Wind turbine generator overhauling method and device for multi-energy system

Abstract

The invention relates to the technical field of wind turbine generator operation and maintenance, and particularly discloses a wind turbine generator maintenance method and device for a multi-energy system, and the method comprises the steps: determining the maintenance priority score of each wind turbine generator according to the maintenance associated data of a plurality of generator components of each wind turbine generator in a plurality of wind turbine generators; determining power generation output time sequence data of the wind power generation system and the photovoltaic power generation system according to the historical illumination data and the historical wind speed data; determining a plurality of maintenance time periods based on the historical load data and the power generation output time sequence data of the wind power generation system; according to the power generation output time sequence data, the output constraint, the power balance constraint and the maintenance constraint of the photovoltaic power generation system, the maintenance capacity corresponding to each maintenance time period is determined; and generating a target maintenance scheme of the wind power generation system in the target time period by using the maintenance priority score, the maintenance time period and the corresponding maintenance capacity. According to the scheme, the maintenance plan can be scientifically and reasonably arranged.

Description

TECHNICAL FIELD

[0001] The present specification relates to the technical field of wind turbine operation and maintenance, and particularly relates to a wind turbine maintenance method and device for a multi-energy system. BACKGROUND

[0002] With the rapid development of modern power systems, multi-energy complementary technology has become an important means to improve energy utilization efficiency and optimize energy structure. Wind power, as a renewable and clean energy source with huge reserves, requires more maintenance. Currently, the maintenance plan of wind turbines is mainly based on fixed cycles or after sudden failures. This method may result in waste of maintenance resources or affect the operation of the unit due to failure to repair in time. The existing method lacks comprehensive consideration of the unit state, maintenance cost and wind power output fluctuation, and it is difficult to achieve a scientific and reasonable maintenance plan.

[0003] At present, there is no effective solution to the above problems. SUMMARY

[0004] The embodiments of the present specification provide a wind turbine maintenance method and device for a multi-energy system to solve the problem that the existing wind turbine maintenance plan formulation method is prone to waste of maintenance resources or affect the operation of the unit due to failure to repair in time.

[0005] The embodiments of the present specification provide a wind turbine maintenance method for a multi-energy system, the multi-energy system comprising a wind power generation system, a photovoltaic power generation system, an energy storage system and a solar-thermal power generation system; the method comprising:

[0006] According to the maintenance correlation data of the unit components of each wind turbine in the plurality of wind turbines in the wind power generation system, the maintenance priority score of each wind turbine is determined;

[0007] According to the historical light data and the historical wind speed data of the multi-energy system in the historical time period, the power generation output time sequence data of the wind power generation system and the photovoltaic power generation system in the multi-energy system is determined; the power generation output time sequence data comprises the power generation output data of the wind power generation system and the photovoltaic power generation system at a plurality of time points in a future target time period;

[0008] Based on the historical load data of the multi-energy system and the power generation output time sequence data of the wind power generation system, a plurality of maintenance time periods of the wind power generation system in a future target time period are determined; according to the power generation output time sequence data of the photovoltaic power generation system, the output constraint of each system in the multi-energy system, the power balance constraint of the multi-energy system and the maintenance constraint of the wind power generation system, the maintenance capacity corresponding to each maintenance time period in the plurality of maintenance time periods of the wind power generation system is determined;

[0009] generate a target maintenance scheme of the wind power system in a target time period according to the maintenance priority scores of the wind power units, the plurality of maintenance time periods and the maintenance capacities corresponding to the maintenance time periods, so as to perform maintenance on the wind power units of the wind power system in the future target time period based on the target maintenance scheme.

[0010] In one embodiment, the maintenance priority scores of the wind power units are determined according to the maintenance correlation data of the unit components of the wind power units in the wind power system, comprising:

[0011] obtaining the maintenance correlation data of the unit components of the wind power units in the wind power system;

[0012] calculating the maintenance priority indexes of the unit components of the wind power units according to the maintenance correlation data of the unit components of the wind power units;

[0013] calculating the maintenance priority scores of the wind power units based on the maintenance priority indexes of the unit components of the wind power units and the component weights corresponding to the unit components.

[0014] In one embodiment, after calculating the maintenance priority indexes of the unit components of the wind power units according to the maintenance correlation data of the unit components of the wind power units, further comprising:

[0015] obtaining the state data of the unit components of the wind power units monitored by the state monitoring system;

[0016] in the case that the state data of the unit components of the wind power units meet the preset conditions, updating the maintenance priority indexes of the unit components so that the maintenance priority indexes of the unit components increase.

[0017] In one embodiment, the maintenance correlation data comprises component cost, maintenance cost, component maintenance duration and component maintenance frequency.

[0018] Correspondingly, calculating the maintenance priority indexes of the unit components of the wind power units according to the maintenance correlation data of the unit components of the wind power units, comprising:

[0019] determining the maintenance correlation scores of the unit components of the wind power units according to the maintenance correlation data of the unit components of the wind power units and the preset correlation data score table; the maintenance correlation scores comprise at least one of the following: component cost score, maintenance cost score, component maintenance duration score and component maintenance frequency score.

[0020] Based on the maintenance correlation score of each component of each wind turbine and the correlation data weight corresponding to the maintenance correlation data, a maintenance priority index of each component of each wind turbine is calculated.

[0021] In one embodiment, according to historical light data and historical wind speed data of the multi-energy system in the historical time period, power generation output time sequence data of a wind power generation system and a photovoltaic power generation system in the multi-energy system are determined, including:

[0022] Obtaining historical light data and historical wind speed data of the multi-energy system in a historical time period;

[0023] Sampling and clustering the historical light data and historical wind speed data to obtain wind speed time sequence simulation data and light time sequence simulation data of the multi-energy system;

[0024] Using the wind speed time sequence simulation data and the light time sequence simulation data, calculating power generation output time sequence data of a wind power generation system and a photovoltaic power generation system in the multi-energy system.

[0025] In one embodiment, sampling and clustering the historical light data and historical wind speed data to obtain wind speed time sequence simulation data and light time sequence simulation data of the multi-energy system, including:

[0026] Dividing the historical time period into a plurality of historical sub-time periods; and performing probability distribution analysis on the historical light data and historical wind speed data in each historical sub-time period in the plurality of historical sub-time periods to obtain probability distribution parameters corresponding to the historical light data and historical wind speed data of each historical sub-time period;

[0027] Based on the probability distribution parameters corresponding to the historical light data and historical wind speed data of each historical sub-time period, Latin hypercube sampling is performed on the historical light data and historical wind speed data in each historical sub-time period, respectively, to obtain wind speed scene sample sets and light scene sample sets corresponding to the historical sub-time periods;

[0028] Performing clustering analysis on the wind speed scene sample sets and light scene sample sets corresponding to the historical sub-time periods to obtain wind speed time sequence simulation data and light time sequence simulation data of the multi-energy system.

[0029] In one embodiment, performing clustering analysis on the wind speed scene sample sets and light scene sample sets corresponding to the historical sub-time periods to obtain wind speed time sequence simulation data and light time sequence simulation data of the multi-energy system, including:

[0030] The wind speed scene in the wind speed scene sample set corresponding to each historical sub-time period is divided into a plurality of clustering clusters by using a clustering algorithm, to obtain a plurality of first clustering clusters corresponding to each historical sub-time period; the illumination scene in the illumination scene sample set corresponding to each historical sub-time period is divided into a plurality of clustering clusters by using a clustering algorithm, to obtain a plurality of second clustering clusters corresponding to each historical sub-time period;

[0031] A first target clustering cluster corresponding to each historical sub-time period is determined from the plurality of first clustering clusters corresponding to each historical sub-time period according to the occurrence probability of each first clustering cluster in the plurality of first clustering clusters corresponding to each historical sub-time period; a second target clustering cluster corresponding to each historical sub-time period is determined from the plurality of second clustering clusters corresponding to each historical sub-time period according to the occurrence probability of each second clustering cluster in the plurality of second clustering clusters corresponding to each historical sub-time period;

[0032] Based on the first target clustering cluster corresponding to each historical sub-time period, wind speed time sequence simulation data of the multi-energy system in a future target time period is generated; based on the second target clustering cluster corresponding to each historical sub-time period, illumination time sequence simulation data of the multi-energy system in the future target time period is generated.

[0033] In one embodiment, based on historical load data of the multi-energy system and power generation output time sequence data of the wind power generation system, a plurality of maintenance time periods of the wind power generation system in a future target time period are determined, including:

[0034] Based on historical load data of the multi-energy system, a low load time period of the multi-energy system in a future target time period is determined; the low load time period is a time period in which the load represented by the historical load data is lower than a preset load;

[0035] Based on power generation output time sequence data of the wind power generation system, a low output time period of the wind power generation system in a future target time period is determined; the low output time period is a time period in which the power generation output of the wind power generation system is lower than a preset output;

[0036] The low load time period and / or the low output time period are used as the plurality of maintenance time periods of the wind power generation system in the future target time period.

[0037] In one embodiment, according to power generation output time sequence data of the photovoltaic power generation system, output constraints of each system in the multi-energy system, power balance constraints of the multi-energy system, and maintenance constraints of the wind power generation system, a maintenance capacity corresponding to each maintenance time period in the plurality of maintenance time periods of the wind power generation system is determined, including:

[0038] solving a target function of the multi-energy system based on the power generation output time sequence data of the photovoltaic power generation system and output constraints of each system in the multi-energy system and power balance constraints of the multi-energy system, to determine power generation output data of each energy system in the multi-energy system in a future target time period;

[0039] determining theoretical maintenance capacities corresponding to each maintenance time period in the plurality of maintenance time periods according to the power generation output data of each energy system in the multi-energy system in the future target time period and historical load data in the historical time period;

[0040] correcting the theoretical maintenance capacities corresponding to each maintenance time period by using maintenance constraints of the wind power generation system, to obtain target maintenance capacities corresponding to each maintenance time period.

[0041] The embodiments of the present specification also provide a wind turbine unit maintenance device for a multi-energy system, comprising:

[0042] a priority determination module configured to determine maintenance priority scores of a plurality of wind turbine units in the wind power generation system according to maintenance association data of a plurality of unit components of each wind turbine unit in the plurality of wind turbine units;

[0043] an output determination module configured to determine power generation output time sequence data of wind power generation systems and photovoltaic power generation systems in the multi-energy system according to historical illumination data and historical wind speed data of the multi-energy system in a historical time period; the power generation output time sequence data comprises power generation output data of the wind power generation systems and the photovoltaic power generation systems at a plurality of time points in a future target time period;

[0044] a maintenance capacity determination module configured to determine a plurality of maintenance time periods of the wind power generation system in the future target time period based on historical load data of the multi-energy system and the power generation output time sequence data of the wind power generation system, and to determine maintenance capacities corresponding to each maintenance time period in the plurality of maintenance time periods of the wind power generation system according to the power generation output time sequence data of the photovoltaic power generation system, output constraints of each system in the multi-energy system, power balance constraints of the multi-energy system, and maintenance constraints of the wind power generation system;

[0045] a maintenance scheme generation module configured to generate a target maintenance scheme of the wind power generation system in the target time period by using the maintenance priority scores of the plurality of wind turbine units, the plurality of maintenance time periods, and the maintenance capacities corresponding to each maintenance time period, to maintain each wind turbine unit of the wind power generation system in the future target time period based on the target maintenance scheme.

[0046] The embodiment of the present specification further provides a computer device, comprising a processor and a memory for storing processor-executable instructions, wherein the processor implements the steps of the wind turbine unit maintenance method for a multi-energy system in any of the above-mentioned embodiments when executing the instructions.

[0047] The embodiment of the present specification further provides a computer-readable storage medium having stored thereon computer instructions, wherein the instructions implement the steps of the wind turbine unit maintenance method for a multi-energy system in any of the above-mentioned embodiments when executed.

[0048] The embodiment of the specification provides a wind turbine unit maintenance method for a multi-energy system. The multi-energy system comprises a wind power generation system, a photovoltaic power generation system, an energy storage system and a solar-thermal power generation system. Maintenance priority scores of wind turbine units in the wind power generation system can be determined according to maintenance correlation data of multiple unit components of each wind turbine unit in the wind power generation system. Generation output time sequence data of the wind power generation system and the photovoltaic power generation system in the multi-energy system can be determined according to historical illumination data and historical wind speed data of the multi-energy system in a historical time period. The generation output time sequence data comprises generation output data of the wind power generation system and the photovoltaic power generation system at multiple time points in a future target time period. Multiple maintenance time periods of the wind power generation system in the future target time period can be determined based on historical load data of the multi-energy system and the generation output time sequence data of the wind power generation system. Maintenance capacities of each maintenance time period of the wind power generation system in the multiple maintenance time periods can be determined according to the generation output time sequence data of the photovoltaic power generation system, output constraints of each system in the multi-energy system, power balance constraints of the multi-energy system and maintenance constraints of the wind power generation system. A target maintenance scheme of the wind power generation system in the target time period can be generated by using the maintenance priority scores of the wind turbine units, the multiple maintenance time periods and the maintenance capacities of each maintenance time period, so as to maintain each wind turbine unit of the wind power generation system based on the target maintenance scheme in the future target time period. In the above scheme, the maintenance priority scores of the wind turbine units are calculated based on the maintenance correlation data of multiple unit components of each wind turbine unit in the wind power generation system, so that the unit maintenance priority can be fully considered when the maintenance plan is generated, the key unit maintenance is arranged preferentially, the maintenance plan is more scientific and reasonable, resource waste is avoided and system operation efficiency is improved. Further, the maintenance time periods are reasonably arranged by combining the output constraints and weather forecast, the maintenance constraints and the multi-energy complementary collaborative optimization mechanism, the wind power-photovoltaic-solar-thermal-energy storage combined output model is used to dynamically coordinate the multi-energy maintenance window, the solar-thermal and energy storage power generation is preferentially called in the calm wind period, and multiple maintenance time periods are determined. Further, the maintenance capacities in each maintenance time period are calculated by using the power balance equation and the maintenance constraints of the wind power generation system. The maintenance capacities are preferentially allocated to the low output window, the shutdown in the high wind speed period is avoided, the system power balance is ensured and the influence on the generation capacity is reduced. Then, the target maintenance scheme of the wind power generation system in the target time period can be generated according to the maintenance priority scores of the wind turbine units, the multiple maintenance time periods and the maintenance capacities of each maintenance time period, and each wind turbine unit is maintained based on the target maintenance scheme. Not only the factors such as wind power output fluctuation, maintenance constraints and power balance are considered, but also the unit operation and unit maintenance priority are considered, so that the maintenance time period and unit sequence can be scientifically arranged on the premise of ensuring stable power supply of the multi-energy system, the maintenance plan table is generated, the influence of maintenance on system output is reduced, and support is provided for long-term operation and maintenance plan formulation of the wind power generation system.

[0049] With reference to the following description and drawings, specific embodiments of the present invention are disclosed in detail, indicating how the principles of the present invention can be employed. It should be understood that the embodiments of the present invention are not limited in scope thereby. Features described and / or illustrated for one embodiment may be used in the same or similar manner in one or more other embodiments, combined with features in other embodiments, or substituted for features in other embodiments.

[0050] It should be emphasized that the term “include / comprises” when used herein refers to the presence of features, parts, steps or components, but does not exclude the presence or addition of one or more other features, parts, steps or components. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The drawings described herein are for illustrative purposes only and are not intended to limit the scope of the present invention in any way. In addition, the shapes and proportional dimensions of the components in the drawings are only schematic and are used to help understand the present invention. They do not specifically limit the shapes and proportional dimensions of the components of the present invention. Those skilled in the art can select various possible shapes and proportional dimensions to implement the present invention according to the specific circumstances under the guidance of the present invention. In the drawings:

[0052] Figure 1 A flow chart of a wind turbine maintenance method for a multi-energy system in an embodiment of this specification is shown;

[0053] Figure 2 Schematic diagram showing the hourly output of wind power, photovoltaic, solar thermal and energy storage systems in the first quarter of an embodiment of this specification;

[0054] Figure 3 A schematic diagram showing the maintenance capacity of wind turbines per week in the first quarter of an embodiment of this specification is shown;

[0055] Figure 4 A schematic diagram of the structure of a wind turbine maintenance device for a multi-energy system according to an embodiment of the present specification is shown;

[0056] Figure 5 A schematic diagram of the structure of a computer device in one embodiment of this specification is shown. DETAILED DESCRIPTION

[0057] The principles and spirit of this specification will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided solely to enable those skilled in the art to better understand and implement this specification, and are not intended to limit the scope of this specification in any way. Rather, these embodiments are provided to make this specification more thorough and complete, and to fully convey the scope of this disclosure to those skilled in the art.

[0058] Those skilled in the art will realize that the embodiments of the present specification can be implemented as a system, device, apparatus, method or computer program product. Therefore, the present specification discloses a computer program product which can be implemented as follows: entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0059] The details of the present specification will be more clearly understood by referring to the drawings and the detailed description of the present specification. However, the detailed description of the present specification described herein is for the purpose of explanation only and is not to be construed as limiting the present specification in any way. Based on the teachings of the present specification, those skilled in the art will be able to conceive of any possible modifications of the present specification, and these are to be considered as falling within the scope of the present specification. It should be noted that when an element is referred to as being "on" another element, it can be directly on the other element or there can be an intervening element. When an element is referred to as being "connected" to another element, it can be directly connected to the other element or there can be an intervening element. The terms "mount", "couple", "connect" are to be construed broadly, for example, they can be mechanical or electrical connections, or connections between two elements, or direct connections, or indirect connections through intervening media, and the specific meaning of the terms can be understood by those skilled in the art according to the specific circumstances. The terms "vertical", "horizontal", "upper", "lower", "left", "right", and the like used herein are for the purpose of illustration only and are not intended to be the only embodiment.

[0060] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present specification belongs. The terminology used in the present specification is for the purpose of describing the particular embodiments only and is not intended to be limiting of the present specification. As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0061] Figure 1A flow chart of a method for wind turbine unit maintenance in a multi-energy system is shown in an embodiment of the present specification. Although the present specification provides method operation steps or device structures as shown in the following embodiments or drawings, more or less operation steps or module units can be included in the method or device based on convention or without creative labor. In steps or structures without necessary causality in logic, the execution order of the steps or the module structure of the device is not limited to the execution order or module structure shown in the embodiment description and drawings of the present specification. When the method or module structure is applied to the actual device or terminal product, it can be sequentially executed or executed in parallel (for example, parallel processor or multi-thread processing environment, even distributed processing environment) according to the method or module structure shown in the embodiment or drawing.

[0062] Specifically, as shown in the present specification, an embodiment provides a method for wind turbine unit maintenance in a multi-energy system, which can include the following steps. Figure 1

[0063] In step S101, a maintenance priority score of each wind turbine unit is determined according to maintenance correlation data of multiple unit components of each wind turbine unit in the multiple wind turbine units in the wind power generation system.

[0064] The multi-energy system includes a wind power generation system, a photovoltaic power generation system, an energy storage system, and a solar-thermal power generation system. The wind power generation system can include multiple wind turbine units. The maintenance priority score of each wind turbine unit can be determined according to maintenance correlation data of multiple unit components of each wind turbine unit in the multiple wind turbine units in the wind power generation system.

[0065] The maintenance correlation data can be data related to the maintenance priority of the component. In an embodiment, the maintenance correlation data can include at least one of the following: component state, component cost, maintenance cost, component maintenance duration, and component maintenance frequency, etc.

[0066] In an embodiment, the maintenance priority index of each unit component of each wind turbine unit can be determined according to the maintenance correlation data of the multiple unit components of each wind turbine unit. Then, the maintenance priority score of each wind turbine unit can be determined according to the maintenance priority index of each unit component of each wind turbine unit. In an embodiment, the maintenance priority index of each unit component of each wind turbine unit can be added to obtain the maintenance priority score of each wind turbine unit. In another embodiment, the maximum value of the maintenance priority index of each unit component of the wind turbine unit can be taken as the maintenance priority score of the wind turbine unit. It can be understood that the above embodiments are only exemplary, and the embodiments of the present specification are not limited thereto.

[0067] ​In one embodiment, the greater the maintenance priority score, the higher the maintenance priority, and the greater the impact of the unit failure on the operation and maintenance of the multi-wind farm.

[0068] In step S102, the power generation output time series data of the wind power generation system and the photovoltaic power generation system in the multi-energy system is determined according to the historical light data and the historical wind speed data of the multi-energy system in a historical time period. The power generation output time series data includes the power generation output data of the wind power generation system and the photovoltaic power generation system at multiple time points in a future target time period.

[0069] Considering that the power generation output of the wind power generation system and the photovoltaic power generation system is related to meteorological data, in order to predict the power generation output data at multiple time points in a future target time period, uncertainty modeling can be performed. Specifically, the power generation output time series data of the wind power generation system and the photovoltaic power generation system in the multi-energy system can be determined according to the historical light data and the historical wind speed data of the multi-energy system in a historical time period. The power generation output time series data can include the power generation output data of the wind power generation system and the photovoltaic power generation system at multiple time points in a future target time period. In one embodiment, the historical light data and the historical wind speed data in the historical time period and the trained machine learning model can be used to predict the light data and the wind speed data in the future target time period. Further, the power generation output time series data of the wind power generation system and the photovoltaic power generation system can be determined based on the light data and the wind speed data in the future target time period. In one embodiment, the historical time period can be the past month, the past quarter, or the past year, etc. Correspondingly, the future target time period can be the future month, the future quarter, or the future year, etc.

[0070] In step S103, the multiple maintenance time periods of the wind power generation system in the future target time period are determined based on the historical load data of the multi-energy system and the power generation output time series data of the wind power generation system. The maintenance capacity of each maintenance time period of the wind power generation system in the multiple maintenance time periods is determined according to the power generation output time series data of the photovoltaic power generation system, the output constraint of each system in the multi-energy system, the power balance constraint of the multi-energy system, and the maintenance constraint of the wind power generation system.

[0071] After obtaining the power generation time series data of the wind power generation system and the photovoltaic power generation system, the multiple maintenance time periods of the wind power generation system in the future target time period can be determined based on the historical load data of the multi-energy system and the power generation time series data of the wind power generation system. In an embodiment, the load data of the multi-energy system in the future target time period can be predicted according to the historical load data of the multi-energy system. Then, the multiple maintenance time periods can be determined based on the load data of the multi-energy system in the future target time period and the power generation time series data of the wind power generation system. The length, number and interval of two maintenance time periods of the maintenance time periods can be preset. In an embodiment, the low load time period of the multi-energy system can be used as the maintenance time period. In another embodiment, the low output time period of the wind power generation system can be used as the maintenance time period.

[0072] After the multiple maintenance time periods are determined, the maintenance capacity of the wind power generation system in each maintenance time period of the multiple maintenance time periods can be determined according to the power generation time series data of the photovoltaic power generation system, the output constraints of each system in the multi-energy system, the power balance constraint of the multi-energy system and the maintenance constraints of the wind power generation system. The output constraints of each system in the multi-energy system can include the output constraints of the wind power generation system, the output constraints of the photovoltaic power generation system, the output constraints of the solar-thermal power generation system and the output constraints of the energy storage system. The output constraints of the wind power generation system can be that the output is between zero and the maximum wind power generation output. The output constraints of the photovoltaic power generation system can be that the output is between zero and the maximum photovoltaic power generation output. The output constraints of the solar-thermal power generation system can include the heat dynamic balance of the heat collection field and the heat storage tank, and the upper and lower limits and the climbing limit of the generator output. The output constraints of the energy storage system can include the maximum power constraint of power generation and charging, the energy storage capacity constraint and the state of charge balance constraint. The power balance constraint of the multi-energy system means that the output and charging power of the multi-energy system can meet the load demand and discharging power of the multi-energy system. The maintenance constraints of the wind power generation system can include the number of maintenance, the maintenance time, the maintenance continuity, the maintenance time interval and the maintenance capacity constraints. The number of maintenance can be the number of times of maintenance of the wind turbine in a time period. The maintenance time is the maintenance time length of the wind turbine in one maintenance process. The maintenance time interval is the minimum time interval between two consecutive maintenance of the wind turbine. The maintenance capacity means the number of wind turbines that can be simultaneously maintained in a time period.

[0073] Under the premise of meeting the output constraints of each system in the multi-energy system, the power balance constraint of the multi-energy system and the maintenance constraints of the wind power generation system, the determination of the maintenance capacity of the wind power generation system in each maintenance time period of the multiple maintenance time periods can enable the maintenance of the wind turbine without affecting the power supply. The maintenance capacity means the number of wind turbines that can be maintained in the maintenance time period.

[0074] In step S104, a target maintenance scheme of the wind power system in a target time period is generated based on the maintenance priority scores of the wind turbines, the multiple maintenance time periods and the maintenance capacities corresponding to the multiple maintenance time periods, so as to maintain the wind turbines of the wind power system in the future target time period based on the target maintenance scheme.

[0075] After the multiple maintenance time periods and the corresponding maintenance capacities are determined, the wind turbines can be arranged in the corresponding maintenance time periods based on the maintenance priority scores of the wind turbines, so as to generate the target maintenance scheme of the wind power system in the target time period. The wind turbines with high maintenance priority scores can be arranged for maintenance in priority. Then, the wind turbines of the wind power system can be maintained in the future target time period based on the target maintenance scheme.

[0076] In the above embodiment, the maintenance priority scores of the wind turbines are calculated based on the maintenance correlation data of the multiple unit components of the wind turbines in the wind power system, so that the unit maintenance priority can be fully considered when the maintenance plan is generated, the key unit maintenance is arranged in priority, the maintenance plan is ensured to be more scientific and reasonable, the resource waste is avoided, and the system operation efficiency is improved. Further, the multiple maintenance time periods are determined by combining the power output constraint and the weather forecast, by reasonably arranging the maintenance time periods through the maintenance constraint and the multi-energy complementary collaborative optimization mechanism, by using the wind power-photovoltaic-photothermal-energy storage combined power output model, and by dynamically coordinating the multi-energy maintenance window. The photothermal and energy storage power generation is called in priority in the calm wind period. Further, the maintenance capacities in the multiple maintenance time periods are calculated by using the power balance equation and the maintenance constraint of the wind power system. The maintenance capacities are preferentially allocated to the low power output window, the shutdown in the high wind speed period is avoided, the system power balance is ensured, and the influence on the power generation capacity is reduced. Then, the target maintenance scheme of the wind power system in the target time period can be generated based on the maintenance priority scores of the wind turbines, the multiple maintenance time periods and the maintenance capacities corresponding to the multiple maintenance time periods, and the wind turbines can be maintained based on the target maintenance scheme. Not only the factors such as the wind power output fluctuation, the maintenance constraint and the power balance are considered, but also the unit operation and the unit maintenance priority are considered. The maintenance time period and the unit sequence can be scientifically arranged to generate the maintenance schedule table under the premise of ensuring the stable power supply of the multi-energy system, the influence of the maintenance on the system output is reduced, and the support is provided for the long-term operation of the wind power system and the formulation of the maintenance plan.

[0077] In some embodiments of the present specification, determining the maintenance priority score of each wind turbine generator set in the wind power generation system according to the maintenance correlation data of the plurality of unit components of each wind turbine generator set in the plurality of wind turbine generator sets in the wind power generation system can comprise: obtaining the maintenance correlation data of the plurality of unit components of each wind turbine generator set in the plurality of wind turbine generator sets in the wind power generation system; calculating the maintenance priority index of each component of each wind turbine generator set according to the maintenance correlation data of each component of each wind turbine generator set; and calculating the maintenance priority score of each wind turbine generator set based on the maintenance priority index of each component of each wind turbine generator set and the component weight corresponding to each component.

[0078] In the present embodiment, different weights can be assigned to different components according to the importance of different components, and the weighted sum of the maintenance priority indexes of the components of each wind turbine generator set is calculated to obtain the maintenance priority index of each wind turbine generator set. Through the above-mentioned manner, the criticality and importance of each component can be accurately quantified, and the differentiated maintenance can be realized by accurately calculating the maintenance priority index of the unit component through the system-level risk aggregation algorithm.

[0079] In some embodiments of the present specification, after calculating the maintenance priority index of each component of each wind turbine generator set according to the maintenance correlation data of each component of each wind turbine generator set, the method can further comprise: obtaining the state data of each unit component of each wind turbine generator set monitored by the condition monitoring system; and updating the maintenance priority index of the unit component of the wind turbine generator set in the case where the state data of the unit component of the wind turbine generator set meets the preset condition, so that the maintenance priority index of the component is increased.

[0080] In the present embodiment, the maintenance priority index of the component can be dynamically adjusted by obtaining the state data of the component monitored by the condition monitoring system, and the maintenance priority score of the unit is adjusted, so that the maintenance plan is dynamically adjusted. According to the real-time wind power output and the unit maintenance priority, the maintenance opportunity of each unit is optimized, the priority is updated and the maintenance period is optimized when the real-time fault occurs, the state of the unit component is detected by the condition monitoring system, and the maintenance priority index of the component is automatically recalculated when the vibration of the component of the unit suddenly increases and exceeds the threshold. The maintenance priority index is increased, the comprehensive priority of the unit is improved, the maintenance sequence is advanced, the fault is avoided from expanding, the downtime is reduced, and the power generation efficiency and economic benefit are improved. Although the plan is mainly arranged based on the unit maintenance priority and the pre-calculated maintenance capacity and maintenance period, the priority is updated and the maintenance period is optimized when the real-time fault occurs, the state of the unit component is detected by the condition monitoring system, and the maintenance priority index of the component is automatically recalculated when the vibration of the component of the unit suddenly increases and exceeds the threshold. The maintenance priority index is increased, and the comprehensive priority of the unit is improved. According to the original plan, the unit is arranged to be maintained in the third week, and after the system detects that the maintenance priority index is increased, it is combined with the current wind power output data to advance the maintenance to the first week, so that the fault is avoided from expanding.

[0081] In some embodiments of the present specification, the maintenance-related data may include: component cost, maintenance cost, component maintenance time and component maintenance frequency; accordingly, calculating the maintenance priority index of each component of each wind turbine according to the maintenance-related data of each component of each wind turbine may include: determining the maintenance-related score of each component of each wind turbine according to the maintenance-related data of each component of each wind turbine and a preset related data scoring table; the maintenance-related score may include at least one of the following: component cost score, maintenance cost score, component maintenance time score and component maintenance frequency score; calculating the maintenance priority index of each component of each wind turbine based on the maintenance-related score of each component of each wind turbine and the related data weight corresponding to the maintenance-related data.

[0082] In this embodiment, different weights can be assigned to different types of maintenance-related data. The weight corresponding to each maintenance-related data can be preset. The weight corresponding to each maintenance-related data can be set by experts based on years of operation and maintenance experience to ensure practical significance. In an exemplary embodiment, the weight corresponding to the component cost can be set to 0.3, the weight corresponding to the maintenance cost can be set to 0.2, the weight corresponding to the component maintenance time can be set to 0.2, and the weight corresponding to the operation and maintenance frequency can be set to 0.3. Afterwards, based on the real-time collection of multi-dimensional parameters such as component cost, maintenance cost, maintenance time, operation and maintenance frequency by the digital detection system, the maintenance priority index of the component can be calculated using a weighted maintenance priority index calculation model.

[0083] The maintenance priority score of the computer group is calculated through the system-level risk aggregation algorithm. When the maintenance priority score exceeds the threshold, the unit is marked as high-risk; the units are sorted and repaired according to the maintenance priority score. The higher the score, the greater the impact of the unit failure on the operation and maintenance of the wind farm. Early maintenance replaces reactive maintenance with preventive maintenance, which can significantly reduce the probability of sudden downtime. At the same time, by optimizing the centralized allocation of maintenance resources during low wind speed periods, the power generation loss rate is reduced.

[0084] In some embodiments of the present specification, determining the power generation output timing series data of the wind power generation system and the photovoltaic power generation system in the multi-energy system based on the historical light data and the historical wind speed data of the multi-energy system in the historical time period may include: obtaining the historical light data and the historical wind speed data of the multi-energy system in the historical time period; sampling and clustering the historical light data and the historical wind speed data to obtain the wind speed timing simulation data and the light timing simulation data of the multi-energy system; and calculating the power generation output timing series data of the wind power generation system and the photovoltaic power generation system in the multi-energy system using the wind speed timing simulation data and the light timing simulation data.

[0085] Specifically, by sampling the historical light data and the historical wind speed data, a large number of light samples and wind speed samples can be obtained to fully reflect the volatility, seasonal characteristics and uncertainty of new energy output such as wind power and photovoltaic, and thus improve the accuracy of the prediction. The obtained large number of samples can be clustered to obtain a plurality of different clustering clusters. Then, the wind speed time series simulation data and the light time series simulation data are determined according to the plurality of different clustering clusters. The wind speed time series simulation data can include wind speed simulation data at a plurality of time points in a future target time period. The light time series simulation data can include light simulation data at a plurality of time points in the future target time period. Then, the corresponding output can be calculated by using the wind speed time series simulation data and the light time series simulation data through the output formula, that is, the power generation output time series data of the wind power generation system and the photovoltaic power generation system are obtained. In this way, the power generation output time series data of the wind power generation system and the photovoltaic power generation system in the future preset time period can be determined, so as to facilitate subsequent determination of the maintenance time period and the maintenance capacity.

[0086] In some embodiments of the present specification, sampling and clustering the historical light data and the historical wind speed data to obtain the wind speed time series simulation data and the light time series simulation data of the multi-energy system can include: dividing the historical time period into a plurality of historical sub-time periods; performing probability distribution analysis on the historical light data and the historical wind speed data in each historical sub-time period in the plurality of historical sub-time periods to obtain probability distribution parameters corresponding to the historical light data and the historical wind speed data of each historical sub-time period; based on the probability distribution parameters corresponding to the historical light data and the historical wind speed data of each historical sub-time period, respectively sampling the historical light data and the historical wind speed data in each historical sub-time period by Latin hypercube sampling to obtain wind speed scene sample sets and light scene sample sets corresponding to the historical sub-time periods; and performing clustering analysis on the wind speed scene sample sets and the light scene sample sets corresponding to the historical sub-time periods to obtain the wind speed time series simulation data and the light time series simulation data of the multi-energy system.

[0087] In one embodiment, the historical time period can be the past year, and the historical sub-time period can be each month in the past year. In another embodiment, the historical time period can be the past quarter, and the historical sub-time period can be each week in the past quarter. It can be understood that the historical time period and the historical sub-time period can be other time lengths.

[0088] The probability distribution parameters of each new energy power plant (including a wind power generation system and a photovoltaic power generation system) can be calculated based on historical data of annual wind speed and light intensity in a monthly manner to more accurately reflect the resource characteristics in different time periods. The probability distribution parameters here are the distribution parameters of wind speed and light intensity. The historical wind speed and light intensity are sampled and clustered to simulate new wind speed and light intensity. The corresponding output is calculated using the obtained new wind speed and light intensity through the output formula. The new energy power generation output probability distribution parameters of each month can be Latin sampled according to months, and a large number of new energy daily output scenarios are obtained through sampling to ensure that the samples uniformly cover the probability distribution space (including extreme values), so as to fully reflect the volatility, seasonal characteristics and uncertainty of wind power, photovoltaic and other new energy output. After obtaining the wind speed scenario sample set and the light scenario sample set corresponding to each historical sub-time period, clustering analysis can be performed on the wind speed scenario sample set and the light scenario sample set corresponding to each historical sub-time period to obtain wind speed time series simulation data and light time series simulation data of the multi-energy system. The random optimization problem is converted into a solvable deterministic optimization problem.

[0089] In some embodiments of the present specification, the clustering analysis of the wind speed scenario sample set and the light scenario sample set corresponding to each historical sub-time period to obtain the wind speed time series simulation data and the light time series simulation data of the multi-energy system can include: dividing the wind speed scenarios in the wind speed scenario sample set corresponding to each historical sub-time period into multiple clustering clusters using a clustering algorithm to obtain multiple first clustering clusters corresponding to each historical sub-time period; dividing the light scenarios in the light scenario sample set corresponding to each historical sub-time period into multiple clustering clusters using a clustering algorithm to obtain multiple second clustering clusters corresponding to each historical sub-time period; determining a first target clustering cluster corresponding to each historical sub-time period from the multiple first clustering clusters corresponding to each historical sub-time period according to the occurrence probability of each first clustering cluster in the multiple first clustering clusters corresponding to each historical sub-time period; determining a second target clustering cluster corresponding to each historical sub-time period from the multiple second clustering clusters corresponding to each historical sub-time period according to the occurrence probability of each second clustering cluster in the multiple second clustering clusters corresponding to each historical sub-time period; generating wind speed time series simulation data of the multi-energy system in a future target time period based on the first target clustering cluster corresponding to each historical sub-time period; and generating light time series simulation data of the multi-energy system in the future target time period based on the second target clustering cluster corresponding to each historical sub-time period.

[0090] In this embodiment, the massive sampling scenarios are divided into k disjoint clusters by the k-medoids clustering algorithm, so that the similarity of data objects within the cluster is maximized and the similarity between clusters is minimized, and finally the representative typical daily output scenarios are extracted. The center (medoid) of each cluster corresponds to a typical output mode, thereby converting the random optimization problem into a solvable deterministic optimization problem. Each typical scenario is assigned a weight. Here the weight value is the probability corresponding to each scenario, and the weight is assigned according to the variance of the scenario, and then the low-impact scenarios are gradually deleted, the distance transfer probability is calculated, and finally the weight is normalized to obtain the final weight. Specifically, the initial weight is allocated based on the variance as the core index, and the high-variance scenario is assigned a higher initial weight, breaking the limitation of the traditional equal probability assumption, mapping the physical domain fluctuation characteristics to the probability domain, realizing the risk-oriented initial weight configuration, and avoiding underestimating the impact of extreme scenarios. Then the similarity between scenarios is measured to calculate the Euclidean distance between scenarios. Based on the risk contribution, iterative optimization is realized to achieve dynamic weight adjustment. Through the calculated Euclidean distance, scenarios with high repetition are preferentially reduced, and then by deleting the scenario, the weight is transferred to the nearest scenario according to the similarity, and finally the weight after each iteration is normalized. This method preserves key risk scenarios during dimensionality reduction through risk-geometric joint optimization. The cluster with the largest weight is taken as the target cluster. Then the target clusters corresponding to multiple historical sub-time periods are combined to obtain wind speed simulation data and light timing simulation data in the future target time period. Through the above method, the random optimization problem can be converted into a solvable deterministic optimization problem, and the meteorological data in the future target time period can be predicted, so as to facilitate the prediction of the output data of the wind power generation system and the photovoltaic power generation system in the future target time period.

[0091] In some embodiments of the present specification, based on the historical load data of the multi-energy system and the power generation output time sequence data of the wind power generation system, determining a plurality of maintenance time periods of the wind power generation system in a future target time period can include: determining a low load time period of the multi-energy system in the future target time period based on the historical load data of the multi-energy system; the low load time period is a time period in which the load represented by the historical load data is lower than a preset load; determining a low output time period of the wind power generation system in the future target time period according to the power generation output time sequence data of the wind power generation system; the low output time period is a time period in which the power generation output of the wind power generation system is lower than a preset output; and taking the low load time period and / or the low output time period as the plurality of maintenance time periods of the wind power generation system in the future target time period. By taking the low load time period and the low output time period as the maintenance time period, the shutdown of the high wind speed period can be avoided, the system power balance can be ensured, and the impact on the power generation capacity can be reduced.

[0092] In some embodiments of the present specification, the determination of the maintenance capacity corresponding to each of the plurality of maintenance time periods of the wind power generation system based on the time series data of power generation output of the photovoltaic power generation system, the output constraints of each system in the multi-energy system, the power balance constraints of the multi-energy system, and the maintenance constraints of the wind power generation system can include: solving a target function of the multi-energy system based on the time series data of power generation output of the photovoltaic power generation system and the output constraints of each system in the multi-energy system and the power balance constraints of the multi-energy system to determine the power generation output data of each energy system in the multi-energy system in a future target time period; determining the theoretical maintenance capacity corresponding to each of the plurality of maintenance time periods based on the power generation output data of each energy system in the multi-energy system in the future target time period and the historical load data in the historical time period; and correcting the theoretical maintenance capacity corresponding to each of the plurality of maintenance time periods by using the maintenance constraints of the wind power generation system to obtain the target maintenance capacity corresponding to each of the plurality of maintenance time periods.

[0093] In the present embodiment, the power generation output data of each energy system in the multi-energy system in a future target time period can be determined by solving a target function of the multi-energy system based on the time series data of power generation output of the photovoltaic power generation system and the output constraints of each system in the multi-energy system and the power balance constraints of the multi-energy system. In one embodiment, the lowest production cost of system operation can be taken as the target function. In another embodiment, in addition to considering the production cost, other indicators such as the newly added reliability indicators (such as system backup capacity margin) and environmental benefit indicators (such as carbon emission change during maintenance) can be considered to construct a multi-objective optimization model. After solving the target function, the power generation output data of each energy system in the multi-energy system in the future target time period can be determined. Further, the theoretical maintenance capacity corresponding to each of the plurality of maintenance time periods can be determined based on the power generation output data of each energy system in the multi-energy system in the future target time period and the historical load data in the historical time period. The determined theoretical maintenance capacity can be the maximum number of wind turbines that can be shut down while ensuring that the load is met. After determining the theoretical maintenance capacity, the target maintenance capacity corresponding to each of the plurality of maintenance time periods can be obtained by correcting the theoretical maintenance capacity corresponding to each of the plurality of maintenance time periods by using the maintenance constraints of the wind power generation system. The target maintenance capacity satisfies the maintenance constraints. Then, the maintenance plan of the wind power generation system can be generated based on the plurality of maintenance time periods, the target maintenance capacity, and the maintenance priority scores of each wind turbine. The method in the present embodiment not only considers the volatility of wind power output, maintenance constraints, power balance, etc., but also considers the operation of the unit and the priority of the unit maintenance; the maintenance period and the unit sequence can be arranged scientifically, and the maintenance schedule can be generated.

[0094] Each of the embodiments in the specification is described in a progressive manner, and the same or similar parts between each embodiment can be referred to each other, and each embodiment focuses on the difference from other embodiments. For specific description, refer to the description of the related processing related embodiments described above, which will not be repeated here.

[0095] The above describes specific embodiments of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different than the order in the embodiments and still achieve the desired result. In addition, the processes depicted in the figures do not necessarily require the particular order shown or sequential order to achieve the desired results. In certain implementations, multitasking and parallel processing are also possible or advantageous.

[0096] The above method will be described in conjunction with a specific embodiment, however, it is worth noting that this specific embodiment is only for better illustration of the specification and does not constitute an improper limitation of the specification.

[0097] A wind turbine unit maintenance method for a multi-energy system is provided in the specific embodiment. The method in the embodiment of the specification applies an optimization algorithm based on unit importance evaluation and wind power output constraint analysis, establishes a unit component evaluation and importance calculation model, an output constraint and maintenance capacity calculation model, and integrates maintenance plan optimization and power balance guarantee, effectively reducing the downtime loss of the wind farm and improving the operation efficiency and power supply stability of the wind power system. The embodiment of the specification faces the wind turbine unit maintenance plan optimization method based on unit importance evaluation, and is implemented according to the following steps.

[0098] Step 1, first, the unit components of the wind turbine unit are evaluated by using the digital detection system, the importance of the components is evaluated by combining the cost, maintenance time and other factors, and then the maintenance priority of the unit is determined. The specific process is: the cost, maintenance cost, maintenance time and maintenance frequency of each wind turbine unit are obtained by the digital detection system. These data provide a basis for subsequent calculation of unit component maintenance priority index.

[0099] The wind turbine is divided into 11 subsystems according to system functions, which are wind wheel system, variable pitch system, transmission system, generator system, frequency converter system, main control system, hydraulic system, yaw system, nacelle tower system, protection system and box transformer system. Each system includes many components, such as transmission system including gear box, gear box bearing, gear box transmission shaft, gear box lubricating oil, brake, etc. Taking gear box transmission shaft and brake as an example, the cost of a gear box is 1 million yuan, the operation and maintenance frequency of gear box transmission shaft is high, and the severity of failure is high under normal circumstances. After failure, the unit will usually be shut down, and the repair time is also relatively long, usually 20 to 25 days. As for the brake and other components, although the operation and maintenance frequency is also relatively high, the severity of failure is generally low, and the repair time is usually 1 day, which is relatively simple and the repair cost is relatively low.

[0100] The cost, repair cost, repair time, operation and maintenance frequency and other factors of the components are comprehensively evaluated by using the weighted average method. By assigning weights to each evaluation factor, the repair priority index of each component is calculated using a weighted summation model. The above four factors are divided into scores according to intervals, as shown in Table 1.

[0101] Table 1

[0102]

[0103] This score will reflect the importance of the component in the unit, facilitating the priority arrangement of the subsequent repair plan. The following weighted summation model is used:

[0104]

[0105] Wherein, MRI is the component repair priority index; S Cp is the component cost score; S Cm is the repair cost score; S Tm is the repair time; S Fo is the operation and maintenance frequency; α1, α2, α3, α4 are weight coefficients, which are determined by actual situation and expert judgment. The weight coefficients can be formulated by a team of experienced experts in the field of wind power, based on years of operation and maintenance experience, to ensure that the weight distribution not only meets the industry standards, but also accurately reflects the impact of component failure on the system.

[0106] After obtaining the repair priority index of each component, the repair priority of each wind turbine is aggregated and evaluated, and the weighted average method is used to summarize the repair priority index of each component into the repair priority of the unit. The unit with high comprehensive repair priority will be arranged for repair in priority, so as to ensure that the high-risk unit is maintained in time and optimize the effect of the overall repair plan.

[0107]

[0108] where IMP total is the priority score of the unit comprehensive maintenance; MRI i is the maintenance priority index of the ith component; ω i is the weight coefficient of the ith component, representing the importance of the component to the priority of the unit comprehensive maintenance; and n is the number of components in the unit.

[0109] Through the above process, the maintenance priority of each unit can be accurately evaluated, and the order of the unit in the maintenance plan can be determined, thereby providing a basis for subsequent maintenance plan optimization.

[0110] Step 2, considering the power characteristics of multiple energy sources, power balance, and maintenance constraints, determine the output of each type of energy source and the maintenance capacity of wind power; the specific process is as follows:

[0111] Step 2.1, first, based on historical wind speed and light intensity data, perform probability distribution analysis on the output of wind power and photovoltaic power generation. This process divides the annual wind speed and light intensity data into monthly probability distribution parameters by dividing them into monthly increments. The uncertainty of wind speed is approximated by Weibull distribution, where the probability density function of wind speed can be expressed as:

[0112]

[0113] where f(x, λ, k) is the probability density function of wind speed, x is the wind speed, λ is the scale parameter, and k is the shape parameter. Similarly, the uncertainty of light intensity can be described using Beta distribution, which is expressed as:

[0114]

[0115] where f(I, α, β) is the uncertainty distribution function of light intensity, I is the random variable of light, I max is the maximum light amount, α is the shape factor of Beta distribution, α>0, and β is the scale factor of Beta distribution, β>0. The uncertainty of load follows a normal distribution, which is expressed as:

[0116]

[0117] where f(P L ) is the uncertainty distribution function of load, P L is the size of the load, μ is the average value of the load in the statistical period, and σ is the standard deviation of the load in the statistical period.

[0118] Step 2.2, After obtaining the probability distribution of wind speed and light, Latin Hypercube Sampling (LHS) is used to simulate a large number of wind speed and light scenarios. This method can generate a representative sample set, reflecting the resource characteristics and load patterns at different times. Next, the k-medoids clustering algorithm is used to process these scenarios and divide them into several typical scenarios. The k-medoids algorithm optimizes the clustering effect of scenarios by calculating the Euclidean distance between samples, thereby selecting the most representative scenarios.

[0119]

[0120] where d(x i ,x j ) is the Euclidean distance, x i and x j represent the feature vectors of the data points.

[0121] Specifically, Latin sampling is performed on the monthly new energy generation output probability distribution parameters of each month to ensure uniform coverage of the probability distribution space (including extreme values) through sampling, obtaining a large number of new energy daily output scenarios to fully reflect the volatility, seasonal characteristics, and uncertainty of wind power, photovoltaic, and other new energy output. Further, through the k-medoids clustering algorithm, the massive sampling scenarios are divided into k disjoint clusters, maximizing the similarity of data objects within the cluster and minimizing the similarity between clusters, and finally extracting representative typical daily output scenarios. The center (medoid) of each cluster corresponds to a typical output mode, thereby converting the random optimization problem into a solvable deterministic optimization problem.

[0122] By weighting the clustering results, the impact of different scenarios on system operation can be reflected in the model. Scenarios with larger weights will have a higher proportion in subsequent simulations, making the simulation results more consistent with actual energy supply and demand. Weighting assigns weights to each typical scenario. Here, the weight value is the probability corresponding to each scenario, and the weight is assigned according to the scenario variance. Low-impact scenarios are then gradually removed, and the final weight is normalized according to the distance transfer probability. The model is a multi-scenario random optimization model used to simulate the operation of a power system with a high proportion of new energy. The model is the model used for subsequent production simulation, including wind power, photovoltaic, solar thermal, and energy storage models, which are modeled based on their output.

[0123] Initial weight allocation: The initial weights are allocated based on the variance as the core indicator. High variance scenarios are given higher initial weights, breaking the limitations of traditional equal probability assumptions, mapping the physical domain fluctuation characteristics to the probability domain, achieving risk-oriented initial weight configuration, and avoiding underestimating the impact of extreme scenarios. Then, the Euclidean distance between scenarios is calculated through similarity measurement. Based on risk contribution, iterative optimization is performed to achieve dynamic weight adjustment. Through the calculated Euclidean distance, scenarios with high repetition are preferentially reduced. Then, by deleting the scene, the weight is transferred to the nearest scene according to the similarity. Finally, the weights after each iteration are normalized. This method preserves key risk scenarios in the dimensionality reduction process through risk-geometric joint optimization. The weight of each typical scenario is related to its occurrence probability. In the optimization process, the model will give priority to the impact of high-weight scenarios. In the objective function of multi-energy complementary production simulation, the penalty cost (such as wind curtailment, light curtailment, and load loss) and operation cost of different scenarios are weighted and summed according to the scenario weight.

[0124] Step 2.3, based on the above obtained wind speed and light data scenarios, the wind power and photovoltaic power generation output are calculated respectively through known conversion formula. The output expression of wind power is as follows:

[0125]

[0126] wherein, is the output of wind turbine; v t is the size of real-time wind speed at t time; v in is the cut-in wind speed of wind turbine; v out is the cut-out wind speed of wind turbine; v r is the rated wind speed; is the rated power of wind turbine; is the real-time power of wind turbine. Similarly, the photovoltaic power generation output is calculated by the light intensity and the conversion efficiency of photovoltaic panel:

[0127]

[0128] wherein, P(t) is the photovoltaic power generation output; I std is the unit area light intensity under standard conditions, taking the value of 1000 W / m 2 ; I(t) is the real-time light intensity; R c is a specific light intensity, taking the value of 150 W / m 2 ; P sn is the rated power of photovoltaic panel under standard conditions; η is the photoelectric conversion efficiency of photovoltaic panel. And repeat the above steps to statistically calculate the time series of new energy of each month, and combine to obtain the time series data of one year, providing a basis for subsequent analysis.

[0129] Step 2.4, in order to make the model run more in line with the actual demand, the production cost of system operation is taken as the objective function. It mainly includes the fuel consumption cost of photo-thermal and the penalty cost of abandoned wind, light and load loss. The specific objective function form is as follows:

[0130]

[0131] Wherein, f is the objective function, t represents the period; T is the total length of the calculation period; are the generation cost of photo-thermal and energy storage unit in t period respectively; λ R , λ L are the new energy abandoned electricity penalty cost and load shedding penalty cost respectively; are the new energy abandoned electricity and load shedding electricity respectively; is the function between the operation cost of photo-thermal unit and the output size; are the start and stop state of the i th unit in photo-thermal power station respectively; are the start and stop cost of the i th unit in photo-thermal power station respectively; is the operation cost function in the discharging process of energy storage battery; are the real-time output of wind farm and photovoltaic farm in t period respectively; are the maximum generation output of wind power and photovoltaic in t period respectively; load,t represent the real-time load of system in t period and the load participating in dispatching balance respectively; N csp , N bat are the number of photo-thermal units and battery respectively.

[0132] Step 2.5, considering the output constraint of each type of unit, the output of wind power and photovoltaic generation in t period is between its maximum output and 0. The output constraint expression of wind power and photovoltaic generation is as follows:

[0133]

[0134] The constraint conditions of photo-thermal power station model cover the heat dynamic balance of heat collection field and heat storage tank, as well as the upper and lower limits and climbing restrictions of generator output.

[0135]

[0136] Wherein, are the heat used for power generation by the i th unit of photo-thermal power station in t period, the total solar heat absorbed by the heat collection field, the heat stored in the heat tank of photo-thermal power station, and the abandoned heat of photo-thermal power station respectively; are the heat stored in the heat tank in t period, the heat transferred from the heat collection field to the heat storage tank, and the heat transferred from the heat storage tank to the power generation side respectively;​ are the heat storage efficiency, heat release efficiency, and the i-th unit's power generation efficiency, respectively. are the lower limit, actual power, and upper limit of the i-th unit's power generation, respectively. are the minimum and maximum heat storage capacity of the heat storage tank, respectively. U,i D,i are the maximum and minimum ramping capability of the i-th unit, respectively. is the on-off state of the i-th unit in the t-th period.

[0137] The constraints in the electrochemical energy storage operation are also incorporated into the production simulation model, which include the maximum power constraint for charging and discharging, the energy storage capacity constraint, and the state of charge balance constraint, which are expressed as follows:

[0138] 0 < SOC w,t < SOC w,max

[0139]

[0140] where SOC w,max and SOC w,t are the maximum capacity of the w-th energy storage battery and the battery charge at time t, respectively. are the discharging / charging state of the w-th energy storage battery in the t-th period. are the real-time power, minimum / maximum power of the w-th energy storage battery during charging in the t-th period. are the real-time power, minimum / maximum power of the w-th energy storage battery during discharging in the t-th period.

[0141] Step 2.6: Consider the wind turbine maintenance constraints. The expressions of the maintenance frequency, maintenance time, maintenance continuity, maintenance time interval, and maintenance capability constraints are as follows:

[0142]

[0143] where z pw,t is a 0-1 variable indicating whether the unit starts maintenance; MN pw is the number of times the unit needs to be maintained in the T period; x pw,t is a 0-1 variable indicating whether the unit is in maintenance; MT pw is the duration of each maintenance of the unit; MG pw is the minimum time interval between two consecutive maintenance of the unit; MC pws is the maintenance capability of the power plant, i.e., the number of units that can be simultaneously maintained.

[0144] ​Step 2.7, In addition to the constraints of each unit and the maintenance constraints, the system stable operation also needs to meet the power balance constraints.

[0145]

[0146] Wherein is the discharge and charge power of each battery at time t; is the load size at time t; is the load shedding power at time t. is the actual power of the i-th unit of the solar thermal power plant at time t. is the dispatch real-time output of the photovoltaic power plant at time t. is the new energy curtailment. is the power generation output of the wind power plant at time t.

[0147] Step 2.8, Calculate the wind power maintenance capacity based on the power balance constraints and maintenance resource constraints.

[0148] (1) Identify the maintenance window: based on the wind power output time series data in step 2.3 and the typical low output scenario in step 2.2, filter the low output period (such as calm period, night low) as the candidate maintenance window;

[0149] (2) Calculate the theoretical maintenance capacity: calculate the maximum maintenance capacity allowed in this period through the power balance equation (step 2.7).

[0150] (3) Superimpose maintenance resource constraints correction: according to the maintenance frequency MN pw , the duration of single maintenance MT pw , the interval of continuous maintenance MG pw and the simultaneous maintenance capacity of power plant MC pws , correct the theoretical capacity.

[0151] Step 3, based on the state of each wind turbine unit and the maintenance capacity, make an optimal maintenance plan. The specific process is as follows:

[0152] According to the obtained monthly, quarterly and annual maintenance capacity of the system, allocate the maintenance capacity of each time period. Based on the importance of each wind turbine unit obtained in step 1, arrange the maintenance of the units with high importance in order from high to low. Thus, a maintenance schedule table is generated, which outputs the maintenance plan of each time period, including information: maintenance time period, maintenance unit number, maintenance duration of the unit. If the importance of multiple units is the same, further sorting is carried out according to the following rules: a, the unit with lower maintenance cost is preferred. b, the unit with shorter maintenance time is preferred.

[0153] The above method is described below with a specific embodiment. The wind turbine maintenance planning optimization method considering the priority of unit maintenance is used to simulate the production of a multi-energy system composed of a wind farm, a photovoltaic power station, a solar-thermal power station, and an energy storage power station, and to develop a maintenance plan for 48 wind turbine units. The system and component composition of the wind turbine units are shown in Table 2.

[0154] The installed capacity of the wind power is 216 MW, the installed capacity of the photovoltaic power is 50 MW, the installed capacity of the solar-thermal power is 100 MW, and the energy storage is equipped with 10 MW / 20 MWh. According to the installed capacity of each type of energy and the constraints such as unit output constraints, while constraining the number of unit maintenance, maintenance time, maintenance continuity and maintenance capacity, the hourly output process of each type of energy in the first quarter is simulated as shown in Figure 2 , and the wind turbine maintenance arrangement, the results are shown in Figure 3 .

[0155] Table 2

[0156]

[0157] Figure 2 The hourly output process of the wind power, photovoltaic power, solar-thermal power and energy storage system in the first quarter is shown. As shown in Figure 2 , the output of the wind power system fluctuates greatly, showing obvious intermittency and volatility, reflecting the instability of wind resources. The output of the photovoltaic system has strong volatility during the day, and shows a typical sunshine periodicity, with high output during the day and close to zero at night. The solar-thermal system shows a relatively stable output curve, with less volatility than wind power and photovoltaic power, mainly affected by light intensity and technical constraints. The role of the energy storage system is to smooth the fluctuations of the above-mentioned energies, by storing excess power and releasing power at peak demand, effectively balancing the system load demand. Figure 3 The wind turbine maintenance capacity of each week in the first quarter is compared with Figure 2 and Figure 3 It can be seen that when the wind is strong, the power generation capacity of the wind turbine units is high, and large-scale maintenance during these periods may result in a large loss of power generation. Therefore, the maintenance plan of the wind turbine units tends to be arranged in periods of weak wind, in order to avoid maintenance during periods of high wind speed as much as possible, and to ensure that the power generation capacity of the system is not affected too much. In periods of low wind power output (such as the 4th week and the 10th week), more wind turbine units are arranged for maintenance, so that even if part of the units are in maintenance, the overall load of the system will not be affected too much. This can ensure the stability of the system and reduce the pressure on the power grid caused by the inability of the wind turbine units to provide sufficient power.

[0158] On the basis of the obtained wind turbine maintenance capacity, the 48 wind turbines are further arranged in maintenance sequence according to the maintenance priority of the wind turbines, so as to obtain a wind turbine maintenance schedule for the first quarter, and ensure the stability and efficient operation of the system.

[0159] According to the digital detection system, the data of each component of each wind turbine is obtained, including component cost, maintenance cost, maintenance time and operation and maintenance frequency. Different operation states of the wind turbine monitored online correspond to different maintenance costs and maintenance times. The data of each component of the wind turbine is shown in Table 3.

[0160] Table 3

[0161]

[0162] The maintenance priority index of each component is calculated by the given weighting coefficients α1=0.3; α2=0.2; α3=0.2; α4=0.3, and the calculation is as follows:

[0163]

[0164] The maintenance priority index of each component is used to calculate the comprehensive maintenance priority of the wind turbine. By weighted average method, the scores of each component are combined to obtain the maintenance priority of each wind turbine, so as to arrange the maintenance sequence of each wind turbine. Through the above calculation, the maintenance priority scores (the highest score is 3.7) of the following wind turbines are obtained, as shown in Table 4.

[0165] Table 4

[0166] Unit number Status score Unit 1 2.955 Unit 2 3.567 Unit 3 2.576 … … Unit 48 3.178

[0167] According to the comprehensive maintenance priority index of the wind turbine, the wind turbine with a higher score is arranged to be maintained first. The higher the score of the wind turbine, the higher the maintenance priority. On the basis of the obtained maintenance capacity, the maintenance time of each wind turbine is arranged. For the first week, the maintenance capacity is only 5.15 MW, and each wind turbine has a capacity of 4.5 MW, so only one wind turbine can be maintained. Therefore, the wind turbine with the highest comprehensive maintenance priority index, i.e. wind turbine 2, is arranged to be maintained, and the same is applied to the other wind turbines. Finally, the maintenance schedule for the first quarter is obtained, as shown in Table 5.

[0168] Table 5

[0169]

[0170] The wind turbine maintenance schedule optimization method considering the maintenance priority of the wind turbine of the embodiments of the present specification arranges the maintenance of the key wind turbine first by calculating the maintenance priority index of the components of the wind turbine, ensures that the maintenance schedule is more scientific and reasonable, avoids waste of resources, and improves the efficiency of the system operation.

[0171] The embodiment of the specification combines wind power output constraint and weather forecast, reasonably arranges the maintenance period through maintenance constraint and multi-energy complementary collaborative optimization mechanism, first, based on wind power output time series data (quantifying output characteristics of each period throughout the year) and typical low output scene clustering results (such as calm wind period, night low valley), using wind power-photovoltaic photothermal- energy storage combined output model, dynamically coordinating multi-energy maintenance window, preferentially calling photothermal heat storage power generation in calm wind period, improving energy storage discharge power in photovoltaic low valley period, and using power balance equation to calculate the theoretical maximum maintenance capacity in the period; At the same time, combine the maintenance constraint parameters (single unit maintenance times, maintenance duration, continuous maintenance minimum interval and simultaneous maintenance capacity) to correct the maintenance capacity; Finally, preferentially allocate the maintenance capacity to the low output window to avoid shutdown in high wind speed period, ensure system power balance, and reduce the impact on power generation capacity.

[0172] The embodiment of the specification dynamically adjusts the maintenance plan, optimizes the maintenance time of each unit according to real-time wind power output and unit maintenance priority, and when real-time failure occurs, priority update and maintenance period optimization are triggered. The CMS system detects the state of the unit component, when the vibration of a component of a unit suddenly increases and exceeds the threshold value, the system automatically triggers the MRI recalculation of the component. MRI increases, the comprehensive priority of the unit improves, the maintenance sequence is advanced, the failure is avoided to expand, the downtime is reduced, the power generation efficiency and economic benefit are improved. Although it is mainly based on unit maintenance priority and pre-calculated maintenance capacity for planning arrangement, but real-time failure will trigger priority update and maintenance period optimization, the CMS system detects the state of the unit component, when the vibration of a component of a unit suddenly increases and exceeds the threshold value, the system automatically triggers the MRI recalculation of the component. MRI increases, the comprehensive priority of the unit improves. Originally planned, the unit was scheduled to be maintained in the third week, after the system detected the MRI increase, combined with the current wind power output data, it was advanced to the first week, avoiding the expansion of the failure.

[0173] The embodiment of the present specification is based on the real-time acquisition of multi-dimensional parameters such as component cost, repair cost, repair time, and operation and maintenance frequency by a digital detection system, adopts a weighted MRI model, can accurately quantify the criticality of each component, accurately calculates the repair priority index of the unit component by a system-level risk aggregation algorithm to realize differentiated repair, sorts and repairs the unit according to the IMP score, and the higher the score, the greater the impact of the unit failure on the operation and maintenance of the wind farm, implements preventive maintenance, prolongs the service life of the unit, reduces major failures, and greatly reduces the probability of sudden shutdown. Based on the real-time acquisition of multi-dimensional parameters such as component cost, repair cost, repair time, and operation and maintenance frequency by a digital detection system, a weighted MRI index model is adopted, wherein the operation and maintenance frequency weight ratio can quickly respond to the risk of high-frequency maintenance components; the system-level risk aggregation algorithm is used to calculate the comprehensive priority of the unit, and when the score breaks through the threshold, it is marked as a high-risk unit (for example, unit 2 with a score of 3.567 is given priority to repair in the first week); the unit is sorted and repaired according to the IMP score, and the higher the score, the greater the impact of the unit failure on the operation and maintenance of the wind farm, and preventive maintenance is used to replace passive maintenance, which can greatly reduce the probability of sudden shutdown, and at the same time, by optimizing the centralized allocation of repair resources in low wind speed periods, the power generation loss rate is reduced.

[0174] The method in the embodiment not only considers factors such as the volatility of wind power output, repair constraints, and power balance, but also considers unit operation and unit repair priority, so that the repair period and unit sequence can be scientifically arranged, and a repair schedule can be generated.

[0175] Based on the same inventive concept, the present specification also provides a wind turbine generator unit repair device for a multi-energy system, as described in the following embodiments. Since the wind turbine generator unit repair device for a multi-energy system solves the problem by the same principle as the wind turbine generator unit repair method for a multi-energy system, the implementation of the wind turbine generator unit repair device for a multi-energy system can be referred to the implementation of the wind turbine generator unit repair method for a multi-energy system, and the repeated parts will not be described again. The term "unit" or "module" used below can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware, or a combination of software and hardware is also possible and contemplated. Figure 4 is a structural block diagram of the wind turbine generator unit repair device for a multi-energy system of the present specification, as shown in Figure 4 The structure is described as follows.

[0176] The priority determination module 401 is configured to determine the repair priority score of each wind turbine generator unit in the wind power system according to the repair correlation data of the unit components of each wind turbine generator unit in the plurality of wind turbine generator units in the wind power system.

[0177] The output determination module 402 is configured to determine power generation output time sequence data of the wind power generation system and the photovoltaic power generation system in the multi-energy system according to historical illumination data and historical wind speed data of the multi-energy system in a historical time period; the power generation output time sequence data includes power generation output data of the wind power generation system and the photovoltaic power generation system at multiple time points in a future target time period.

[0178] The maintenance capacity determination module 403 is configured to determine multiple maintenance time periods of the wind power generation system in the future target time period based on historical load data of the multi-energy system and the power generation output time sequence data of the wind power generation system, and determine a maintenance capacity corresponding to each maintenance time period of the wind power generation system in the multiple maintenance time periods according to the power generation output time sequence data of the photovoltaic power generation system, output constraints of each system in the multi-energy system, power balance constraints of the multi-energy system, and maintenance constraints of the wind power generation system.

[0179] The maintenance scheme generation module 404 is configured to generate a target maintenance scheme of the wind power generation system in the target time period by using the maintenance priority scores of the wind power generation units, the multiple maintenance time periods, and the maintenance capacities corresponding to the multiple maintenance time periods, so as to maintain each wind power generation unit of the wind power generation system in the future target time period based on the target maintenance scheme.

[0180] In some embodiments of the present disclosure, the priority determination module is specifically configured to: obtain maintenance correlation data of multiple unit components of each wind power generation unit in the wind power generation system; calculate maintenance priority indexes of the components of each wind power generation unit according to the maintenance correlation data of the components of each wind power generation unit; and calculate the maintenance priority score of each wind power generation unit based on the maintenance priority indexes of the components of each wind power generation unit and the component weights corresponding to the components.

[0181] In some embodiments of the present disclosure, the priority determination module is further specifically configured to: after calculating the maintenance priority indexes of the components of each wind power generation unit according to the maintenance correlation data of the components of each wind power generation unit, obtain state data of the unit components of each wind power generation unit monitored by a state monitoring system; and in a case where the state data of a unit component of a wind power generation unit satisfies a preset condition, update the maintenance priority index of the unit component, so that the maintenance priority index of the component increases.

[0182] In some embodiments of the present disclosure, the maintenance correlation data can include component cost, maintenance cost, component maintenance duration, and component maintenance frequency; accordingly, the priority determination module is specifically configured to determine maintenance correlation scores of the components of the wind turbines according to the maintenance correlation data of the components of the wind turbines and a preset correlation data scoring table; the maintenance correlation scores can include at least one of component cost score, maintenance cost score, component maintenance duration score, and component maintenance frequency score; and based on the maintenance correlation scores of the components of the wind turbines and correlation data weights corresponding to the maintenance correlation data, maintenance priority indexes of the components of the wind turbines are calculated.

[0183] In some embodiments of the present disclosure, the output determination module: obtains historical illumination data and historical wind speed data of the multi-energy system in a historical time period; performs sampling clustering on the historical illumination data and the historical wind speed data to obtain wind speed time sequence simulation data and illumination time sequence simulation data of the multi-energy system; and calculates power generation output time sequence data of the wind power generation system and the photovoltaic power generation system in the multi-energy system by using the wind speed time sequence simulation data and the illumination time sequence simulation data.

[0184] In some embodiments of the present disclosure, the sampling clustering on the historical illumination data and the historical wind speed data to obtain the wind speed time sequence simulation data and the illumination time sequence simulation data of the multi-energy system can include: dividing the historical time period into a plurality of historical sub-time periods; performing probability distribution analysis on the historical illumination data and the historical wind speed data in each historical sub-time period in the plurality of historical sub-time periods to obtain probability distribution parameters corresponding to the historical illumination data and the historical wind speed data in each historical sub-time period; based on the probability distribution parameters corresponding to the historical illumination data and the historical wind speed data in each historical sub-time period, performing Latin hypercube sampling on the historical illumination data and the historical wind speed data in each historical sub-time period respectively to obtain wind speed scene sample sets and illumination scene sample sets corresponding to the historical sub-time periods; and performing clustering analysis on the wind speed scene sample sets and the illumination scene sample sets corresponding to the historical sub-time periods to obtain the wind speed time sequence simulation data and the illumination time sequence simulation data of the multi-energy system.

[0185] In some embodiments of the present disclosure, the clustering analysis of the wind speed scene sample set and the light scene sample set corresponding to each historical sub-time period to obtain the wind speed time series simulation data and the light time series simulation data of the multi-energy system can include: dividing the wind speed scenes in the wind speed scene sample set corresponding to each historical sub-time period into a plurality of clustering clusters using a clustering algorithm to obtain a plurality of first clustering clusters corresponding to each historical sub-time period; dividing the light scenes in the light scene sample set corresponding to each historical sub-time period into a plurality of clustering clusters using a clustering algorithm to obtain a plurality of second clustering clusters corresponding to each historical sub-time period; determining a first target clustering cluster corresponding to each historical sub-time period from the plurality of first clustering clusters corresponding to each historical sub-time period according to the occurrence probability of each first clustering cluster in the plurality of first clustering clusters corresponding to each historical sub-time period; determining a second target clustering cluster corresponding to each historical sub-time period from the plurality of second clustering clusters corresponding to each historical sub-time period according to the occurrence probability of each second clustering cluster in the plurality of second clustering clusters corresponding to each historical sub-time period; generating wind speed time series simulation data of the multi-energy system in a future target time period based on the first target clustering cluster corresponding to each historical sub-time period; and generating light time series simulation data of the multi-energy system in the future target time period based on the second target clustering cluster corresponding to each historical sub-time period.

[0186] In some embodiments of the present disclosure, the maintenance capacity determination module is specifically configured to: determine a low load time period of the multi-energy system in a future target time period based on historical load data of the multi-energy system; the low load time period is a time period in which the load represented by the historical load data is lower than a preset load; determine a low output time period of the wind power generation system in the future target time period according to the power generation output time series data of the wind power generation system; the low output time period is a time period in which the power generation output of the wind power generation system is lower than a preset output; and take the low load time period and / or the low output time period as a plurality of maintenance time periods of the wind power generation system in the future target time period.

[0187] In some embodiments of the present specification, the maintenance capacity determination module is specifically configured to: based on the power generation time sequence data of the photovoltaic power generation system and the power generation constraints of each system in the multi-energy system and the power balance constraints of the multi-energy system, solve the objective function of the multi-energy system to determine the power generation data of each energy system in the multi-energy system in the future target time period; according to the power generation data of each energy system in the multi-energy system in the future target time period and the historical load data in the historical time period, determine the theoretical maintenance capacity corresponding to each maintenance time period in the plurality of maintenance time periods; and correct the theoretical maintenance capacity corresponding to each maintenance time period by using the maintenance constraints of the wind power generation system to obtain the target maintenance capacity corresponding to each maintenance time period.

[0188] The present specification also provides a computer device, which can specifically refer to Figure 5 The computer device for implementing the wind turbine maintenance method for a multi-energy system provided by the embodiments of the present specification can specifically include an input device 51, a processor 52, and a memory 53. The memory 53 is configured to store processor-executable instructions. The processor 52 implements the steps of the wind turbine maintenance method for a multi-energy system provided by any of the embodiments of the present specification when executing the instructions.

[0189] In the present embodiment, the input device can be one of the main devices for exchanging information between the user and the computer system. The input device can include a keyboard, a mouse, a camera, a scanner, a light pen, a handwriting input board, a voice input device, etc.; the input device is used to input raw data and programs for processing these data into the computer. The input device can also obtain data transmitted by other modules, units, and devices. The processor can be implemented in any appropriate manner. For example, the processor can take the form of a microprocessor or a processor and a computer readable medium storing computer readable program codes (such as software or firmware) executable by the (micro) processor, logic gates, switches, application specific integrated circuits (ASIC), programmable logic controllers, and embedded microcontrollers, etc. The memory can be a memory device used for storing information in modern information technology. The memory can include multiple levels, and in a digital system, as long as it can store binary data, it can be a memory; in an integrated circuit, a circuit without a physical form with a storage function is also called a memory, such as RAM, FIFO, etc.; in a system, a storage device with a physical form is also called a memory, such as a memory stick, a TF card, etc.

[0190] In the embodiment, the functions and effects realized by the computer device can be explained in comparison with other embodiments, and will not be repeated here.

[0191] The embodiment of the present specification also provides a computer storage medium based on the wind turbine unit maintenance method for a multi-energy system, which stores computer program instructions. When the computer program instructions are executed, the steps of the wind turbine unit maintenance method for the multi-energy system in any of the above embodiments are realized.

[0192] In the embodiment, the storage medium includes but is not limited to random access memory (RAM), read-only memory (ROM), cache, hard disk drive (HDD) or memory card. The storage can be used to store computer program instructions. The network communication unit can be an interface set according to the standard of the communication protocol, used for network connection communication.

[0193] In the embodiment, the functions and effects realized by the program instructions stored in the computer storage medium can be explained in comparison with other embodiments, and will not be repeated here.

[0194] Obviously, those skilled in the art should understand that each module or each step of the above-mentioned embodiments of the present specification can be realized by a general computing device, which can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be realized by program codes executable by a computing device, so that they can be stored in a storage device and executed by a computing device, and in some cases, the steps shown or described can be executed in different order, or they can be manufactured into each integrated circuit module, or multiple modules or steps among them can be manufactured into a single integrated circuit module. Therefore, the embodiments of the present specification are not limited to any specific combination of hardware and software.

[0195] It should be understood that the above description is for illustration only and not for limitation. Many implementations and many applications other than the examples provided would be apparent to those skilled in the art from the above description. Therefore, the scope of the present specification should not be determined with reference to the above description, but should be determined with reference to the appended claims and the full scope of equivalents to which the claims are entitled.

[0196] The above merely provides preferred embodiments of the present specification but are not intended to limit the present specification. The present specification can have various modifications and changes for those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification shall be included in the protection scope of the present specification.

Claims

1. A wind turbine maintenance method for a multi-energy system, characterized in that: The multi-energy system includes a wind power generation system, a photovoltaic power generation system, an energy storage system and a solar thermal power generation system; the method includes: determining a maintenance priority score for each wind turbine in the wind power generation system based on maintenance-related data of multiple turbine components of each wind turbine; Determining power generation output time series data of a wind power generation system and a photovoltaic power generation system in the multi-energy system based on historical sunlight data and historical wind speed data of the multi-energy system in a historical time period; the power generation output time series data includes power generation output data of the wind power generation system and the photovoltaic power generation system at multiple moments in a future target time period; Determine, based on the historical load data of the multi-energy system and the power generation output time series data of the wind power generation system, multiple maintenance time periods of the wind power generation system within a future target time period; determine, based on the power generation output time series data of the photovoltaic power generation system, the output constraints of each system in the multi-energy system, the power balance constraints of the multi-energy system, and the maintenance constraints of the wind power generation system, the maintenance capacity of the wind power generation system corresponding to each maintenance time period in the multiple maintenance time periods; By utilizing the maintenance priority scores of the wind turbines, the multiple maintenance time periods, and the maintenance capacity corresponding to each maintenance time period, a target maintenance plan for the wind power generation system within a target time period is generated, so that the wind turbines of the wind power generation system can be maintained based on the target maintenance plan within a future target time period.

2. The wind turbine maintenance method for a multi-energy system according to claim 1, characterized in that: Determining a maintenance priority score of each wind turbine in the wind power generation system based on maintenance-related data of multiple turbine components of each wind turbine, including: Acquiring maintenance-related data of a plurality of unit components of each of a plurality of wind turbine units in the wind power generation system; Calculating the maintenance priority index of each component of each wind turbine generator set according to the maintenance association data of each component of each wind turbine generator set; Based on the maintenance priority index of each component of each wind turbine generator set and the component weight corresponding to each component, a maintenance priority score of each wind turbine generator set is calculated.

3. The wind turbine maintenance method for a multi-energy system according to claim 2, characterized in that: The maintenance-related data includes: component cost, maintenance cost, component maintenance time and component maintenance frequency; Accordingly, calculating the maintenance priority index of each component of each wind turbine generator set according to the maintenance related data of each component of each wind turbine generator set includes: Determining a maintenance correlation score for each component of each wind turbine generator set based on the maintenance correlation data of each component of each wind turbine generator set and a preset correlation data scoring table; the maintenance correlation score includes at least one of the following: a component cost score, a maintenance cost score, a component maintenance time score, and a component maintenance frequency score; Based on the maintenance association scores of the components of the wind turbine generator sets and the association data weights corresponding to the maintenance association data, maintenance priority indexes of the components of the wind turbine generator sets are calculated.

4. The wind turbine maintenance method for a multi-energy system according to claim 2, characterized in that: After calculating the maintenance priority index of each component of each wind turbine generator set according to the maintenance related data of each component of each wind turbine generator set, the method further includes: Acquiring status data of each unit component of each wind turbine generator set monitored by a status monitoring system; When the status data of a wind turbine component meets a preset condition, the maintenance priority index of the wind turbine component is updated so that the maintenance priority index of the component increases.

5. The wind turbine maintenance method for a multi-energy system according to claim 1, characterized in that: Determining power generation output time series data of a wind power generation system and a photovoltaic power generation system in the multi-energy system according to historical sunlight data and historical wind speed data of the multi-energy system in the historical time period includes: Obtaining historical sunlight data and historical wind speed data of the multi-energy system within a historical time period; Sampling and clustering the historical light data and the historical wind speed data to obtain wind speed time series simulation data and light time series simulation data of the multi-energy system; The wind speed time series simulation data and the light time series simulation data are used to calculate the power generation output time series data of the wind power generation system and the photovoltaic power generation system in the multi-energy system.

6. The wind turbine maintenance method for a multi-energy system according to claim 5, characterized in that: Sampling and clustering the historical light data and the historical wind speed data to obtain wind speed time series simulation data and light time series simulation data of the multi-energy system, including: Dividing the historical time period into a plurality of historical sub-time periods; performing probability distribution analysis on the historical sunlight data and the historical wind speed data in each of the plurality of historical sub-time periods to obtain probability distribution parameters corresponding to the historical sunlight data and the historical wind speed data in each of the plurality of historical sub-time periods; Based on the probability distribution parameters corresponding to the historical light data and the historical wind speed data of each historical sub-time period, Latin hypercube sampling is performed on the historical light data and the historical wind speed data in each historical sub-time period to obtain a wind speed scene sample set and a light scene sample set corresponding to each historical sub-time period; Cluster analysis is performed on the wind speed scene sample set and the light scene sample set corresponding to each historical sub-time period to obtain wind speed time series simulation data and light time series simulation data of the multi-energy system.

7. The wind turbine maintenance method for a multi-energy system according to claim 6, characterized in that: Performing cluster analysis on the wind speed scene sample set and the light scene sample set corresponding to each historical sub-time period to obtain wind speed time series simulation data and light time series simulation data of the multi-energy system, including: Using a clustering algorithm, the wind speed scenes in the wind speed scene sample set corresponding to each of the historical sub-time periods are divided into a plurality of clusters to obtain a plurality of first clusters corresponding to each of the historical sub-time periods; using a clustering algorithm, the illumination scenes in the illumination scene sample set corresponding to each of the historical sub-time periods are divided into a plurality of clusters to obtain a plurality of second clusters corresponding to each of the historical sub-time periods; Determining, based on the occurrence probabilities of each first cluster in the plurality of first clusters corresponding to each historical sub-time period, a first target cluster corresponding to each historical sub-time period from the plurality of first clusters corresponding to each historical sub-time period; and determining, based on the occurrence probabilities of each second cluster in the plurality of second clusters corresponding to each historical sub-time period, a second target cluster corresponding to each historical sub-time period from the plurality of second clusters corresponding to each historical sub-time period; Based on the first target clusters corresponding to each historical sub-time period, the wind speed time series simulation data of the multi-energy system in the future target time period is generated; based on the second target clusters corresponding to each historical sub-time period, the light time series simulation data of the multi-energy system in the future target time period is generated.

8. The wind turbine maintenance method for a multi-energy system according to claim 1, characterized in that: Determining multiple maintenance time periods of the wind power generation system within a future target time period based on historical load data of the multi-energy system and power generation output time series data of the wind power generation system includes: Based on the historical load data of the multi-energy system, determining a low-load time period of the multi-energy system within a future target time period; the low-load time period is a time period when the load represented by the historical load data is lower than a preset load; determining, based on the power generation output time series data of the wind power generation system, a low output time period of the wind power generation system within a future target time period; the low output time period is a time period when the power generation output of the wind power generation system is lower than a preset output; The low load time period and / or the low output time period are used as multiple maintenance time periods of the wind power generation system within a future target time period.

9. The wind turbine maintenance method for a multi-energy system according to claim 1, characterized in that: Determining, based on the power generation output time series data of the photovoltaic power generation system, the output constraints of each system in the multi-energy system, the power balance constraints of the multi-energy system, and the maintenance constraints of the wind power generation system, a maintenance capacity corresponding to each of the multiple maintenance time periods of the wind power generation system, including: Solving the objective function of the multi-energy system based on the power generation output time series data of the photovoltaic power generation system, the output constraints of each system in the multi-energy system, and the power balance constraints of the multi-energy system to determine the power generation output data of each energy system in the multi-energy system within a future target time period; Determining a theoretical maintenance capacity corresponding to each of the multiple maintenance time periods based on power generation output data of each energy system in the multi-energy system in a future target time period and historical load data in the historical time period; The maintenance constraints of the wind power generation system are used to correct the theoretical maintenance capacity corresponding to each maintenance time period to obtain the target maintenance capacity corresponding to each maintenance time period.

10. A wind turbine maintenance device for a multi-energy system, characterized in that: The multi-energy system includes a wind power generation system, a photovoltaic power generation system, an energy storage system and a solar thermal power generation system; the device includes: a priority determination module, configured to determine a maintenance priority score of each wind turbine in the wind power generation system based on maintenance-related data of a plurality of turbine components of each wind turbine; an output determination module, configured to determine, based on historical sunlight data and historical wind speed data of the multi-energy system within a historical time period, power generation output time series data of the wind power generation system and the photovoltaic power generation system in the multi-energy system; the power generation output time series data including power generation output data of the wind power generation system and the photovoltaic power generation system at multiple moments within a future target time period; a maintenance capacity determination module for determining, based on historical load data of the multi-energy system and time series data of power generation output of the wind power generation system, a plurality of maintenance time periods for the wind power generation system within a future target time period; and for determining, based on time series data of power generation output of the photovoltaic power generation system, output constraints of each system in the multi-energy system, power balance constraints of the multi-energy system, and maintenance constraints of the wind power generation system, a maintenance capacity corresponding to each maintenance time period of the wind power generation system in the plurality of maintenance time periods; A maintenance plan generation module is used to generate a target maintenance plan for the wind power generation system within a target time period by using the maintenance priority scores of the wind turbines, the multiple maintenance time periods, and the maintenance capacity corresponding to each maintenance time period, so as to perform maintenance on the wind turbines of the wind power generation system based on the target maintenance plan within a future target time period.

11. A computer device, characterized in that: The method comprises a processor and a memory for storing processor-executable instructions, wherein the processor implements the steps of the method according to any one of claims 1 to 9 when executing the instructions.

12. A computer-readable storage medium having computer instructions stored thereon, characterized in that: When the instructions are executed by a processor, the steps of the method according to any one of claims 1 to 9 are implemented.

Images