A system and method for evaluating the effectiveness of wind turbine generator power enhancement and upgrade products.
By generating short-term operating condition sets before and after wind turbine upgrades through operating condition recognition algorithms, the objectivity and sustainability issues of wind turbine power enhancement product effectiveness evaluation are solved, realizing low-cost, automated wind turbine power enhancement evaluation and accurately calculating changes in power generation and profits or losses.
Patent Information
- Application Number
- CN202310100765.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-01-13
- Publication Date
- 2025-12-02
- Estimated Expiration
- 2043-01-13
AI Technical Summary
The effectiveness assessment of existing wind turbine generator power enhancement products lacks objectivity, sustainability, and long-term verification capabilities, and is costly, making it difficult for users to accurately determine whether power generation has increased and quantify profits or losses.
A working condition identification algorithm is used to generate a short-term set of working conditions before and after the wind turbine upgrade. The effectiveness of the power increase is quantified by comparing the power generation capacity. By using pre-processed and filtered data, the operating conditions of the wind turbine under different working conditions are recorded, and the difference in power generation is calculated to estimate profit or loss.
It enables low-cost, automated, objective and reliable effectiveness assessment of wind turbine power enhancement upgrade products, and can accurately calculate changes in power generation after the upgrade, meeting users' needs for accurate calculation of profits or losses.
Smart Images

Figure CN116109152B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of wind power generation technology, specifically to an effectiveness evaluation system and method for upgrading wind turbine generator sets. Background Technology
[0002] With the rapid development of wind power in my country, numerous software and hardware products for increasing power generation on wind turbines have emerged. Many older wind farms choose to install such products to improve power generation. However, most of these products, which increase wind turbine power generation and efficiency, are derived through mathematical models and simulation software, and verified through prototypes or limited operational wind farms. When installed in large quantities in real wind farms, there is a lack of methods to evaluate and quantify the increase in power generation. In other words, these power-enhancing products cannot guarantee that their actual effects are equivalent to experimental results or the effects claimed by the product. Furthermore, some power-enhancing products are even misleading or deceptive, not only failing to increase power generation and generate profits but potentially affecting the normal operation of wind turbines and causing losses for users.
[0003] However, after upgrading wind turbines, users are most concerned about whether their investment can be converted into returns. But wind energy is unpredictable, making it difficult for users to easily determine and quantify whether the upgrade has effectively increased the turbine's power generation. Currently, users mainly rely on two methods to verify the effectiveness of wind turbine upgrades. First, they refer to the upgrade service provider's documentation of increased power generation after the upgrade; this method lacks objectivity. Second, they hire a third party to verify the upgrade's effectiveness; this method can only verify effectiveness at a specific point in time, lacks sustainability and long-term verification capabilities, and is expensive, consuming significant human and material resources. Summary of the Invention
[0004] To overcome the shortcomings of existing technologies, this invention provides an effectiveness evaluation system and method for wind turbine generator set power enhancement and upgrade products, which solves the problems of lack of objectivity, lack of sustainability and long-term verification capabilities, and high cost of existing technologies.
[0005] The technical solution adopted by the present invention to solve the above problems is:
[0006] A system for evaluating the effectiveness of wind turbine generator upgrades generates short-term operating condition sets before and after the upgrade for all wind turbines already in operation in wind farms. By comparing the power generation capacity of the same unit before and after the upgrade, the system quantifies the effectiveness of the wind turbine generator upgrade as the change in the power generation capacity of the wind turbine generator, and then calculates the profit or loss that the unit upgrade may generate. The short-term operating conditions refer to operating conditions with a time range of 1-30 seconds.
[0007] As a preferred technical solution, a long-term continuous wind turbine operation data is input using an operating condition recognition algorithm. After preprocessing, the wind turbine operation data is divided into several short-term uniform continuous time data segments. Finally, the short-term operating conditions are output through the operating condition recognition algorithm. The operation of the wind turbine is recorded under all operating conditions with the power boost function turned on and off, until the number of operating conditions collected meets the user's preset number of operating conditions. Among them, the long-term operating condition refers to the operating condition in which at least 80% of the preset short-term operating conditions can be collected by the operating condition recognition algorithm.
[0008] As a preferred technical solution, preprocessing includes preprocessing and filtering the data, and handling abnormal data.
[0009] As a preferred technical solution, the number of short-term working conditions preset by the user is determined based on the user's preset set of working conditions.
[0010] As a preferred technical solution, the preset operating conditions include: average wind speed, rotational speed, blade angle, average power, wind turbine operating status, average wind direction, initial wind speed and final wind speed, wind speed variance, and the order of the wind speed fitting function.
[0011] As a preferred technical solution, the data structure of the operating condition node should include at least the following attributes: basic wind turbine information, 30-second average yaw angle against the wind, real-time wind speed, instantaneous power, and wind turbine operating status.
[0012] A method for evaluating the effectiveness of wind turbine generator set power enhancement and upgrade products, based on the aforementioned wind turbine generator set power enhancement and upgrade product effectiveness evaluation system, includes the following steps:
[0013] S1, configure and operate the wind turbine generator set power enhancement and upgrade product effectiveness evaluation system, preset operating condition set;
[0014] S2: For wind turbines that have already been upgraded, acquire historical operating data of the wind turbine generator set before or after the upgrade; for wind turbines with insufficient or non-compliant historical data, shut down the upgrade function and continuously acquire real-time operating data of the wind turbine during free power generation until all the data required for system verification is obtained.
[0015] S3: For wind turbines that have been upgraded but whose effectiveness needs to be verified, the system acquires the historical operating data of the wind turbine generator set after the upgrade; for wind turbines with insufficient historical data, the power boost function is activated to continuously acquire data on the operation in the upgraded state until the system obtains all the data required for verification.
[0016] S4, the collected data is preprocessed to obtain preprocessed data;
[0017] S5: Based on the preprocessed data, map it to the defined data structure operating condition nodes, input a batch of continuous time operating condition nodes into the operating condition identification algorithm, and generate short-term operating conditions before and after the wind turbine upgrade at the same time interval.
[0018] S6 collects different short-term operating conditions and generates full-frequency short-term operating condition sets before and after the wind turbine upgrade. The two sets are then fed into the power generation capacity comparison algorithm. The power generation changes are compared by the difference in power generation under the same short-term operating conditions before and after the upgrade. The profit or loss generated by the upgrade is then estimated by the change in power generation.
[0019] As a preferred technical solution, step S5, the working condition identification algorithm includes the following steps:
[0020] S51, Input the queue of working condition nodes;
[0021] S52, using the least squares method to fit the time-wind speed scatter curve;
[0022] S53 records statistical indicators such as power generation, average wind angle, and wind speed.
[0023] S54, forming a short-term working condition object;
[0024] S55, search the database and compare operating conditions;
[0025] S56, determine whether the database can search for working conditions with a matching degree higher than 90%; if yes, proceed to step S57; if no, store this short-term working condition as a new object in the database, and then return to step S51.
[0026] S57, compare the correlation coefficient and cosine similarity with objects in the database;
[0027] S58. If the correlation coefficient and cosine similarity of the data are both higher than 94%, it is considered to be the same working condition, and the frequency of the working condition object in the database is increased by 1; otherwise, the current short-term working condition is stored as a new object in the database, and then the process returns to step S51.
[0028] S59, determine whether the data collection is complete; if yes, end the working condition identification algorithm; if no, return to step S51.
[0029] As a preferred technical solution, the data structure for short-term operating conditions includes the following characteristics: median operating wind speed = (wind speed at the head of the queue + wind speed at the tail of the queue) / 2; the order of the operating wind speed is obtained from the fitted function, with a maximum order of 4; the operating point time length is defined by the user, with a maximum value of 10 seconds and a minimum value of 2 seconds; the operating time interval is defined by the user, with a maximum value of 1 second and a minimum value of 10 milliseconds; the operating point queue satisfies the first-in-first-out (FIFO) function.
[0030] Compared with the prior art, the present invention has the following advantages:
[0031] This invention generates a "short-term operating condition set" for all wind turbines already in operation in wind farms, before and after the upgrade. By comparing the power generation capacity of the same unit before and after the upgrade, the effectiveness of the power increase of the wind turbine generator set is quantified into the change in its power generation capacity. In this way, the profit or loss that the unit upgrade can generate can be estimated, thus meeting the user's need to accurately calculate the profit from the modification and upgrade of wind turbine generator sets. Attached Figure Description
[0032] Figure 1 This is a flowchart of the operation of an effectiveness evaluation system for wind turbine generator set power enhancement and upgrade products as described in this invention;
[0033] Figure 2 This is a flowchart of real-time data processing and algorithm input preparation;
[0034] Figure 3 This is a flowchart of historical data processing and algorithm input preparation;
[0035] Figure 4 This is a flowchart of the short-term operating condition identification algorithm. Detailed Implementation
[0036] The present invention will be further described in detail below with reference to the embodiments and accompanying drawings, but the embodiments of the present invention are not limited thereto.
[0037] Example 1
[0038] like Figures 1 to 4 As shown, in order to solve the problems of the prior art, the present invention provides a wind turbine power enhancement evaluation system based on the operating condition identification algorithm, which has the characteristics of low cost, automaticity, objectivity and reliability.
[0039] This invention extracts the difference in power generation under the same operating conditions before and after the wind turbine upgrade, in order to evaluate and quantify the effect of the unit upgrade product.
[0040] This invention provides the following technical solution:
[0041] A method for evaluating the effectiveness of wind turbine generator power enhancement upgrade products based on operating condition identification algorithm:
[0042] step:
[0043] S1. Configure and run the "Wind Turbine Generator Power Enhancement and Upgrade Product Effectiveness Evaluation System" (hereinafter referred to as the Power Enhancement Evaluation System), and preset a set of operating conditions. (The user first presets a batch of short-term operating conditions based on the attributes and parameters of the wind turbine generator.)
[0044] S2. For wind turbines that have already been upgraded, acquire the unit's historical operating data before or after the upgrade. For wind turbines with insufficient or unacceptable historical data, the upgrade function needs to be disabled, and real-time operating data of the wind turbine during free power generation should be continuously acquired until all the data required for system verification is obtained.
[0045] S3. For wind turbines that have been upgraded but whose effectiveness needs to be verified, the system needs to acquire historical operating data of the wind turbine generator after the upgrade. For wind turbines with insufficient historical data, activate their power boost function and continuously acquire data from their operation in the upgraded state until the system obtains all the data required for verification.
[0046] S4. Input the collected data into the data preprocessing module to obtain the preprocessed data.
[0047] S5. Map the preprocessed data to the data structure "operating condition node" defined in this method, input the node into the operating condition identification algorithm, and generate "short-term operating conditions" before and after the wind turbine upgrade at the same time interval.
[0048] S6. By collecting different "short-term operating conditions," "full-frequency short-term operating condition sets" are generated before and after the wind turbine upgrade. The two sets are then fed into the "power generation capacity comparison algorithm," and the change in power generation is compared by the difference in power generation under the same "short-term operating conditions" before and after the upgrade. Users can estimate the profit or loss generated by the upgrade based on the change in power generation.
[0049] Among them, the preferred ones are:
[0050] The power enhancement assessment system determines the number of short-term operating conditions to be collected based on the user's preset set of operating conditions.
[0051] The power enhancement assessment system uses a working condition recognition algorithm to input a long-term continuous wind turbine operating data. After preprocessing, it is divided into several short-term uniform continuous time data segments. Finally, the algorithm outputs short-term working conditions. This method records the wind turbine's operation under all working conditions with the power enhancement function turned on and off. This process continues until the number of collected working conditions meets the user's preset number.
[0052] The preprocessing module preprocesses and filters the data, handles abnormal data, and ensures the normal operation of subsequent algorithms.
[0053] The power enhancement assessment system collects a large number of short-term operating conditions of wind turbines under real operating conditions and merges them to generate a set of short-term operating conditions before and after the wind turbine upgrade.
[0054] The power enhancement assessment system can calculate the changes in power generation of wind turbines at different wind speeds after the power enhancement function is turned on through short-term operating condition set calculations. This can be used to calculate the increase or loss in power generation, and then to calculate the profit or loss brought about by the power enhancement function.
[0055] The operating condition identification algorithm takes as input a dynamic short-term operating condition node obtained by mapping the historical operating history of wind turbines under different power generation states over a long period of time, and outputs the short-term operating condition. This dynamic operating condition node adopts a first-in-first-out queue data structure, progressing over time and reading the historical operating data of the wind turbine. Each output short-term operating condition represents a unique wind speed change pattern of the wind turbine.
[0056] For short-term applications, accuracy can be controlled according to user needs. Higher accuracy typically corresponds to longer preset time intervals.
[0057] The short-term operating condition set consists of multiple short-term operating conditions, including all the operating conditions of the wind turbine before and after the upgrade, preset under the accuracy selected by the user.
[0058] The wind turbine power generation capacity comparison algorithm compares the power generation capacity of the same wind turbine under the same operating conditions at different times before and after an upgrade, and calculates the difference in power generation capacity. This allows for the estimation of potential profits or losses from the wind turbine upgrade.
[0059] The technical solution of the present invention is further described as follows:
[0060] The data structure for the operating condition node is defined as follows:
[0061] Operation Point (OP): For a wind turbine, the operating status at the current moment is called the Operation Point. The attributes of this point contain all the data required for power increase assessment at a given instant.
[0062] The operating condition nodes all have the characteristics of abstract data structure, which are inherited from the "basic operating condition node". They are scalable and can be expanded according to the characteristics of different wind turbines. In the future, they can also be upgraded accordingly with the development of wind turbines.
[0063] The data structure of the basic operating condition node should at least include the following attributes:
[0064] 1. Basic information about the wind turbine;
[0065] 2.30-second average yaw angle against the wind;
[0066] 3. Real-time wind speed;
[0067] 4. Instantaneous power;
[0068] 5. Fan operating status;
[0069] The short-term operating condition data structure is defined as follows:
[0070] Short Operation Period (SOP): A queue data structure consisting of operation nodes with the same time interval for a short period of time is called a Short Operation Period.
[0071] The data structure for short-term operating conditions includes the following attributes:
[0072] 1. Operating condition identification code;
[0073] 2. Power generation before the upgrade;
[0074] 3. Power generation after upgrade;
[0075] 4. Duration of operating conditions;
[0076] 5. Time interval between operating conditions;
[0077] 6. Working condition node queue;
[0078] 7. Frequency of occurrence of the operating condition;
[0079] 8. Least squares fitting function for wind speed in the operating condition range;
[0080] 9. Operating wind speed statistics: maximum value, minimum value, mean, standard deviation, initial value, and final value;
[0081] 10. Other operating parameters: average speed, average wind speed, average blade angle, average power matching;
[0082] 11. Order of the wind speed fitting function;
[0083] The 12.30-second average yaw angle against the wind corresponds to the specified range.
[0084] 13.10-minute average wind speed and engine speed;
[0085] The data structure for short-term operating conditions has the following characteristics:
[0086] 1. Median wind speed under operating conditions = (wind speed at the head of the queue + wind speed at the tail of the queue) / 2;
[0087] 2. The wind speed order under operating conditions is obtained from the fitted function, with a maximum order of 4;
[0088] 3. The duration of each working condition node is user-defined, with a maximum value of 10 seconds and a minimum value of 2 seconds;
[0089] 4. The operating time interval is defined by the user, with a maximum value of 1 second and a minimum value of 10 milliseconds;
[0090] 5. The working node queue has all the methods of the basic data structure queue (Queue), and satisfies the first-in, first-out (FIFO) function;
[0091] The short-term load case set data structure is defined as follows:
[0092] Short Operation Period Set (SOPS): A set consisting of several short operation period structures.
[0093] The short-term load case set has the following properties:
[0094] 1. User-preset short-term data collection waiting conditions;
[0095] 2. All short-term operating conditions already collected by the system;
[0096] 3. Preset short-term operating conditions that have not yet been collected and those that have been collected;
[0097] Data collection process}
[0098] The effectiveness assessment system requires operational data before and after the wind turbine upgrade as input. Operational data collection is divided into two categories: historical data collection and real-time data collection.
[0099] The historical data collection process is as follows:
[0100] 1. Users can configure fixed time intervals and fixed time intervals for "short-term operating conditions";
[0101] 2. Read the required historical data from the wind turbine monitoring system, then map each data point to a "condition node", and take a segment of data according to the configured time range and interval to form a data queue;
[0102] 3. Perform data validation filtering on the data queue;
[0103] 4. Input the data into the working condition identification algorithm;
[0104] 5. Update the data queue for the next second, that is, delete the old data from the queue and add the new data to the queue, repeat step 3 until the system has collected enough operating conditions.
[0105] The real-time data collection process is as follows:
[0106] 1. Users can configure fixed time intervals and fixed time intervals for "short-term operating conditions";
[0107] 2. Read the required wind turbine operation data from the wind turbine monitoring system in real time at set time intervals, then map each data point into an "operating condition node", and form a data queue after collecting enough data;
[0108] 3. Perform data validation filtering on the data queue;
[0109] 4. Input the data into the working condition identification algorithm;
[0110] 5. Delete the oldest 1-second data from the queue, and at the same time collect new operating condition nodes and add them to the operating condition queue. Repeat step 3 until the system has collected enough operating conditions.
[0111] The data preprocessing process is as follows:
[0112] Traverse the entire data segment; if the data volume is large, traverse in segments using multiple threads. Investigate data with low reliability in wind turbine operation data. Replace unreasonable data with reasonable data or discard data to ensure data continuity and accuracy.
[0113] The basic criteria for data screening are as follows:
[0114] 1. Wind speed: The wind speed does not match the changes in time or exceeds the limit;
[0115] 2. Instantaneous power: Use the Raida criterion to identify bad data, replace bad data, unreasonable values, and missing values with static power curve values, or discard a segment of data.
[0116] 3. Fan operating status: The status does not match the preceding and following points or does not conform to the actual operating logic;
[0117] 4. Other parameters: Unreasonable changes or exceeding composition limits exist; if problems persist, the sensor needs to be checked.
[0118] The basic process for handling abnormal data is as follows:
[0119] 1. If the wind turbine operating data is normal at the beginning and end, but abnormal in the middle, the middle point is replaced by the average of the beginning and end values;
[0120] 2. If more than 30% of the operating data of a certain section of the fan is abnormal, the entire section will be filtered.
[0121] The preset short-term operating conditions are as follows:
[0122] Users need to preset a set of short-term operating conditions. The system collects all preset short-term operating conditions from historical and real-time data. The preset operating conditions mainly include the following:
[0123] 1. Average wind speed, rotational speed, and propeller angle;
[0124] 2. Average power;
[0125] 3. Fan operating status;
[0126] 4. Average wind direction;
[0127] 5. Initial and final wind speeds;
[0128] 6. Wind speed variance;
[0129] 7. Order of the wind speed fitting function;
[0130] When an identified working condition meets one of the preset working conditions, the identification of that working condition is complete. This process continues until all preset working conditions have been collected.
[0131] The working condition recognition algorithm process is as follows:
[0132] For a single wind turbine, the identified short-term operating conditions are stored in a database to form a set of operating conditions:
[0133] 1. Configure basic fan information;
[0134] 2. Obtain the operating condition queue input;
[0135] 3. Obtain the least squares fitting function corresponding to the wind speed;
[0136] 4. Power generation = Cumulative power generation at the head of the queue - Cumulative power generation at the tail of the queue;
[0137] 5. Obtain the maximum, minimum, average, standard deviation, initial value, and final value of wind speed;
[0138] 6. Obtain other basic operating parameters such as average speed and propeller angle;
[0139] 7. Record the current power generation and function order, and save them as short-term operating condition objects according to the preset operating condition ID;
[0140] 8. New operating conditions are initially identified based on the average operating parameters of the wind turbine. These conditions are then compared with historical operating conditions in the database to determine if the match rate is higher than 90%. Operating conditions with a match rate lower than 90% are stored as new operating conditions in the database.
[0141] 9. For further comparison of the cosine similarity of the working condition nodes with a similarity higher than 90%, the correlation of the fitted curves is compared. If the cosine similarity and correlation of the fitted curves are both higher than 94%, they are considered to be the same working condition; otherwise, they are considered to be lower.
[0142] 10. Repeat the previous steps until enough short-term condition objects have been accumulated and stored in the database.
[0143] The complete set of working conditions is as follows:
[0144] Collect short-term operating conditions before and after the power boost function is turned on, until a complete set of user-preset operating conditions is completed.
[0145] The calculation for increased power generation is as follows:
[0146] Iterate through the set of short-term operating conditions to calculate the increased power generation capacity.
[0147]
[0148] Where R represents the percentage increase in power generation, i represents the operating condition object number, n represents the total number of operating condition objects, and Sop.P ai Sop.P bi This represents the power generation before and after a short-term upgrade of a certain operating condition.
[0149] For users with wind turbine retrofitting needs, the most important requirement is to determine the increased power generation of the turbine under actual operating conditions after the upgrade, as this allows for the calculation of the actual profit or loss generated by the upgrade. This invention generates a "short-term operating condition set" for all wind turbines already in operation in wind farms, comparing the power generation capacity of the same unit before and after the upgrade. By comparing the power generation capacity of the same unit before and after the upgrade, the effectiveness of the power increase in the wind turbine generator set is quantified as a change in its power generation capacity. This allows for the calculation of the profit or loss generated by the unit upgrade, meeting users' needs for accurately calculating the profit from retrofitting and upgrading wind turbine generator sets.
[0150] In this invention, short-term wind speed is used to identify the operating condition of the fan, and two operating conditions are compared to determine whether they are the same.
[0151] As described above, the present invention can be implemented well.
[0152] All features disclosed in all embodiments of this specification, or steps in all methods or processes implied in the disclosure, may be combined and / or extended or replaced in any way, except for mutually exclusive features and / or steps.
[0153] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Based on the technical essence of the present invention, any simple modifications, equivalent substitutions, and improvements made to the above embodiments within the spirit and principles of the present invention shall still fall within the protection scope of the present invention.
Claims
1. A system for evaluating the effectiveness of wind turbine generator set power enhancement and upgrade products, characterized in that, For all wind turbines already in operation at wind farms, short-term operating condition sets are generated before and after turbine upgrades. By comparing the power generation capacity of the same unit before and after the upgrade, the effectiveness of the power enhancement of the wind turbine is quantified as the change in the power generation capacity of the wind turbine, thereby calculating the profit or loss that the unit upgrade may generate. Among them, short-term operating conditions refer to operating conditions with a time range of 1-30 seconds. Using an operating condition recognition algorithm, a long-term continuous wind turbine operation data is input. After preprocessing, the wind turbine operation data is divided into several short-term uniform continuous time data segments. Finally, the operating condition recognition algorithm outputs the short-term operating conditions, recording the wind turbine's operation under all operating conditions with the power enhancement function turned on and off, until the number of operating conditions collected meets the user's preset number of operating conditions. Among them, long-term operating conditions refer to operating conditions in which at least 80% of the preset short-term operating conditions can be collected by the operating condition recognition algorithm. The working condition identification algorithm includes: S51, Input the queue of working condition nodes; S52, using the least squares method to fit the time-wind speed scatter curve; S53 records statistical indicators such as power generation, average wind angle, and wind speed. S54, forming a short-term working condition object; S55, search the database and compare operating conditions; S56, determine whether the database can search for working conditions with a matching degree higher than 90%; if yes, proceed to S57; if no, store this short-term working condition as a new object in the database, and then return to S51. S57, compare the correlation coefficient and cosine similarity with objects in the database; S58. If the correlation coefficient and cosine similarity of the data are both higher than 94%, they are considered to be the same working condition, and the frequency of the working condition object in the database is incremented by 1; otherwise, the current short-term working condition is stored as a new object in the database, and then S51 is returned. S59, determine whether the data acquisition is complete; if yes, end the working condition identification algorithm; if no, return to S51. The data structure for the short-term operating conditions includes the following characteristics: median operating wind speed = (wind speed at the head of the queue + wind speed at the tail of the queue) / 2; the order of the operating wind speed is obtained from the fitted function, with a maximum order of 4; the operating point time length is defined by the user, with a maximum value of 10 seconds and a minimum value of 2 seconds; the operating time interval is defined by the user, with a maximum value of 1 second and a minimum value of 10 milliseconds; the operating point queue satisfies the first-in-first-out (FIFO) function.
2. The effectiveness evaluation system for wind turbine generator set power enhancement and upgrade products according to claim 1, characterized in that, Preprocessing includes preprocessing and filtering data, and handling abnormal data.
3. The effectiveness evaluation system for wind turbine generator set power enhancement and upgrade products according to claim 1 or 2, characterized in that, The number of short-term working conditions preset by the user is determined based on the set of working conditions preset by the user.
4. The effectiveness evaluation system for wind turbine generator set power enhancement and upgrade products according to claim 3, characterized in that, The preset operating conditions include: average wind speed, rotational speed, blade angle, average power, wind turbine operating status, average wind direction, initial and final wind speeds, wind speed variance, and the order of the wind speed fitting function.
5. The effectiveness evaluation system for wind turbine generator set power enhancement and upgrade products according to claim 4, characterized in that, The data structure of the operating condition node should include at least the following attributes: basic wind turbine information, 30-second average yaw angle against the wind, real-time wind speed, instantaneous power, and wind turbine operating status.
6. A method for evaluating the effectiveness of wind turbine generator set power enhancement and upgrade products, characterized in that, A system for evaluating the effectiveness of wind turbine generator power enhancement and upgrade products according to any one of claims 1 to 5 includes the following steps: S1, configure and operate the wind turbine generator set power enhancement and upgrade product effectiveness evaluation system, preset operating condition set; S2: For wind turbines that have already been upgraded, acquire historical operating data of the wind turbine generator set before or after the upgrade; for wind turbines with insufficient or non-compliant historical data, shut down the upgrade function and continuously acquire real-time operating data of the wind turbine during free power generation until all the data required for system verification is obtained. S3: For wind turbines that have been upgraded but whose effectiveness needs to be verified, the system acquires the historical operating data of the wind turbine generator set after the upgrade; for wind turbines with insufficient historical data, the power boost function is activated to continuously acquire data on the operation in the upgraded state until the system obtains all the data required for verification. S4, the collected data is preprocessed to obtain preprocessed data; S5: Based on the preprocessed data, map it to the defined data structure operating condition nodes, input a batch of continuous time operating condition nodes into the operating condition identification algorithm, and generate short-term operating conditions before and after the wind turbine upgrade at the same time interval. S6 collects different short-term operating conditions and generates full-frequency short-term operating condition sets before and after the wind turbine upgrade. The two sets are then fed into the power generation capacity comparison algorithm. The power generation is changed by comparing the difference in power generation under the same short-term operating conditions before and after the upgrade. The profit or loss generated by the upgrade is then estimated by the change in power generation. In step S5, the working condition identification algorithm includes the following steps: S51, Input the queue of working condition nodes; S52, using the least squares method to fit the time-wind speed scatter curve; S53 records statistical indicators such as power generation, average wind angle, and wind speed. S54, forming a short-term working condition object; S55, search the database and compare operating conditions; S56, determine whether the database can search for working conditions with a matching degree higher than 90%; if yes, proceed to step S57; if no, store this short-term working condition as a new object in the database, and then return to step S51. S57, compare the correlation coefficient and cosine similarity with objects in the database; S58. If the correlation coefficient and cosine similarity of the data are both higher than 94%, it is considered to be the same working condition, and the frequency of the working condition object in the database is increased by 1; otherwise, the current short-term working condition is stored as a new object in the database, and then the process returns to step S51. S59, determine whether the data acquisition is complete; if yes, end the working condition identification algorithm; if no, return to step S51. The data structure for the short-term operating conditions includes the following characteristics: median operating wind speed = (wind speed at the head of the queue + wind speed at the tail of the queue) / 2; the order of the operating wind speed is obtained from the fitted function, with a maximum order of 4; the operating point time length is defined by the user, with a maximum value of 10 seconds and a minimum value of 2 seconds; the operating time interval is defined by the user, with a maximum value of 1 second and a minimum value of 10 milliseconds; the operating point queue satisfies the first-in-first-out (FIFO) function.
Citation Information
Patent Citations
Ship navigation work condition dividing method based on clustering analysis
CN108052707A
Wind turbine generator performance evaluation method and device
CN114595989A