CN110059872A - A kind of marine wind electric field O&M dispatching method based on status monitoring - Google Patents
A kind of marine wind electric field O&M dispatching method based on status monitoring Download PDFInfo
- Publication number
- CN110059872A CN110059872A CN201910280153.9A CN201910280153A CN110059872A CN 110059872 A CN110059872 A CN 110059872A CN 201910280153 A CN201910280153 A CN 201910280153A CN 110059872 A CN110059872 A CN 110059872A
- Authority
- CN
- China
- Prior art keywords
- maintenance
- offshore wind
- unit
- component
- cost
- 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 60
- 238000012544 monitoring process Methods 0.000 title claims abstract description 46
- 230000005684 electric field Effects 0.000 title abstract 4
- 238000012423 maintenance Methods 0.000 claims abstract description 352
- 230000000694 effects Effects 0.000 claims description 20
- 238000013528 artificial neural network Methods 0.000 claims description 19
- 230000003449 preventive effect Effects 0.000 claims description 12
- 238000006731 degradation reaction Methods 0.000 claims description 11
- 230000015556 catabolic process Effects 0.000 claims description 10
- UONOETXJSWQNOL-UHFFFAOYSA-N tungsten carbide Chemical compound [W+]#[C-] UONOETXJSWQNOL-UHFFFAOYSA-N 0.000 claims description 10
- 238000009826 distribution Methods 0.000 claims description 8
- 238000005457 optimization Methods 0.000 claims description 8
- 238000004088 simulation Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 7
- 230000008439 repair process Effects 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 7
- 230000006399 behavior Effects 0.000 claims description 6
- 238000002360 preparation method Methods 0.000 claims description 4
- 230000009471 action Effects 0.000 claims description 3
- 125000004432 carbon atom Chemical group C* 0.000 claims description 3
- 238000012897 Levenberg–Marquardt algorithm Methods 0.000 claims description 2
- 238000004422 calculation algorithm Methods 0.000 claims description 2
- 238000003062 neural network model Methods 0.000 claims description 2
- 238000010248 power generation Methods 0.000 claims description 2
- 238000004458 analytical method Methods 0.000 abstract description 3
- 230000006866 deterioration Effects 0.000 abstract 2
- 210000005036 nerve Anatomy 0.000 abstract 1
- 230000008859 change Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000009434 installation Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 206010003591 Ataxia Diseases 0.000 description 1
- 206010010947 Coordination abnormal Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 208000028756 lack of coordination Diseases 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000010206 sensitivity analysis Methods 0.000 description 1
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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06313—Resource planning in a project environment
-
- 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
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
- Y02E40/70—Smart grids as climate change mitigation technology in the energy generation sector
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Educational Administration (AREA)
- Wind Motors (AREA)
Abstract
The invention discloses a kind of marine wind electric field O&M dispatching method based on status monitoring.Step: acquisition monitoring data relevant to each offshore wind farm machine group parts deterioration state, and corresponding artificial nerve network model is constructed to predict the remaining life of each machine group parts；Remaining life reliability of each machine group parts of comprehensive analysis after repairing lead time and maintenance behavior economics, construct the effective maintenance cost function of consecutive mean of each machine group parts, and the foundation of maintenance decision is formulated as each machine group parts；State Maintenance threshold value and opportunity maintenance threshold value are set, and the effective maintenance cost of consecutive mean of each machine group parts of building is compared with the two threshold values, to formulate optimal O&M operation plan.The present invention realizes different times to the Maintenance Scheduling of the machine group parts with different deterioration states a series of in marine wind electric field, and reduces the O&M cost of marine wind electric field.
Description
Technical Field
The invention belongs to the technical field of offshore wind farms, and particularly relates to an operation and maintenance scheduling method of an offshore wind farm.
Background
The unique offshore environment presents a significant challenge to the operation and maintenance management of offshore wind farms. Offshore wind turbines operate in dynamic load conditions and harsh natural environments for long periods of time, resulting in high failure risks and complex degradation processes of the wind turbine components. In addition, maintenance operations performed by maintenance teams entering offshore wind farms must be carried out by means of ships or airplanes, and these means of transport are subject to restrictions of offshore weather, so that poor accessibility to the wind farms results in long maintenance waiting times; and the cost of a single transport of these marine vehicles is extremely expensive.
Most of the current operation and maintenance scheduling methods of offshore wind farms still use the experience of onshore wind farms, a strategy of combining post and preventive maintenance is adopted, and maintenance decisions of all unit components are made based on product data (time or reliability) estimated by the manufacturing characteristics and engineering knowledge of the components. However, when making maintenance decisions for the same type of unit components, these product data often do not take into account the degradation characteristics of the individual unit components in the actual wind farm, so that a targeted maintenance plan cannot be made. The current operation and maintenance scheduling method has the problems of insufficient maintenance or excessive maintenance, and the maintenance activities among all the units are lack of coordination and cooperation, so that the high operation and maintenance cost in the offshore wind power plant is caused, and the operation and maintenance cost accounts for 14-30% of the total life cycle cost of the offshore wind power project.
Disclosure of Invention
In order to solve the technical problems in the background art, the invention provides an operation and maintenance scheduling method for an offshore wind farm, which realizes maintenance scheduling of a series of unit components with different degradation states in the offshore wind farm in different periods and reduces the operation and maintenance cost of the offshore wind farm.
In order to achieve the technical purpose, the technical scheme of the invention is as follows:
an offshore wind farm operation and maintenance scheduling method based on state monitoring is disclosed, wherein the offshore wind farm comprises a plurality of offshore wind generating sets, each offshore wind generating set comprises a plurality of set components, and the method comprises the following steps:
(1) collecting monitoring data related to the degradation state of each offshore wind turbine component, and constructing a corresponding artificial neural network model to predict the residual life of each turbine component;
(2) comprehensively analyzing the reliability of the residual service life and the economic performance of maintenance behaviors of each unit component after a maintenance and stock period, constructing a dynamic average effective maintenance cost function of each unit component, and taking the function as a basis for making a maintenance decision of each unit component;
(3) and (3) setting a state maintenance threshold and an opportunity maintenance threshold, and comparing the dynamic average effective maintenance cost function of each unit component constructed in the step (2) with the two thresholds to make an optimal operation and maintenance scheduling plan.
Further, in step (1), the artificial neural network includes:
selecting model parameters, wherein the selected model input parameters are the service lives and a plurality of state monitoring data measured values of the current and previous monitoring moments of the offshore wind turbine component; the selected model output parameter is the service life percentage of the offshore wind turbine component;
constructing a model, wherein the constructed model is a feedforward neural network model with multiple inputs and single output;
and (3) training a model, wherein the used training algorithm is a Levenberg-Marquardt algorithm.
Further, in step (2), the dynamic average effective repair cost function is as follows:
in the above formula, the first and second carbon atoms are,the average effective maintenance cost of the components j in the offshore wind turbine generator is calculated; t is ti,jIs the service life of a member j in an offshore wind turbine unit i; t is tLIn order to maintain the preparation period;representing the predicted value of the residual life of the component j in the offshore wind turbine unit i;the preventive maintenance cost of the component j in the offshore wind turbine generator system i;the maintenance cost of the fault of the component j in the offshore wind turbine generator set i; p (×) represents the probability.
Further, predicted value of residual life of component j in offshore wind turbine generator system iThe distribution of (a) is as follows:
wherein,service life predicted for artificial neural network modelPercent; u. ofp,jAnd σp,jThe average value and the standard deviation of the life percentage prediction error of the artificial neural network model are respectively.
Further, in step (3), the specific process of comparing the dynamic average effective maintenance cost function of each unit component with two thresholds to make an optimal operation and maintenance scheduling plan is as follows:
when the dynamic average effective maintenance cost of the unit component is smaller than the state maintenance threshold value, the residual life reliability, the maintenance cost and the service life of the current unit component are comprehensively measured, the time for executing preventive maintenance behavior after the performance state of the unit component is maintained and stocked is proper, and the state maintenance decision of the unit component is determined;
when the dynamic average effective maintenance cost of the unit component is greater than or equal to the state maintenance threshold and less than the opportunity maintenance threshold, the reliability, the maintenance cost and the working age of the current residual life of the unit component are comprehensively measured, and it is economical to execute maintenance activities together with the unit component for determining the state maintenance decision, and an opportunity maintenance plan of the unit component is made;
when the dynamic average effective maintenance cost of the unit components is greater than the opportunity maintenance threshold, no maintenance action is executed;
the operation and maintenance scheduling plan determined according to the method is subjected to common maintenance activities after the changed maintenance stock period; when all the unit components meeting the conditions execute common maintenance activities after the maintenance and stock period, which indicates that the maintenance period is finished, each unit component continuously runs until the next fault occurs or the dynamic average effective maintenance cost of the unit component at the new monitoring moment is less than the state maintenance threshold value.
Further, in step (3), the status repair threshold and the opportunity repair threshold are set according to experience or simulation experiments.
The method for determining the state maintenance threshold and the opportunity maintenance threshold by adopting the simulation experiment comprises the following steps:
establishing an operation and maintenance scheduling optimization model of the offshore wind power plant as follows:
the above formula is an annual operation and maintenance cost minimization objective function of an offshore wind farm, CE(cc,co) Annual operation and maintenance costs of offshore wind farms, ccAnd coRespectively, a status maintenance threshold and an opportunity maintenance threshold, trAnd tqThe times of starting the q-th maintenance period and the r-th maintenance period are respectively; TC (tungsten carbide)kFor the total operation and maintenance cost, TC, of the offshore wind power plant in a single maintenance cyclek＝TCR+TCC+TCO+CfixedWhen any unit part in the offshore wind power plant fails, a subsequent maintenance plan of the unit part is determined, and subsequent maintenance cost is generatedWherein,is the failure maintenance cost of the component j in the offshore wind turbine unit i,is a binary variable which indicates whether the component j of the unit i has a fault or not, and has a value of 1 or 0,is the fixed cost of entering the offshore wind turbine IiThe number of the wind turbines is a binary variable which indicates whether a maintenance team enters an offshore wind turbine i to execute maintenance activities, the value of the binary variable is 1 or 0, N is the number of the wind turbines, and M is the number of components in each wind turbine; when the average mean effective maintenance cost of a unit component is less than the stateful maintenance threshold, a stateful maintenance plan for the unit component is formulated and a stateful maintenance cost is generatedWherein,is a preventive maintenance cost of the components j in the unit i,is a binary variable which indicates whether a unit component meets the condition for establishing state maintenance or not, and the value of the binary variable is 1 or 0; when the dynamic average effective maintenance cost of the unit component is more than or equal to the state maintenance threshold and less than or equal to the opportunity maintenance threshold, the opportunity maintenance plan of the unit component is determined, and the opportunity maintenance cost is generatedWherein,for preventive maintenance costs of components j in the unit i,is a binary variable which indicates whether a unit component meets the condition for establishing state maintenance or not, and the value of the binary variable is 1 or 0; when a maintenance cycle is initiated, a fixed cost C will be incurred for the operation and maintenance vessel to transport the operation and maintenance team to the offshore wind farmfixed；
The above formula is a maintenance necessity constraint, and means that at most one part of each offshore wind power generation unit has a fault in any maintenance period in the offshore wind power plant;
the above formula is a maintenance capability constraint, meaning that the number of maintenance personnel owned in the offshore wind farm is limited, resulting in a limitation of the working capability to perform maintenance activities during maintenance;
and solving an optimal solution corresponding to the minimization of the annual operation and maintenance cost in the model by simulating the operation parameters of the actual offshore wind farm, wherein the optimal solution is used as a state maintenance threshold value and an opportunity maintenance threshold value.
Adopt the beneficial effect that above-mentioned technical scheme brought:
(1) the invention constructs an artificial neural network model driven by the integration of current and previous monitoring time-based offshore wind turbine component service life and a plurality of state monitoring data, effectively extracts the degradation state of each turbine component in actual operation, thereby providing accurate residual life prediction information for supporting maintenance decision and reducing the fault risk of each offshore wind turbine component;
(2) the invention analyzes the particularity of long and variable maintenance and stocking periods caused by accessibility of an offshore wind farm in different periods, provides a new maintenance basis, namely a dynamic average effective maintenance cost function, is used for making maintenance decisions of all unit components, and effectively reduces the effect influence of accessibility factors on the specific implementation of a determined maintenance plan after the maintenance and stocking periods;
(3) the maintenance and economic relevance among the units in the offshore wind power plant are considered, and the maintenance frequency and the transportation cost of a maintenance team and a transportation tool entering the offshore wind power plant are reduced by carrying out common maintenance activities on a plurality of offshore wind power plant parts at one time;
(4) the invention is simple and convenient to use, has easy data acquisition, does not need other additional equipment cost except the existing facilities and the existing technology of the offshore wind farm, and is feasible and effective in technology and economy;
(5) the method is also suitable for operation and maintenance scheduling of the open sea area, so that the possibility of reliable and economic operation is provided for the future offshore wind farm to challenge the deep sea area.
Drawings
FIG. 1 is an overall flow chart of the present invention;
FIG. 2 is a flow chart embodying the present invention;
FIG. 3 is a diagram of an artificial neural network model architecture based on condition monitoring data according to the present invention;
FIG. 4 is a graph of annual operation and maintenance costs for different combinations of maintenance thresholds in the embodiment;
FIG. 5 is a graph of annual operational costs as a function of repair and stocking periods in an embodiment.
Detailed Description
The technical scheme of the invention is explained in detail in the following with the accompanying drawings.
As shown in fig. 1 and 2, a state monitoring based offshore wind farm operation and maintenance scheduling method includes three modules, wherein the module one is based on the residual life prediction of state monitoring data, the module two is based on the maintenance basis of average effective maintenance cost, and the module three is an opportunity maintenance strategy, which is specifically as follows:
a first module: collecting monitoring data related to the degradation state of each offshore wind turbine component, and constructing a corresponding artificial neural network model to predict the residual life of each turbine component;
and a second module: comprehensively analyzing the reliability of the residual service life and the economic performance of maintenance behaviors of each unit component after a maintenance and stock period, constructing a dynamic average effective maintenance cost function of each unit component, and taking the function as a basis for making a maintenance decision of each unit component;
and a third module: and setting a state maintenance threshold and an opportunity maintenance threshold, and comparing the constructed dynamic average effective maintenance cost of each unit component with the two thresholds to formulate an optimal operation and maintenance scheduling plan.
In this embodiment, the first module may be implemented by the following preferred scheme:
step 1-1: collecting historical fault data of each component in an offshore wind power plant and establishing a database, wherein the database comprises work age values of each component at different monitoring moments and a plurality of state monitoring data related to the degradation state of the component;
step 1-2: dividing available state data into a training set and a verification set, and performing corresponding data processing;
step 1-3: the constructed artificial neural network model of the offshore wind turbine component is shown in fig. 3, the artificial neural network prediction model of each component is trained by using the processed data, and the artificial neural network model with the minimum mean square error of the verification set in the training process is selected as the prediction model of the subsequent wind turbine component; in FIG. 3, ti,jAndis the service life of the current and previous monitoring time of the component j within the unit i,andis the value of the condition monitoring measurement 1 of the component j in the unit i at the current and previous monitoring time,andis the value of the state measurement q of the component j in the unit i at the current and previous monitoring time,the service life percentage of the component j in the unit i at the current monitoring time is shown;
step 1-4: and predicting the service life percentage of each unit component at the current monitoring moment by using the trained artificial neural network model based on the service lives of the unit components at the current and previous monitoring moments and the input values of a plurality of state monitoring data measured values.
In this embodiment, the second module can be implemented by the following preferred scheme:
step 2-1: calculating a residual life prediction value of the unit component at the current monitoring time according to the predicted service life percentage, and estimating uncertainty of the residual life prediction value by using a prediction error of the service life percentage of an artificial neural network model in the training and verification processes;
wherein the working age of the offshore wind turbine component at the current monitoring time is ti,jThe percentage of the service life predicted by the artificial neural network model isAccording to the obtained ANN prediction error set, the average value mu of the ANN service life percentage prediction error can be calculatedp,jAnd standard deviation σp,j. The predicted time to failure of the unit component will beThe predicted value of the remaining service life isAnd the standard deviation of the predicted remaining life will beTherefore, the remaining life of the unit component at the current monitoring moment also follows normal distribution, and the remaining life distributionCan be expressed as follows:
wherein, the prediction error of the service life percentage in the artificial neural network model is assumed to be subject to normal distribution; repeating steps 1-4 and 2-1 as the service life of the unit and the plurality of state monitoring data measurements collected at the new monitoring time are available, and continuously updating the residual life prediction distribution of the unit;
step 2-2: based on the prediction distribution of the residual life of the unit components at the current monitoring moment, comprehensively analyzing the residual life reliability and the maintenance economy of each unit component in a long and variable maintenance and stocking period, and updating the dynamic average effective maintenance cost of each unit component in real time:
in the above formula, the first and second carbon atoms are,the average effective maintenance cost of the components j in the offshore wind turbine generator is calculated; t is ti,jIs the service life of a member j in an offshore wind turbine unit i; t is tLIn order to maintain the preparation period;representing the predicted value of the residual life of the component j in the offshore wind turbine unit i;the preventive maintenance cost of the component j in the offshore wind turbine generator system i;the maintenance cost of the fault of the component j in the offshore wind turbine generator set i; p (×) represents the probability.
In this embodiment, the module three can be implemented by adopting the following preferred scheme:
step 3-1: the preset state maintenance threshold and the opportunity maintenance threshold can be obtained in a simulation mode;
step 3-2: comparing the updated average effective maintenance cost of each unit component with a preset state maintenance threshold value and an opportunity maintenance threshold value to formulate an operation and maintenance scheduling plan of each unit component in the offshore wind farm at the current monitoring moment, wherein the specific implementation process comprises the following steps:
step 3-2-1: when any unit part in the offshore wind power plant breaks down, a subsequent maintenance plan of the unit part is determined, and a subsequent maintenance cost TC is generatedRThe total cost of entering the unit where the fault component is located and the cost required for maintaining the fault unit component is included;
wherein,is the maintenance cost of the components j in the offshore wind turbine generator system i.Is a binary variable which indicates whether the component j of the i in the unit has a fault or not, and the value of the binary variable is 1 or 0.Is the fixed cost of entering the offshore wind turbine IiA value of 1 or 0 indicating whether a maintenance team enters the offshore wind turbine i to perform a maintenance activity;
step 3-2-2: if the average effective maintenance cost of the unit component at the current monitoring moment is lower than the state maintenance threshold value, a state maintenance plan of the unit component is made, and state maintenance cost TC is generatedCMainly by the entry cost of the unit in which the component of the maintenance schedule is determined and the maintenance of the unit component of the current operating stateCost and the like are required;
wherein,represents a preventive maintenance cost of the components j in the unit i,is a binary variable, representing whether a crew member meets the conditions for instituting a state repair, which may have a value of 1 or 0,indicating that a maintenance schedule of condition of component j within unit i is to be determined;
step 3-2-3: the occurrence of any maintenance action starts a maintenance period, and a fixed cost C for transporting the operation and maintenance team to the offshore wind farm by the operation and maintenance ship is generatedfixed；
Step 3-2-4: in the maintenance period, the average effective maintenance cost of other unit components still in the running state is judged, if the average effective maintenance cost of the unit components falls between the state maintenance threshold and the opportunity maintenance threshold, the opportunity maintenance plan of the unit components is determined, and opportunity maintenance cost TC is generatedOMainly the cost required for maintaining the unit components;
wherein,is a binary variable that is a function of the variable,indicating that it is economically feasible to perform a common maintenance activity with other crew components for which a maintenance plan has been determined;
step 3-2-5: the average effective maintenance cost of the unit components is greater than the opportunity maintenance threshold value, which indicates that the current running state of the unit components is good and no preventive maintenance measures are required to be implemented;
when all the unit components meeting the conditions execute common maintenance activities after the maintenance and stock period, the end of the maintenance period is indicated, and all the unit components continuously run until the next fault occurs or the average effective maintenance cost of the unit components at the new monitoring moment is less than a state maintenance threshold value;
step 3-2-6: based on the maintenance implementation process, the total operation and maintenance cost TC in a single maintenance period of the offshore wind farmkCan be expressed as follows:
dividing the sum of the operation and maintenance costs from the beginning of the qth maintenance period to the beginning of the r maintenance period by the time interval between two maintenance periods to obtain the daily operation and maintenance cost, wherein q < r, the offshore wind farm pursues the minimization of the annual operation and maintenance cost, so that an annual operation and maintenance cost minimization objective function of the offshore wind farm can be obtained:
wherein, trAnd tqRespectively the times at which the qth and the r-th repair cycles start, ccAnd coRespectively, a state maintenance threshold and an opportunity maintenance threshold;
(1) maintenance necessity constraints:
the method is characterized in that the fault of at most one part occurs in each offshore wind turbine in any maintenance period in the offshore wind power plant;
(2) and (4) maintenance capacity constraint:
the meaning is that the number of maintenance personnel owned in the offshore wind farm is limited, resulting in a certain limitation of the working capacity for performing maintenance activities during maintenance;
based on the offshore wind farm operation and maintenance scheduling optimization model constructed in the step 3-2-6, by simulating the operation parameters (the operation process of the unit components, the weather conditions of the area, the type and the number of the wind turbines, the number and the quality of maintenance personnel, the type and the number of operation and maintenance ships and the like) of the actual offshore wind farm, the optimal solution corresponding to the minimization of the annual operation and maintenance cost in the model is solved, and the optimal solution can be used as a preset state maintenance threshold value and an opportunity maintenance threshold value of the actual offshore wind farm and used for making an operation and maintenance scheduling plan of each unit component.
Through the operation, under the existing equipment and technology of the current offshore wind farm, the scheduling of the optimal maintenance plan of a series of unit components with different degradation states in the offshore wind farm in different periods can be realized by using the offshore wind farm operation and maintenance scheduling method based on the state monitoring data.
The following is a specific example:
construction example for simulation analysis, an offshore wind farm consists of 60 offshore wind energy installations of the same type, with 4 critical components (rotor, main bearing, gearbox and generator) in each installation, and a failure of any one component can lead to a shutdown of the entire installation. The operation age limit of the offshore wind farm is set to be 20 years; assuming individual unit componentsThe maintenance and preparation period is a fixed value t in the running processLDay 30; in addition, the remaining life of the unit components is predicted every 10 days and the average effective maintenance cost, t, is calculatedIDay 10. The relevant parameters of the individual assembly components are shown in tables 1 to 2.
TABLE 1 cost and Weibull distribution parameters for key components of offshore wind turbines
TABLE 2 percentage of Life prediction error for Artificial neural network model
| Component j | Mean of prediction error | Standard deviation of prediction error |
| Rotor | 8.00％ | 10.00％ |
| Main bearing | 6.68％ | 7.53％ |
| Gear box | 8.00％ | 10.00％ |
| Generator | 6.68％ | 7.53％ |
The simulation model is implemented in MATLAB, and annual operation and maintenance cost curves under different maintenance threshold combinations are obtained, as shown in fig. 4, the optimization result shows that the preset state maintenance threshold and the opportunity maintenance threshold are respectively taken as follows:the annual operation and maintenance cost corresponding to the optimal offshore wind farm is $ 2423050/year.
In order to analyze the economy of the proposed operation and maintenance scheduling method, the following 5 operation and maintenance scheduling methods are set for simulation comparison analysis.
1) The method comprises the following steps: and establishing an operation and maintenance scheduling plan of the unit component only when the unit component in the offshore wind power plant fails.
1) The method 2 comprises the following steps: and respectively making an operation and maintenance scheduling plan of the single unit component in the offshore wind power plant based on the reliability.
2) The method 3 comprises the following steps: and respectively making an operation and maintenance scheduling plan of the single unit component in the offshore wind power plant based on a fixed time interval.
3) The method 4 comprises the following steps: and respectively making an operation and maintenance scheduling plan of the single unit component in the offshore wind power plant based on the average effective maintenance cost.
4) The method 5 comprises the following steps: an operation and maintenance scheduling plan is made for a series of unit components in the offshore wind power plant based on the average effective maintenance cost, namely the operation and maintenance scheduling method provided by the invention.
The operation and maintenance scheduling method 1 is the simplest and most basic method in the offshore wind power plant; methods 2 and 3 are the most common operation and maintenance scheduling methods in the current offshore wind power plant; the method 4 is a method for making an operation and maintenance scheduling plan of a single offshore wind turbine component based on the new maintenance basis provided by the invention; the method 5 is a scheduling method which considers an opportunity maintenance strategy on the basis of the proposed maintenance basis, namely, provides an opportunity for the unit component which is not reached but has a degradation state close to the state maintenance requirement to carry out a common maintenance activity with other unit components for determining the maintenance plan. The optimization results obtained by the above 5 operation and maintenance scheduling methods are shown in table 3.
Compared with the optimization results of the method 4 and the methods 1, 2 and 3, the new maintenance basis, namely the average effective maintenance cost, has good expressive performance in formulating the operation and maintenance scheduling plan of a single unit component in the offshore wind farm, and can respectively reduce 34.14%, 32.92% and 27.08% of the annual operation and maintenance cost in the offshore wind farm.
In addition, comparing the optimization results of methods 5 and 4, it can be seen that considering the opportunistic maintenance strategy based on the operation and maintenance scheduling plan for the offshore wind turbine components based on the average effective maintenance cost can directly bring about a reduction of $ 193050 to the annual operation and maintenance cost of the offshore wind farm.
Table 35 operation and maintenance scheduling method optimization results
| Operation and maintenance scheduling method | Method 1 | Method 2 | Method 3 | Method 4 | Method 5 |
| Total operation and maintenance cost | 79756000 | 77996000 | 71750000 | 52322000 | 48461000 |
| Annual operation and maintenance cost | 3987800 | 3899800 | 3587500 | 2616100 | 2423050 |
| The cost is reduced by percentage | 34.14％ | 32.92％ | 27.08％ | 7.38％ | — |
In order to specifically analyze the influence of long and variable maintenance and stocking periods caused by poor accessibility to the offshore wind farm at different periods on the determined operation and maintenance scheduling plan of the offshore wind turbine component, the operation and maintenance scheduling method 4 is subjected to sensitivity analysis in this example, and the result is shown in fig. 5.
The result shows that under the condition that other parameters are not changed, the expected annual operation and maintenance cost of the offshore wind farm is in a severe fluctuation condition along with the change of the maintenance and stocking period, and the change of the maintenance and stocking period can be known to have a significant influence on the annual operation and maintenance cost of the offshore wind farm. Considering that long and variable maintenance stocking periods are reasonable and necessary for making maintenance bases for the operation and maintenance scheduling plan of the offshore wind turbine components, the new maintenance bases proposed by the present invention are reasonable and effective in making maintenance decisions for each offshore wind turbine component.
The most key concept of the invention is as follows: the influence of the change of the maintenance and stocking period on the implementation effect of the determined maintenance plan caused by the accessibility of the offshore wind farm is considered, the average effective maintenance cost function is provided by comprehensively analyzing the residual service life reliability and the maintenance behavior economy of each unit component after the maintenance and stocking period, and the average effective maintenance cost function is used as the basis for making maintenance decisions of each unit component in the wind farm; and considering the maintenance and economic relevance among the unit components, an opportunity maintenance interval is set, so that an opportunity for carrying out maintenance activities together with other unit components is provided for the unit components which are not reached yet and the degradation state of the unit components is close to the maintenance requirement.
The embodiments are only for illustrating the technical idea of the present invention, and the technical idea of the present invention is not limited thereto, and any modifications made on the basis of the technical scheme according to the technical idea of the present invention fall within the scope of the present invention.
Claims (7)
1. An offshore wind farm operation and maintenance scheduling method based on state monitoring is characterized by comprising the following steps of:
(1) collecting monitoring data related to the degradation state of each offshore wind turbine component, and constructing a corresponding artificial neural network model to predict the residual life of each turbine component;
(2) comprehensively analyzing the reliability of the residual service life and the economic performance of maintenance behaviors of each unit component after a maintenance and stock period, constructing a dynamic average effective maintenance cost function of each unit component, and taking the function as a basis for making a maintenance decision of each unit component;
(3) and (3) setting a state maintenance threshold and an opportunity maintenance threshold, and comparing the dynamic average effective maintenance cost of each unit component constructed in the step (2) with the two thresholds to make an optimal operation and maintenance scheduling plan.
2. The offshore wind farm operation and maintenance scheduling method based on condition monitoring according to claim 1, wherein in the step (1), the artificial neural network comprises:
selecting model parameters, wherein the selected model input parameters are the service lives and a plurality of state monitoring data measured values of the current and previous monitoring moments of the offshore wind turbine component; the selected model output parameter is the service life percentage of the offshore wind turbine component;
constructing a model, wherein the constructed model is a feedforward neural network model with multiple inputs and single output;
and (3) training a model, wherein the used training algorithm is a Levenberg-Marquardt algorithm.
3. The offshore wind farm operation and maintenance scheduling method based on condition monitoring according to claim 1, wherein in step (2), the dynamic average effective repair cost function is as follows:
in the above formula, the first and second carbon atoms are,the average effective maintenance cost of the components j in the offshore wind turbine generator is calculated; t is ti,jIs the service life of a member j in an offshore wind turbine unit i; t is tLIn order to maintain the preparation period;representing the predicted value of the residual life of the component j in the offshore wind turbine unit i;the preventive maintenance cost of the component j in the offshore wind turbine generator system i;the maintenance cost of the fault of the component j in the offshore wind turbine generator set i; p (×) represents the probability.
4. The offshore wind farm operation and maintenance scheduling method based on condition monitoring of claim 3, wherein predicted value of residual life of component j in offshore wind turbine unit iThe distribution of (a) is as follows:
wherein,a predicted percentage of life for the artificial neural network model; u. ofp,jAnd σp,jThe average value and the standard deviation of the life percentage prediction error of the artificial neural network model are respectively.
5. The offshore wind farm operation and maintenance scheduling method based on condition monitoring as claimed in claim 1, wherein in step (3), the dynamic average effective maintenance cost function of each unit component is compared with two thresholds to make an optimal operation and maintenance scheduling plan by the specific process as follows:
when the dynamic average effective maintenance cost of the unit component is smaller than the state maintenance threshold value, the residual life reliability, the maintenance cost and the service life of the current unit component are comprehensively measured, the time for executing preventive maintenance behavior after the performance state of the unit component is maintained and stocked is proper, and the state maintenance decision of the unit component is determined;
when the dynamic average effective maintenance cost of the unit component is more than or equal to the state maintenance threshold and less than or equal to the opportunity maintenance threshold, the reliability, the maintenance cost and the working age of the current residual life of the unit component are comprehensively measured, and it is economic to execute maintenance activities together with the unit component determining the state maintenance decision, and an opportunity maintenance plan of the unit component is made;
when the dynamic average effective maintenance cost of the unit components is greater than the opportunity maintenance threshold, no maintenance action is executed;
the operation and maintenance scheduling plan determined according to the method is subjected to common maintenance activities after the changed maintenance stock period; when all the unit components meeting the conditions execute common maintenance activities after the maintenance and stock period, which indicates that the maintenance period is finished, each unit component continuously runs until the next fault occurs or the dynamic average effective maintenance cost of the unit component at the new monitoring moment is less than the state maintenance threshold value.
6. The offshore wind farm operation and maintenance scheduling method based on condition monitoring according to claim 5, wherein in step (3), the condition maintenance threshold and the opportunity maintenance threshold are determined according to experience or simulation experiments.
7. The offshore wind farm operation and maintenance scheduling method based on condition monitoring according to claim 6, wherein the method for determining the condition maintenance threshold and the opportunity maintenance threshold by adopting a simulation experiment is as follows:
establishing an operation and maintenance scheduling optimization model of the offshore wind power plant as follows:
the above formula is an annual operation and maintenance cost minimization objective function of an offshore wind farm, CE(cc,co) For offshore wind farmsAnnual maintenance cost, ccAnd coRespectively, a status maintenance threshold and an opportunity maintenance threshold, trAnd tqThe times of starting the q-th maintenance period and the r-th maintenance period are respectively; TC (tungsten carbide)kFor the total operation and maintenance cost, TC, of the offshore wind power plant in a single maintenance cyclek＝TCR+TCC+TCO+CfixedWhen any unit part in the offshore wind power plant fails, a subsequent maintenance plan of the unit part is determined, and subsequent maintenance cost is generatedWherein,is the failure maintenance cost of the component j in the offshore wind turbine unit i,is a binary variable which indicates whether the component j of the unit i has a fault or not, and has a value of 1 or 0,is the fixed cost of entering the offshore wind turbine IiThe number of the wind turbines is a binary variable which indicates whether a maintenance team enters an offshore wind turbine i to execute maintenance activities, the value of the binary variable is 1 or 0, N is the number of the wind turbines, and M is the number of components in each wind turbine; when the average mean effective maintenance cost of a unit component is less than the stateful maintenance threshold, a stateful maintenance plan for the unit component is formulated and a stateful maintenance cost is generatedWherein,is a preventive maintenance cost of the components j in the unit i,is a binary variable which indicates whether a unit component meets the condition for establishing state maintenance or not, and the value of the binary variable is 1 or 0; when the dynamic average effective maintenance cost of the unit component is more than or equal to the state maintenance threshold and less than or equal to the opportunity maintenance threshold, the opportunity maintenance plan of the unit component is determined, and the opportunity maintenance cost is generatedWherein,for preventive maintenance costs of components j in the unit i,is a binary variable which indicates whether a unit component meets the condition for establishing state maintenance or not, and the value of the binary variable is 1 or 0; when a maintenance cycle is initiated, a fixed cost C will be incurred for the operation and maintenance vessel to transport the operation and maintenance team to the offshore wind farmfixed；
The above formula is a maintenance necessity constraint, and means that at most one part of each offshore wind power generation unit has a fault in any maintenance period in the offshore wind power plant;
the above formula is a maintenance capability constraint, meaning that the number of maintenance personnel owned in the offshore wind farm is limited, resulting in a limitation of the working capability to perform maintenance activities during maintenance;
and solving an optimal solution corresponding to the minimization of the annual operation and maintenance cost in the model by simulating the operation parameters of the actual offshore wind farm, wherein the optimal solution is used as a state maintenance threshold value and an opportunity maintenance threshold value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910280153.9A CN110059872A (en) | 2019-04-09 | 2019-04-09 | A kind of marine wind electric field O&M dispatching method based on status monitoring |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910280153.9A CN110059872A (en) | 2019-04-09 | 2019-04-09 | A kind of marine wind electric field O&M dispatching method based on status monitoring |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110059872A true CN110059872A (en) | 2019-07-26 |
Family
ID=67318695
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910280153.9A Pending CN110059872A (en) | 2019-04-09 | 2019-04-09 | A kind of marine wind electric field O&M dispatching method based on status monitoring |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110059872A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111612219A (en) * | 2020-04-24 | 2020-09-01 | 明阳智慧能源集团股份公司 | Wind power generation prediction system |
| CN111817880A (en) * | 2020-06-17 | 2020-10-23 | 安徽创米信息技术有限公司 | Oil and gas field production equipment health management system and implementation method |
| CN113627706A (en) * | 2020-05-06 | 2021-11-09 | 株式会社 A2M | Maintenance support operation management platform device of wind driven generator based on dispatcher |
| CN113919965A (en) * | 2020-07-10 | 2022-01-11 | 上海电动工具研究所（集团）有限公司 | Model training method and system, energy storage inverter and prediction method based on energy storage inverter |
| CN114692369A (en) * | 2020-12-30 | 2022-07-01 | 新疆金风科技股份有限公司 | Wind turbine generator operation control method and device, controller and storage medium |
| CN115358639A (en) * | 2022-10-20 | 2022-11-18 | 国网山东省电力公司烟台供电公司 | Offshore wind power operation risk analysis system based on data analysis |
| US11635060B2 (en) | 2021-01-20 | 2023-04-25 | General Electric Company | System for operating a wind turbine using cumulative load histograms based on actual operation thereof |
| US11661919B2 (en) | 2021-01-20 | 2023-05-30 | General Electric Company | Odometer-based control of a wind turbine power system |
| US11728654B2 (en) | 2021-03-19 | 2023-08-15 | General Electric Renovables Espana, S.L. | Systems and methods for operating power generating assets |
| WO2023226539A1 (en) * | 2022-05-25 | 2023-11-30 | 江苏科技大学 | Offshore wind farm multi-unit operation and maintenance strategy optimization method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102011112627A1 (en) * | 2011-09-06 | 2013-03-07 | Robert Bosch Gmbh | Method for monitoring and operating wind energy plant within wind farm, involves determining mechanical load of energy plant by evaluating device, and providing control variables of energy plant to control device based on measured variables |
| CN109301852A (en) * | 2018-11-23 | 2019-02-01 | 武汉理工大学 | A kind of micro-capacitance sensor classification united economic load dispatching method of multiple target |
| CN109359742A (en) * | 2018-06-27 | 2019-02-19 | 广州地铁集团有限公司 | A kind of generation method in subway subsystem preventive maintenance period |
-
2019
- 2019-04-09 CN CN201910280153.9A patent/CN110059872A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102011112627A1 (en) * | 2011-09-06 | 2013-03-07 | Robert Bosch Gmbh | Method for monitoring and operating wind energy plant within wind farm, involves determining mechanical load of energy plant by evaluating device, and providing control variables of energy plant to control device based on measured variables |
| CN109359742A (en) * | 2018-06-27 | 2019-02-19 | 广州地铁集团有限公司 | A kind of generation method in subway subsystem preventive maintenance period |
| CN109301852A (en) * | 2018-11-23 | 2019-02-01 | 武汉理工大学 | A kind of micro-capacitance sensor classification united economic load dispatching method of multiple target |
Non-Patent Citations (2)
| Title |
|---|
| ZHIGANG TIAN: "Condition based maintenance optimization for wind power generation systems under continuous monitoring", 《RENEWABLE ENERGY》 * |
| 张路朋: "风电机组的状态机会维修策略", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111612219A (en) * | 2020-04-24 | 2020-09-01 | 明阳智慧能源集团股份公司 | Wind power generation prediction system |
| CN113627706A (en) * | 2020-05-06 | 2021-11-09 | 株式会社 A2M | Maintenance support operation management platform device of wind driven generator based on dispatcher |
| CN113627706B (en) * | 2020-05-06 | 2024-05-10 | 株式会社AtwoM | Maintenance support operation management platform device of wind driven generator based on scheduler |
| CN111817880A (en) * | 2020-06-17 | 2020-10-23 | 安徽创米信息技术有限公司 | Oil and gas field production equipment health management system and implementation method |
| CN113919965A (en) * | 2020-07-10 | 2022-01-11 | 上海电动工具研究所（集团）有限公司 | Model training method and system, energy storage inverter and prediction method based on energy storage inverter |
| CN114692369A (en) * | 2020-12-30 | 2022-07-01 | 新疆金风科技股份有限公司 | Wind turbine generator operation control method and device, controller and storage medium |
| US11635060B2 (en) | 2021-01-20 | 2023-04-25 | General Electric Company | System for operating a wind turbine using cumulative load histograms based on actual operation thereof |
| US11661919B2 (en) | 2021-01-20 | 2023-05-30 | General Electric Company | Odometer-based control of a wind turbine power system |
| US11728654B2 (en) | 2021-03-19 | 2023-08-15 | General Electric Renovables Espana, S.L. | Systems and methods for operating power generating assets |
| WO2023226539A1 (en) * | 2022-05-25 | 2023-11-30 | 江苏科技大学 | Offshore wind farm multi-unit operation and maintenance strategy optimization method |
| CN115358639A (en) * | 2022-10-20 | 2022-11-18 | 国网山东省电力公司烟台供电公司 | Offshore wind power operation risk analysis system based on data analysis |
| CN115358639B (en) * | 2022-10-20 | 2023-01-24 | 国网山东省电力公司烟台供电公司 | Offshore wind power operation risk analysis system based on data analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110059872A (en) | A kind of marine wind electric field O&M dispatching method based on status monitoring | |
| Shafiee et al. | Maintenance optimization and inspection planning of wind energy assets: Models, methods and strategies | |
| Lu et al. | Condition based maintenance optimization for offshore wind turbine considering opportunities based on neural network approach | |
| Tian et al. | Condition based maintenance optimization for wind power generation systems under continuous monitoring | |
| Liu et al. | Quantifying spinning reserve in systems with significant wind power penetration | |
| CN103296701B (en) | Active power control method in wind power plant | |
| CN104952000A (en) | Wind turbine operating state fuzzy synthetic evaluation method based on Markov chain | |
| CN106991538A (en) | A kind of method for maintaining and device evaluated based on Wind turbines Degrees of Importance of Components | |
| Amayri et al. | Condition based maintenance of wind turbine systems considering different turbine types | |
| El-Naggar et al. | Optimal maintenance strategy of wind turbine subassemblies to improve the overall availability | |
| CN114183314A (en) | Wind turbine generator opportunity maintenance method based on reliability | |
| Su et al. | Opportunistic maintenance optimisation for offshore wind farm with considering random wind speed | |
| CN118316013A (en) | New energy power station generated power prediction method | |
| Li et al. | Optimal chartering decisions for vessel fleet to support offshore wind farm maintenance operations | |
| Santos et al. | Influence of logistic strategies on the availability and maintenance costs of an offshore wind turbine | |
| Liang et al. | Probabilistic generation and transmission planning with renewable energy integration | |
| Shafiee et al. | Optimal redundancy and maintenance strategy decisions for offshore wind power converters | |
| Li et al. | A review of maintenance strategy optimization for wind energy | |
| Miao et al. | Energy Availability Analysis of Offshore Wind Farms Considering the Correlation between Wind Speed Cloud Model and Parameters | |
| Li et al. | Two-stage robust unit commitment with wind farms and pumped hydro energy storage systems under typhoons | |
| Ding | Comparative study of maintenance strategies for wind turbine systems | |
| Dong et al. | Research on the condition based maintenance decision of equipment in power plant | |
| Brandão et al. | Condition monitoring of the wind turbine generator slip ring | |
| CN111884266A (en) | Gas turbine intraday rolling unit combination optimization method | |
| Borowski et al. | Regression model in the operation of wind turbines |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190726 |
|
| RJ01 | Rejection of invention patent application after publication |