CN117034744A - Offshore floating wind power reliability assessment method and device, equipment and storage medium - Google Patents
Offshore floating wind power reliability assessment method and device, equipment and storage medium Download PDFInfo
- Publication number
- CN117034744A CN117034744A CN202310854093.3A CN202310854093A CN117034744A CN 117034744 A CN117034744 A CN 117034744A CN 202310854093 A CN202310854093 A CN 202310854093A CN 117034744 A CN117034744 A CN 117034744A
- Authority
- CN
- China
- Prior art keywords
- wind power
- reliability
- sample
- offshore wind
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 75
- 238000007667 floating Methods 0.000 title claims abstract description 58
- 238000003860 storage Methods 0.000 title claims abstract description 22
- 238000012423 maintenance Methods 0.000 claims abstract description 167
- 238000011156 evaluation Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 14
- 238000012216 screening Methods 0.000 claims description 13
- 230000002159 abnormal effect Effects 0.000 claims description 11
- 238000004140 cleaning Methods 0.000 claims description 6
- 230000000007 visual effect Effects 0.000 claims description 6
- 230000001364 causal effect Effects 0.000 claims description 3
- 238000012800 visualization Methods 0.000 claims description 3
- 238000007726 management method Methods 0.000 description 77
- 238000004458 analytical method Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 238000012544 monitoring process Methods 0.000 description 6
- 238000012795 verification Methods 0.000 description 5
- 238000004590 computer program Methods 0.000 description 4
- 238000009826 distribution Methods 0.000 description 4
- 238000007476 Maximum Likelihood Methods 0.000 description 3
- 238000012937 correction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000003449 preventive effect Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000011058 failure modes and effects analysis Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 238000013439 planning Methods 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 239000013589 supplement Substances 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000012098 association analyses Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 238000010206 sensitivity analysis Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000007723 transport mechanism Effects 0.000 description 1
- 238000012384 transportation and delivery Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00002—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by monitoring
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/18—Network design, e.g. design based on topological or interconnect aspects of utility systems, piping, heating ventilation air conditioning [HVAC] or cabling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/28—Design optimisation, verification or simulation using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00006—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by information or instructions transport means between the monitoring, controlling or managing units and monitored, controlled or operated power network element or electrical equipment
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
- H02J3/381—Dispersed generators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/08—Probabilistic or stochastic CAD
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/10—Numerical modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/06—Wind turbines or wind farms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
- H02J2300/20—The dispersed energy generation being of renewable origin
- H02J2300/28—The renewable source being wind energy
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computer Hardware Design (AREA)
- Mathematical Analysis (AREA)
- Business, Economics & Management (AREA)
- Algebra (AREA)
- Mathematical Physics (AREA)
- Economics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Computational Mathematics (AREA)
- Fluid Mechanics (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Wind Motors (AREA)
Abstract
The invention discloses a method and a device for evaluating the reliability of offshore floating wind power, equipment and a storage medium, wherein the method comprises the following steps: acquiring sample system data of an offshore wind power system; wherein the sample system data comprises: sample historical operation data, sample fault records and sample operation and maintenance records; inputting the sample historical operation data into a pre-constructed offshore wind power reliability estimation model to perform reliability estimation to obtain reliability estimation information; parameter adjustment is carried out on the offshore wind power reliability estimation model according to the reliability estimation information, the sample fault record and the sample operation and maintenance record; acquiring current system operation data of the offshore wind power system, and inputting the current system operation data into the adjusted offshore wind power reliability estimation model to perform reliability estimation to obtain a reliability estimation result. The method and the device can improve the accuracy of reliability estimation of the offshore wind power system.
Description
Technical Field
The invention relates to the technical field of electric power operation and maintenance, in particular to a method and a device for evaluating reliability of offshore floating wind power, equipment and a storage medium.
Background
Currently, the traditional offshore floating wind power reliability analysis method is mainly realized based on a statistical method and a reliability theory, such as fault mode and effect analysis, failure mode, influence and association analysis, reliability block diagram and the like. These methods rely on a large amount of measured data and expert experience, but in the face of complex offshore wind power systems, there are problems such as insufficient processing of inter-system correlations, which results in lower accuracy in reliability assessment of offshore floating wind power. Based on this, a method capable of improving reliability evaluation accuracy of offshore floating wind power is needed.
Disclosure of Invention
The present invention aims to solve at least one of the technical problems existing in the prior art. Therefore, the invention provides the offshore floating wind power reliability assessment method, which can improve the accuracy of the offshore floating wind power reliability assessment.
The invention further provides an offshore floating wind power reliability assessment device.
The invention further provides electronic equipment.
The invention also provides a computer storage medium.
In a first aspect, an embodiment of the present invention provides an offshore floating wind power reliability assessment method, the method comprising:
Acquiring sample system data of an offshore wind power system; wherein the sample system data comprises: sample historical operation data, sample fault records and sample operation and maintenance records;
inputting the sample historical operation data into a pre-constructed offshore wind power reliability estimation model to perform reliability estimation to obtain reliability estimation information;
parameter adjustment is carried out on the offshore wind power reliability estimation model according to the reliability estimation information, the sample fault record and the sample operation and maintenance record;
acquiring current system operation data of the offshore wind power system, and inputting the current system operation data into the adjusted offshore wind power reliability estimation model to perform reliability estimation to obtain a reliability estimation result.
According to other embodiments of the present invention, the method for evaluating reliability of offshore floating wind power further comprises, after obtaining the sample system data of the wind power system, at least one of:
data cleaning is carried out on the sample system data so as to reject the unqualified sample system data;
performing missing value compensation on the sample system data to patch the missing data into the sample system data;
And correcting the abnormal value of the sample system data to correct the abnormal sample system data.
According to other embodiments of the present invention, before the inputting the sample historical operation data into a pre-constructed offshore wind power reliability estimation model to perform reliability estimation, the method further includes:
the method for constructing the offshore wind power reliability estimation model specifically comprises the following steps:
acquiring association information between two system nodes and state parameters of each system node; wherein the system node comprises any one of the following: the system, the subsystem, the parts and the events; the association information includes: dependency, connection, dependency, causal; the state parameters include: wind, temperature, humidity and running state;
and connecting each system node according to the associated information and the state parameters to construct the offshore wind power reliability estimation model.
According to other embodiments of the present invention, the offshore floating wind power reliability estimation model includes: a failure probability estimation network and a component influence estimation network; the reliability estimation result comprises: reliability prediction indexes, current node prediction influence degree and fault prediction reasons; the step of obtaining current system operation data of the offshore wind power system, inputting the current system operation data into the adjusted offshore wind power reliability estimation model to perform reliability estimation, and obtaining a reliability estimation result, comprises the following steps:
Acquiring current system operation data of the offshore wind power system;
inputting the current system operation data into the failure probability estimation network to perform failure probability estimation, obtaining a current failure estimation probability value, and screening the reliability estimation index from preset candidate reliability indexes according to the current failure estimation probability value;
inputting the current system operation data into the component influence degree estimation network to estimate influence degree, so as to obtain the estimated influence degree of each system node on the current node of the offshore wind power system;
and screening out failure influence estimated nodes from the system nodes according to the current node estimated influence degree, and constructing the failure estimated reasons according to the failure influence estimated nodes and the current node estimated influence degree of the failure influence estimated nodes.
According to other embodiments of the present invention, in the offshore floating wind power reliability assessment method, after the current system operation data of the offshore wind power system is obtained, and the current system operation data is input to the adjusted offshore wind power reliability prediction model to perform reliability prediction, the method further includes:
Performing visualization processing on the reliability estimation result to obtain a reliability estimation view;
performing visual processing on a preset operation and maintenance management decision to obtain an operation and maintenance management view;
and displaying the reliability estimation view and the operation and maintenance management view.
According to other embodiments of the present invention, in the offshore floating wind power reliability assessment method, after the current system operation data of the offshore wind power system is obtained, and the current system operation data is input to the adjusted offshore wind power reliability prediction model to perform reliability prediction, the method further includes:
adjusting the operation and maintenance time period of the operation and maintenance management decision according to the reliability estimated result;
and receiving a policy execution request, and periodically executing the operation and maintenance management decision according to the policy execution request and the operation and maintenance time period.
According to other embodiments of the present invention, in the offshore floating wind power reliability assessment method, after the current system operation data of the offshore wind power system is obtained, and the current system operation data is input to the adjusted offshore wind power reliability prediction model to perform reliability prediction, the method further includes:
Screening a target management operation type from candidate management operation types according to the reliability pre-estimated index;
screening at least one target node management operation and maintenance strategy from candidate node management operation and maintenance strategies according to the target management operation and maintenance type and the fault pre-estimated reason;
and constructing the target management operation and maintenance strategy by at least one target node management operation and maintenance strategy.
In a second aspect, an embodiment of the present invention provides an offshore floating wind power reliability assessment apparatus, the apparatus comprising:
the data acquisition module is used for acquiring sample system data of the offshore wind power system; wherein the sample system data comprises: sample historical operation data, sample fault records and sample operation and maintenance records;
the first reliability evaluation module is used for inputting the sample historical operation data into a pre-constructed offshore wind power reliability estimation model to perform reliability evaluation to obtain reliability estimation information;
the parameter adjustment module is used for carrying out parameter adjustment on the offshore wind power reliability estimation model according to the reliability estimation information, the sample fault record and the sample operation and maintenance record;
the second reliability estimation module is used for acquiring current system operation data of the offshore wind power system, inputting the current system operation data into the adjusted offshore wind power reliability estimation model to perform reliability estimation, and obtaining a reliability estimation result.
In a third aspect, an embodiment of the present application provides an electronic device including:
at least one processor, and,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the offshore floating wind power reliability assessment method of the first aspect.
In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing computer-executable instructions for causing a computer to perform the offshore floating wind power reliability assessment method according to the first aspect.
According to the offshore floating wind power reliability assessment method, device, equipment and storage medium, the offshore wind power reliability prediction model is trained through the sample historical operation data, the sample fault records and the sample operation and maintenance records to obtain the offshore wind power reliability prediction model capable of accurately performing reliability prediction, and then the reliability prediction model is used for performing reliability prediction on the current system operation data to obtain a reliability prediction result so as to improve the accuracy of the reliability prediction of the offshore wind power system.
Additional features and advantages of the application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the application. The objectives and other advantages of the application may be realized and attained by the structure particularly pointed out in the written description and drawings.
Drawings
FIG. 1 is a schematic flow chart of an embodiment of a method for evaluating reliability of offshore floating wind power according to the present application;
FIG. 2 is a schematic flow chart of another embodiment of a method for evaluating reliability of offshore floating wind power in an embodiment of the application;
FIG. 3 is a network topology diagram of a Bayesian network model corresponding to an offshore wind power system in an offshore floating wind power reliability evaluation method in an embodiment of the application;
FIG. 4 is a flowchart of step S104 in FIG. 1;
FIG. 5 is a schematic flow chart of another embodiment of a method for evaluating reliability of offshore floating wind power in an embodiment of the application;
FIG. 6 is a schematic flow chart of another embodiment of a method for evaluating reliability of offshore floating wind power in an embodiment of the application;
FIG. 7 is a schematic flow chart of another embodiment of a method for evaluating reliability of offshore floating wind power in an embodiment of the application;
FIG. 8 is a block diagram of an embodiment of an offshore floating wind power reliability assessment device in accordance with an embodiment of the present invention;
FIG. 9 is a block diagram of an embodiment of an electronic device in accordance with an embodiment of the present invention.
Detailed Description
The conception and the technical effects produced by the present invention will be clearly and completely described in conjunction with the embodiments below to fully understand the objects, features and effects of the present invention. It is apparent that the described embodiments are only some embodiments of the present invention, but not all embodiments, and that other embodiments obtained by those skilled in the art without inventive effort are within the scope of the present invention based on the embodiments of the present invention.
In the description of the present invention, if an orientation description such as "upper", "lower", "front", "rear", "left", "right", etc. is referred to, it is merely for convenience of description and simplification of the description, and does not indicate or imply that the apparatus or element referred to must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the invention. If a feature is referred to as being "disposed," "secured," "connected," or "mounted" on another feature, it can be directly disposed, secured, or connected to the other feature or be indirectly disposed, secured, connected, or mounted on the other feature.
In the description of the embodiments of the present invention, if "several" is referred to, it means more than one, if "multiple" is referred to, it is understood that the number is not included if "greater than", "less than", "exceeding", and it is understood that the number is included if "above", "below", "within" is referred to. If reference is made to "first", "second" it is to be understood as being used for distinguishing technical features and not as indicating or implying relative importance or implicitly indicating the number of technical features indicated or implicitly indicating the precedence of the technical features indicated.
Noun interpretation:
offshore floating wind power: the basic principle of the offshore floating wind power is that a wind driven generator is hung on a buoy or a semi-submersible platform and floats along with waves, so that wind energy is converted into electric energy. Compared with the traditional fixed offshore wind power, the offshore floating wind power has the following advantages: 1. the adaptability is strong; 2. the installation is convenient; 3. higher efficiency, 4 and small environmental impact.
Bayesian network model: is a probabilistic graphical model that describes random events by representing the dependency between variables and the conditional probability density. Bayesian networks are widely used in the fields of machine learning, artificial intelligence, decision analysis, and the like. The basic idea of the bayesian network model is to consider variables as nodes in a directed acyclic graph, each node representing a variable, directed edges representing dependency relationships and conditional probability distributions between the variables. These dependencies can be represented by conditional independence of the graph. By means of a bayesian network model, it is possible to learn the dependency relationships and conditional probability distributions between variables and to calculate the probability distributions of other variables given some observations.
Maximum likelihood estimation: the method is a commonly used parameter estimation method in probability statistics, and the basic idea is to find proper parameter values on the premise of knowing some sample observed values so as to maximize the occurrence probability of the observed values.
Bayesian estimation: the method is a parameter estimation method based on the Bayesian theorem and is used for estimating posterior distribution of model parameters under the conditions of prior experimental knowledge and observed data.
With the increasing environmental awareness and the increasing energy demand, offshore floating wind power is widely focused and applied as an emerging clean energy form. The offshore floating wind power system consists of a floating platform, a wind power generator set, a cable system, a converter and the like. It works in complex marine environments, facing various reliability risks such as storms, corrosion, electrical faults, etc. Therefore, in order to ensure high reliability and long-term stable operation of the offshore floating wind power system, it is important to perform reliability analysis and evaluation thereof.
In the related art, the offshore floating wind power reliability assessment method is mainly implemented based on a statistical method and a reliability theory, such as Failure Mode and Effect Analysis (FMEA), failure mode, influence and correlation analysis (FMECA), reliability Block Diagram (RBD) and the like. These methods generally rely on a large amount of measured data and expert experience, but when faced with complex wind power systems, they have problems such as insufficient processing of inter-system correlations and low accuracy of reliability predictions for offshore wind power systems. Therefore, a method capable of improving the accuracy of the reliability assessment of offshore floating wind power is needed.
Based on the above, the embodiment of the invention discloses an offshore floating wind power reliability assessment method, which is used for training an offshore wind power reliability estimation model based on sample historical operation data, sample fault records and sample operation and maintenance records to obtain the offshore wind power reliability estimation model capable of accurately estimating the reliability. And then reliability estimation is carried out on the current system operation data through the offshore wind power reliability estimation model to obtain a reliability estimation result so as to improve the accuracy of offshore wind power reliability estimation.
Referring to fig. 1, a flow diagram of a method for evaluating reliability of offshore floating wind power in an embodiment of the invention is shown. It specifically includes steps but is not limited to including steps S101 to S104:
step S101, acquiring sample system data of an offshore wind power system; wherein the sample system data comprises: sample historical operation data, sample fault records and sample operation and maintenance records;
step S102, inputting sample historical operation data into a pre-constructed offshore wind power reliability estimation model for reliability estimation to obtain reliability estimation information;
step S103, parameter adjustment is carried out on the offshore wind power reliability estimation model according to the reliability estimation information, the sample fault records and the sample operation and maintenance records;
Step S104, current system operation data of the offshore wind power system are obtained, and the current system operation data are input into the adjusted offshore wind power reliability estimation model to carry out reliability estimation, so that a reliability estimation result is obtained.
In steps S101 to S104 of the present embodiment, by acquiring the sample historical operation data, the sample fault record and the sample operation and maintenance record, and training the offshore wind power reliability prediction model according to the sample historical operation data, the sample fault record and the sample operation and maintenance record, so as to obtain an offshore wind power reliability prediction model with accurate reliability prediction, when in use, the current system operation data of the offshore wind power system is input into the offshore wind power reliability prediction model to perform reliability prediction, so as to obtain a more accurate reliability prediction result, and facilitate operation and management by operation and maintenance personnel according to the reliability prediction result with higher accuracy, and improve the stability of the offshore wind power system.
In step S101 of some embodiments, measurement data is obtained by measuring an offshore wind power system in real time, that is, historical operation data is obtained by collecting operation data of each subsystem and components under the subsystems in the offshore wind power system, and the historical operation data is stored in a preset database to obtain sample historical operation data. And when each fault occurs, recording operation data storage at the moment of the fault, and recording the fault reason and the fault condition to obtain a sample fault record. Meanwhile, operation and maintenance can be performed when faults occur, and operation and maintenance can be performed when faults do not occur. And when operation and maintenance are performed each time, recording historical operation data of the offshore wind power system during operation and maintenance to store the historical operation data into a database to obtain sample historical operation data, and storing the operation and maintenance records into the database. Wherein the sample historical operating data comprises: wind speed, wind direction, temperature, humidity, unit running state, sample fault record includes: fault occurrence time and fault type, and the sample operation and maintenance record comprises: operation and maintenance processing time and operation and maintenance strategies. The database comprises: the system comprises a database of a monitoring system and a maintenance record database, wherein the monitoring system is used for acquiring the running state of the offshore wind power system to obtain historical running data, the historical running data are stored in the database of the monitoring system to obtain sample historical data, and fault records and operation and maintenance records are stored in the maintenance record database to obtain sample fault records and sample operation and maintenance records. Therefore, when offshore wind power reliability estimation model training is needed, sample historical operation data are directly extracted from a database of the monitoring system, and sample fault records and sample operation and maintenance records are extracted from a maintenance record database, so that sample system data of an offshore wind power system are easy to extract.
After step S101, the offshore floating wind power reliability assessment method further includes:
sample system data is screened to filter unacceptable sample system data.
The method is characterized in that the historical operation data of the samples, the fault records of the samples and the operation and maintenance records of the samples are screened to select data meeting the use requirement of the offshore wind power reliability estimation model. The data arrangement and pretreatment comprises any one of the following steps: data cleansing, outlier processing, and missing value processing, and the specific manner of data processing and preprocessing is not particularly limited.
Wherein, screening the sample system data may include at least one of:
step S1, data cleaning is carried out on sample system data so as to reject unqualified sample system data;
step S2, carrying out missing value compensation on the sample system data so as to supplement the missing data into the sample system data;
and S3, carrying out abnormal value correction on the sample system data so as to correct the abnormal sample system data.
In step S1 of some embodiments, data cleaning is performed on the sample system data, that is, data cleaning is performed on the sample historical operation data, the sample fault record and the sample operation and maintenance record, and unreasonable data in the sample historical operation data, the sample fault record and the sample operation and maintenance record is cleaned, so as to extract unreasonable sample historical operation data, sample fault record and sample operation and maintenance record. The sample historical operation data, the sample fault record and the sample operation and maintenance record are possibly abnormal by the monitoring system, so that the abnormal monitoring system collects the unreasonable sample historical operation data, the sample fault record and the sample operation and maintenance record.
In step S2 of some embodiments, in order to perform offshore wind power reliability assessment, time-continuous sample historical operational data, sample fault records, and sample operational dimension records need to be taken. If the sample historical operation data, the sample fault record and the sample operation and maintenance record collected by a certain time node have gaps, the accuracy of the offshore floating wind power reliability assessment can be affected. Thus, the data is supplemented by missing sample historical operational data, sample fault records, and sample operational dimension records. The method comprises the steps of supplementing missing data in sample historical operation data, sample fault records and sample operation and maintenance records through interpolation or curve fitting methods so as to obtain continuous sample historical operation data, sample fault records and sample operation and maintenance records.
In step S3 of some embodiments, if abnormal values exist in the sample historical operation data, the sample fault record and the sample operation and maintenance record, data correction is required to be performed on the abnormal sample historical operation data, the sample fault record and the sample operation and maintenance record, so as to obtain sample system data meeting the requirements of the subsequent offshore wind power reliability estimation model construction and parameter learning.
At least one of steps S1 to S3 illustrated in the present embodiment is performed by performing at least one of the following operations on the sample history operation data, the sample failure record, the sample operation and maintenance record: in data cleaning, missing supplement and abnormal value correction, more reasonable and continuous sample historical operation data, sample fault records and sample operation and maintenance records are constructed, so that data meeting the reliability prediction requirement of a subsequent offshore wind power reliability prediction model is obtained, and a more accurate offshore wind power reliability prediction model for reliability prediction is constructed.
In some embodiments, prior to step S102, the offshore floating wind power reliability assessment method further comprises:
and constructing an offshore wind power reliability estimation model.
When the offshore wind power reliability estimation model is constructed, the offshore wind power reliability estimation model is constructed by relying on the correlation relationship between different components in the offshore wind power system in expert experience, so that a more accurate offshore wind power reliability estimation model is constructed. The selection and connection relation of the nodes in the offshore wind power reliability estimation model are optimized through expert experience, and the appropriate offshore wind power reliability estimation model is constructed by considering the mutual relevance among different components in the offshore wind power system.
Referring to FIG. 2, in some embodiments, constructing an offshore wind reliability estimation model may include, but is not limited to, steps S201 through S202:
step S201, obtaining association information between two system nodes and state parameters of each system node; wherein, the system node includes any one of the following: systems, subsystems, components, and events; the association information includes: dependency, connection, dependency; the state parameters include: custom, temperature, moderate, running status;
step S202, each system node is connected according to the associated information and the state parameters, so that an offshore wind power reliability estimation model is constructed.
In step S201 of some embodiments, an association relationship between two system nodes and a state parameter of each system node are acquired, and the association relationship of the system nodes is determined according to expert experience. The system nodes represent the components or events of the system, the subsystem and the subsystem, the association relationship represents the probability dependency relationship among the system nodes, and the events comprise fault events and failure reasons. And selecting proper system nodes, connection relations of the system nodes and state parameters according to the subordinate relations among the systems, the subsystems and the parts in expert experience. The connection relation between the system nodes is an AND gate or OR gate, which respectively correspond to a series system and a parallel system. The parts of the subsystem comprise different components of the wind power system, and the components comprise: fan, converter, cable, gear box, generator etc. and the associated information includes: the state parameters include: the degree of wind, temperature, humidity, and operation state, and the content of the state parameters is not particularly limited. For example, if the acquisition system node includes: the system comprises a supporting structure, a pitch system, a gear box, a generator and an auxiliary system, and the causal relationship, the dependency relationship and the state parameters of each system node are acquired.
In step S202 of some embodiments, each system node is contacted according to the association information and the state parameter, so as to construct a connection relationship between systems to obtain an offshore wind power reliability estimation model. The marine wind power reliability estimation model is a Bayesian network model, the Bayesian network model is a core tool for reliability analysis, and the Bayesian network model is a probability graph model capable of representing probability dependency relations among variables and carrying out uncertainty inference through probability reasoning. Therefore, the dependency relationship between each system node is connected through matrix logic operation to form a Bayesian network model, and the topological structure of the Bayesian network model can reflect the mutual relevance among different components in the offshore wind power system, so that reliability analysis and evaluation can be conveniently carried out through the Bayesian network model.
For example, referring to fig. 3, fig. 3 is a network topology diagram of a bayesian network model corresponding to the offshore wind turbine system, and the offshore wind turbine system in fig. 3 includes: support structure, pitch system, gear box, generator and auxiliary system, and S1 represents support structure, S2 represents the pitch system, S3 represents the gear box, S4 represents the generator, S5 represents speed governing system, S6 represents other electronic device, S7 is the blade, S8 is auxiliary system, axx represents the fault event, bxx represents the cause of failure. Therefore, the system nodes are associated according to the association information of the system nodes, and the operation data of each system node is set according to the state parameters so as to construct the Bayesian network model. The Bayesian network model after the operation data of each system node is modified can display the corresponding probability value in each fault event and failure reason so as to realize the reliability estimation of the offshore wind power system, and the reliability estimation of the offshore wind power system is more accurate.
In the steps S201 to S202 illustrated in the present embodiment, after the association information and the state parameters of the system node are obtained through expert experience, a connection relationship is set up for the system node according to the association information of the system node, and then the operation data of the system node is input according to the state parameters to obtain a bayesian network model, so that the correlation between different components in the offshore wind power system can be reflected through the topological structure of the bayesian network model, so that reliability analysis and evaluation can be made through the bayesian network model.
After the offshore wind power reliability estimation model is built, in step S102 of some embodiments, the sample historical operation data is input into the offshore wind power reliability estimation model, and reliability estimation is performed on the sample historical operation data through the wind power reliability estimation model to obtain reliability estimation information. The sample historical operation data is the sample historical operation data of each system node and comprises historical operation parameters of a plurality of time nodes, so that the reliability estimated information is estimated data of the corresponding time nodes and is characterized by a sequence. The sample fault records and sample operational records are also represented in a sequence and are the fault states and operational states at a plurality of time nodes for each system component. The reliability estimation information comprises: the estimated probability value of the failure of the sample and the estimated influence of the sample assembly are calculated, and the estimated influence of the sample assembly is the influence degree of the system node on the failure. Therefore, the estimation accuracy of the offshore wind power reliability estimation model can be judged through the sample failure estimation probability value and the sample assembly estimation influence degree.
Specifically, the offshore wind power reliability estimation model is a bayesian network model, and a formula for calculating the failure probability of the bayesian network model is shown as a formula (1):
wherein X is i For sample history run data at the i-th time, P (X 1 ,X 2 ,...,X n ) And estimating a probability value for the sample failure. Therefore, by constructing the Bayesian network model, the probability value of each fault event and failure cause can be obtained only by setting the operation data of each system node so as to perform reliability estimation of the offshore wind power system and provide reliability estimationAnd the result is used as a reference for operation and maintenance personnel, the offshore wind power system is maintained according to the reliability estimation result, and the stability of the offshore wind power system is improved.
After the reliability estimation information calculation is completed, in step S103 of some embodiments, the sample fault record and the sample operation and maintenance record are subjected to numerical conversion to obtain a sample failure verification probability value of the system and a sample component verification influence degree of each system component, where the sample component verification influence degree and the sample component estimation influence degree are expressed by percentages. And carrying out loss calculation on the sample failure verification probability value, the sample failure prediction probability value, the sample component verification influence degree and the sample component prediction influence degree to obtain loss data, and adjusting parameters of the offshore wind power reliability prediction model according to the loss data so as to realize parameter learning of the offshore wind power reliability prediction model until the loss data is converged. In addition, the parameters of the offshore wind power reliability estimation model can be estimated by adopting methods such as maximum likelihood estimation, bayesian estimation and the like according to the failure estimation probability value of the sample and the estimated influence degree of the sample assembly, so as to construct the offshore wind power reliability estimation model with more accurate reliability estimation.
After parameter learning of the offshore wind power reliability estimation model is completed, reliability analysis and estimation are needed to be carried out by adopting the offshore wind power reliability estimation model after parameter learning based on current system operation data, so that a reliability estimation result is calculated and provided for operation and maintenance personnel to serve as reference data of an offshore wind power system. The reliability estimated result output by the offshore wind power reliability estimated model in the actual use process is only a reference result, and is not the reliability of a real offshore wind power system, and the reliability estimated result is used as reliability reference data of the offshore wind power system.
In some embodiments, the offshore wind power reliability estimation model comprises: a failure probability estimation network and a component influence estimation network; the reliability estimation result comprises the following steps: reliability prediction indexes, current node prediction influence degree and fault prediction reasons.
The marine wind power reliability estimation model is a Bayesian network model, and the Bayesian network model can estimate the failure probability of the marine wind power system and the influence degree of each system node on the system failure, so as to determine a reliability estimation index according to the failure probability, and determine a failure estimation reason causing the failure according to the influence degree of the system node on the system failure. The reliability prediction index, the current node prediction influence degree and the fault prediction reason are output through a Bayesian network model to serve as reference data of the reliability of the offshore wind power system, and serve as reference data of potential risks and fault propagation paths of the offshore wind power system.
Referring to fig. 4, step S104 may include, but is not limited to, steps S401 to S404:
step S401, current system operation data of an offshore wind power system are obtained;
step S402, inputting current system operation data into a failure probability estimation network to perform failure probability estimation, obtaining a current failure estimation probability value, and screening a reliability estimation index from preset candidate reliability indexes according to the current failure estimation probability value;
step S403, inputting current system operation data into a component influence degree estimation network to estimate influence degree, so as to obtain the estimated influence degree of each system node on the current node of the offshore wind power system;
and step S404, screening out failure influence estimated nodes from the system nodes according to the current node estimated influence degree, and constructing failure estimated reasons according to the failure influence estimated nodes and the current node estimated influence degree of the failure influence estimated nodes.
In step S401 of some embodiments, in the parameter learning process of the offshore wind power reliability estimation model, sample historical operation data needs to be collected. When the reliability estimation model is actually used for reliability estimation after parameter learning of the offshore wind power reliability estimation model is completed, current system operation data of the offshore wind power system are collected in real time, the current system operation data can be system operation data of a pre-set time period, but the duration of the pre-set time period is generally set within 3 days so as to make reliability estimation of the offshore wind power system in real time, and reliability references of the offshore wind power system can be provided for operation and maintenance personnel. The current system operation data comprises: wind speed, temperature, unit running state and the like, and the current system running data is used as an input node of the offshore wind power reliability estimation model so as to facilitate the reliability estimation of the offshore wind power system.
In step S402 of some embodiments, the failure probability estimating network is a part of the network for performing failure probability prediction in the bayesian network model, and a specific formula of the failure probability estimating network is shown in formula (1), which is not described herein. The current system operation data is input into a failure probability prediction network to perform failure probability prediction to obtain a current failure prediction probability value of the offshore wind power system, and the reliability prediction index is screened out from the candidate reliability indexes according to the current failure prediction probability value. For example, if the candidate reliability index includes: the method has the advantages that the method is low, medium, good and excellent, the current failure probability estimated value is inversely proportional to the candidate reliability index, if the candidate reliability index is screened out to be low according to the current failure estimated probability value, the output reliability estimated index is low, and the reliability estimated index can be directly used as reference data of the offshore wind power system according to the reliability estimated index so as to manage and operate the offshore wind power system.
In step S403 of some embodiments, the bayesian network model further includes an impact prediction network, and the impact prediction network performs sensitivity analysis, that is, predicts the impact degree of each system node in the offshore wind power system on the failure. Therefore, the influence degree estimation network is used for estimating the influence degree of the current system operation data so as to estimate the influence degree of each system node on failure to obtain the estimated influence degree of the current node.
In step S404 of some embodiments, which are system nodes affecting failure may be determined according to the estimated influence of the current node, so that the failure influence estimated node is selected from the system nodes according to the estimated influence of the current node, the estimated influence of the current node of the failure influence estimated node is also obtained as the estimated influence of the target node, and the estimated influence of the failure influence estimated node and the estimated influence of the target node are combined to form a failure estimated cause as a potential reference cause for causing the failure of the offshore wind power system, so that the failure estimated cause is used as reference data for making operation and maintenance management and maintenance decision of the subsequent offshore wind power system. And selecting failure influence estimated nodes from the system nodes according to the estimated influence degree of the current nodes, sorting the system nodes from large to small according to the estimated influence degree of the current nodes, acquiring the system nodes with preset numbers before sorting as the failure influence estimated nodes, and extracting the system nodes with high failure influence degree as the failure influence estimated nodes.
In steps S401 to S404 illustrated in this embodiment, the current failure prediction probability value and the current node prediction influence degree are calculated based on the current system operation data, so as to determine a reliability prediction index according to the current failure prediction probability value, and then determine a failure prediction reason according to the current node prediction influence degree, so that the reliability prediction index and the failure prediction reason are used as reference data for operation and maintenance management of the offshore wind power system, so that more optimal operation and maintenance management and maintenance can be conveniently performed, and stability of the offshore wind power system is improved.
In some embodiments, after the bayesian network model completes outputting the reliability estimation result, the reliability estimation result needs to be displayed to an operation and maintenance person, so that the operation and maintenance person can intuitively know the situation that the offshore wind power system may fail.
Referring to fig. 5, after step S104, the offshore floating wind power reliability assessment method may further include, but is not limited to, steps S501 to S503:
step S501, carrying out visualization processing on the reliability estimation result to obtain a reliability estimation view;
step S502, carrying out visual processing on a preset operation and maintenance management decision to obtain an operation and maintenance management view;
step S503, displaying the reliability estimation view and the operation and maintenance management view.
In step S501 and step S502 in some embodiments, the reliability prediction result and the operation and maintenance management decision may be output in a visual manner, or the reliability prediction result and the operation and maintenance management decision may be output in a reporting manner, and the manner of outputting the reliability prediction result and the operation and maintenance management decision is not particularly limited.
In the steps S501 to S503 illustrated in the present embodiment, the reliability prediction result is visualized to obtain a reliability prediction view, and the operation and maintenance management decision is visualized to obtain an operation and maintenance management view, so that the reliability prediction result and the operation and maintenance management decision are output to the operation and maintenance personnel through a visual interface mode, and then the operation and maintenance personnel can directly make corresponding policy execution according to the output result, so as to improve the automatic operation and maintenance management of the offshore wind power system, and improve the reliability and availability of the offshore wind power system.
After the bayesian network model completes the output of the reliability estimation result, operation and maintenance adjustment needs to be further carried out. In this embodiment, the operation and maintenance means is periodic operation and maintenance to stabilize the offshore wind power system. However, the operation and maintenance management decision is preset in the regular operation and maintenance implementation, so that the operation and maintenance time period needs to be determined, and the operation and maintenance management decision is executed in the operation and maintenance time period, so that the stability of the offshore wind power system is higher, and the service life is prolonged.
Referring to fig. 6, in some embodiments, after step S104, the offshore floating wind power reliability assessment method may further include, but is not limited to, steps S601 to S602:
step S601, adjusting the operation and maintenance time period of a preset operation and maintenance management decision according to the reliability estimation result;
step S602, a policy execution request is received, and an operation and maintenance management decision is executed periodically according to the policy execution request and the operation and maintenance time period.
The reliability estimated result can be used as a reference for operation and maintenance management and maintenance decision of the offshore wind power system. In step S601 of some embodiments, an operation and maintenance time period of the operation and maintenance management decision is adjusted according to the reliability pre-estimation result, that is, the time when the offshore wind power system has failure is adjusted according to the reliability pre-estimation result of the current offshore wind power system, and the operation and maintenance time period is set according to the possible failure time, so as to improve the reliability and availability of the offshore wind power system to the maximum extent, reduce the failure of the offshore wind power system, further reduce the maintenance cost and prolong the service life of the offshore wind power system.
In step S602 of some embodiments, since the operation and maintenance management decision is preset, and the reliability estimation result and the operation and maintenance management decision are output in a visual manner, the operation and maintenance personnel can select the corresponding operation and maintenance management decision to execute to obtain the policy execution request based on the visualized reliability estimation result and operation and maintenance management decision. Judging whether the current time reaches an operation and maintenance time period or not according to the strategy execution request, namely judging whether the current time is out of a window period for operation and maintenance or not, so that operation and maintenance management decisions are executed before the offshore wind power system fails, automation of operation and maintenance management decisions is carried out, manual operation is not needed, operation and maintenance management accuracy of the offshore wind power system can be guaranteed, and reliability and availability of the offshore wind power system are improved. Wherein performing the operation and maintenance management decision comprises at least one of: preventive maintenance, repairing faults, updating spare parts, adjusting operation and maintenance plans, and specific content of operation and maintenance management decisions is not limited.
In addition, if the policy execution request is automatic execution, the operation and maintenance management decision is executed regularly according to the adjusted operation and maintenance time period. If the strategy execution request is immediate execution, the operation and maintenance management decision is directly executed so as to prevent the execution of the operation and maintenance management decision from being manually interfered when the automatic execution fails, thereby improving the reliability of the offshore wind power system.
In steps S601 to S602 illustrated in this embodiment, by adjusting the operation and maintenance time period of the operation and maintenance management decision, when automatic execution is required, a policy execution request is received, so that the operation and maintenance management decision is executed periodically according to the operation and maintenance time period of the adjustment week, so as to improve the reliability and availability of the offshore wind power system.
Referring to fig. 7, in some embodiments, after step S104, the offshore floating wind power reliability assessment method may further include, but is not limited to, steps S701 to S703:
step S701, screening out a target management operation type from candidate management operation types according to the reliability pre-estimated index;
step S702, at least one target node management operation and maintenance strategy is screened out from candidate node management operation and maintenance strategies according to the target management operation and maintenance type and the failure prediction reason;
step S703, constructing at least one target node management operation policy into a target management operation policy.
In step S701 of some embodiments, the candidate management operation type includes: periodic inspection, preventive maintenance, fault diagnosis, maintenance planning, and the like. And after the reliability pre-estimated index is determined, screening the target management operation and maintenance type from the candidate management operation and maintenance types directly according to the reliability pre-estimated index so as to determine that the corresponding management operation and maintenance type is adopted under different reliability degrees, so that operation and maintenance management can be performed pertinently.
After the target management operation and maintenance type is determined, in step S702 of some embodiments, candidate node management operation and maintenance policies corresponding to the failure prediction reason are screened out from the same target management operation and maintenance type to obtain at least one target node management operation and maintenance policy, so as to obtain more accurate node management operation and maintenance policies.
In step S703 of some embodiments, at least one target node management operation and maintenance policy is combined to form a target management operation and maintenance policy, so as to implement automatic formulation of the management operation and maintenance policy, and an operation and maintenance policy conforming to the failure condition of the current offshore wind power system can be executed, so as to improve reliability and availability of the offshore wind power system.
In steps S701 to S703 illustrated in this embodiment, after the management operation type is determined, an operation and maintenance management decision conforming to the failure prediction reason is selected from the same management operation and maintenance type as the management operation and maintenance policy of each system node. And then combining the management operation and maintenance strategies of the plurality of system nodes to form an operation and maintenance management decision of the whole offshore wind power system so as to obtain the operation and maintenance management decision meeting the fault reason and reliability conditions, and executing the self-defined operation and maintenance management decision can improve the reliability and availability of the offshore wind power system, thereby prolonging the service life of the offshore wind power system.
An offshore floating wind power reliability assessment method according to an embodiment of the present invention will be described in detail with reference to fig. 1 to 7. It is to be understood that the following description is exemplary only and is not intended to limit the invention in any way.
(1) Collecting and arranging actual measurement data of an offshore wind power system to obtain sample system data and expert experience data; the expert experience data are association information among the system nodes and state parameters of each system node.
(2) The method comprises the steps of constructing an offshore wind power reliability estimation model in the form of a Bayesian network model, wherein the offshore wind power reliability estimation model comprises the selection of system nodes and the establishment of connection relations so as to obtain association relations which can accurately represent sub-systems, parts and events of an offshore wind power system. When the reliability estimation model of the offshore wind power is built, the mutual relevance among different components in the wind power system is determined through expert experience data, so that the system nodes in the Bayesian network model are selected and the connection relation is optimized, and the reliability estimation model capable of accurately representing the offshore wind power system is obtained.
(3) And learning parameters of the Bayesian network model by using sample system data and expert experience data, and estimating the parameters of the Bayesian network model by using a maximum likelihood estimation and Bayesian estimation method to construct the Bayesian network model capable of accurately making reliability estimation of the offshore wind power system.
(4) And (3) carrying out reliability analysis and evaluation according to the Bayesian network model, and collecting current system operation data of the current offshore wind power system. The reliability estimation is carried out on the current system operation data through the Bayesian network model, the reliability estimation comprises the reliability index estimation of the system, the potential risk sources and fault propagation paths and the influence degree of each system node on failure are identified, and the reliability estimation of the offshore wind power system is more comprehensive.
(5) Based on the reliability estimation result, operation and maintenance management and maintenance decision support of the offshore wind power system is provided, wherein the operation and maintenance decision support comprises optimization maintenance planning, spare part management, preventive maintenance strategy, strategy execution period adjustment and the like, so that the reliability and economy of the offshore wind power system are improved.
In summary, the embodiment provides a bayesian network-based offshore floating wind power reliability assessment method, which is used for carrying out parameter learning by constructing a bayesian network model and combining sample historical operation data, so that the reliability of an offshore wind power system is quantitatively assessed and analyzed in uncertainty, and support is provided for operation and maintenance management and maintenance decision. The method can improve the reliability and availability of the offshore wind power system, reduce the maintenance cost, prolong the service life of the system and have practical application value and commercial popularization prospect.
In addition, referring to fig. 8, the embodiment further provides an offshore floating wind power reliability assessment device, which can implement the above offshore floating wind power reliability assessment method, and the offshore floating wind power reliability assessment device includes:
the data acquisition module 801 is used for acquiring sample system data of the offshore wind power system; wherein the sample system data comprises: sample historical operation data, sample fault records and sample operation and maintenance records;
the first reliability evaluation module 802 is configured to input the sample historical operation data to a pre-constructed offshore wind power reliability estimation model for reliability evaluation, so as to obtain reliability estimation information;
the parameter adjustment module 803 is configured to perform parameter adjustment on the offshore wind power reliability estimation model according to reliability estimation information, a sample fault record, and a sample operation and maintenance record;
the second reliability estimation module 804 is configured to obtain current system operation data of the offshore wind power system, and input the current system operation data to the adjusted offshore wind power reliability estimation model to perform reliability estimation, so as to obtain a reliability estimation result.
The specific implementation of the offshore floating wind power reliability assessment device is basically the same as the specific example of the above-mentioned offshore floating wind power reliability assessment method, and will not be repeated here.
The embodiment of the application also provides electronic equipment, which comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the offshore floating wind power reliability evaluation method when executing the computer program. The electronic equipment can be any intelligent terminal including a tablet personal computer, a vehicle-mounted computer and the like.
Referring to fig. 9, fig. 9 illustrates a hardware structure of an electronic device according to another embodiment, the electronic device includes:
the processor 901 may be implemented by a general purpose CPU (central processing unit), a microprocessor, an application specific integrated circuit (ApplicationSpecificIntegratedCircuit, ASIC), or one or more integrated circuits, etc. for executing related programs to implement the technical solution provided by the embodiments of the present application;
the memory 902 may be implemented in the form of read-only memory (ReadOnlyMemory, ROM), static storage, dynamic storage, or random access memory (RandomAccessMemory, RAM). The memory 902 may store an operating system and other application programs, and when the technical solution provided in the embodiments of the present disclosure is implemented by software or firmware, relevant program codes are stored in the memory 902, and the processor 901 is used to invoke the offshore floating wind power reliability assessment method for executing the embodiments of the present disclosure;
An input/output interface 903 for inputting and outputting information;
the communication interface 904 is configured to implement communication interaction between the device and other devices, and may implement communication in a wired manner (e.g. USB, network cable, etc.), or may implement communication in a wireless manner (e.g. mobile network, WIFI, bluetooth, etc.);
a bus 905 that transfers information between the various components of the device (e.g., the processor 901, the memory 902, the input/output interface 903, and the communication interface 904);
wherein the processor 901, the memory 902, the input/output interface 903 and the communication interface 904 are communicatively coupled to each other within the device via a bus 905.
The embodiment of the application also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program realizes the offshore floating wind power reliability evaluation method when being executed by a processor.
The memory, as a non-transitory computer readable storage medium, may be used to store non-transitory software programs as well as non-transitory computer executable programs. In addition, the memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory optionally includes memory remotely located relative to the processor, the remote memory being connectable to the processor through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The above described apparatus embodiments are merely illustrative, wherein the units illustrated as separate components may or may not be physically separate, i.e. may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
Those of ordinary skill in the art will appreciate that all or some of the steps, systems, and methods disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as known to those skilled in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by a computer. Furthermore, as is well known to those of ordinary skill in the art, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media.
The embodiments of the present invention have been described in detail with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge of one of ordinary skill in the art without departing from the spirit of the present invention. Furthermore, embodiments of the invention and features of the embodiments may be combined with each other without conflict.
Claims (10)
1. An offshore floating wind power reliability assessment method, comprising:
acquiring sample system data of an offshore wind power system; wherein the sample system data comprises: sample historical operation data, sample fault records and sample operation and maintenance records;
inputting the sample historical operation data into a pre-constructed offshore wind power reliability estimation model to perform reliability estimation to obtain reliability estimation information;
parameter adjustment is carried out on the offshore wind power reliability estimation model according to the reliability estimation information, the sample fault record and the sample operation and maintenance record;
acquiring current system operation data of the offshore wind power system, and inputting the current system operation data into the adjusted offshore wind power reliability estimation model to perform reliability estimation to obtain a reliability estimation result.
2. The method of claim 1, wherein after obtaining sample system data for a wind power system, the method further comprises at least one of:
data cleaning is carried out on the sample system data so as to reject the unqualified sample system data;
performing missing value compensation on the sample system data to patch the missing data into the sample system data;
and correcting the abnormal value of the sample system data to correct the abnormal sample system data.
3. The method of claim 1, wherein before the inputting the sample historical operating data into a pre-constructed offshore wind power reliability prediction model for reliability assessment, the method further comprises:
the method for constructing the offshore wind power reliability estimation model specifically comprises the following steps:
acquiring association information between two system nodes and state parameters of each system node; wherein the system node comprises any one of the following: the system, the subsystem, the parts and the events; the association information includes: dependency, connection, dependency, causal; the state parameters include: wind, temperature, humidity and running state;
And connecting each system node according to the associated information and the state parameters to construct the offshore wind power reliability estimation model.
4. A method according to claim 3, wherein the offshore wind power reliability estimation model comprises: a failure probability estimation network and a component influence estimation network; the reliability estimation result comprises: reliability prediction indexes, current node prediction influence degree and fault prediction reasons; the step of obtaining current system operation data of the offshore wind power system, inputting the current system operation data into the adjusted offshore wind power reliability estimation model to perform reliability estimation, and obtaining a reliability estimation result, comprises the following steps:
acquiring current system operation data of the offshore wind power system;
inputting the current system operation data into the failure probability estimation network to perform failure probability estimation, obtaining a current failure estimation probability value, and screening the reliability estimation index from preset candidate reliability indexes according to the current failure estimation probability value;
inputting the current system operation data into the component influence degree estimation network to estimate influence degree, so as to obtain the estimated influence degree of each system node on the current node of the offshore wind power system;
And screening out failure influence estimated nodes from the system nodes according to the current node estimated influence degree, and constructing the failure estimated reasons according to the failure influence estimated nodes and the current node estimated influence degree of the failure influence estimated nodes.
5. The method according to any one of claims 1 to 4, wherein after the obtaining current system operation data of the offshore wind power system and inputting the current system operation data into the adjusted offshore wind power reliability estimation model to perform reliability estimation, the method further comprises:
performing visualization processing on the reliability estimation result to obtain a reliability estimation view;
performing visual processing on a preset operation and maintenance management decision to obtain an operation and maintenance management view;
and displaying the reliability estimation view and the operation and maintenance management view.
6. The method according to any one of claims 1 to 4, wherein after the obtaining current system operation data of the offshore wind power system and inputting the current system operation data into the adjusted offshore wind power reliability estimation model to perform reliability estimation, the method further comprises:
Adjusting the operation and maintenance time period of a preset operation and maintenance management decision according to the reliability estimated result;
and receiving a policy execution request, and periodically executing the operation and maintenance management decision according to the policy execution request and the operation and maintenance time period.
7. The method according to claim 4, wherein after the obtaining the current system operation data of the offshore wind power system and inputting the current system operation data into the adjusted offshore wind power reliability estimation model to perform reliability estimation, the method further comprises:
screening a target management operation type from candidate management operation types according to the reliability pre-estimated index;
screening at least one target node management operation and maintenance strategy from candidate node management operation and maintenance strategies according to the target management operation and maintenance type and the fault pre-estimated reason;
and constructing the target management operation and maintenance strategy by at least one target node management operation and maintenance strategy.
8. An offshore floating wind power reliability assessment device, the device comprising:
the data acquisition module is used for acquiring sample system data of the offshore wind power system; wherein the sample system data comprises: sample historical operation data, sample fault records and sample operation and maintenance records;
The first reliability evaluation module is used for inputting the sample historical operation data into a pre-constructed offshore wind power reliability estimation model to perform reliability evaluation to obtain reliability estimation information;
the parameter adjustment module is used for carrying out parameter adjustment on the offshore wind power reliability estimation model according to the reliability estimation information, the sample fault record and the sample operation and maintenance record;
the second reliability estimation module is used for acquiring current system operation data of the offshore wind power system, inputting the current system operation data into the adjusted offshore wind power reliability estimation model to perform reliability estimation, and obtaining a reliability estimation result.
9. An electronic device, the electronic device comprising:
at least one processor, and,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the offshore floating wind power reliability assessment method of any one of claims 1 to 7.
10. A computer-readable storage medium storing computer-executable instructions for causing a computer to perform the offshore floating wind power reliability assessment method according to any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310854093.3A CN117034744A (en) | 2023-07-12 | 2023-07-12 | Offshore floating wind power reliability assessment method and device, equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310854093.3A CN117034744A (en) | 2023-07-12 | 2023-07-12 | Offshore floating wind power reliability assessment method and device, equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117034744A true CN117034744A (en) | 2023-11-10 |
Family
ID=88601313
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310854093.3A Pending CN117034744A (en) | 2023-07-12 | 2023-07-12 | Offshore floating wind power reliability assessment method and device, equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117034744A (en) |
-
2023
- 2023-07-12 CN CN202310854093.3A patent/CN117034744A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP3770620B1 (en) | Deterioration estimation device and deterioration estimation method | |
CN109146093B (en) | Power equipment field investigation method based on learning | |
CN112036610A (en) | Intelligent cable early warning platform and early warning method based on big data analysis | |
JP7079662B2 (en) | Power demand forecasting system, learning device and power demand forecasting method | |
CN113487447A (en) | Power distribution network load prediction and line loss cause analysis method based on big data | |
CN115587672A (en) | Distribution transformer load prediction and heavy overload early warning method and system | |
Fawcett et al. | Markov chain models for extreme wind speeds | |
CN111458661A (en) | Power distribution network line variation relation diagnosis method, device and system | |
Kharlamova et al. | A digital twin of battery energy storage systems providing frequency regulation | |
Wu et al. | Adaptive sequential predictive maintenance policy with nonperiodic inspection for hard failures | |
CN115081647A (en) | Industrial intelligent instrument fault pre-diagnosis method based on Bayesian network model | |
CN102095953B (en) | A kind of performance of accumulator charger online test method | |
CN117592975A (en) | Operation and maintenance decision processing method and system for electromechanical equipment of expressway based on cloud computing | |
CN117669960A (en) | New energy power prediction method based on multivariable meteorological factors | |
CN117350897A (en) | Method and system for predicting conversion power by considering air humidity | |
CN117454771A (en) | Mechanical equipment dynamic maintenance decision-making method based on evaluation and prediction information | |
CN117445755A (en) | Cloud computing-based remote monitoring system for batteries of electric vehicle | |
CN112345972A (en) | Power failure event-based power distribution network line transformation relation abnormity diagnosis method, device and system | |
CN117034744A (en) | Offshore floating wind power reliability assessment method and device, equipment and storage medium | |
Lin et al. | Hpt-rl: Calibrating power system models based on hierarchical parameter tuning and reinforcement learning | |
CN115936663A (en) | Maintenance method and device for power system | |
CN113872780A (en) | Fault root cause analysis method, device and storage medium | |
CN117589444B (en) | Wind driven generator gear box fault diagnosis method based on federal learning | |
CN117113157B (en) | Platform district power consumption fault detection system based on artificial intelligence | |
US20230315940A1 (en) | Method and system for monitoring and/or operating a power system asset |
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 |