Wind turbine operation evaluation method and system based on loss power and time decomposition

Abstract

The application discloses a wind turbine operation evaluation method and system based on loss power and time decomposition, which comprises the following steps: 1) obtaining unit operation data and operation log; 2) aggregating the operation data to obtain operation data of a preset granularity, identifying the state label thereof, classifying according to the state label to obtain a data set under each state label; 3) obtaining the total time length of different operation states of the unit from each data set to realize time decomposition; obtaining the power curve and the wind frequency distribution and power generation of each data set according to the data set of each state label; obtaining the loss power corresponding to each operation state of the unit through the wind frequency distribution, the power generation and the power curve to realize loss power decomposition; 4) performing operation evaluation according to the loss power and the time decomposition result. The application evaluates the operation condition from the time and loss power dimensions and can comprehensively and accurately evaluate the operation condition of the unit to provide a breakthrough point for power generation improvement.

Description

TECHNICAL FIELD

[0001] The present application mainly relates to the field of wind power technology, and in particular to a wind turbine operation evaluation method and system based on loss power and time decomposition. BACKGROUND

[0002] In the past decade, the installed capacity of wind power in China has increased significantly, and wind power has become the third largest energy source after thermal power and hydropower. Due to the uneven technical level of wind power manufacturers and a series of quality problems caused by rush installation, some low-output wind turbines with low power generation, high failure rate and poor operation stability have appeared in the wind power industry. At present, the wind power industry is about to enter an era of no subsidy, flat price and bidding. In order to ensure income, wind farm owners must compete for electricity and be careful with money. In order to tap the power generation potential of wind turbines and improve the power generation of low-output units, it is necessary to conduct a comprehensive operation evaluation of wind turbines.

[0003] Currently, the wind power industry mostly uses TBA, MTBF, power generation, loss of power due to power limitation, loss of power due to failure, and failure duration as KPI indicators to analyze and evaluate the operation of wind farms from a macro perspective, which is difficult to comprehensively, accurately and in detail assess the operation of wind turbines. Therefore, it is necessary to propose a comprehensive, accurate and detailed multi-dimensional operation evaluation method for wind turbines to find a breakthrough point for improving the quality and efficiency of wind turbines and to improve the power generation of wind turbines. SUMMARY

[0004] The technical problem to be solved by the present application is to provide a comprehensive, accurate and detailed wind turbine operation evaluation method and system based on loss power and time decomposition to solve the problems in the prior art.

[0005] To solve the above technical problems, the technical solution provided by the present application is as follows:

[0006] A wind turbine operation evaluation method based on loss power and time decomposition, comprising the steps of:

[0007] 1) obtaining unit operation data and unit operation log of the same period from the SCADA historical database;

[0008] 2) aggregating the unit operation data to obtain unit operation data of a preset granularity, identifying the state label of each preset granularity operation data, and classifying each preset granularity operation data according to the state label to obtain a data set under each state label;

[0009] 3) obtaining the total duration of different operation states of the unit from the data set under each state label to realize time decomposition based on the state label;

[0010] According to the data set under each state label, the unit power curve, and the wind frequency distribution and power generation of each data set are obtained by statistics; through the wind frequency distribution, power generation and power curve, the loss power corresponding to each operating state of the unit is obtained, and the loss power decomposition of the wind turbine based on the state label is realized;

[0011] 4) According to the loss power and time decomposition results of each unit or wind farm or field group, the operation evaluation of the unit or wind farm or field group is carried out, the loss power composition and source are clarified, and the efficiency improvement potential of the unit or wind farm or field group is evaluated.

[0012] As a further improvement of the above technical solution:

[0013] In step 2), according to the unit main control state, the same period operation log, the unit specific working condition recognition strategy within the preset granularity, and combined with the preset wind turbine state model, the state label of each preset granularity operation data is recognized.

[0014] The operating state category in the wind turbine state model includes full performance power generation, partial performance power generation, technical standby, power failure, fault, command shutdown, exceeding environmental conditions, planned maintenance or repair, and exceeding electrical specifications; wherein the exceeding environmental conditions include small wind, large wind and wind direction mutation; the fault is divided into different faults 1, 2, 3…, n; the partial performance power generation includes SCADA limited power, HMI limited power, blade icing and unit active limited power; the technical standby includes yaw cable release, unit startup, charging, heating, self-checking and initialization.

[0015] In step 3), the actual power generation Pri under each operating state of the unit is obtained by statistics from the unit active power data in the data set; based on the unit power curve, the potential power generation Ppi is calculated by combining the wind frequency distribution of the data set Si; thus the loss power Pli corresponding to each operating state of the unit can be obtained.

[0016] In step 4), the operation evaluation process of each unit is:

[0017] By comparing the duration and loss power of each operating state of different units, the loss power composition and source of each unit are understood, so as to evaluate the efficiency improvement potential of the unit and provide a starting point for power generation improvement; specifically, by comparing the battery charging time and loss power of each unit, the battery performance degradation unit can be found; by comparing the blade icing time and loss power of each unit, the economy of installing blade deicing system can be evaluated; by comparing the fault time and loss power of each unit, the main source of unit fault loss can be clarified.

[0018] In step 4), the operation evaluation process of the wind farm is:

[0019] By comparing the duration and loss power of different wind farms in different operating states, the loss power composition and source of each wind farm can be clearly understood, so as to evaluate the efficiency improvement potential of the wind farm and provide a starting point for power generation improvement. Specifically, by comparing the duration and loss power of each wind farm in strong wind, the optimization potential of the wind turbine cutout of the wind farm can be evaluated; by comparing the duration and loss power of each wind farm in light wind, the optimization potential of the wind turbine cut-in of the wind farm can be evaluated; by comparing the duration and loss power of each wind farm in fault, the power generation improvement potential brought by the reduction of fault rate of the wind farm can be evaluated.

[0020] In step 1), a pretreatment process is also included: removing abnormal invalid data and special characters in the unit operation data, and removing sub-faults and useless warning records in the unit operation log.

[0021] The application further discloses a wind turbine operation evaluation system based on loss power and time decomposition, comprising:

[0022] A data acquisition module is configured to acquire unit operation data and unit operation log of the same period from a SCADA historical database.

[0023] A data aggregation and state label identification module is configured to aggregate the unit operation data to obtain unit operation data of a preset granularity, identify state labels of the unit operation data of the preset granularity, and classify the unit operation data of the preset granularity according to the state labels to obtain data sets under the state labels.

[0024] A state label-based time decomposition module is configured to obtain total duration of different operating states of the unit from the data sets under the state labels to realize state label-based time decomposition.

[0025] A state label-based loss power decomposition module is configured to obtain a unit power curve and wind frequency distribution and power generation of each data set according to the data sets under the state labels, obtain loss power corresponding to each operating state of the unit through the wind frequency distribution, power generation and power curve, and realize state label-based loss power decomposition of the wind turbine.

[0026] An operation evaluation module is configured to evaluate operation of the unit or the wind farm or the field group according to the loss power and time decomposition results of the unit or the wind farm or the field group, determine loss power composition and source, and realize efficiency improvement potential evaluation of the unit or the wind farm or the field group.

[0027] The application further discloses a computer readable storage medium having a computer program stored thereon, wherein the computer program performs the steps of the wind turbine operation evaluation method based on loss power and time decomposition when executed by a processor.

[0028] The application further discloses a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the computer program performs the steps of the wind turbine operation evaluation method based on loss power and time decomposition when executed by the processor.

[0029] Compared with the prior art, the application has the following advantages:

[0030] (1) The application realizes operation evaluation and efficiency improvement potential assessment of the wind turbine through loss power and time decomposition of each unit / wind farm / farm group, and evaluates the operation of the unit from multiple dimensions such as time dimension, loss power dimension, single unit dimension and wind farm dimension, so as to comprehensively and accurately assess the actual operation condition of the unit and provide a breakthrough point for power generation improvement.

[0031] (2) The application comprehensively determines the running data state label of each preset granularity through the unit master control state, operation log and unit specific working condition identification strategy, so as to avoid identification error of the data label caused by a single data source.

[0032] (3) The wind turbine state model constructed by the application divides the operation state of the unit in detail, and basically covers all states of the unit, so as to improve the comprehensive reliability of the evaluation result. BRIEF DESCRIPTION OF DRAWINGS

[0033] Figure 1 FIG. 1 is a structural schematic diagram of the wind turbine state model I in the embodiment of the application.

[0034] Figure 2 FIG. 2 is a structural schematic diagram of the wind turbine state model II in the embodiment of the application.

[0035] Figure 3 FIG. 3 is a flowchart of the method in the embodiment of the application.

[0036] Figure 4 FIG. 4 is a comparative analysis diagram of the duration and loss power of different operation states of different units in the application.

[0037] Figure 5 FIG. 5 is a comparative analysis diagram of the duration and loss power of different operation states of different wind farms in the application.

[0038] Figure 6 FIG. 6 is a structural schematic diagram of the system in the embodiment of the application. DETAILED DESCRIPTION

[0039] The application will be further described below in combination with the drawings and specific embodiments.

[0040] AsFigure 3 As shown, the wind turbine operation evaluation method based on loss power and time decomposition of the embodiment is used to realize multi-dimensional operation evaluation of the wind turbine, find the quality improvement and efficiency improvement point of the wind turbine, and improve the power generation, and specifically includes the following steps:

[0041] 1) Obtain the unit operation data and the unit operation log of the same period from the SCADA historical database;

[0042] 2) Aggregate the unit operation data to obtain the unit operation data of a preset granularity (such as 1 min granularity, which is selected according to the actual situation), and identify the state label of each preset granularity operation data, then classify each preset granularity operation data according to the state label to obtain the data set under each state label;

[0043] 3) Obtain the total time length of different operation states of the unit from the data set under each state label, and realize time decomposition based on the state label;

[0044] According to the data set under each state label, the unit power curve, the wind frequency distribution of each data set, and the power generation are obtained; through the wind frequency distribution, the power generation, and the power curve, the loss power corresponding to each operation state of the unit is obtained, and the loss power decomposition of the wind turbine based on the state label is realized;

[0045] 4) According to the loss power and time decomposition results of each unit or wind farm or field group, the operation of the unit or wind farm or field group is evaluated, the loss power composition and source are clarified, and the efficiency improvement potential of the unit or wind farm or field group is evaluated.

[0046] The present application realizes the operation evaluation and efficiency improvement potential evaluation of the unit / wind farm / field group through the loss power and time decomposition of each unit / wind farm / field group; from the time dimension and the loss power dimension, the single unit dimension and the wind farm dimension, etc. The operation of the unit is evaluated from multiple dimensions, which can more comprehensively, accurately and detailedly evaluate the actual operation condition of the unit, and provide a breakthrough point for improving the power generation.

[0047] In a specific embodiment, in step 2), according to the unit main control state, the same period operation log, the unit specific working condition identification strategy, and combined with the preset wind turbine state model, the state label of each preset granularity operation data is identified. For example Figure 1 As shown, the operation state category of the wind turbine can be divided into full performance power generation, partial performance power generation, technical standby, power failure, fault, command shutdown, exceeding environmental conditions, planned maintenance / maintenance, and exceeding electrical specifications according to Figure 1 The wind turbine state model I is further subdivided to obtain the wind turbine state model II, as shown in Figure 2As shown, the environmental conditions exceeding the limit include light wind, strong wind, and sudden changes in wind direction; faults are also classified into different faults 1, 2, 3, ..., n; partial performance power generation includes SCADA power limiting, HMI power limiting, blade icing, and active power limiting of the unit (corresponding to specific operating conditions at the turbine level); technical standby includes yaw untying, unit startup, charging, heating, self-testing, and initialization; and multi-dimensional operation evaluation of the wind turbine is achieved based on power loss and time decomposition according to wind turbine state models I and II. The wind turbine state model constructed above divides the unit's operating state in detail, basically encompassing all states of the unit, thereby improving the comprehensive reliability of the evaluation results. Furthermore, by fusing multiple data information to identify and determine state labels, errors in state label identification caused by a single data source can be avoided. Of course, in other embodiments, the above-mentioned state label identification can also be obtained through unit operation logs, operation logs + main control status, or operation logs + specific operating condition identification strategies.

[0048] In one specific embodiment, in step 3), the actual power generation Pr of the unit under each operating state is statistically obtained from the active power data of the unit in the dataset. i Based on the unit power curve, combined with the dataset S i Based on the wind frequency distribution, the potential power generation Pp was calculated. i Therefore, the power loss P1 corresponding to each operating state of the unit can be obtained. i =Pp i -Pr i .

[0049] In one specific embodiment, in step 4), the operation evaluation process of each unit is as follows: by comparing the duration and power loss of each operating state of different units, the composition and source of power loss of each unit can be understood, so as to assess the efficiency potential of the units and provide an entry point for increasing power generation; specifically, by comparing the battery charging time and power loss of each unit, units with degraded battery performance can be identified; by comparing the blade icing time and power loss of each unit, the economics of installing a blade de-icing system can be evaluated; by comparing the fault time and power loss of each unit, the main sources of unit fault losses can be identified.

[0050] The wind farm operation evaluation process is as follows: By comparing the duration and power loss of different wind farms under various operating conditions, the composition and source of power loss of each wind farm can be clearly understood, which facilitates the assessment of the wind farm's efficiency improvement potential and provides an entry point for increasing power generation. Specifically, by comparing the duration of strong winds and power loss of each wind farm, the potential for wind turbine cut-out optimization can be assessed; by comparing the duration of low winds and power loss of each wind farm, the potential for wind turbine cut-in optimization can be assessed; and by comparing the duration of faults and power loss of each wind farm, the potential for increasing power generation by reducing the fault rate can be assessed.

[0051] The invention will be further described below with reference to a complete specific embodiment:

[0052] The operating status categories of wind turbine units can be classified according to Figure 1 The wind turbine state model I shown is divided into several types, including full-performance power generation, partial-performance power generation, technical standby, power outage, fault, commanded shutdown, exceeding environmental conditions, planned maintenance / repair, and exceeding electrical specifications. Further subdivision of wind turbine state model I yields wind turbine state model II, as shown below. Figure 2 As shown. This invention realizes a multi-dimensional operational evaluation of wind turbine units based on state model I and state model II, using power loss and time decomposition; the specific implementation of this method is as follows. Figure 3 As shown, the main steps include the following:

[0053] (1) Acquisition and preprocessing of second-level running data and running log data

[0054] Retrieve second-level operating data of the unit and the unit operating log of the same period from the SCADA historical database; preprocess the retrieved second-level operating data by removing abnormal and invalid data and special characters; preprocess the unit operating log by removing sub-faults and useless warning records.

[0055] (2) Data aggregation and status label determination

[0056] The preprocessed second-level operation data is aggregated to obtain 1-minute granular unit operation data; based on the unit main control status within the 1-minute time period, the synchronous operation log, the unit specific operating condition identification strategy, and combined with the wind turbine state model II, the status label of each 1-minute granular operation data is determined.

[0057] The specific operating conditions of the unit mainly include SCADA power limiting, HMI power limiting, blade icing, and active power limiting of the unit.

[0058] (3) Dataset partitioning

[0059] The 1-minute granular data within the analysis period are classified according to state labels to obtain dataset S under each state label. i (i = 1, 2, 3, ..., n);

[0060] (4) Time decomposition of wind turbine generators based on status labels

[0061] From dataset S i (i = 1, 2, ..., n) can be used to obtain the total duration T of each different operating state of the unit. i (i = 1, 2, ..., n);

[0062] (5) Unit power curves and wind frequency distribution statistics for each dataset

[0063] According to the data set S of the full performance state of the unit m , the interval method is used to obtain the unit power curve;

[0064] Based on the wind speed data in the data set S i (i=1, 2, 3,..., m-1, m+1.., n), the wind frequency distribution of each data set is obtained by dividing the wind speed interval by 0.5m / s;

[0065] The power curve statistical method refers to "GBT 18451.2-2012 Wind Turbine Power Performance Test".

[0066] (6) Loss power decomposition of wind turbine based on state label

[0067] The actual power generation Pr i of the unit in each operating state is obtained by statistical analysis of the active power data of the unit in the data set S i (i=1, 2, 3,..., m-1, m+1.., n); i Based on the unit power curve, the potential power generation Pp i is calculated combined with the wind frequency distribution of the data set S i ; Thus, the loss power Pl i of each operating state of the unit can be obtained, which realizes the loss power decomposition of the wind turbine based on the state label. i i

[0068] (7) Multi-dimensional operation evaluation of wind turbine

[0069] According to the time decomposition result T i (i=1, 2,..., n) and the loss power decomposition result Pl i , the duration and loss power of each operating state of the unit can be understood in detail; the duration and loss power of each operating state of the unit can be obtained by statistical analysis of the duration and loss power of each operating state of the unit.

[0070] Single unit dimension: as shown in Figure 4 , by comparing the duration and loss power of each operating state of different units, the loss power composition and source of each unit can be clearly understood, which is convenient for efficiency improvement potential assessment and provides a starting point for power generation improvement.

[0071] Specifically, by comparing the battery charging time and loss power of each unit, the battery performance degradation unit can be found; by comparing the blade icing time and loss power of each unit, the economy of installing blade deicing system can be evaluated; by comparing the fault time and loss power of each unit, the main source of unit fault loss can be determined.

[0072] Wind farm dimension: As shown in the table, by comparing the duration and loss of power of different wind farms in each operating state, the loss of power and source of each wind farm can be clearly understood, which facilitates the efficiency potential assessment of the wind farm and provides a starting point for power generation improvement. Figure 5

[0073] Specifically, by comparing the duration and loss of power of each wind farm in strong wind, the optimization potential of the wind turbine of the wind farm can be evaluated; by comparing the duration and loss of power of each wind farm in light wind, the optimization potential of the wind turbine of the wind farm can be evaluated; by comparing the duration and loss of power of each wind farm in fault, the power generation improvement potential brought by the reduction of fault rate of the wind farm can be evaluated.

[0074] As shown in the table, the application also discloses a wind turbine operation evaluation system based on loss of power and time decomposition, which comprises: Figure 6

[0075] The data acquisition module is used to acquire the unit operation data and the unit operation log of the same period from the SCADA historical database.

[0076] The data aggregation and state label identification module is used to aggregate the unit operation data to obtain unit operation data of a preset granularity, identify the state label of each preset granularity operation data, and classify each preset granularity operation data according to the state label to obtain a data set under each state label.

[0077] The time decomposition module based on the state label is used to obtain the total duration of different operating states of the unit from the data set under each state label, and realize time decomposition based on the state label.

[0078] The loss of power decomposition module based on the state label is used to obtain the unit power curve, the wind frequency distribution and the power generation of each data set according to the data set under each state label; the loss of power corresponding to each operating state of the unit is obtained through the wind frequency distribution, the power generation and the power curve, and the loss of power decomposition of the wind turbine based on the state label is realized.

[0079] The operation evaluation module is used to evaluate the operation of the unit or the wind farm or the field group according to the loss of power and the time decomposition result of each unit or the wind farm or the field group, to clarify the loss of power and the source, and to realize the efficiency potential assessment of the unit or the wind farm or the field group, and to provide a starting point for power generation improvement.

[0080] Further, the data acquisition module comprises a data preprocessing module for eliminating abnormal invalid data and special characters in the unit operation data, and eliminating sub-faults and useless warning records in the unit operation log.

[0081] ​​The wind turbine operation evaluation system based on loss power and time decomposition of the present application is used to execute the evaluation method as described above, and has the advantages as described above.

[0082] The present application further discloses a computer readable storage medium, which stores a computer program, and the computer program executes the steps of the wind turbine operation evaluation method based on loss power and time decomposition when executed by a processor. The present application also discloses a computer device, which comprises a memory and a processor, and the memory stores a computer program, and the computer program executes the steps of the wind turbine operation evaluation method based on loss power and time decomposition when executed by the processor.

[0083] The present application realizes all or part of the processes in the above-mentioned embodiment methods, and can also be completed by a computer program instructing related hardware. The computer program can be stored in a computer readable storage medium, and the computer program can realize the steps of the above-mentioned various method embodiments when executed by a processor. The computer program includes computer program code, which can be in the form of source code, object code, executable files or some intermediate forms, etc. The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc. The memory can be used to store computer programs and / or modules, and the processor realizes various functions by running or executing the computer programs and / or modules stored in the memory, and calling the data stored in the memory. The memory can include high-speed random access memory, and can also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device, etc.

[0084] The above is only the preferred embodiment of the present application, and the protection scope of the present application is not limited to the above-mentioned embodiment. Any technical solution falling within the idea of the present application belongs to the protection scope of the present application. It should be noted that some improvements and decorations without departing from the principle of the present application are considered as the protection scope of the present application.

Claims

1. A wind turbine generator operation evaluation method based on loss power and time decomposition, characterized in that, The method comprises the steps of: 1) obtaining unit operation data and unit operation log of the same period from a SCADA historical database; 2) aggregating the unit operation data to obtain unit operation data of a preset granularity, identifying state labels of each preset granularity operation data, and classifying each preset granularity operation data according to the state labels to obtain data sets under each state label; 3) obtaining the total duration of different operation states of the unit from the data sets under each state label to realize time decomposition based on the state labels; According to the data sets under each state label, the unit power curve, the wind frequency distribution and the power generation of each data set are obtained; through the wind frequency distribution, the power generation and the power curve, the loss power corresponding to each operation state of the unit is obtained, and the loss power decomposition of the wind turbine based on the state label is realized; 4) According to the loss power and the time decomposition result of each unit or wind farm or field group, the operation of the unit or wind farm or field group is evaluated to clarify the loss power composition and source, and the efficiency improvement potential of the unit or wind farm or field group is evaluated; In step 2), the state labels of each preset granularity operation data are identified according to the unit main control state, the same period operation log, the unit specific working condition identification strategy, and combined with the preset wind turbine state model; The operation state categories in the wind turbine state model include full performance power generation, partial performance power generation, technical standby, power failure, fault, command shutdown, exceeding environmental conditions, planned maintenance or repair, and exceeding electrical specifications; wherein the exceeding environmental conditions include light wind, strong wind and wind direction mutation; the fault is divided into different faults 1, 2, 3, …, n; the partial performance power generation includes SCADA power limit, HMI power limit, blade icing and unit active power limit; the technical standby includes yaw cable release, unit startup, charging, heating, self-checking and initialization.

2. The wind turbine generator operation evaluation method based on loss energy and time decomposition according to claim 1, characterized in that, In step 3), the actual power generation of the unit in each operating state is calculated from the active power data of the unit in the data set Pr i ; based on the power curve of the unit, combined with the wind frequency distribution of the data set S i , the potential power generation is calculated Pp i ; Loss electric quantity corresponding to each operating state of the unit Pl i = Pp i - Pr i .

3. The wind turbine generator operation evaluation method based on loss energy and time decomposition according to claim 1, characterized in that, In step 4), the operation evaluation process of each unit is: By comparing the duration and loss power of each operation state of different units, the loss power composition and source of each unit are understood to facilitate the efficiency improvement potential evaluation of the unit and provide a starting point for power generation improvement; specifically, by comparing the battery charging time and loss power of each unit, the battery performance degradation unit can be found; by comparing the blade icing time and loss power of each unit, the economy of installing a blade deicing system can be evaluated; by comparing the fault time and loss power of each unit, the main source of unit fault loss can be clarified.

4. The wind turbine generator operation evaluation method based on loss energy and time decomposition according to any one of claims 1 to 3, characterized in that, In step 4), the operation evaluation process of the wind farm is: By comparing the duration and loss power of each operation state of different wind farms, the loss power composition and source of each wind farm can be clearly understood to facilitate the efficiency improvement potential evaluation of the wind farm and provide a starting point for power generation improvement; specifically, by comparing the strong wind duration and loss power of each wind farm, the wind turbine cut-out optimization potential of the wind farm can be evaluated; by comparing the light wind duration and loss power of each wind farm, the wind turbine cut-in optimization potential of the wind farm can be evaluated; by comparing the fault duration and loss power of each wind farm, the power generation improvement potential brought by reducing the fault rate of the wind farm can be evaluated.

5. The wind turbine generator operation evaluation method based on loss energy and time decomposition according to any one of claims 1 to 3, characterized in that, In step 1), a preprocessing process is further included: removing abnormal and invalid data and special characters in the unit operation data, and removing sub-faults and useless warning records in the unit operation log.

6. A wind turbine operation evaluation system based on loss energy and time decomposition, for performing the steps of the wind turbine operation evaluation method based on loss energy and time decomposition according to any one of claims 1 to 5, characterized in that, Comprise: a data acquisition module, configured to acquire unit operation data and unit operation log in the same period from a SCADA historical database; a data aggregation and state label identification module, configured to aggregate the unit operation data to obtain unit operation data of a preset granularity, identify state labels of each preset granularity operation data, and classify each preset granularity operation data according to the state labels to obtain data sets under each state label; a state label-based time decomposition module, configured to obtain total time lengths of different operation states of the unit from the data sets under each state label, and realize state label-based time decomposition; a state label-based loss power decomposition module, configured to obtain a unit power curve and a wind frequency distribution and power generation of each data set according to the data sets under each state label, and obtain loss power corresponding to each operation state of the unit through the wind frequency distribution, the power generation and the power curve, and realize state label-based loss power decomposition of the wind turbine; an operation evaluation module, configured to evaluate operation of each unit or wind farm or field group according to loss power and time decomposition results of each unit or wind farm or field group, to clarify loss power composition and sources, and to realize efficiency improvement potential evaluation of the unit or wind farm or field group.

7. A computer-readable storage medium having stored thereon a computer program, characterized in that The computer program, when executed by a processor, performs the steps of the wind turbine operation evaluation method based on loss power and time decomposition according to any one of claims 1-5. 8.A computer device, comprising a memory and a processor, wherein a computer program is stored on the memory, and the computer device is characterized in that, The computer program, when executed by a processor, performs the steps of the wind turbine operation evaluation method based on loss power and time decomposition according to any one of claims 1-5.

Images