Method and system for identifying low efficiency of power generation performance of wind generating set

Abstract

The invention relates to the technical field of wind power generation and big data, in particular to a method and a system for identifying low efficiency of power generation performance of a wind generating set, which can quickly discover the low efficiency problem of the power generation performance of the wind generating set through data collection, processing and analysis. Comprising the steps of collecting data and performing primary processing to obtain first-class data; further processing and correcting the first-class data to obtain second-class data; then, further calculating and determining the power performance of the unit based on the second-class data; and finally, comparing the unit power obtained by calculation with the standard, and detecting the change trend of the performance of the unit in real time in combination with a monitoring and early warning mechanism. Through cooperative work of the data processing module, the correction calculation module, the power evaluation module and the monitoring and early warning module, the power generation performance degradation condition of the wind turbine generator can be found in advance, early warning can be triggered in time, operation and maintenance personnel are helped to take effective measures, and therefore power generation performance loss is reduced.

Description

Technical Field

[0001] The present invention relates to the field of wind power generation and big data technology, and in particular to a method and system for identifying inefficient power generation performance of a wind turbine generator set. Background Art

[0002] At present, the performance assessment of wind turbines is mainly based on the theoretical dynamic wind speed power curve provided by the whole machine manufacturer to the owner in the contract and whether its compliance meets the threshold agreed in the contract (generally 98%). However, the assessment data are uploaded to the owner by the manufacturer's wind turbine through software, and the accuracy of the wind speed provided greatly affects the assessment results of the wind speed power curve.

[0003] As the owner, we also hope to have other methods to identify inefficient power generation performance to identify the units that need to be optimized and upgraded to improve the power generation capacity of the units. The present invention mainly uses the data of the operation and maintenance center to compare the power curve of a single unit vertically (different years in the same period) to find the abnormal degradation of the power curve of the unit. It can also compare the power curve of a single unit horizontally (different units in the same wind farm of the same period, the same year, the same model) and judge the ranking of the whole field based on the power curve compliance to find the wind turbine with poor power curve. The power curve inefficiency alarm is given every six months (the statistical period is December-May and June-November), and the corresponding data display is provided.

[0004] In summary, a method and system for identifying inefficient power generation performance of wind turbines is intended to solve the problem that the current performance evaluation of wind turbines relies on manufacturer data and the accuracy of the data cannot be guaranteed. At the same time, it provides a means based on autonomous data collection and standardized processing to timely identify units with inefficient power generation performance, thereby improving the power generation capacity and reliability of the units. Summary of the invention

[0005] In view of the above problems existing in the prior art, the present invention is proposed.

[0006] Therefore, the technical problem to be solved by the present invention is: based on the data of the operation and maintenance center, the power curve of a single unit is compared vertically (different years in the same period) to discover abnormal degradation of the power curve of the unit; based on the data of the operation and maintenance center, the power curve of a single unit is compared horizontally (different units in the same wind farm of the same period, the same year, the same model), and the ranking of the entire field of converted power curve compliance is judged to discover wind turbines with poor power curves.

[0007] To solve the above technical problems, the present invention provides the following technical solutions: a method for identifying inefficient power generation performance of a wind turbine generator set, comprising: collecting data and performing primary processing to obtain a type of data; processing and correcting the type of data to obtain a type of data; further calculating and determining the unit power; comparing the unit power and performing monitoring and early warning.

[0008] As a preferred solution of the method for identifying inefficient power generation performance of a wind turbine generator set described in the present invention, the primary processing to obtain a type of data includes collecting data and then performing primary processing on the data to preliminarily obtain a type of data.

[0009] As a preferred solution of the method for identifying inefficient power generation performance of a wind turbine generator set described in the present invention, the processing and correction of a type of data includes further analyzing and processing the type of data to obtain a second type of data for determining the power of the unit.

[0010] As a preferred solution of the method for identifying inefficient power generation performance of a wind turbine generator set described in the present invention, the further calculation to determine the power of the unit includes further calculation to determine the power of the unit through two types of data.

[0011] As a preferred solution of the method for identifying inefficient power generation performance of a wind turbine generator set described in the present invention, the comparing of the unit power and monitoring and early warning includes comparing and monitoring the determined unit power and issuing an early warning.

[0012] As a preferred solution of the method for identifying inefficient power generation performance of a wind turbine generator set described in the present invention, the primary processing includes converting the initially collected raw data into a standardized format that meets the requirements.

[0013] As a preferred solution of the method for identifying inefficient power generation performance of a wind turbine generator set described in the present invention, the first type of data includes standardized data obtained through primary processing, which is used for calculation and comparison.

[0014] Another object of the present invention is to provide a system for identifying inefficient power generation performance of a wind turbine generator set, the system comprising a data processing module, a correction calculation module, a power evaluation module and a monitoring and early warning module. The data processing module is responsible for collecting and preliminarily processing data to obtain a type of data; the correction calculation module processes and corrects the type of data to obtain a type of data; the power evaluation module further calculates and determines the power of the unit; the monitoring and early warning module compares and monitors the power of the unit, and triggers an early warning when an abnormality is detected. The system can efficiently and accurately identify the inefficient power generation performance of a wind turbine generator set, and provide early warning information to operation and maintenance personnel, so as to facilitate timely maintenance measures.

[0015] In order to solve the above technical problems, the present invention provides the following technical solutions: a system for identifying inefficient power generation performance of a wind turbine generator set, comprising: a data processing module, a correction calculation module, a power evaluation module and a monitoring and early warning module;

[0016] The data processing module collects data and performs primary processing to obtain a type of data;

[0017] The correction calculation module processes and corrects the first type of data to obtain the second type of data;

[0018] The power evaluation module further calculates and determines the unit power;

[0019] The monitoring and early warning module compares the unit power and performs monitoring and early warning.

[0020] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, the steps of the above-mentioned method for identifying inefficient power generation performance of a wind turbine generator set are implemented.

[0021] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of the above-mentioned method for identifying inefficient power generation performance of a wind turbine generator set are implemented.

[0022] The beneficial effects of the present invention are as follows: a method for identifying inefficient power generation performance of a wind turbine is provided, which can detect power generation performance problems of the unit as soon as possible, and enable personnel to discover problems in advance through early warning, thereby reducing power generation performance loss. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0024] Figure 1 A flow chart of a method for identifying inefficient power generation performance of a wind turbine generator set provided by an embodiment of the present invention.

[0025] Figure 2 An embodiment of the present invention provides a method for identifying inefficient power generation performance of a wind turbine generator set, which includes a longitudinal comparison abnormal warning diagram of a wind turbine power curve of a certain unit.

[0026] Figure 3 An embodiment of the present invention provides a method for identifying inefficient power generation performance of a wind turbine generator set, which includes a horizontal comparison abnormal warning diagram of a wind turbine power curve of a certain unit.

[0027] Figure 4 A data flow diagram of a method for identifying inefficient power generation performance of a wind turbine generator set provided by an embodiment of the present invention.

[0028] Figure 5 A wind power curve diagram of a wind turbine generator set according to a method for identifying inefficient power generation performance of a wind turbine generator set provided by an embodiment of the present invention.

[0029] Figure 6 A wind power curve conformity diagram of a wind turbine generator set according to a method for identifying inefficient power generation performance of a wind turbine generator set provided by an embodiment of the present invention.

[0030] Figure 7 A longitudinal comparison diagram of power curves of a wind turbine generator set according to a method for identifying inefficient power generation performance of a wind turbine generator set provided by an embodiment of the present invention.

[0031] Figure 8 A horizontal comparison diagram of power curves of a wind turbine generator set according to a method for identifying inefficient power generation performance of a wind turbine generator set provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0032] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0033] Example 1, reference Figure 1 , is an embodiment of the present invention, which provides a method for identifying inefficient power generation performance of a wind turbine generator set, comprising:

[0034] S1: Collect data and perform primary processing to obtain a category of data.

[0035] It should be noted that performing primary processing to obtain a category of data includes performing primary processing on the data after data collection to preliminarily obtain a category of data.

[0036] Furthermore, the primary processing includes converting the initially collected raw data into a standardized format that meets the requirements; Class I data includes the standardized data obtained after the primary processing, which is used for calculation and comparison.

[0037] Furthermore, the primary processing process also includes preliminary cleaning of the data to eliminate noise and outliers in the data to ensure the accuracy and consistency of the data; at the same time, the format and unit of the data are unified during the standardization process so that data from different sources can be compatible with each other and provide support for subsequent analysis and calculations; in addition, after the primary processing is completed, a type of data is organized into a structured format that is easy to store and call, so that it can be efficiently processed in subsequent modules.

[0038] In the embodiment of the present application, the first-level processing is to convert the initially collected raw data into a standardized format that meets the requirements to ensure the consistency and integrity of the data for subsequent analysis and calculation; first, the data is collected from the group's operation and maintenance center, which contains data from wind turbines of different manufacturers and models across the country. Through data conversion and standardization, these data are unified into the standard format of the operation and maintenance center database.

[0039] In an optional embodiment, the primary processing can also be achieved by other means, such as directly performing preliminary screening and filtering on the raw data during the data collection process to remove significant noise and outliers; this method can reduce the burden of subsequent processing stages while ensuring the overall quality of the data; specifically, preprocessing rules can be set at the data acquisition end to perform real-time monitoring and simple correction of data such as temperature, air pressure, and wind speed to ensure that each collected data is within a reasonable range; in addition, during the primary processing, simple statistical methods can be used to perform preliminary mean processing on the data in order to remove accidental extreme values; although this method cannot fully achieve standardized accuracy, it can provide a faster preliminary processing method to quickly obtain available data in certain scenarios.

[0040] In an optional embodiment, the primary processing can also be implemented in other ways. For example, in the absence of sufficient computing resources, a distributed processing method is used to store and process the original data in blocks; each data block can complete preliminary format conversion and cleaning work on different nodes, and then the processed data blocks are unified and aggregated to form a type of data; this method is particularly suitable for data processing in large-scale wind farms, because distributed processing can significantly improve data processing efficiency while reducing performance requirements for a single node; in order to achieve consistency, each node can follow the same preset rules for processing, but allow a certain degree of adjustment in details to adapt to the specific data conditions of different units; in this way, even when resources are limited, the basic quality of a type of data can be guaranteed.

[0041] In an embodiment of the present application, a type of data is standardized data obtained after primary processing, which is used for further calculation and comparison to identify the inefficiency of wind turbines; specifically, a type of data undergoes preliminary data cleaning and standardized conversion to ensure that data from different units can be compared and analyzed horizontally and vertically in a unified format.

[0042] In an optional embodiment, a type of data can also be realized in other ways, such as directly performing basic data filtering and grouping after data collection without performing standardization processing; in this way, after the data is initially classified, it can be grouped according to different time periods or geographical locations, rather than converting all data into a unified format; although this method may not be as accurate as standardized processing, in some specific analysis scenarios, such as when quickly evaluating unit performance, grouped data can still provide certain reference value; through this relatively simplified data processing method, a type of data can be quickly generated and used for preliminary analysis.

[0043] In an optional embodiment, a type of data can also be realized in other ways, for example, by directly performing simple statistical aggregation on the wind speed and power data instead of precise grading processing; specifically, the data of different time periods can be averaged or weighted averaged to obtain representative values ​​of a type of data, rather than strictly divided according to specific wind speed and air density intervals; this method is simpler and can reduce processing time when the data volume is large, while providing basic trends and performance overviews; although this processing method lacks precise interval division, it still has certain practicality for application scenarios that require rapid generation of reports or trend analysis; through this relatively loose data processing method, a type of data can be quickly used for rough performance analysis and comparison of wind turbines.

[0044] Example 2, reference Figure 1-Figure 3 , is an embodiment of the present invention, which provides a method for identifying inefficient power generation performance of a wind turbine generator set, comprising:

[0045] S2: Process and modify the first type of data to obtain the second type of data.

[0046] It should be noted that processing and correcting the first type of data includes further analyzing and processing the first type of data to obtain the second type of data for determining the unit power.

[0047] Furthermore, the specific data processing and correction steps are as follows:

[0048] Air density correction:

[0049]

[0050] Among them, ρ 10min : average air density within 10 minutes; T 10min : Average absolute temperature within 10 minutes; B 10min : Average air pressure within 10 minutes; R0: Gas constant of dry air 287.05 J / (kg·K);

[0051] If atmospheric pressure cannot be measured directly, it can be determined by temperature and altitude:

[0052]

[0053] Where, Pb: standard atmospheric pressure 101325Pa; B: constant -6.50 / 1000; T: absolute temperature of the unit; ΔH: altitude of the unit; g: gravitational acceleration 9.806m / s 2 ;

[0054] For wind turbines with variable pitch and variable speed automatic power control, the wind speed should be corrected according to the following formula:

[0055]

[0056] Among them, V n : Corrected wind speed; V 10min : average wind speed within 10 minutes; ρ 10min : average air density within 10 minutes; ρ0: reference air density;

[0057] For a stall-regulated wind turbine with a fixed pitch and a fixed speed, the power should be corrected according to the following formula:

[0058]

[0059] Among them, P n : Corrected power; P 10min : Average power within 10 minutes; ρ0: reference air density.

[0060] S3: Further calculation is performed to determine the unit power.

[0061] It should be noted that further calculating and determining the unit power includes further calculating and determining the unit power through the second type of data.

[0062] Further, the power curve is determined as follows:

[0063] The power curve is determined by the bin method for the corrected data set, i.e., the wind speed is binned by 0.5 m / s and the air density is binned by 0.04 kg / m 3 The interval is calculated according to the following formula:

[0064]

[0065] Among them, V i,j : The average wind speed in the i-th wind speed interval and the j-th air density interval; V n,i,j : Corrected wind speed of data set n in the i-th wind speed interval and the j-th air density interval; N i,j: The number of 10-min data sets in the i-th wind speed interval and the j-th air density interval;

[0066]

[0067] Among them, P i,j : Average power in the i-th wind speed interval and the j-th air density interval; P n,i,j : The power of data set n in the i-th wind speed interval and the j-th air density interval; N i,j : The number of 10-min data sets in the i-th wind speed interval and the j-th air density interval; the corrected wind speed and power need to be standardized, the average wind speed is standardized by multiples of 0.5 m / s, and the power in the corresponding interval is calculated according to the linear interpolation formula.

[0068] Furthermore, the power curve compliance calculation is performed:

[0069] The power curve conformity is an important indicator to measure the power generation performance of the unit. The calculation method of the average power curve conformity is as follows:

[0070] Computer group power compliance for each wind speed segment (focus on tracking key wind speed segments, such as 5-10 meters):

[0071] Power compliance at each wind speed range = (actual power of the unit ÷ power of the comparison unit) × 100%

[0072] Calculate the average conformity of the power curve:

[0073] Average conformity of power curve = ∑ power conformity of each wind speed segment ÷ total number of wind speed segments.

[0074] S4: Compare unit power and conduct monitoring and early warning.

[0075] It should be noted that comparing the unit power and conducting monitoring and early warning includes comparing and monitoring the determined unit power and issuing early warnings.

[0076] Further, such as Figure 2 As shown, a vertical comparison of the power curves of a single unit is performed: the power curves of a single wind turbine unit in different years of the same period in the past two years are calculated, and the power curve conformity values ​​of adjacent years are calculated. If the power curve conformity value is lower than 95%, it indicates that the power generation performance has deteriorated and an early warning is given.

[0077] Furthermore, if Figure 3As shown, a horizontal comparison of the power curves of individual units is performed: the power curves of the same units in the entire field are calculated every year at the same period and year, and the power curve compliance value of each unit is calculated by comparing it with the guaranteed power of the wind turbine; the average power curve compliance value is calculated. If the power curve compliance value of a single unit is 5% lower than the average power curve compliance value (set to be adjustable), and the power curve compliance of a single unit ranks in the bottom three of the field, an alarm for deterioration in power generation performance is given;

[0078] The unit's power curve longitudinal comparison warning and power curve horizontal comparison warning are pushed to the operation and maintenance center monitoring platform for early warning.

[0079] The above is a schematic scheme of a method for identifying inefficient power generation performance of a wind turbine generator set in this embodiment. It should be noted that the technical scheme of the system for identifying inefficient power generation performance of a wind turbine generator set and the technical scheme of the above-mentioned method for identifying inefficient power generation performance of a wind turbine generator set belong to the same concept, and the details not described in detail in the technical scheme of the system for identifying inefficient power generation performance of a wind turbine generator set in this embodiment can all be referred to the description of the technical scheme of the above-mentioned method for identifying inefficient power generation performance of a wind turbine generator set.

[0080] Example 3, reference Figure 4-Figure 8 An embodiment of the present invention provides a method for identifying inefficient power generation performance of a wind turbine. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0081] Transmit wind turbine data from various locations to the group's operation and maintenance center. Data flows like Figure 4 As shown in Figure 1, after receiving the data uploaded by each wind turbine, the group operation and maintenance center first processes the data to obtain the power curve of each unit and its compliance, such as Figure 5 and Figure 6 As shown; by longitudinally comparing the power curves of a single unit, the performance changes of the unit can be discovered.

[0082] For example, Figure 7 As shown in the figure, by comparing the power curves of the same unit in 2022 and 2023, if the power compliance value drops from 1.04 to 0.96, a decrease of 92.3%, which is lower than the threshold of 95%, it indicates that the power generation performance of the unit is at risk of degradation, thus triggering an early warning. In addition, by comparing the power curves of the same type of units in the same wind farm horizontally, individual units with poor performance can be found.

[0083] For example, Figure 8As shown in the figure, in the comparison in the first quarter of 2023, the power curve compliance of Unit 9 was 0.945, which was lower than the average value of 1.0 for the entire field and ranked among the bottom three in the field, so a degradation alarm was also issued. Through this vertical and horizontal comparison and analysis, the operation and maintenance center provides effective data support for the performance monitoring and maintenance of wind turbines, which helps to discover and solve performance problems in advance, thereby reducing power generation losses.

[0084] Embodiment 4 is an embodiment of the present invention, which provides a system for identifying inefficient power generation performance of a wind turbine generator set, including: a data processing module, a correction calculation module, a power evaluation module, and a monitoring and early warning module;

[0085] The data processing module collects data and performs primary processing to obtain a type of data;

[0086] The correction calculation module processes and corrects the first type of data to obtain the second type of data;

[0087] The power evaluation module further calculates and determines the unit power;

[0088] The monitoring and early warning module compares the unit power and performs monitoring and early warning.

[0089] This embodiment further provides a computing device, which is applicable to a method for identifying inefficient power generation performance of a wind turbine generator set, and includes:

[0090] A memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement a method for identifying inefficient power generation performance of a wind turbine generator set as proposed in the above embodiment.

[0091] This embodiment further provides a storage medium on which a computer program is stored. When the program is executed by a processor, a method for identifying inefficient power generation performance of a wind turbine generator set as proposed in the above embodiment is implemented.

[0092] The storage medium proposed in this embodiment and the method for identifying inefficient power generation performance of a wind turbine proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0093] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0094] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0095] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0096] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should be included in the scope of the claims of the present invention.

Claims

1. A method for identifying inefficient power generation performance of a wind turbine generator set, characterized in that: include: Collect data and perform primary processing to obtain a category of data; Process and correct the first type of data to obtain the second type of data; Further calculation is performed to determine the unit power; Compare unit power and conduct monitoring and early warning.

2. A method for identifying low power generation performance of a wind turbine generator set according to claim 1, characterized in that: The performing of primary processing to obtain a type of data includes collecting original data of the unit and performing primary processing to convert the collected original data into a type of data that is convenient for analysis and processing.

3. A method for identifying low power generation performance of a wind turbine generator set as claimed in claim 2, characterized in that: The processing and correction of the first type of data includes in-depth processing of the first type of data obtained, correcting the first type of data, so that the obtained second type of data remains consistent for further calculation.

4. A method for identifying low power generation performance of a wind turbine generator set as claimed in claim 3, characterized in that: The further calculation and determination of the unit power includes further calculation and determination of the second type of data obtained based on the in-depth processing to obtain the unit power for monitoring and early warning.

5. A method for identifying low power generation performance of a wind turbine generator set as claimed in claim 4, characterized in that: The comparing of the unit power and monitoring and early warning includes comparing and monitoring the determined unit power and issuing an early warning.

6. A method for identifying low power generation performance of a wind turbine generator set as claimed in claim 5, characterized in that: The primary processing includes converting the initially collected raw data into a standardized format that meets the requirements.

7. A method for identifying low power generation performance of a wind turbine generator set as claimed in claim 6, characterized in that: The first type of data includes standardized data obtained after primary processing, which is used for calculation and comparison.

8. A system for identifying inefficient power generation performance of a wind turbine generator set according to any one of claims 1 to 7, characterized in that: include: Data processing module, correction calculation module, power evaluation module and monitoring and early warning module; The data processing module collects data and performs primary processing to obtain a type of data; The correction calculation module processes and corrects the first type of data to obtain the second type of data; The power evaluation module further calculates and determines the unit power; The monitoring and early warning module compares the unit power and performs monitoring and early warning.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of a method for identifying inefficient power generation performance of a wind turbine generator set according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a method for identifying inefficient power generation performance of a wind turbine generator set according to any one of claims 1 to 7 are implemented.

Images