Detection method of wind turbine generator set and wind turbine generator set

Abstract

The embodiment of the present application discloses a detection method, a detection device and a wind turbine generator set. The detection method includes: obtaining the actual data of the first operating parameter of the wind turbine generator set; obtaining the simulation data of the second operating parameter according to the actual data of the first operating parameter; comparing the simulation data of the second operating parameter with the design data of the second operating parameter to obtain a comparison result; obtaining the detection result of the wind turbine generator set according to the comparison result; so as to reduce the detection cost of the wind turbine generator set.

Description

Technical Field

[0001] The present invention relates to the field of wind power generation, and particularly to a detection method for a wind turbine generator set and a wind turbine generator set. Background Art

[0002] In recent years, the utilization of renewable energy has been increasing year by year. Wind power generation is a relatively mature renewable energy power generation at present and has received extensive attention from countries around the world. During the process of wind power generation, a wind turbine generator set converts wind energy into mechanical energy and finally outputs electrical energy.

[0003] During the operation of a wind turbine generator set, it is usually necessary to detect the wind turbine generator set. In the prior art, it is usually necessary to deploy sensors at various positions of the wind turbine generator set to collect the actual data of the operating parameters of the wind turbine generator set during operation to complete the detection of the wind turbine generator set. However, the large number of stacked sensors will increase the cost of detecting the wind turbine generator set. Therefore, there is an urgent need for a method for detecting a wind turbine generator set to reduce the cost of detecting the wind turbine generator set. Summary of the Invention

[0004] In view of this, the embodiments of the present application provide a detection method for a wind turbine generator set and a wind turbine generator set to reduce the cost of detecting the wind turbine generator set.

[0005] In a first aspect, the present application provides a detection method for a wind turbine generator set, and the detection method includes:

[0006] Obtain the actual data of the first operating parameter of the wind turbine generator set;

[0007] According to the actual data of the first operating parameter, obtain the simulation data of the second operating parameter;

[0008] Compare the simulation data of the second operating parameter with the design data of the second operating parameter to obtain a comparison result;

[0009] According to the comparison result, obtain the detection result of the wind turbine generator set.

[0010] In a possible implementation manner, the obtaining the simulation data of the second operating parameter according to the actual data of the first operating parameter includes:

[0011] Use the actual data of the first operating parameter as the input of the digital twin simulation model, and determine the output result of the digital twin simulation model as the simulation data of the second operating parameter.

[0012] In a possible implementation manner, before comparing the simulation data of the second operating parameter with the design data of the second operating parameter, it further includes:

[0013] Detect the simulation data of the second operating parameter and the design data of the second operating parameter according to the preset detection conditions;

[0014] If the simulation data of the second operating parameter and / or the design data of the second operating parameter do not meet the preset detection conditions, stop the detection of the wind turbine generator set.

[0015] In a possible implementation manner, after obtaining the detection result of the wind turbine generator set, it further includes:

[0016] Generate a control instruction according to the detection result;

[0017] Control the wind turbine generator set according to the control instruction.

[0018] In a possible implementation manner, comparing the simulation data of the second operating parameter with the design data of the second operating parameter to obtain a comparison result includes:

[0019] Extract features from the simulation data of the second operating parameter;

[0020] Compare the eigenvalue of the simulation data of the second operating parameter with the design data of the second operating parameter to obtain the comparison result.

[0021] In a possible implementation manner, obtaining the detection result of the wind turbine generator set according to the comparison result includes:

[0022] When the deviation between the eigenvalue of the simulation data of the second operating parameter and the design data of the second operating parameter exceeds a first threshold, and the eigenvalue of the simulation data of the second operating parameter exceeds a second threshold, determine that the detection result is abnormal.

[0023] In a possible implementation manner, after obtaining the detection result of the wind turbine generator set, it further includes:

[0024] Transmit the eigenvalue of the simulation data of the second operating parameter, the comparison result, and the detection result to the field management system.

[0025] In a second aspect, the present application provides a detection device for a wind turbine generator set. The detection device includes a processor and a memory. Among them, the memory stores code, and the processor is used to call the code stored in the memory to implement the following functions:

[0026] Obtain the actual data of the first operating parameter of the wind turbine generator set;

[0027] Obtain the simulation data of the second operating parameter according to the actual data of the first operating parameter;

[0028] Compare the simulation data of the second operating parameter with the design data of the second operating parameter to obtain a comparison result;

[0029] Obtain the detection result of the wind turbine according to the comparison result.

[0030] In a third aspect, the present application provides a wind turbine, and the wind turbine includes the detection device of the wind turbine.

[0031] In a fourth aspect, the present application provides a computer-readable storage medium, and the computer-readable storage medium is used to store a computer program, and the computer program is used to execute any one of the above-mentioned control methods of the wind turbine.

[0032] It can be seen that the embodiments of the present application have the following beneficial effects:

[0033] In the embodiments of the present application, by obtaining the actual data of the first operating parameter of the wind turbine, according to the actual data of the first operating parameter, obtaining the simulation data of the second operating parameter, and obtaining the detection result of the wind turbine according to the comparison result obtained from the simulation data of the second operating parameter and the design data of the second operating parameter.

[0034] Compared with the prior art, in order to obtain the data of the operating parameters of the wind turbine during operation, sensors need to be deployed at specific positions, and in order to complete the detection of the wind turbine, a large number of sensors need to be deployed, and the stacking of sensors leads to an increase in detection costs; in the embodiments of the present application, the simulation data of the second operating parameter is obtained through the actual data of the first operating parameter. At this time, according to the comparison result between the simulation data of the second operating parameter and the design data of the second operating parameter, it is possible to determine whether the actual data of the second operating parameter is abnormal, so as to obtain the detection result of the wind turbine. In the embodiments of the present application, in order to determine whether the actual data of the second operating parameter is abnormal, so as to obtain the detection result of the wind power generation set, there is no need to deploy sensors for the second operating parameter anymore, but the simulation data of the second operating parameter is obtained through the actual data of the first operating parameter, thereby reducing the cost of detecting the wind turbine. Description of the Drawings

[0035] Figure 1 is a flowchart of the detection method of the wind turbine provided by the embodiment of the present application;

[0036] Figure 2 is a schematic structural diagram of the wind turbine detection system provided by the embodiment of the present application;

[0037] Figure 3It is a flowchart of a detection method for a wind turbine provided by another embodiment of the present application;

[0038] Figure 4 It is a schematic structural diagram of a detection device for a wind turbine provided by an embodiment of the present application;

[0039] Figure 5 It is a schematic structural diagram of a wind turbine provided by an embodiment of the present application. Detailed implementation manners

[0040] To facilitate the understanding and explanation of the technical solutions provided by the embodiments of the present application, the technical terms in the embodiments of the present application will be described first below.

[0041] Digital twin technology: Make full use of data such as physical models, sensor updates, and operation history, integrate the simulation processes of multiple disciplines, multiple physical quantities, multiple scales, and multiple probabilities, and complete the mapping in the virtual space, so as to reflect the entire life cycle process of the corresponding physical equipment. Digital twin is a concept beyond reality and can be regarded as a digital mapping system of one or more important and interdependent equipment systems. The digital twin simulation model refers to the simulation model used in digital twin technology.

[0042] Prognostics Health Management system (PHM for short). It is proposed to meet the requirements of autonomous guarantee and autonomous diagnosis, and is an upgraded development of condition-based maintenance (CBM). Usually, it emphasizes the state perception in asset equipment management, monitors the health status of equipment, frequent failure areas and cycles, predicts the occurrence of failures through data monitoring and analysis, and thus greatly improves the operation and maintenance efficiency to a certain extent.

[0043] To facilitate the understanding of the technical solutions provided by the embodiments of the present application, a method for detecting a wind turbine and a wind turbine provided by the embodiments of the present application will be described below with reference to the accompanying drawings.

[0044] Although the exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. Based on the embodiments in the present application, other embodiments obtained by those skilled in the art without making creative contributions all fall within the protection scope of the present application.

[0045] In the claims, the description, and the drawings of the present application, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion.

[0046] In the prior art, in order to obtain the data of the operating parameters of a wind turbine during operation, sensors need to be deployed at specific positions. In order to complete the detection of the wind turbine, a large number of sensors need to be deployed, and the stacking of sensors leads to an increase in the detection cost.

[0047] Based on this, in the embodiments of the present application provided by the inventor, by obtaining the actual data of the first operating parameter of the wind turbine, according to the actual data of the first operating parameter, the simulation data of the second operating parameter is obtained, and according to the comparison result obtained from the simulation data of the second operating parameter and the design data of the second operating parameter, the detection result of the wind turbine is obtained.

[0048] In the embodiments of the present application, according to the comparison result between the simulation data of the second operating parameter and the design data of the second operating parameter, it is possible to determine whether the actual data of the second operating parameter is abnormal, thereby obtaining the detection result of the wind turbine. Therefore, in order to determine whether the actual data of the second operating parameter is abnormal, so as to obtain the detection result of the wind power generator, there is no need to deploy sensors for the second operating parameter anymore. Instead, the simulation data of the second operating parameter is obtained through the actual data of the first operating parameter, thereby reducing the cost of detecting the wind turbine.

[0049] Please refer to Figure 1 , Figure 1 which is a flowchart of the detection method for a wind turbine provided by the embodiments of the present application. As Figure 1 shown, the detection method for a wind turbine in the embodiments of the present application includes the following steps:

[0050] S101. Obtain the actual data of the first operating parameter of the wind turbine.

[0051] In S101, the first operating parameter of the wind turbine refers to the parameter used to represent the operating state of the wind turbine during operation; the actual parameter refers to the real data corresponding to the parameter during the operation of the wind turbine.

[0052] S102. Obtain the simulation data of the second operating parameter according to the actual data of the first operating parameter.

[0053] In S101, the second operating parameter is different from the first operating parameter; the simulation data of the second operating parameter is obtained based on the actual data of the first operating parameter; the simulation data refers to the data obtained through certain simulation means. For example, the simulation data of the second operating parameter can be obtained through a simulation model, using the actual data of the first operating parameter as the input of the simulation model, and the simulation data of the second operating parameter as the output of the simulation model; to a certain extent, the simulation data of the second operating parameter represents the value of the second operating parameter when the wind turbine is in the operating state represented by the actual data of the first operating parameter.

[0054] S103. Compare the simulation data of the second operating parameter with the design data of the second operating parameter to obtain a comparison result.

[0055] S104. Obtain the detection result of the wind turbine according to the comparison result.

[0056] In S103 - S104, the design data of the second operating parameter represents, to a certain extent, the allowable operating boundary of the second operating parameter of the wind turbine. For example, the design data generally refers to the operating boundary or allowable upper / lower limit of the unit operating data, such as the allowable load limit, or the allowable fatigue load, allowable minimum clearance, allowable maximum nacelle acceleration, etc. And the simulation data of the second operating parameter represents, to a certain extent, the value of the second operating parameter when the wind turbine is in the operating state represented by the actual data of the first operating parameter. The comparison process in S103 can obtain the difference between the simulation data and the design data of the second operating parameter, that is, obtain the difference between the value of the second operating parameter and the design value when the wind turbine is in the operating state represented by the actual data of the first operating parameter, which can indicate whether the wind turbine is in a normal operating state. Thus, without using sensors to detect the second operating parameter, the detection result of the wind turbine can be obtained, reducing the cost of detecting the wind turbine. Since the first operating parameter and the second operating parameter are used to represent the operating state of the wind turbine, the obtained detection result of the unit can include the detection result of the operating state of the unit.

[0057] Further, in the embodiments of the present application, the second operating parameter may include the parameters of the components without deployed sensors. In the prior art, it is necessary to deploy sensors on the components. During the operation of the unit, the data of the parameters of the components are collected through the deployed sensors, and the operation state of the unit is detected according to the collected data. Therefore, for the components without deployed sensors, for example, due to difficulties in deploying sensors caused by component positions, or not being deployed due to cost limitations, it is difficult to obtain the data of the parameters of the components, and the relevant operation states cannot be detected. However, in the embodiments of the present application, the simulation data of the second operating parameter is obtained according to the first operating parameter, and the detection result of the unit can be obtained according to the comparison result of the second operating parameter, the simulation data and the design data.

[0058] Further, in step S101 of the embodiments of the present application, obtaining the actual data of the first operating parameter of the wind turbine generator set may include obtaining the actual data of the first operating parameter of the wind turbine generator set in real time. Since the actual data of the first operating parameter is obtained in real time, through certain simulation means to obtain the simulation data of the second operating parameter, obtain the comparison result, and obtain the detection result according to the comparison result, a certain degree of real-time can also be achieved, so as to detect the wind turbine generator set to a certain extent in real time and generate a business response to the abnormality of the unit relatively quickly.

[0059] Further, in the embodiments of the present application, obtaining the simulation data of the second operating parameter according to the actual data of the first operating parameter may include: using the actual data of the first operating parameter as the input of the digital twin simulation model, and determining the output result of the digital twin simulation model as the simulation data of the second operating parameter.

[0060] The digital twin simulation model is a simulation model applied in digital twin technology, which can obtain an output that is more in line with the input situation of the model according to the input of the model. The simulation model is pre-constructed.

[0061] Inputting the actual data of the first operating parameter into the digital twin simulation model, the output of the model can represent the data of the second operating parameter of the unit when the unit is in the operating state corresponding to the actual data of the first operating parameter. Obtaining the data of the second operating parameter through the digital twin simulation model instead of detecting the data of the second operating parameter through sensors can save the cost caused by deploying sensors. Further, in the actual application process, multiple types of digital twin simulation models can be used. The multiple types of digital twin simulation models can be arbitrarily combined, and each digital twin simulation model operates independently of each other to obtain their respective simulation data.

[0062] Further, in the embodiments of the present application, before comparing the simulation data of the second operating parameter with the design data of the second operating parameter, it may further include: detecting the simulation data of the second operating parameter and the design data of the second operating parameter according to a preset detection condition; if the simulation data of the second operating parameter and / or the design data of the second operating parameter do not meet the preset detection condition, stop detecting the wind turbine generator set.

[0063] In the actual application process, the simulation data and design data of the second operating parameter may not meet the expectations, or there may be errors, etc., which will lead to inaccurate detection results finally obtained. Therefore, a preset detection condition is used to detect the simulation data and design data of the second operating parameter. When at least one of the data does not meet the preset condition, the detection process is stopped.

[0064] For the preset detection condition, the embodiments of the present application provide several specific implementation manners.

[0065] Condition 1: Check the running state of the simulation model. If the state is abnormal and does not meet the preset detection condition, stop the detection process. The simulation data of the second operating parameter obtained from the simulation model is one of the parameter data for obtaining the detection result. An abnormal running state of the simulation model may lead to inaccurate detection results. Therefore, the condition can be preset to be related to the running state of the simulation model. Further, when the simulation model is a digital twin simulation model, Condition 1 is to check the running state of the digital twin simulation model. If the state is abnormal and does not meet the preset detection condition, stop the detection process.

[0066] Condition 2: Screen for outliers in the simulation data of the second operating parameter and the design data of the second operating parameter. If there are outliers and do not meet the preset detection condition, stop the detection process. An outlier refers to a value that is significantly different from other data. The existence of outliers may lead to inaccurate detection results. Therefore, the condition can be preset to be related to outliers. Further, when the simulation data and / or design data of the second operating parameter are abnormal, outliers can also be removed. After removing the outliers, the detection process can continue. The advantage of doing this is to improve the utilization rate of the data.

[0067] Condition 3: Screen the fan status. If the simulation data of the second operating parameter and / or the design data of the second operating parameter contain data corresponding to a non-operating fan status, it is determined that the preset detection conditions are not met, and the detection process is stopped. Usually, the collected data is data within a certain time period. If, within this time period, the data is not all data corresponding to the fan operating status, then this data may be inaccurate in representing the operating status of the wind turbine generator set during this time period. Therefore, it is best to use data corresponding to the fan being in the operating state within a complete time period. Further, to determine whether the data within the complete period is data in the fan operating state, a data integrity label can be generated. If there is data with poor integrity, it is determined that the preset detection conditions are not met, and the detection process is stopped.

[0068] Condition 4: Detect the sensor zero drift phenomenon. If there is a sensor zero drift phenomenon, it is determined that the preset detection conditions are not met, and the determination of the operating status of the wind turbine generator set is stopped. When there is no signal input, the theoretical output value of the sensor is zero. The sensor zero drift phenomenon refers to the phenomenon that when there is no signal input, the output value of the sensor is not zero. The sensor zero drift phenomenon usually leads to inaccurate detected data. Further, after detecting the sensor zero drift phenomenon, sensor data zero drift removal can be performed, and the detection result can be obtained using the data after zero drift removal. The advantage of doing this is to improve the utilization rate of the data.

[0069] The preset detection conditions can be at least one of Conditions 1 to 4; the specific implementation manner of the above preset detection conditions is only a specific description of the embodiments of the present application, and does not limit the embodiments of the present application; it can be understood that how to preset the detection conditions does not affect the implementation of the embodiments of the present application.

[0070] Further, for step S104 of the embodiments of the present application, after obtaining the detection result of the wind turbine generator set, it may further include: generating a control instruction according to the detection result; and controlling the wind turbine generator set according to the control instruction.

[0071] During the operation of a wind turbine generator set, abnormalities may occur. The purposes of detecting the wind turbine generator set mainly include that when an abnormality occurs during the operation of the detected unit, corresponding control is performed on the unit according to the abnormality to reduce the adverse consequences brought by the abnormality. Since the control instruction is generated according to the detection result, the control instruction is related to the process of performing corresponding control on the unit according to the abnormality. Further, since if the generator set is still in the operating state after the abnormality occurs, it may cause adverse consequences to the generator set, so the instruction may be a shutdown instruction for controlling the wind turbine generator set to stop; the control instruction may also be an instruction for limiting power / limiting blade angle / limiting speed, or optimizing parameters, giving an early warning, etc.; further, when an abnormality occurs, a control instruction can be automatically generated.

[0072] Further, according to the control instruction, controlling the wind turbine generator set may include: sending the control instruction to the control device of the wind turbine generator set so that the control device controls the wind turbine generator set according to the control instruction. Further, the control device of the wind turbine generator set may include a PLC for controlling the unit to enable the PLC to control the unit according to the detection result. To a certain extent, it changes the situation where human intervention is required for control in traditional detection methods.

[0073] Further, comparing the simulation data of the second operating parameter and the design data of the second operating parameter to obtain a comparison result may include: extracting the features of the simulation data of the second operating parameter; comparing the eigenvalue of the simulation data of the second operating parameter with the design data of the second operating parameter to obtain a comparison result. Feature values can be extracted from the data, and results can be obtained through the operation of the feature values of the data to improve the operation efficiency. Further, the eigenvalue may include standard deviation, mean value, maximum value, minimum value, etc.

[0074] Further, in step S104 of the embodiment of the present application, obtaining the detection result of the wind turbine generator set according to the comparison result may include: when the deviation between the eigenvalue of the simulation data of the second operating parameter and the design data of the second operating parameter exceeds the first threshold, and the eigenvalue of the simulation data of the second operating parameter exceeds the second threshold, determining that the detection result is abnormal.

[0075] Since the simulation data of the second operating parameter is obtained through certain simulation means and is used for comparison with the design data, and the comparison result is used to determine the detection result; when the simulation data is too small, the multiple difference between the simulation data and the design data will be relatively large, thus leading to the conclusion that the simulation data deviates greatly from the design data. At this time, the smaller simulation data will affect the final detection result and reduce the accuracy of the detection. Therefore, when determining the detection result based on the deviation between the simulation data and the design data of the second operating parameter, setting that the eigenvalue of the simulation data exceeds the second threshold as a condition that needs to be satisfied simultaneously is used to improve the accuracy of the detection.

[0076] Further, in the embodiment S104 of the present application, obtaining the detection result of the wind turbine generator according to the comparison result may include: when the deviation between the eigenvalue of the simulation data of the second operating parameter and the design data of the second operating parameter exceeds the first threshold, and the eigenvalue of the simulation data of the second operating parameter exceeds the second threshold, determining the risk level according to the deviation; when the risk level exceeds the preset level, determining that the detection result is abnormal. The setting of the risk level is used to more clearly determine the operating state of the wind turbine generator.

[0077] Further, for the embodiment S104 of the present application, after obtaining the detection result of the wind turbine generator, it may further include: uploading the eigenvalue of the simulation data of the second operating parameter, the comparison result, and the detection result to the wind farm management system.

[0078] The wind farm management system refers to the management system used to manage wind turbine generators. Since the data generated during the operation of wind turbine generators is large and the data is usually collected within a certain time period, communication anomalies such as network interruptions may affect the transmission of key data. Minimizing the amount of data of the wind turbine generators that need to be transmitted during the transmission process, so the parameter data is transmitted in the form of eigenvalues instead of all data, which is beneficial to reducing the amount of data for transmission and can reduce data loss to a certain extent. Further, the wind farm management system can be PHM, and transmitting data to PHM can provide characteristic data of the unit operation for fault prediction and health management of the wind farm. Compared with the prior art, usually the fan PLC transmits the operation parameter data (usually the data collected within 20 ms) to the wind farm (farm PHM). In the embodiment of the present application, the transmitted data is in the form of eigenvalues, which can reduce the amount of transmitted data; through the transmission of the operation eigenvalues to the wind farm PHM, it also provides relatively rich characteristic data of the unit operation for the wind farm fault test / prediction and health management.

[0079] Further, the data transmitted to the PHM can be further uploaded to the cloud, forming operation characteristic data of the wind turbine generator set in the cloud, which can provide data samples for big data diagnosis and model training. Further, according to the description of the embodiments of the present application above, the data for uploading to the cloud may further include risk levels, data integrity tags, etc.

[0080] Further, in step S101 of the embodiments of the present application, when obtaining the actual data of the first operating parameter, a control instruction can also be obtained for triggering the operation of the simulation model.

[0081] Further, steps S101 - S104 of the embodiments of the present application can be completed by an auxiliary control device deployed on the wind turbine generator set. By communicating with the PLC, the auxiliary control device obtains the actual data of the first operating parameter of the wind turbine generator set; the simulation model is run on the auxiliary control device, and the auxiliary control device obtains the simulation data of the second operating parameter according to the actual data of the first operating parameter; the auxiliary control device compares the simulation data of the second operating parameter with the design data of the second operating parameter to obtain a comparison result; the auxiliary control device obtains the detection result of the wind turbine generator set according to the comparison result, and the auxiliary control device obtains a control instruction according to the detection result and sends the instruction to the unit control device PLC, and the PLC controls the unit; the data and results obtained during the detection process can be transmitted to the wind farm PHM, and the PHM can further push the characteristic data to the cloud.

[0082] An auxiliary control device capable of integrating computing and application is set near the PLC side of the wind turbine generator. Using the auxiliary control device that integrates computing and application belongs to the edge computing - based unit auxiliary diagnosis and control architecture, which provides the unit PLC - side digital - twin - based unit detection service nearby; it can generate faster service responses for unit testing, meeting the requirements of wind farm units in terms of real - time performance, intelligence, network security, etc.; at the same time, through the digital - twin - based method, the deployment of traditional sensors can be reduced to a certain extent, thereby reducing the cost of unit detection; it also improves the current situation of diagnostic analysis at centralized nodes such as the cloud and the wind farm to a certain extent, and more reliable auxiliary diagnosis based on actual data can be carried out at the edge side such as the fan PLC, and the unit auxiliary equipment, PLC, and wind farm PHM are connected together.

[0083] The data transmitted between the auxiliary control device and the PLC through communication can be data with a certain time period (for example, 20 ms), that is, the actual data of the first operating parameter, and can be data continuously collected within a certain time period; this data can be collected by sensors on the PLC and then stored in a database or other data file storage locations, and the auxiliary control system obtains it from the database or other data file storage locations when in use; the auxiliary control device can also have detectors for collecting data; when the auxiliary control device runs the simulation model, the simulation data obtained by the simulation model can also be stored in this database or other data file storage locations.

[0084] Further, for the simulation data of the second operating parameter obtained through the simulation model, the simulation model can be triggered at a certain interval, for example, the simulation model is triggered at the first interval time; after triggering, data (data of the first operating parameter) within a certain time period (for example, the first time period) is obtained, and the entire time period of data can be obtained, for example, the first time period is 1 min, for example, from 9 minutes 0 seconds to 10 minutes 0 seconds, aiming to facilitate data recording and analysis.

[0085] Comparing the simulation data of the second operating parameter with the design data to obtain a comparison result, and determining the detection result based on the comparison result can also be completed through a model, such as a unit detection model; further, the unit detection model can also be triggered at a certain interval, for example, the second interval time; after triggering, data (simulation data and design data of the second operating parameter) within a certain time period (for example, the second time period) is obtained, and the entire time period of data can be obtained.

[0086] Since it takes a certain amount of time to obtain simulation data through the simulation model, there are certain limiting conditions between the triggering times of the simulation model and the unit detection model, that is, for the unit detection model, in order to obtain the detection result using the data within the second time period, it is necessary to analyze the data after the simulation model obtains the simulation data within the second time period. Therefore, when the actual data of the first operating parameter and the obtained simulation data are both placed in the database, the data read by the unit detection model needs to meet the above limiting conditions.

[0087] Further, an industrial control computer and multiple PLCs can also be used to implement the embodiments S101 - S104 of the present application, and the modules for implementing the above models can also be directly integrated on the PLC, and the PLC completes the corresponding functions.

[0088] Further, in the embodiments of the present application, the first operating parameter and the second operating parameter refer to the parameters used to represent the operating state of the unit during the operation of the unit. The embodiments of the present application provide examples of the types of the second operating parameter. For example, the second operating parameter may be the unit clearance. For a unit without a clearance measurement device, in the embodiments of the present application, the simulation data of the unit clearance is obtained through a digital twin simulation model, and by comparing the simulation data of the unit clearance with the design data, abnormal clearance problems can be detected; it is usually difficult to deploy a load sensor or difficult to maintain the middle part of the blade, and the second operating parameter may be the load of the unit in the middle of the blade. In the embodiments of the present application, the simulation data of the load of the unit in the middle of the blade is obtained through a digital twin simulation model, and by comparing the simulation data of the load of the unit in the middle of the blade with the design data, abnormal load problems can be detected; the second operating parameter may also be other parameters. The above-mentioned second operating parameters are only examples provided in the embodiments of the present application, and the specific parameter types and categories included in the second operating parameter do not affect the implementation of the embodiments of the present application.

[0089] Further, in step S102 of the embodiments of the present application, in order to obtain the simulation data of the second operating parameter, certain simulation means are adopted. The simulation means may be simulation based on lidar wind speed, simulation based on root load, simulation based on nacelle wind speed, simulation based on tower load, etc. The above-mentioned simulation means are only examples provided in the embodiments of the present application, and the specific types and categories included in the simulation means do not affect the implementation of the embodiments of the present application.

[0090] The embodiments of the present application give two specific implementation manners.

[0091] First, the method for detecting a wind turbine generator set in the embodiments of the present application is used to determine the detection result of the unit according to the tower bottom load.

[0092] The second operating parameter is the tower bottom load; the simulation model for generating the simulation data of the second operating parameter is a digital twin simulation model; the actual data of the first operating parameter, i.e., the wind speed data, is input into the digital twin simulation model;

[0093] The digital twin simulation model is used to generate the simulation data of the tower bottom load;

[0094] After initialization, detection is performed according to the preset detection conditions: check the state of the digital twin simulation model, and if it is abnormal, terminate the process; detect and process the simulation data of the tower bottom load according to the preset detection conditions: perform outlier rejection, generate integrity labels according to the fan state, and perform screening;

[0095] Extract the characteristic value of the simulation data of the tower bottom load, and the characteristic value is the absolute value extreme value; compare the absolute value extreme values of the design data and the simulation data of the tower bottom load to obtain the absolute value extreme value deviation of the tower bottom load; the design data is a preset parameter, and the simulation data is obtained after running the simulation model according to the actual data.

[0096] The extreme value of the absolute value of the tower bottom load is divided into bins according to the wind speed, and the average value of the load in the bin is calculated; the average value of the load in the bin is compared with the designed value of the average value of the load in the bin to obtain the average value deviation of the tower bottom bin; the comparison result between the absolute value of the simulation data of the tower bottom load and the second threshold within 10 minutes is extracted; it can be expressed as the percentage of the number of the absolute values of the simulation data of the bottom load greater than the second threshold in the absolute values of the simulation data of the bottom load, denoted as the simulation deviation ratio.

[0097] Generate risk levels: When the extreme value deviation of the absolute value of the tower bottom load is greater than the first extreme value threshold (the extreme value of the instantaneous load absolute value is greater than the ratio threshold), generate the tower bottom load risk level 1; when the average value deviation of the tower bottom bin is greater than the first average value threshold (the average value of the absolute values of the extreme values of the load in at least one same bin is greater than the first average value threshold), generate the tower bottom load risk level 2; when the simulation deviation ratio is greater than the ratio threshold (the instantaneous load absolute value within 10 minutes is greater than the ratio threshold), generate the tower bottom load risk level 3.

[0098] When the tower bottom load risk level 3 is generated within 10 minutes, generate and send a shutdown control instruction to the PLC to enable the PLC to control the unit to shut down.

[0099] Transmit operation characteristics such as the data integrity label, the extreme value of the absolute value of the tower bottom load, the extreme value deviation of the bottom load absolute value, and the tower bottom load risk level to the field-level PHM.

[0100] Second, the method for detecting a wind turbine generator set in the embodiment of the present application is used to determine the detection result of the unit according to the clearance.

[0101] The second operating parameter is the clearance; the simulation model for generating the simulation data of the second operating parameter is a digital twin simulation model; the actual data wind speed data of the first operating parameter is input into the digital twin simulation model.

[0102] Generate the simulation data of the clearance by using the digital twin simulation model.

[0103] After initialization, perform detection according to the preset detection conditions: check the status of the digital twin simulation model, and if it is abnormal, terminate the process; detect and process the simulation data of the clearance according to the preset detection conditions: perform outlier rejection, generate a integrity label according to the fan status, and perform screening.

[0104] Extract the characteristic value of the simulation data of the clearance, and the characteristic value is the minimum value; compare the designed data of the clearance with the minimum value of the simulation data to obtain the clearance deviation.

[0105] Compare the clearance deviation with the first threshold; when the clearance deviation exceeds the first threshold, generate the clearance risk level.

[0106] Check the net clearance risk level; when the net clearance risk level exceeds the preset level, generate and send a shutdown control instruction to the PLC to enable the PLC to control the unit to shut down;

[0107] Transmit the operation characteristics such as the data integrity label, the minimum value of the net clearance simulation data, the net clearance deviation, and the net clearance risk level to the field-level PHM.

[0108] Third, the method for detecting a wind turbine generator set in the embodiment of the present application is used to determine the detection result of the unit according to the nacelle displacement.

[0109] The second operating parameter is the nacelle displacement; the simulation model for generating the simulation data of the second operating parameter is a digital twin simulation model; the actual data wind speed data of the first operating parameter is input into the digital twin simulation model;

[0110] Generate the simulation data of the nacelle displacement by using the digital twin simulation model;

[0111] After initialization, perform detection according to the preset detection conditions: check the status of the digital twin simulation model, and if it is abnormal, terminate the process; perform detection and processing on the simulation data of the nacelle displacement according to the preset detection conditions: perform outlier rejection, generate an integrity label according to the fan status, and perform screening;

[0112] Extract the characteristic value of the simulation data of the nacelle displacement, and the characteristic value is the maximum value; compare the maximum values of the design data and the simulation data of the nacelle displacement to obtain the nacelle displacement deviation;

[0113] Compare the nacelle displacement deviation with the first threshold; when the nacelle displacement deviation exceeds the first threshold, generate the nacelle displacement risk level;

[0114] Check the nacelle displacement risk level; when the nacelle displacement risk level exceeds the preset level, generate and send a shutdown control instruction to the PLC to enable the PLC to control the unit to shut down;

[0115] Transmit the operation characteristics such as the data integrity label, the minimum value of the simulation data of the nacelle displacement, the nacelle displacement deviation, and the nacelle displacement risk level to the field-level PHM.

[0116] In the above three implementation manners, the simulation data generated by using the digital twin simulation model and the obtained actual data can both be stored in the database.

[0117] It can be understood that the above three implementation manners are all examples of the embodiment of the present application, and the specific types and quantities of the parameters do not limit the embodiment of the present application.

[0118] Please refer to Figure 2 , Figure 2 is the structural schematic diagram of the detection system of the wind turbine generator set provided by the embodiment of the present application, and this system usesFigure 1 The detection method of the wind turbine provided by the embodiment of the present application; the system 200 includes a wind turbine 201, an auxiliary control device 202, a control device PLC 203, and a PHM.

[0119] The auxiliary control device 202 is used to implement Figure 1 the detection methods S101 - S104 for the wind turbine provided by the embodiment of the present application, and the control device PLC 203 is used to control the unit 201;

[0120] The auxiliary control device 202 is deployed on the unit 201, communicates with the PLC 203 to transfer 20 - ms data, runs a digital twin simulation model. The auxiliary control device 202 compares the simulation result with the actual operation result of the unit 201, that is, compares the simulation data and the actual data of the comparison control parameters, to determine the operation state of the unit 201; the auxiliary control device 202 transmits the generated control instructions and the obtained status information to the PLC 203, and transmits the data diagnosis result to the wind farm PHM 204, and the PHM 204 can further push these transmitted characteristic data to the cloud.

[0121] Please refer to Figure 3 , Figure 3 which is the flowchart of the detection method for the wind turbine provided by another embodiment of the present application. The steps included in the detection method of the wind turbine in the embodiment of the present application are as Figure 3 shown.

[0122] Obtain the actual data of the unit; the actual data is the actual data of the unit parameters, which may include data of unit parameters such as lidar wind speed, blade root load, nacelle wind speed, tower load, etc. These data, the unit control instructions (PLC control instructions), and (other) unit statuses are transmitted to the auxiliary control device (referred to as the auxiliary control device for short) as the input of the auxiliary control digital twin, and the simulation based on the parameters is completed to obtain the simulation data.

[0123] The simulation based on parameters may include the simulation based on lidar wind speed, blade root load, nacelle wind speed, and tower load to achieve the simulation under multiple types of inputs.

[0124] After the feature extraction of the obtained digital twin simulation unit state (represented by the simulation data), it is input into the auxiliary control anomaly detection model for the detection of the wind turbine in the form of feature values, and the simulation data and the design data are compared to complete the verification based on the digital twin simulation state; during the operation of the auxiliary control anomaly detection model, it may also be necessary to input model parameters.

[0125] Return the obtained status verification secondary control instruction to the unit (PCL) to control the unit, and transmit the obtained risk level, data records, etc. to the field-level PHM to provide characteristic data of the unit operation for fault prediction and health management of the wind farm; the data records may include measured and simulated characteristic data, instantaneous data at the risk trigger moment, etc.

[0126] The data transmitted to the PHM can be further uploaded to the cloud, forming characteristic data of the operation of the wind turbine generator set in the cloud, which can provide data samples for big data diagnosis and model training.

[0127] Please refer to Figure 4 , Figure 4 , which is a schematic structural diagram of the detection device for a wind turbine generator set provided by an embodiment of the present application. The detection device 400 includes a processor 401 and a memory 402. Among them, the memory 402 stores corresponding codes, and the processor 401 is used to call the codes stored in the memory 402 to implement the following functions:

[0128] Obtain the actual data of the first operating parameter of the wind turbine generator set;

[0129] Obtain the simulation data of the second operating parameter according to the actual data of the first operating parameter;

[0130] Compare the simulation data of the second operating parameter with the design data of the second operating parameter to obtain a comparison result;

[0131] Obtain the detection result of the wind turbine generator set according to the comparison result.

[0132] The units included in the electronic device and the connection relationship between the units can achieve the same technical effect as the method for determining the operating state of the above-mentioned wind turbine generator set. To avoid repetition, it will not be elaborated here.

[0133] Please refer to Figure 5 , Figure 5 , which is a wind turbine generator set provided by an embodiment of the present application. The wind turbine generator set includes Figure 4 The corresponding detection device for the wind turbine generator set provided by the embodiment of the present application.

[0134] The units included in the wind turbine generator set and the connection relationship between the units can achieve the same technical effect as the method for determining the operating state of the above-mentioned wind turbine generator set. To avoid repetition, it will not be elaborated here.

[0135] In an embodiment of the present application, a computer-readable storage medium is further provided. The computer-readable storage medium is used to store a computer program, and the computer program is used to execute the method for detecting a wind turbine generator as described above, and can achieve the same technical effects. To avoid repetition, it will not be elaborated here. Among them, the computer-readable storage medium includes, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc, etc. The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to these embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A detection method for a wind power generation unit, characterized in that, The method includes: Obtaining the actual data of the first operating parameter of the wind turbine generator set; Obtaining the simulation data of the second operating parameter based on the actual data of the first operating parameter, where the second operating parameter includes parameters for which data can be collected by sensors; Comparing the simulation data of the second operating parameter with the design data of the second operating parameter to obtain a comparison result; Obtaining the detection result of the wind turbine generator set according to the comparison result; Before comparing the simulation data of the second operating parameter with the design data of the second operating parameter, it further includes: Detecting the simulation data of the second operating parameter and the design data of the second operating parameter according to preset detection conditions; If the simulation data of the second operating parameter and / or the design data of the second operating parameter do not meet the preset detection conditions, stop detecting the wind turbine generator set.

2. The detection method according to claim 1, wherein The obtaining the simulation data of the second operating parameter according to the actual data of the first operating parameter includes: Using the actual data of the first operating parameter as the input of the digital twin simulation model, and determining the output result of the digital twin simulation model as the simulation data of the second operating parameter.

3. The detection method according to claim 1, wherein After obtaining the detection result of the wind turbine generator set, it further includes: Generating a control instruction according to the detection result; Controlling the wind turbine generator set according to the control instruction.

4. The detection method according to claim 1, wherein The comparing the simulation data of the second operating parameter with the design data of the second operating parameter to obtain a comparison result includes: Performing feature extraction on the simulation data of the second operating parameter; Comparing the feature values of the simulation data of the second operating parameter with the design data of the second operating parameter to obtain the comparison result.

5. The detection method according to claim 4, wherein The obtaining the detection result of the wind turbine generator set according to the comparison result includes: When the deviation between the feature value of the simulation data of the second operating parameter and the design data of the second operating parameter exceeds the first threshold, and the feature value of the simulation data of the second operating parameter exceeds the second threshold, determining that the detection result is abnormal.

6. The detection method according to claim 4, wherein After obtaining the detection result of the wind turbine generator set, it further includes: Transmitting the feature value of the simulation data of the second operating parameter, the comparison result, and the detection result to the wind farm management system.

7. A detection device for a wind turbine, characterized in that, The detection device includes a processor and a memory. Among them, the memory stores code, and the processor is used to call the code stored in the memory to implement the following functions: Obtaining the actual data of the first operating parameter of the wind turbine generator set; Obtaining the simulation data of the second operating parameter based on the actual data of the first operating parameter, where the second operating parameter includes parameters for which data can be collected by sensors; Comparing the simulation data of the second operating parameter with the design data of the second operating parameter to obtain a comparison result; Obtaining the detection result of the wind turbine generator set according to the comparison result; Before comparing the simulation data of the second operating parameter with the design data of the second operating parameter, the processor is further used to call the code stored in the memory to implement the following functions: Detect the simulation data of the second operating parameter and the design data of the second operating parameter according to preset detection conditions; If the simulation data of the second operating parameter and / or the design data of the second operating parameter do not meet the preset detection conditions, stop the detection of the wind turbine generator set.

8. A wind power generating set, characterized in that, The wind turbine generator set includes the detection device of the wind turbine generator set according to claim 7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store a computer program, and the computer program is used to execute the detection method of the wind turbine generator set according to any one of claims 1 to 6.

Images