling system comprises a first sonar signal receiving unit, a second sonar signal receiving unit, a third sonar signal receiving unit, a fourth sonar signal receiving unit, a fifth sonar signal receiving unit, a system overall reliability integration and calculation unit, a system residual life calculation unit, a cloud data acquisition unit and a performance feedback unit; the first sonar signal receiving unit is communicated with the first sonar signal transmitting unit through a sonar and is used for receiving the reliability data of the water control module transmitted by the first sonar signal transmitting unit; the second sonar signal receiving unit is communicated with the second sonar signal transmitting unit through a sonar and is used for receiving the reliability data of the hydraulic power unit transmitted by the second sonar signal transmitting unit; the third sonar signal receiving unit is communicated with the third sonar signal transmitting unit through a sonar and is used for receiving reliability data of the electric power unit transmitted by the third sonar signal transmitting unit; the fourth sonar signal receiving unit is communicated with the fourth sonar signal transmitting unit through a sonar and is used for receiving the reliability data of the underwater control module transmitted by the fourth sonar signal transmitting unit; the fifth sonar signal receiving unit is communicated with the fifth sonar signal transmitting unit through a sonar and is used for receiving reliability data of the underwater Christmas tree transmitted by the fifth sonar signal transmitting unit; the system integral reliability integration and calculation unit is connected with the first sonar signal receiving unit, the second sonar signal receiving unit, the third sonar signal receiving unit, the fourth sonar signal receiving unit and the fifth sonar signal receiving unit through cables and is used for integrating the degradation data received by the first sonar signal receiving unit, the second sonar signal receiving unit, the third sonar signal receiving unit, the fourth sonar signal receiving unit and the fifth sonar signal receiving unit and calculating the integral reliability of the underwater production system; the system residual life calculating unit is connected with the system integral reliability integration and calculating unit through a cable and is used for calculating the residual life of the underwater production system; the cloud data acquisition unit is connected with the system residual life calculation unit through a cable and is used for supplementing incomplete degradation data and correcting the residual life of the underwater production system; the performance feedback unit is connected with the system residual life calculation unit and a main control station in the water control module through cables and used for extracting life data in the system residual life calculation unit, feeding the data back to the main control station, analyzing residual life information and realizing optimal control of the underwater production system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010856388.0A CN112001545B (en) | 2020-08-24 | 2020-08-24 | Digital twin-driven marine oil underwater production system fault prediction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010856388.0A CN112001545B (en) | 2020-08-24 | 2020-08-24 | Digital twin-driven marine oil underwater production system fault prediction method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112001545A CN112001545A (en) | 2020-11-27 |
| CN112001545B true CN112001545B (en) | 2022-03-15 |
Family
ID=73470311
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010856388.0A Active CN112001545B (en) | 2020-08-24 | 2020-08-24 | Digital twin-driven marine oil underwater production system fault prediction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112001545B (en) |
Families Citing this family (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110109359B (en) * | 2019-05-21 | 2023-03-10 | 中国石油大学(华东) | Safety integrity level evaluation method for offshore oil well control equipment |
| CN113240240A (en) * | 2021-04-12 | 2021-08-10 | 国网河北省电力有限公司沧州供电分公司 | Offshore oilfield group power system reliability assessment system and method thereof |
| CN113250674B (en) * | 2021-04-27 | 2023-06-30 | 山东恒信电器集团有限公司 | Electric control system for petroleum drilling equipment |
| CN113255117B (en) * | 2021-05-11 | 2022-08-02 | 北京航空航天大学 | Reliability digital twinning model of liquid level volatile product |
| CN113378480B (en) * | 2021-07-02 | 2022-04-15 | 中国石油大学(华东) | Method and system for maintaining underwater Christmas tree according to situations based on residual service life prediction |
| CN113432857B (en) * | 2021-07-02 | 2022-04-12 | 中国石油大学(华东) | Method and system for predicting residual service life of underwater Christmas tree system based on digital twins |
| CN113485213A (en) * | 2021-07-05 | 2021-10-08 | 北京瑞博众成科技有限公司 | Intelligent real-time monitoring system for digital twin regulating valve |
| CN113378482B (en) * | 2021-07-07 | 2022-06-14 | 哈尔滨工业大学 | Digital twin modeling reasoning method based on variable structure dynamic Bayesian network |
| CN113435660B (en) * | 2021-07-13 | 2022-07-08 | 中国石油大学(华东) | Underwater Christmas tree re-prediction method integrating Kalman filtering and Bayesian network |
| CN113848806B (en) * | 2021-10-12 | 2023-05-23 | 中国石油大学(华东) | Digital twin-driven efficient discharge pulse arc milling fault diagnosis method and system |
| CN114089708B (en) * | 2021-11-19 | 2024-03-26 | 江苏科技大学 | Digital twinning-based offshore power generation platform management system and optimization regulation and control method thereof |
| CN114923261B (en) * | 2022-05-05 | 2023-07-18 | 青岛海信日立空调系统有限公司 | Central air conditioner unit fault monitoring method and system and central air conditioner unit |
| CN115203987B (en) * | 2022-09-16 | 2023-01-06 | 中国石油大学(华东) | Submarine pipeline dependent competition failure real-time reliability assessment system and method |
| CN115680616B (en) * | 2022-11-04 | 2024-06-25 | 中国石油大学(华东) | Digital twin body modeling method and operation system of underwater production system |
| CN115857447B (en) * | 2022-11-28 | 2023-06-09 | 安徽宝信信息科技有限公司 | Digital twinning-based complex industrial system operation monitoring method and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102262690A (en) * | 2011-06-07 | 2011-11-30 | 中国石油大学(北京) | Modeling method of early warning model of mixed failures and early warning model of mixed failures |
| CN110134113A (en) * | 2019-05-20 | 2019-08-16 | 中国石油大学(华东) | A kind of offshore oil well control equipment method for protecting and system |
| CN110489862A (en) * | 2019-08-19 | 2019-11-22 | 重庆大学 | A kind of complex electromechanical systems life-span prediction method |
-
2020
- 2020-08-24 CN CN202010856388.0A patent/CN112001545B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102262690A (en) * | 2011-06-07 | 2011-11-30 | 中国石油大学(北京) | Modeling method of early warning model of mixed failures and early warning model of mixed failures |
| CN110134113A (en) * | 2019-05-20 | 2019-08-16 | 中国石油大学(华东) | A kind of offshore oil well control equipment method for protecting and system |
| CN110489862A (en) * | 2019-08-19 | 2019-11-22 | 重庆大学 | A kind of complex electromechanical systems life-span prediction method |
Non-Patent Citations (2)
| Title |
|---|
| Remaining Useful Life Estimation of Structure Systems Under the Influence of Multiple Causes: Subsea Pipelines as a Case Study;Cai, Baoping 等;《IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS》;20200731;5737-5747 * |
| 基于多阶段相关性性能退化的剩余寿命预测方法;邵筱焱 等;《第十九届中国海洋（岸）工程学术讨论会论文集》;20191031;348-354 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112001545A (en) | 2020-11-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112001545B (en) | Digital twin-driven marine oil underwater production system fault prediction method and system | |
| AU2020102863A4 (en) | Digital-twin-driven fault prognosis method and system for subsea production system of offshore oil | |
| CN111967189B (en) | Fault diagnosis method and system for digital twin driven marine oil underwater production system | |
| CN110135079B (en) | Macroscopic elasticity evaluation method and system for offshore oil well control equipment | |
| CN109145428B (en) | Vulnerability assessment method for information physical fusion system in cascading failure mode | |
| CN110619386B (en) | TMR operation monitoring and fault intelligent research and judgment method and system | |
| CN110866314A (en) | Method for predicting residual life of rotating machinery of multilayer bidirectional gate control circulation unit network | |
| CN113435660B (en) | Underwater Christmas tree re-prediction method integrating Kalman filtering and Bayesian network | |
| CN102695943A (en) | Universal sensor self-diagnosis device and diagnosis method therefor | |
| Christos et al. | Data-centric operations in oil & gas industry by the use of 5G mobile networks and industrial Internet of Things (IIoT) | |
| CN105634819A (en) | Intelligent monitoring and dynamic fault diagnosis system for subsea tree | |
| CN108830335A (en) | Photovoltaic plant fault early warning method and system | |
| CN114048790B (en) | Road base strain analysis method based on coupling bidirectional LSTM and convolution structure network | |
| CN112906957A (en) | BP neural network coal conveying fault prediction method based on genetic algorithm optimization | |
| AU2021105665A4 (en) | Remaining useful life prediction method and system of subsea christmas tree system based on digital twin | |
| CN113705095B (en) | Digital twin modeling method for circulating water pump | |
| CN111680398B (en) | Single machine performance degradation prediction method based on Holt-windows model | |
| CN115877312A (en) | Electric energy meter informatization evaluation calibration model based on station area electric energy conservation | |
| CN114741815A (en) | Seabed petroleum pipeline health management method based on digital twinning | |
| CN115877068A (en) | Voltage sag propagation track identification method of regional power grid based on deep learning | |
| CN114648212A (en) | Cloud computing-based ship equipment performance intelligent management system and method | |
| CN113627780A (en) | Integrated digital twin system based on deepwater floating platform state monitoring and evaluation | |
| CN115099129A (en) | Natural gas well yield prediction method based on input characteristic error correction | |
| CN116247807A (en) | Digital twinning-based transformer station cable maintenance monitoring method and system | |
| CN115099464A (en) | Oil well yield prediction method based on choke model flow coefficient prediction |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |