Wind turbine generator operation performance monitoring system and method based on PLC hardware platform

Abstract

The invention discloses a wind turbine generator operation performance monitoring system and method based on a PLC hardware platform, and relates to the technical field of wind turbine generator monitoring, and the method comprises the following steps: obtaining the operation performance evaluation data of a wind turbine generator, obtaining the historical operation data of the wind turbine generator, and analyzing the operation performance evaluation index of the wind turbine generator. Analyzing a wind turbine generator operation performance correction index, generating early warning information, determining unmanned aerial vehicle inspection demand information, analyzing a wind turbine generator unmanned aerial vehicle inspection verification indication coefficient, determining wind turbine generator remote early warning demand information, and adaptively adjusting an unmanned aerial vehicle inspection period. The system can more accurately monitor the operation performance of the wind turbine generator, timely find whether the operation of the wind turbine generator is abnormal or not, provide data basis for subsequent analysis, accurately early warn fault risks, effectively avoid fault deterioration, reduce the maintenance cost and downtime, optimize the unmanned aerial vehicle inspection strategy, improve the inspection efficiency and pertinence, and improve the unmanned aerial vehicle inspection efficiency and pertinence. Power generation loss is reduced and power generation efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of wind turbine monitoring, and in particular to a system and method for monitoring the operating performance of a wind turbine set based on a PLC hardware platform. Background Art

[0002] With the continuous growth of clean energy demand, wind energy as a renewable energy source has played an increasingly important role in the energy field. As a key device for converting wind energy into electrical energy, the performance of wind turbines is directly related to wind energy utilization efficiency, power generation stability, equipment life, etc. During the operation of wind turbines, on the one hand, the harsh natural environment conditions of wind farms will have a significant impact on the operation of wind turbines. On the other hand, wind turbines are in outdoor operation for a long time and are eroded by corrosive substances such as sand, dust, and salt spray, which can easily cause corrosion of electrical equipment and degradation of insulation performance, increasing the risk of equipment failure.

[0003] The prior art, such as the invention patent with announcement number: CN112032003B, is a method for monitoring the operating performance of a large wind turbine, wherein the method comprises the following steps: acquiring operating data and preprocessing data; dividing wind speed intervals; dividing operating areas; and determining abnormal performance. The operating area is divided according to the shape of the data scatter plot of the wind speed interval where inefficient data points are likely to accumulate, and the entire operating space is divided into a normal operating area and an inefficient operating area, and the abnormal state of the unit's operating performance is determined based on two quantitative indicators: the area of ​​the inefficient area and the proportion of inefficient data.

[0004] The prior art, such as the invention patent with announcement number: CN113107785B, is a real-time monitoring method and device for abnormal power performance of a wind turbine, comprising the steps of: obtaining historical operating data of the wind turbine to be monitored and historical data of the wind farm wind tower in the same period; cleaning the historical operating data of the wind turbine to be monitored, eliminating invalid data, and retaining the data of the wind turbine to be monitored under normal operating conditions; and constructing a multidimensional feature vector that characterizes the power performance of the wind turbine, and dividing the multidimensional feature vector into a model learning group and a model verification group.

[0005] It can be seen from the above scheme that the current wind turbine performance monitoring system has certain deficiencies in effectiveness and accuracy. It often focuses on data processing or feature construction in specific aspects, but in the actual wind turbine operating environment, the performance of the unit is affected by a combination of multiple complex factors. The operating conditions of various components inside the wind turbine are interrelated and synergistic, and the variability of the external environment also continues to interfere with the operation of the unit. This complex coupling relationship means that it is difficult to fully and accurately grasp the true operating performance of the wind turbine by monitoring only from local data or a single angle. It is easy to miss potential problems and fail to make accurate judgments on performance change trends in a timely manner, which may delay maintenance opportunities, increase the probability of sudden equipment failures, reduce the power generation efficiency and overall operating stability of wind turbines, and affect the energy supply reliability of wind farms. Summary of the invention

[0006] In view of the deficiencies in the prior art, the present invention provides a wind turbine operating performance monitoring system and method based on a PLC hardware platform, which can effectively solve the problems involved in the above-mentioned background technology.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: In a first aspect, the present invention provides a wind turbine operating performance monitoring system based on a PLC hardware platform, comprising:

[0008] The operation performance evaluation data acquisition module is used to collect the operation parameters of the wind turbine set and input them into the central processing unit of the PLC hardware platform to analyze and process the operation parameters of the wind turbine set to obtain the operation performance evaluation data of the wind turbine set.

[0009] The wind turbine performance evaluation label determination module is used to synchronously obtain the historical operation data of the wind turbine according to the wind turbine operation performance evaluation data, and analyze and process to obtain the wind turbine operation performance evaluation index.

[0010] The UAV inspection demand information determination module is used to obtain the basic operating parameters of the wind turbine set, and analyze the wind turbine set operating performance correction indicators in combination with the wind turbine set operating performance evaluation indicators. Based on the wind turbine set operating performance correction indicators, early warning information is generated, and the UAV inspection demand information is simultaneously determined. The UAV inspection demand information includes demand inspection and no inspection required.

[0011] The drone inspection analysis module is used to collect the drone inspection data of the wind turbine when the drone inspection demand information is determined to be a demand inspection, analyze the drone inspection verification indicator coefficient of the wind turbine, and determine the remote early warning demand information of the wind turbine in combination with the wind turbine operation performance correction index, and simultaneously adaptively adjust the drone inspection cycle based on the wind turbine drone inspection verification indicator coefficient.

[0012] A second aspect of the present invention provides a method for monitoring the operating performance of a wind turbine generator system based on a PLC hardware platform, comprising the following steps:

[0013] S1, collects wind turbine operating parameters and inputs them into the central processing unit of the PLC hardware platform to analyze and process the wind turbine operating parameters to obtain wind turbine operating performance evaluation data.

[0014] S2, based on the wind turbine operating performance evaluation data, synchronously obtain the wind turbine historical operating data, analyze and process to obtain the wind turbine operating performance evaluation index.

[0015] S3, obtaining the basic operating parameters of the wind turbine set, and analyzing the wind turbine set operating performance correction indicators in combination with the wind turbine set operating performance evaluation indicators, generating early warning information based on the wind turbine set operating performance correction indicators, and simultaneously determining the drone inspection demand information, wherein the drone inspection demand information includes required inspection and no inspection required.

[0016] S4, when the UAV inspection demand information is determined to be a demand inspection, the wind turbine UAV inspection data is collected, the wind turbine UAV inspection verification indicator coefficient is analyzed, and the wind turbine operating performance correction index is combined to determine the wind turbine remote warning demand information, and the UAV inspection cycle is adaptively adjusted based on the wind turbine UAV inspection verification indicator coefficient.

[0017] Compared with the prior art, the embodiments of the present invention have at least the following beneficial effects:

[0018] (1) The present invention provides a wind turbine operating performance monitoring system and method based on a PLC hardware platform, and utilizes the powerful data processing capabilities of the PLC hardware platform to achieve accurate collection and analysis of wind turbine operating parameters, and can obtain accurate operating performance evaluation data, monitor the wind turbine operating performance more accurately, and can promptly detect whether the wind turbine is operating abnormally, providing a reliable data basis for subsequent analysis and decision-making. By comprehensively considering multiple factors to calculate the operating performance correction index, it can accurately warn of fault risks, discover potential problems in advance, effectively avoid fault deterioration, reduce maintenance costs and downtime, and optimize drone inspection strategies, improve inspection efficiency and pertinence, reduce power generation losses, and improve power generation efficiency.

[0019] (2) The present invention obtains wind turbine operating performance evaluation indicators through analysis and processing, which can realize accurate judgment of the operating status of the wind turbine. Operation and maintenance personnel can more accurately understand the health status and performance trends of the wind turbine and timely discover potential performance degradation or abnormal changes, so as to take effective preventive measures before failure occurs, accurately allocate resources, improve the reliability and stability of the wind turbine, extend the service life of the equipment, and ultimately improve the overall power generation efficiency and economic benefits of the wind farm.

[0020] (3) The present invention can improve the scientific nature of wind turbine performance monitoring by generating early warning information based on the wind turbine operating performance correction index and simultaneously determining the drone inspection demand information. The early warning information generated based on the operating performance correction index can timely and accurately reflect whether the wind turbine operating status is abnormal, so that the operation and maintenance personnel can quickly know the potential risks of the unit, avoid further expansion of the fault, effectively reduce the probability of sudden shutdown, ensure the continuous and stable power generation of the wind turbine, and reduce the power generation loss caused by shutdown. At the same time, the drone inspection demand information is reasonably determined to avoid excessive or insufficient inspections, and to achieve the optimal allocation of inspection resources. When the unit operating performance shows abnormal signs, drone inspections are arranged in time, providing numerical basis for subsequent precise maintenance, further improving the maintenance efficiency and quality, and ensuring the long-term and efficient operation of the wind turbine.

[0021] (4) The present invention can accurately measure the degree of remote warning demand of wind turbines by determining the remote warning demand information of wind turbines and calculating the remote warning demand assessment indicator parameter. When the parameter is greater than or equal to the remote warning demand assessment threshold, a remote warning is issued in a timely manner, so that operation and maintenance personnel can obtain potential serious fault information of the unit in the first time when they are far away from the wind farm, effectively avoiding long-term shutdown of wind turbines or aggravated equipment damage caused by sudden faults. At the same time, the remote warning mechanism helps to realize the centralized management of wind farms, improve the efficiency of operation and maintenance management, and ensure that wind turbines always maintain a safe, stable and efficient operating state in a complex and changeable operating environment.

[0022] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a schematic diagram of system module connection of the present invention;

[0024] Figure 2 It is a schematic diagram of the method flow of the present invention. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] See also Figure 1 As shown, the embodiment of the present invention provides a wind turbine operating performance monitoring system based on a PLC hardware platform, including:

[0027] The operation performance evaluation data acquisition module is used to collect the operation parameters of the wind turbine set and input them into the central processing unit of the PLC hardware platform to analyze and process the operation parameters of the wind turbine set to obtain the operation performance evaluation data of the wind turbine set.

[0028] In this embodiment, the wind turbine operating performance evaluation data is obtained, and the specific acquisition method is as follows:

[0029] During the preset monitoring period, the wind turbine operating parameters are collected. The wind turbine operating parameters include the total wind energy of the wind turbine, the total electric energy output by the wind turbine, the wind turbine voltage at each time point, the wind turbine current, the wind turbine power factor, the wind turbine yaw angle, the wind turbine rotor speed, and the wind direction of the wind farm.

[0030] It should be noted that the operating parameters of the wind turbine generator set can be collected by means of the wind turbine generator set integrated sensor device.

[0031] The actual output power of the wind turbine at each time point is obtained by analyzing the voltage, current and power factor of the wind turbine at each time point. Based on the actual output power of the wind turbine at each time point, the actual output power variance of the wind turbine is calculated.

[0032] It should be noted that the actual output power of the wind turbine at each time point is equal to the voltage multiplied by the current multiplied by the power factor at that time point.

[0033] It should be noted that the actual output power variance of the wind turbine is obtained in the following way: Among them, a is the actual output power variance of the wind turbine, α i is the actual output power of the wind turbine at the i-th time point, i is the number of each time point, i=1,2,...,n, and n is the number of time points.

[0034] The power generation efficiency of the wind turbine is calculated based on the total amount of wind energy of the wind turbine and the total amount of electrical energy output by the wind turbine.

[0035] It should be noted that the power generation efficiency of wind turbines can be obtained in the following ways: Among them, b is the power generation efficiency of the wind turbine, b1 is the total wind energy of the wind turbine, and b2 is the total electrical energy output by the wind turbine.

[0036] Based on the yaw angle of the wind turbine and the wind direction of the wind farm at each time point, the yaw error rate of the wind turbine is calculated.

[0037] It should be noted that the yaw angle of a wind turbine refers to the yaw angle of the wind turbine nacelle relative to the wind direction.

[0038] It should be noted that the yaw error rate of a wind turbine is specifically obtained as follows: the yaw error angle at each time point is obtained by performing difference processing on the yaw angle of the wind turbine and the wind direction of the wind farm, and the absolute value of the yaw error angle at each time point is accumulated to obtain the total yaw error angle within the monitoring period, and the reference total yaw error angle preset in the database is extracted, and the total yaw error angle within the monitoring period is subtracted from the reference total yaw error angle to obtain the total yaw error deviation angle, and the yaw error rate of the wind turbine is obtained by dividing the total yaw error deviation angle by the reference total yaw error angle.

[0039] Based on the wind turbine rotor speed at each time point, the wind turbine speed fluctuation rate is calculated.

[0040] It should be noted that the speed fluctuation rate of a wind turbine is obtained in the following way: the average speed of the wind turbine rotor at each time point is processed, and the average speed of the wind turbine rotor within the monitoring period is obtained; the difference between the wind turbine rotor speed at each time point and the average speed of the wind turbine rotor is processed, and the speed fluctuation of the wind turbine rotor at each time point is obtained; the standard deviation of the speed fluctuation of the wind turbine rotor at each time point is calculated, and the standard deviation of the speed fluctuation of the wind turbine rotor is recorded as the speed fluctuation rate of the wind turbine rotor.

[0041] It should also be noted that the standard deviation of the wind turbine speed fluctuation at each time point is calculated as follows: Among them, d is the standard deviation of the wind turbine speed fluctuation, β i is the speed fluctuation of the wind turbine at the i-th time point, i is the number of each time point, i=1,2,...,n, and n is the number of time points.

[0042] The actual output power variance of the wind turbine, the power generation efficiency of the wind turbine, the yaw error rate of the wind turbine and the speed fluctuation rate of the wind turbine are jointly used as the wind turbine operation performance evaluation data.

[0043] The wind turbine performance evaluation label determination module is used to synchronously obtain the historical operation data of the wind turbine according to the wind turbine operation performance evaluation data, and analyze and process to obtain the wind turbine operation performance evaluation index.

[0044] In this embodiment, the wind turbine operating performance evaluation index is obtained through analysis and processing, and the specific analysis process is as follows:

[0045] The historical operation data of the wind turbine generator set includes the historical average power factor, the historical average wind rotor speed, the historical average nacelle vibration speed and the historical average oil temperature of the wind turbine generator set.

[0046] It should be noted that the historical operation data of the wind turbine is extracted from the wind turbine affiliation database.

[0047] Based on the wind turbine operating performance evaluation data and the wind turbine historical operating data, the wind turbine operating performance evaluation index is obtained through analysis and processing.

[0048] The wind turbine operating performance evaluation index is used to characterize the wind turbine operating performance.

[0049] In a specific embodiment, the wind turbine operating performance evaluation index is obtained in the following manner:

[0050] The wind turbine reference operation performance evaluation data and wind turbine reference historical operation data stored in the database are extracted, wherein the wind turbine reference operation performance evaluation data includes the wind turbine reference output power variance, the wind turbine reference power generation efficiency, the wind turbine reference yaw error rate and the wind turbine reference speed fluctuation rate.

[0051] The reference historical operation data of the wind turbine generator set includes the reference historical average power factor of the wind turbine generator set, the ideal historical average wind rotor speed, the reference historical average nacelle vibration speed and the reference historical average oil temperature.

[0052] It should be noted that the wind turbine reference operation performance evaluation data and wind turbine reference historical operation data are obtained by collecting a large amount of operation performance evaluation data and historical operation data and performing mean processing before establishing the database.

[0053]

[0054]

[0055] Among them, A is the wind turbine operating performance evaluation index, A1 is the wind turbine operating performance evaluation data characterization factor, A2 is the wind turbine historical operating data characterization factor, is the weight of the wind turbine operating performance evaluation data characterization factor, is the weight of the characterization factor of the historical operation data of the wind turbine, a is the actual output power variance of the wind turbine, b is the power generation efficiency of the wind turbine, c is the yaw error rate of the wind turbine, d is the speed fluctuation rate of the wind turbine, f is the historical average power factor of the wind turbine, g is the historical average rotor speed of the wind turbine, h is the historical average nacelle vibration speed of the wind turbine, j is the historical average oil temperature of the wind turbine, a0 is the reference output power variance of the wind turbine, b0 is the reference power generation efficiency of the wind turbine, c0 is the reference yaw error rate of the wind turbine, d0 is the reference speed fluctuation rate of the wind turbine, f0 is the reference historical average power factor of the wind turbine, g0 is the ideal historical average rotor speed of the wind turbine, h0 is the reference historical average nacelle vibration speed of the wind turbine, j0 is the reference historical average oil temperature of the wind turbine, and e is a natural constant.

[0056] It should be noted that the weights of the wind turbine operation performance evaluation data characterization factors and the wind turbine historical operation data characterization factors are both in the range of 0-1. In a specific embodiment, a preset value can be directly extracted from the database. For example, the collected wind turbine operation performance evaluation data characterization factors, wind turbine historical operation data characterization factors and wind turbine operation performance evaluation data characterization factor weights, wind turbine historical operation data characterization factor weights are mapped and associated in the database to construct a mapping association system. When it is necessary to obtain the weights, the system inputs the actual current wind turbine operation performance evaluation data characterization factors and wind turbine historical operation data characterization factors, and directly extracts the corresponding preset weights in the mapping association system.

[0057] It should also be noted that the wind turbine operation performance evaluation index is obtained by analyzing and processing the wind turbine operation performance evaluation data and the historical operation data of the wind turbine, taking into account the mutual influence between these parameters. For example, the actual output power variance reflects the stability of the wind turbine output power. When the actual output power variance is large, it means that the output power of the wind turbine fluctuates violently, which may be caused by unstable wind speed, mechanical component failure or improper adjustment of the control system. Such power fluctuations will make it difficult for the wind turbine to operate under the optimal working conditions, thereby reducing the power generation efficiency. A large yaw error rate means that the wind turbine cannot accurately align with the wind direction, resulting in the wind rotor unable to capture wind energy to the maximum extent, which will make the actual output power of the wind turbine lower than the optimal value, and due to the continuous change of wind direction, the actual output power will fluctuate greatly, thereby increasing the actual output power variance. The speed fluctuation rate reflects the stability of the wind turbine rotor speed. When the speed fluctuation rate is large, the output power of the wind turbine will fluctuate accordingly, because the output power of the wind turbine is closely related to the wind rotor speed. A high yaw error rate will prevent the wind turbine from fully utilizing wind energy, thereby reducing the power generation efficiency. A large speed fluctuation rate is not conducive to the operation of the wind turbine under the optimal working conditions and will reduce the power generation efficiency. When the yaw error rate is large, the wind turbine rotor is unevenly stressed, which will lead to unstable speed and increased speed fluctuation rate. The historical average power factor reflects the past power quality of the wind turbine. If the historical average power factor is low, it means that the wind turbine may have problems such as insufficient reactive power compensation in the past operation, which may affect the stability of the control system of the wind turbine. An unstable control system may cause the wind turbine to be unable to effectively adjust the output power in the current operation, thereby increasing the actual output power variance. The historical average oil temperature reflects the working conditions of the heat dissipation and lubrication system of the wind turbine in the past. If the historical average oil temperature is high, it may indicate that there are problems with the heat dissipation system or poor lubrication. In the current operation, this may affect the working efficiency and reliability of the mechanical components, resulting in unstable output power of the wind turbine and increased actual output power variance. A low historical average power factor may indicate that there are problems on the grid side or that the wind turbine itself has insufficient reactive power regulation capabilities, which may affect the grid-connected stability of the wind turbine and thus affect the power generation efficiency. The high historical average oil temperature may be caused by heat dissipation or lubrication problems, which will affect the working environment of the internal components of the wind turbine and reduce the power generation efficiency. A large yaw error rate causes the wind turbine to be unable to effectively utilize wind energy and the output power is unstable, which may have an impact on the grid side and affect the power factor. When the yaw error rate is large, the wind rotor is unevenly stressed and the speed is unstable, which will affect the statistics of the historical average wind rotor speed. A large speed fluctuation rate causes large changes in the internal energy loss of the wind turbine and large fluctuations in the heat generated, which will affect the oil temperature change and make the historical average oil temperature unstable. For example, when the speed increases, the mechanical and electrical losses of the wind turbine will increase, and the oil temperature will rise faster.

[0058] In a specific embodiment, by analyzing and processing the wind turbine operating performance evaluation index, it is possible to accurately judge the operating status of the wind turbine. Operation and maintenance personnel can more accurately understand the health status and performance trends of the wind turbine, and promptly discover potential performance degradation or abnormal changes, so that they can take effective preventive measures before a failure occurs, accurately allocate resources, improve the reliability and stability of the wind turbine, extend the service life of the equipment, and ultimately improve the overall power generation efficiency and economic benefits of the wind farm.

[0059] The UAV inspection demand information determination module is used to obtain the basic operating parameters of the wind turbine set, and analyze the wind turbine set operating performance correction indicators in combination with the wind turbine set operating performance evaluation indicators. Based on the wind turbine set operating performance correction indicators, early warning information is generated, and the UAV inspection demand information is simultaneously determined. The UAV inspection demand information includes demand inspection and no inspection required.

[0060] In this embodiment, the basic operating parameters of the wind turbine generator set include wind turbine generator set equipment parameters and external environment parameters, where:

[0061] Wind turbine equipment parameters include the age of the wind turbine, the total amount of bearing wear and the average response time of the controller.

[0062] It should be noted that the service life of the wind turbine is extracted from the wind turbine affiliation database.

[0063] The total amount of bearing wear can be monitored using a wind turbine main shaft sliding bearing wear monitoring sensor. The bearing operating status and wear amount can be converted into electrical signals in real time through monitoring contacts, and the connected monitoring equipment can be fed through signal cables to output the total amount of bearing wear data.

[0064] The average response time of the controller can be collected and recorded by the wind turbine controller monitoring system.

[0065] External environmental parameters include the standard deviation of the daily average wind speed, the daily average wind direction change frequency and the altitude of the wind farm.

[0066] It should be noted that the wind speed can be obtained by an anemometer, the wind direction can be obtained by a wind vane, and the altitude can be obtained by a barometric altimeter.

[0067] In this embodiment, the wind turbine operating performance correction index is analyzed, and the specific analysis process is as follows:

[0068] According to the basic operating parameters of the wind turbine generator set, the wind turbine generator set operation correction coefficient is obtained through analysis and processing.

[0069] In a specific embodiment, the wind turbine operation correction coefficient is obtained by analysis and processing, and the specific analysis method is as follows:

[0070] According to the basic operation parameters of the wind turbine generator set, the basic operation characteristic values ​​of the wind turbine generator set are analyzed and processed to obtain the basic operation characteristic values ​​of the wind turbine generator set, which are used to characterize the degree of use of the wind turbine generator set equipment and the degree of influence of the wind farm environment on the wind turbine generator set.

[0071] In a specific embodiment, the basic operation characteristic value of the wind turbine generator set is obtained in the following manner:

[0072] The reference wind turbine equipment parameters and reference external environment parameters stored in the database are extracted, wherein the reference wind turbine equipment parameters include the rated service life of the wind turbine, the total amount of tolerable bearing wear, and the average response time of the reference controller.

[0073] The reference external environmental parameters include the ideal daily average wind speed standard deviation of the wind farm, the reference daily average wind direction change frequency and the ideal altitude.

[0074]

[0075] Among them, B is the basic operation characteristic value of the wind turbine, k is the service life of the wind turbine, m is the total amount of bearing wear of the wind turbine, p is the average response time of the controller of the wind turbine, q is the standard deviation of the average daily wind speed of the wind farm, r is the average daily wind direction change frequency of the wind farm, s is the altitude of the wind farm, k0 is the rated service life of the wind turbine, m0 is the tolerable total amount of bearing wear of the wind turbine, p0 is the average response time of the reference controller of the wind turbine, q0 is the standard deviation of the ideal average daily wind speed of the wind farm, r0 is the reference average daily wind direction change frequency of the wind farm, s0 is the ideal altitude of the wind farm, and e is a natural constant.

[0076] It is important to understand that the softsign function is a built-in function in Pytnon.

[0077] It should be noted that the basic operation characteristic values ​​of the wind turbine are obtained by analyzing and processing the basic operation parameters of the wind turbine, taking into account the mutual influence between these parameters. For example, as the service life of the wind turbine increases, the operating time of each component of the equipment increases, and the wear accumulation increases. The bearing, as a key rotating component, will gradually accelerate its wear rate during long-term operation due to continuous friction, vibration and load under different working conditions. When the service life of the wind turbine increases, problems such as aging of electronic components and aging of lines gradually appear. As the control core of the wind turbine, the performance of the electronic components inside the controller will decrease over time. When the total amount of bearing wear increases, the rotational imbalance of the wind turbine will increase and the vibration will intensify. This vibration will be transmitted to the entire wind turbine structure, including the cabin part where the controller is installed. Strong vibration may interfere with the normal operation of the electronic components inside the controller, such as loosening the solder joints and poor contact of the connectors, thereby affecting the signal transmission and processing speed of the controller, resulting in an increase in the average response time. When the standard deviation of the daily average wind speed of a wind farm is large, it means that the wind speed fluctuates more violently. This unstable wind speed will affect the wind direction, making it easier for the wind direction to change. Conversely, a high frequency of daily average wind direction changes will also affect the distribution of wind speed. Frequent wind direction changes will make the airflow in the wind farm turbulent. The airflows in different directions interact with each other, causing the measured wind speed values ​​to be more dispersed, thereby increasing the standard deviation of the daily average wind speed. Generally speaking, the higher the altitude, the more complex the atmospheric environment, and the more drastic the change in wind speed, which usually leads to an increase in the standard deviation of the daily average wind speed. At the same time, the size of the standard deviation of the daily average wind speed will also affect the operating performance of wind turbines at different altitudes. A larger standard deviation of wind speed means that wind turbines need to adjust operating parameters more frequently to adapt to changes in wind speed. This adjustment may be more difficult in high altitude areas. In high altitude areas, the atmospheric circulation is more complex, and the terrain is relatively less affected, but the scale of atmospheric flow is larger, which makes the wind direction more susceptible to large-scale weather systems and changes frequently. Changes in wind speed and direction in the external environment will affect the wear of the bearings. In wind farms with large standard deviations of daily average wind speed and high frequency of changes in daily average wind direction, the operation of wind turbines is unstable, and the loads on the bearings change frequently, with unstable directions and magnitudes. This unstable load will accelerate the wear of the bearings and increase the total amount of bearing wear. Altitude will also affect the working environment of the bearings. Low air pressure and low temperatures in high altitude areas will change the performance of the lubricating oil and deteriorate the lubrication effect, thereby increasing the friction coefficient of the bearings and causing faster bearing wear.

[0078] In a specific embodiment, by analyzing the basic operating characteristic values ​​of wind turbines, the use degree of wind turbine equipment and the comprehensive impact of the wind farm environment on its operating status can be fully reflected. It helps to accurately locate potential problems that wind turbines may face during operation, and provide a numerical basis for formulating targeted maintenance strategies, thereby effectively reducing the probability of sudden equipment failures, extending the service life of wind turbines, ensuring the stable operation of wind farms, improving wind energy utilization efficiency, and reducing power generation losses caused by equipment failures. At the same time, it is also conducive to optimizing the allocation of wind farm operation and maintenance resources, making operation and maintenance work more scientific and efficient, and ensuring that wind turbines always maintain good operating performance in complex and changing environments.

[0079] The correction coefficients corresponding to the basic operation characteristic value intervals stored in the database are extracted, and the operation correction coefficients corresponding to the intervals in which the basic operation characteristic values ​​of the wind turbine generator set are extracted are mapped and marked as the wind turbine generator set operation correction coefficients.

[0080] Based on the wind turbine operation correction coefficient and the wind turbine operation performance evaluation index, the wind turbine operation performance correction index is obtained through analysis and processing.

[0081] The wind turbine generator set operating performance correction index is used to characterize the actual operating performance of the wind turbine generator set after correction.

[0082] In a specific embodiment, the basic operation characteristic value of the wind turbine covers key information such as the service life of the equipment, bearing wear, controller response time, and wind farm environment. These factors are interrelated and have a complex impact on the operation performance of the wind turbine. The operation correction coefficient is obtained based on the comparison between the basic operation characteristic value and the characteristic value under the standard or ideal state in the database. It can quantify the performance deviation caused by these factors, and can accurately reflect the degree of difference between the wind turbine in the current actual state and the ideal state, so as to correct the operation performance evaluation index in a targeted manner. For example, when the service life is long or the bearing wear is serious, the operation correction coefficient will be adjusted accordingly to make the operation performance evaluation index more in line with the actual performance level of the wind turbine, avoiding the wrong judgment of the operation status of the wind turbine due to failure to consider these actual factors, and thus providing a reliable basis for accurate evaluation and effective maintenance. Based on the wind turbine operation correction coefficient and the wind turbine operation performance evaluation index, the wind turbine operation performance correction index is analyzed and processed to obtain the wind turbine operation performance correction index, which can more accurately characterize the actual operation performance of the wind turbine after correction, more sensitively capture the actual operation status of the wind turbine, and timely discover potential abnormalities, so as to avoid misjudging the unit status due to the limitations of a single evaluation index. It helps to provide early warning of failure risks, optimize maintenance resource allocation, reduce downtime, improve the stability, reliability and overall power generation efficiency of wind turbine operations, and ensure continuous and efficient operation of wind farms.

[0083] In a specific embodiment, the wind turbine operating performance correction index is obtained in the following manner:

[0084]

[0085] Among them, C is the wind turbine operating performance correction index, A is the wind turbine operating performance evaluation index, is the wind turbine operation correction coefficient, and e is a natural constant.

[0086] In this embodiment, based on the wind turbine operating performance correction index, early warning information is generated, and the drone inspection demand information is simultaneously determined. The specific process is as follows:

[0087] A first threshold value for wind turbine generator set operation performance correction verification and a second threshold value for wind turbine generator set operation performance correction verification preset in a database are extracted.

[0088] It should be noted that the first threshold value for correcting and verifying the operation performance of the wind turbine generator set is less than the second threshold value for correcting and verifying the operation performance of the wind turbine generator set.

[0089] It should be noted that the first threshold value for wind turbine operating performance correction verification and the second threshold value for wind turbine operating performance correction verification are pre-set in the database and are critical indicators used to measure whether the operating status of the wind turbine is within the normal range and whether corresponding maintenance or inspection measures need to be taken.

[0090] In a specific embodiment, there are multiple ways to set the first threshold value for wind turbine operating performance correction verification and the second threshold value for wind turbine operating performance correction verification. Various operating performance data of the wind turbine during long-term operation can be collected, and these data can be analyzed in detail to determine the boundary values ​​at which the wind turbine can operate normally and ensure safety performance under different circumstances and the boundary values ​​at which the wind turbine is abnormal, and these boundary values ​​are processed comprehensively, such as taking the average value, weighted average, or setting a certain safety margin according to the actual situation to obtain the first threshold value for wind turbine operating performance correction verification and the second threshold value for wind turbine operating performance correction verification.

[0091] The warning information includes whether a local warning is required or not.

[0092] If the wind turbine operating performance correction index is greater than or equal to the first threshold of the wind turbine operating performance correction verification, the warning information will be marked as a required local warning; if the wind turbine operating performance correction index is less than the first threshold of the wind turbine operating performance correction verification, the warning information will be marked as no warning required.

[0093] If the wind turbine operating performance correction index is greater than or equal to the first threshold of the wind turbine operating performance correction verification, it means that the current operating performance of the wind turbine is poor and has exceeded the acceptable range of normal operation. There may be problems and timely local early warning is required so that on-site operation and maintenance personnel can quickly take corresponding measures to inspect, repair or adjust the wind turbine to prevent the problem from further deteriorating, ensure that the wind turbine can return to normal operation as soon as possible, and ensure the stable power generation and overall operating efficiency of the wind farm.

[0094] If the wind turbine operating performance correction index is less than the first threshold of the wind turbine operating performance correction verification, it means that the current operating performance of the wind turbine is in a relatively normal state. Although there may be some small fluctuations or potential problems, it has not reached the level where an immediate local warning needs to be issued.

[0095] If the wind turbine operating performance correction index is greater than or equal to the second threshold of the wind turbine operating performance correction verification, the UAV inspection demand information of the wind turbine will be marked as required inspection; if the wind turbine operating performance correction index is less than the second threshold of the wind turbine operating performance correction verification, the UAV inspection demand information of the wind turbine will be marked as no inspection required.

[0096] If the wind turbine operating performance correction index is greater than or equal to the second threshold of the wind turbine operating performance correction verification, it means that the wind turbine operating performance has shown obvious abnormalities or potential risks. It may not be possible to fully and accurately judge its internal conditions only through conventional monitoring data and analysis. It is necessary to use drone inspections to conduct detailed inspections of the external structure of the wind turbine, such as whether there are cracks on the blades, whether the tower is tilted, whether the anti-vibration hammer is displaced, etc., so as to promptly discover possible safety hazards and equipment failures, provide data basis for subsequent precise repairs and maintenance, ensure the safe and stable operation of the wind turbine, avoid serious equipment damage or shutdown accidents due to failure to discover potential problems in time, and ensure normal power generation in the wind farm.

[0097] If the wind turbine operating performance correction index is less than the second threshold of the wind turbine operating performance correction verification, it means that although the current operating performance of the wind turbine may have certain fluctuations, the existing monitoring methods and performance evaluation can provide a clearer understanding of its operating status, and there is no need to start drone inspection for the time being.

[0098] In a specific embodiment, by generating early warning information based on the wind turbine operating performance correction index and simultaneously determining the drone inspection demand information, the scientific nature of wind turbine performance monitoring can be improved. The early warning information generated based on the operating performance correction index can timely and accurately reflect whether the wind turbine operating status is abnormal, so that the operation and maintenance personnel can quickly know the potential risks of the unit, avoid further expansion of the fault, effectively reduce the probability of sudden shutdown, ensure the continuous and stable power generation of the wind turbine, and reduce the power generation loss caused by shutdown. At the same time, the reasonable determination of drone inspection demand information avoids excessive or insufficient inspections, realizes the optimal allocation of inspection resources, and arranges drone inspections in time when abnormal signs of unit operating performance appear, providing numerical basis for subsequent precise maintenance, further improving maintenance efficiency and quality, and ensuring the long-term and efficient operation of wind turbines.

[0099] The drone inspection analysis module is used to collect the drone inspection data of the wind turbine when the drone inspection demand information is determined to be a demand inspection, analyze the drone inspection verification indicator coefficient of the wind turbine, and determine the remote early warning demand information of the wind turbine in combination with the wind turbine operation performance correction index, and simultaneously adaptively adjust the drone inspection cycle based on the wind turbine drone inspection verification indicator coefficient.

[0100] In this embodiment, the wind turbine UAV inspection verification indicator coefficient is analyzed, and the specific analysis process is as follows:

[0101] The drone inspection data of wind turbines includes the average crack width of the wind turbine blades, the cumulative surface defect area, the tower inclination angle and the shock-absorbing hammer displacement.

[0102] In a specific embodiment, the specific method for obtaining the average crack width of the blade is as follows: the drone carries a high-definition image acquisition device to capture images of the wind turbine blades and obtain image data containing complete information on the blade surface. Then, the captured images are preprocessed, including image enhancement, denoising and other operations, to improve the image quality for subsequent analysis. Next, image recognition technology and edge detection algorithms are used to accurately identify the crack area on the blade and extract the contour information of the crack. For the multiple cracks identified, their maximum widths are measured respectively, and finally all the crack widths are summed and averaged to obtain the average crack width of the blade.

[0103] The specific method of obtaining the cumulative defect area of ​​the surface is as follows: the drone carries a high-definition image acquisition device to take images of the wind turbine to ensure that the entire area where defects may exist is covered, and accurately identifies various defect areas to separate the defective parts from the background. The area of ​​each segmented defect area is calculated, and the pixel area is converted into the actual area through methods such as pixel counting and combined with parameters such as image resolution. Finally, the areas of all identified defect areas are accumulated to obtain the cumulative defect area of ​​the wind turbine surface.

[0104] The tower inclination angle is obtained as follows: use a drone to take a picture of the wind turbine tower, identify and locate the top center point and the bottom center point of the tower, thereby obtaining the connecting line between the top center point and the bottom center point of the tower, and simultaneously obtain the ground horizontal line to obtain the deviation angle between the tower and the ground, extract the initial picture of the wind turbine tower stored in the same shooting location stored in the database, obtain the initial deviation angle between the tower and the ground, and subtract the deviation angle between the tower and the ground from the initial deviation angle between the tower and the ground to obtain the tower inclination angle.

[0105] The method for obtaining the displacement of the shock-proof hammer is as follows: use a drone to take a picture of the shock-proof hammer of the wind turbine, identify and locate the coordinates of the center point of the shock-proof hammer, and simultaneously extract the initial picture of the shock-proof hammer of the wind turbine stored in the database at the same shooting location, identify and locate the initial coordinates of the center point of the shock-proof hammer, and calculate the displacement of the shock-proof hammer based on the coordinates of the center point of the shock-proof hammer and the initial coordinates of the center point of the shock-proof hammer.

[0106] It should be noted that the same shooting location refers to a place where all factors that may affect the content of the picture, such as shooting angle and shooting height, are exactly the same.

[0107] Extract wind turbine reference drone inspection data stored in the database.

[0108] The reference UAV inspection data of wind turbines include the reference average blade crack width, reference surface cumulative defect area, reference tower inclination angle and reference shock-absorbing hammer displacement of wind turbines.

[0109] According to the wind turbine UAV inspection data and the wind turbine reference UAV inspection data, a wind turbine UAV inspection verification indicator coefficient is obtained through comprehensive analysis and processing. The wind turbine UAV inspection verification indicator coefficient is used to characterize the degree of external structural defects of the wind turbine during UAV inspection.

[0110] In a specific embodiment, the wind turbine UAV inspection verification indicator coefficient is obtained in the following manner:

[0111]

[0112] Among them, D is the wind turbine UAV inspection and verification indicator coefficient, t is the average crack width of the wind turbine blade, v is the cumulative surface defect area of ​​the wind turbine, w is the tower inclination angle of the wind turbine, z is the anti-vibration hammer displacement of the wind turbine, t0 is the reference blade average crack width of the wind turbine, v0 is the reference surface cumulative defect area of ​​the wind turbine, w0 is the reference tower inclination angle of the wind turbine, z0 is the reference anti-vibration hammer displacement of the wind turbine, x1 is the weight of the average crack width of the blade, x2 is the weight of the cumulative surface defect area, x3 is the weight of the tower inclination angle, x4 is the weight of the anti-vibration hammer displacement, and e is a natural constant.

[0113] It should be noted that the sigmoid function is a built-in function in Pytnon.

[0114] It should be noted that the weight of the average crack width of the blade, the weight of the cumulative defect area on the surface, the weight of the tower inclination angle and the weight of the shock-absorbing hammer displacement all have a value range between 0 and 1. When used, the preset value can be directly extracted from the database. In a specific embodiment, the specific extraction method is, for example: the average crack width of the blade, the cumulative defect area on the surface, the tower inclination angle and the shock-absorbing hammer displacement data obtained by real-time monitoring are sorted and classified. According to the numerical range of these data and the degree of their impact on the operating safety and performance of the wind turbine, a corresponding mapping relationship table is established in the database. When it is necessary to extract the weight, the system accurately searches and directly extracts the corresponding preset weight in the mapping relationship table based on the current actual average crack width of the blade, the cumulative defect area on the surface, the tower inclination angle and the shock-absorbing hammer displacement values.

[0115] It should also be noted that the wind turbine drone inspection verification indicator coefficient is obtained by analyzing and processing the wind turbine drone inspection data, taking into account the correlation between these parameters. For example, when the average crack width of the blade increases, the stress distribution of the blade will change during the operation of the wind turbine, and the crack will be more susceptible to airflow impact and erosion, which will cause the material around the crack to gradually peel off and wear, thereby increasing the cumulative defect area on the surface. The change in the average crack width of the blade will affect the overall balance of the wind turbine. If the crack widths on multiple blades are uneven or the cracks develop to different degrees, the mass distribution of the wind wheel will be unbalanced. When the wind turbine is running, this imbalance will generate an unbalanced torque, which will act on the tower, causing the tower to bear uneven lateral forces, thereby causing the tower to change in inclination angle. When the average crack width of the blade increases, the vibration characteristics of the wind turbine will change, and the vibration amplitude and frequency may increase. The anti-vibration hammer is a device used to reduce the vibration of the conductor. When the vibration of the wind turbine is transmitted to the conductor system, the anti-vibration hammer will correspondingly produce a larger displacement to consume the vibration energy. For example, under normal circumstances, when the blade crack is small, the vibration of the wind turbine is relatively small, and the displacement of the shockproof hammer is also small. When the blade crack expands and the vibration intensifies, the shockproof hammer will be driven to produce a larger displacement to suppress the excessive vibration of the conductor to protect the safety of the conductor and the entire wind turbine electrical system. When the cumulative surface defect area is large, it indicates that the overall structural integrity of the wind turbine is damaged to a certain extent, which will affect the center of gravity distribution of the wind turbine and cause the center of gravity to shift from the original design position. During the operation of the wind turbine, this center of gravity shift will generate additional overturning moment, acting on the tower, causing the tower to increase inclination angle. The increase in the cumulative surface defect area is usually related to the change in the overall vibration level of the wind turbine. When there are many surface defects, the aerodynamic performance of the wind turbine decreases, the operating stability deteriorates, and the vibration intensifies. This vibration is transmitted to the conductor system, which will cause the shockproof hammer to bear greater vibration energy, thereby increasing its displacement. When the inclination angle of the tower changes, the suspension angle and tension distribution of the conductor will change. The change in conductor tension will directly affect the force state of the shockproof hammer and change its displacement.

[0116] In a specific embodiment, by analyzing the wind turbine drone inspection verification indicator coefficient, the defect status of the external structure of the wind turbine can be accurately and comprehensively grasped. Effectively avoid safety accidents caused by external structural problems, such as blade breakage, tower collapse, etc., to ensure the safe and stable operation of the wind turbine. At the same time, it can provide key data support for the optimization of operation and maintenance strategies, improve operation and maintenance efficiency, and reduce operation and maintenance costs. At the same time, it helps to deeply understand the structural change trend of wind turbines during operation, predict possible failures in advance, reduce power generation losses caused by shutdown maintenance, ensure continuous and efficient power generation of wind farms, and improve the reliability of wind farms.

[0117] In a specific embodiment, the drone inspection cycle is adaptively adjusted based on the wind turbine drone inspection verification indicator coefficient, and the specific process is as follows:

[0118] Extract the preset drone inspection verification thresholds in the database.

[0119] It should be noted that the drone inspection verification threshold is pre-set in the database and is a critical indicator used to measure whether the wind turbine needs to adjust the drone inspection cycle.

[0120] In a specific embodiment, there are multiple ways to set the drone inspection verification threshold. First, drone inspection data of many wind turbines in different operating stages, different environmental conditions, and different maintenance states are collected, and the data under these different situations are carefully analyzed to calculate the reasonable range boundary values ​​corresponding to the above inspection data while ensuring the safe and stable operation of the wind turbines and maintaining good performance. These boundary values ​​are comprehensively considered, and the drone inspection verification threshold can be obtained by using interval estimation methods in statistics, empirical formula methods, or calculation methods based on risk assessment models.

[0121] The wind turbine UAV inspection verification indicator coefficient and the UAV inspection verification threshold are subtracted to obtain the wind turbine UAV inspection verification deviation value.

[0122] It should be noted that the difference processing refers to the wind turbine drone inspection and verification indicator coefficient minus the drone inspection and verification threshold. The result of the difference processing can be greater than zero, less than zero or equal to zero.

[0123] The inspection cycle adjustment value corresponding to each inspection verification deviation value interval stored in the database is extracted, and the inspection cycle adjustment value corresponding to the interval in which the wind turbine drone inspection verification deviation value is located is mapped and extracted, and recorded as the wind turbine drone inspection cycle adjustment value.

[0124] The drone inspection cycle is adaptively adjusted based on the adjustment value of the drone inspection cycle of the wind turbine.

[0125] In this embodiment, the remote warning demand information of the wind turbine generator set is determined, and the specific determination process is as follows:

[0126] The remote warning demand information of the wind turbine generator system includes remote warning demand and remote warning not required.

[0127] The correction coefficient corresponding to each UAV inspection verification indicator coefficient interval stored in the database is extracted, and the UAV inspection correction coefficient corresponding to the interval of the wind turbine UAV inspection verification indicator coefficient is mapped and extracted, and marked as the wind turbine correction coefficient.

[0128] According to the wind turbine correction coefficient and wind turbine operation performance correction index, comprehensive analysis and processing are performed to obtain the wind turbine remote warning demand assessment indicator parameters.

[0129] The wind turbine generator set remote warning demand assessment indicator parameter is used to characterize the degree of remote warning demand for the wind turbine generator set.

[0130] In a specific embodiment, the wind turbine remote warning demand assessment indicator parameter is obtained in the following manner:

[0131]

[0132] Among them, F is the wind turbine remote warning demand assessment indicator parameter, C is the wind turbine operation performance correction index, α D is the wind turbine correction coefficient, and e is the natural constant.

[0133] It should be understood that the softplus function is a built-in function in Python, softplus(x) = lg(1+e x ).

[0134] In a specific embodiment, the wind turbine remote warning demand assessment indicator parameters can fully and accurately reflect the actual operating status and potential risk level of the wind turbine. By timely and accurately assessing whether the wind turbine needs remote warning, it can effectively avoid serious equipment damage and long-term shutdown accidents caused by potential faults not being discovered in time, ensure the safe and stable operation of the wind turbine, and greatly improve the power generation reliability of the wind farm. At the same time, it helps to reasonably arrange operation and maintenance resources, plan maintenance work in advance, reduce operation and maintenance costs, and improve operation and maintenance efficiency.

[0135] Extract the remote warning demand assessment threshold preset in the database.

[0136] It should be noted that the remote warning demand assessment threshold is a critical indicator pre-set in the database and used to measure whether a wind turbine needs remote warning.

[0137] In a specific embodiment, the method for setting the remote warning demand assessment threshold has multiple considerations. It can be determined comprehensively based on the design performance parameters of the wind turbine and a large amount of actual operation monitoring data. Under the influence of different wind conditions, environmental conditions, and the operating time of the unit, the various operating performance evaluation indicators of the wind turbine and the relevant data of the remote warning demand assessment indicator parameters are collected. These data are analyzed in depth to find the performance indicator dividing point between the wind turbine in stable operation and the possible risk of failure under different operating conditions. Through statistical processing of these dividing point data, such as cluster analysis, probability distribution statistics and other methods, a reasonable range is determined, and then according to the safe operation requirements and maintenance strategies of the wind farm, a suitable value is selected as the remote warning demand assessment threshold to ensure that a remote warning can be issued in time when the operating state of the unit approaches or exceeds the safe range, so as to ensure the safe and stable operation of the wind turbine.

[0138] If the wind turbine remote warning demand assessment indicator parameter is greater than or equal to the remote warning demand assessment threshold, the wind turbine remote warning demand information is marked as a demand remote warning, and a remote warning is performed.

[0139] If the remote warning demand assessment indicator parameter of the wind turbine is greater than or equal to the remote warning demand assessment threshold, it means that the current operating status of the wind turbine has deviated from the normal range to a large extent, and the potential risk it faces is high. It is necessary to send a remote warning signal to the relevant operation and maintenance personnel in time so that the operation and maintenance personnel can quickly take corresponding measures to avoid possible serious failures, ensure the safe, stable and efficient operation of the wind turbine, reduce energy waste caused by shutdown due to failures, and also help improve the reliability of the entire wind farm.

[0140] If the wind turbine remote warning demand assessment indicator parameter is less than the remote warning demand assessment threshold, the wind turbine remote warning demand information is marked as no remote warning is required.

[0141] If the wind turbine remote warning demand assessment indicator parameter is less than the remote warning demand assessment threshold, it means that the current operating status of the wind turbine is basically within the normal range, various performance indicators are relatively stable, and the potential risks faced are relatively low, so there is no need for immediate remote warning.

[0142] In a specific embodiment, by determining the remote warning demand information of the wind turbine, the remote warning demand assessment indicator parameter calculated can accurately measure the degree of remote warning demand of the wind turbine. When the parameter is greater than or equal to the remote warning demand assessment threshold, a remote warning is issued in a timely manner, so that the operation and maintenance personnel can obtain the potential serious fault information of the unit in the first time when they are far away from the wind farm, effectively avoiding the long-term shutdown of the wind turbine or the aggravation of equipment damage caused by sudden faults. At the same time, the remote warning mechanism helps to realize the centralized management of wind farms, improve the efficiency of operation and maintenance management, and ensure that the wind turbine always maintains a safe, stable and efficient operation state in a complex and changeable operating environment.

[0143] See also Figure 2 As shown, the embodiment of the present invention provides a method for monitoring the operating performance of a wind turbine generator system based on a PLC hardware platform, comprising the following steps:

[0144] S1, collects wind turbine operating parameters and inputs them into the central processing unit of the PLC hardware platform to analyze and process the wind turbine operating parameters to obtain wind turbine operating performance evaluation data.

[0145] S2, based on the wind turbine operating performance evaluation data, synchronously obtain the wind turbine historical operating data, analyze and process to obtain the wind turbine operating performance evaluation index.

[0146] S3, obtaining the basic operating parameters of the wind turbine set, and analyzing the wind turbine set operating performance correction indicators in combination with the wind turbine set operating performance evaluation indicators, generating early warning information based on the wind turbine set operating performance correction indicators, and simultaneously determining the drone inspection demand information, wherein the drone inspection demand information includes required inspection and no inspection required.

[0147] S4, when the UAV inspection demand information is determined to be a demand inspection, the wind turbine UAV inspection data is collected, the wind turbine UAV inspection verification indicator coefficient is analyzed, and the wind turbine operating performance correction index is combined to determine the wind turbine remote warning demand information, and the UAV inspection cycle is adaptively adjusted based on the wind turbine UAV inspection verification indicator coefficient.

[0148] In a specific embodiment, by providing a wind turbine operating performance monitoring system and method based on a PLC hardware platform, the powerful data processing capabilities of the PLC hardware platform are utilized to achieve accurate collection and analysis of wind turbine operating parameters, and accurate operating performance evaluation data can be obtained, so that the monitoring of wind turbine operating performance is more accurate, and whether the wind turbine is operating abnormally can be discovered in time, providing a reliable data basis for subsequent analysis and decision-making. By comprehensively considering multiple factors to calculate the operating performance correction index, it is possible to accurately warn of fault risks, discover potential problems in advance, effectively avoid fault deterioration, reduce maintenance costs and downtime, and optimize drone inspection strategies, improve inspection efficiency and pertinence, reduce power generation losses, and improve power generation efficiency.

[0149] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0150] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that technicians in the relevant technical field can understand and use the present invention well. As long as they do not deviate from the structure of the present invention or exceed the scope defined by the present invention, they should all belong to the protection scope of the present invention.

Claims

1. Wind turbine operation performance monitoring system based on PLC hardware platform, characterized by: include: The operation performance evaluation data acquisition module is used to collect the operation parameters of the wind turbine set and input them into the central processing unit of the PLC hardware platform to analyze and process the operation parameters of the wind turbine set to obtain the operation performance evaluation data of the wind turbine set; The wind turbine performance evaluation label determination module is used to synchronously obtain the historical operation data of the wind turbine according to the wind turbine operation performance evaluation data, and analyze and process to obtain the wind turbine operation performance evaluation index; The UAV inspection demand information determination module is used to obtain the basic operating parameters of the wind turbine set, and analyze the wind turbine set operating performance correction index in combination with the wind turbine set operating performance evaluation index, generate early warning information based on the wind turbine set operating performance correction index, and simultaneously determine the UAV inspection demand information, the UAV inspection demand information includes inspection demand and inspection not required; The drone inspection analysis module is used to collect the drone inspection data of the wind turbine when the drone inspection demand information is determined to be a demand inspection, analyze the drone inspection verification indicator coefficient of the wind turbine, and determine the remote early warning demand information of the wind turbine in combination with the wind turbine operation performance correction index, and simultaneously adaptively adjust the drone inspection cycle based on the wind turbine drone inspection verification indicator coefficient.

2. The wind turbine operating performance monitoring system based on the PLC hardware platform according to claim 1 is characterized in that: The specific method of obtaining the wind turbine operating performance evaluation data is as follows: During the preset monitoring period, the wind turbine operating parameters are collected, including the total wind energy of the wind turbine, the total electric energy output by the wind turbine, the voltage of the wind turbine at each time point, the current of the wind turbine, the power factor of the wind turbine, the yaw angle of the wind turbine, the rotor speed of the wind turbine and the wind direction of the wind farm; The actual output power of the wind turbine at each time point is obtained by analyzing the voltage, current and power factor of the wind turbine at each time point, and the actual output power variance of the wind turbine is calculated based on the actual output power of the wind turbine at each time point; The power generation efficiency of the wind turbine is calculated based on the total amount of wind energy of the wind turbine and the total amount of electric energy output by the wind turbine. Based on the yaw angle of the wind turbine and the wind direction of the wind farm at each time point, the yaw error rate of the wind turbine is calculated; Based on the wind turbine rotor speed at each time point, the wind turbine speed fluctuation rate is calculated; The actual output power variance of the wind turbine, the power generation efficiency of the wind turbine, the yaw error rate of the wind turbine and the speed fluctuation rate of the wind turbine are jointly used as the wind turbine operation performance evaluation data.

3. The wind turbine operating performance monitoring system based on the PLC hardware platform according to claim 2 is characterized in that: The analysis and processing obtains the wind turbine operating performance evaluation index, and the specific analysis process is as follows: The historical operation data of the wind turbine set includes the historical average power factor, historical average wind rotor speed, historical average nacelle vibration speed and historical average oil temperature of the wind turbine set; Based on the wind turbine operating performance evaluation data and the wind turbine historical operating data, the wind turbine operating performance evaluation index is obtained by analysis and processing; The wind turbine operating performance evaluation index is used to characterize the wind turbine operating performance.

4. The wind turbine operating performance monitoring system based on the PLC hardware platform according to claim 3 is characterized in that: The basic operating parameters of the wind turbine generator set include wind turbine generator set equipment parameters and external environment parameters, among which: Wind turbine equipment parameters include the age of the wind turbine, the total amount of bearing wear, and the average response time of the controller; External environmental parameters include the standard deviation of the daily average wind speed, the daily average wind direction change frequency and the altitude of the wind farm.

5. The wind turbine operating performance monitoring system based on the PLC hardware platform according to claim 1 is characterized in that: The specific analysis process of analyzing the wind turbine operating performance correction index is as follows: According to the basic operating parameters of the wind turbine, the wind turbine operation correction coefficient is obtained by analysis and processing; Based on the wind turbine operation correction coefficient and the wind turbine operation performance evaluation index, the wind turbine operation performance correction index is obtained by analysis and processing; The wind turbine generator set operating performance correction index is used to characterize the actual operating performance of the wind turbine generator set after correction.

6. The wind turbine operating performance monitoring system based on the PLC hardware platform according to claim 5 is characterized in that: The above-mentioned process of generating early warning information based on the wind turbine operating performance correction index and simultaneously determining the drone inspection demand information is as follows: Extracting a first threshold value for wind turbine generator set operation performance correction verification and a second threshold value for wind turbine generator set operation performance correction verification preset in a database; The warning information includes the need for local warning and the need for no warning; If the wind turbine operating performance correction index is greater than or equal to the first threshold value of the wind turbine operating performance correction verification, the warning information is marked as a required local warning; if the wind turbine operating performance correction index is less than the first threshold value of the wind turbine operating performance correction verification, the warning information is marked as no warning is required; If the wind turbine operating performance correction index is greater than or equal to the second threshold of the wind turbine operating performance correction verification, the UAV inspection demand information of the wind turbine will be marked as required inspection; if the wind turbine operating performance correction index is less than the second threshold of the wind turbine operating performance correction verification, the UAV inspection demand information of the wind turbine will be marked as no inspection required.

7. The wind turbine operating performance monitoring system based on the PLC hardware platform according to claim 1 is characterized in that: The specific analysis process of analyzing the wind turbine UAV inspection verification indicator coefficient is as follows: The wind turbine UAV inspection data includes the average crack width of the wind turbine blades, the cumulative surface defect area, the tower inclination angle and the anti-vibration hammer displacement; Extract wind turbine reference drone inspection data stored in the database; According to the wind turbine UAV inspection data and the wind turbine reference UAV inspection data, a wind turbine UAV inspection verification indicator coefficient is obtained through comprehensive analysis and processing. The wind turbine UAV inspection verification indicator coefficient is used to characterize the degree of external structural defects of the wind turbine during UAV inspection.

8. The wind turbine operating performance monitoring system based on the PLC hardware platform according to claim 7 is characterized in that: The specific determination process of determining the remote warning demand information of the wind turbine generator set is as follows: The remote warning demand information of the wind turbine generator system includes remote warning demand and remote warning not required; Extract the correction coefficient corresponding to each UAV inspection verification indicator coefficient interval stored in the database, and map the extracted UAV inspection correction coefficient corresponding to the interval where the wind turbine UAV inspection verification indicator coefficient is located, and mark it as the wind turbine correction coefficient; According to the wind turbine correction coefficient and wind turbine operation performance correction index, comprehensive analysis and processing are performed to obtain the wind turbine remote warning demand assessment indicator parameters; The wind turbine remote warning demand assessment indicator parameter is used to characterize the degree of remote warning demand for wind turbines; Extracting the remote warning demand assessment threshold preset in the database; If the wind turbine remote warning demand assessment indicator parameter is greater than or equal to the remote warning demand assessment threshold, the wind turbine remote warning demand information is marked as a demand remote warning, and a remote warning is performed; If the wind turbine remote warning demand assessment indicator parameter is less than the remote warning demand assessment threshold, the wind turbine remote warning demand information is marked as no remote warning is required.

9. The wind turbine operating performance monitoring system based on the PLC hardware platform according to claim 8 is characterized in that: The wind turbine remote warning demand assessment indicator parameters are specifically obtained as follows: Among them, F is the wind turbine remote warning demand assessment indicator parameter, C is the wind turbine operation performance correction index, α D is the wind turbine correction coefficient, and e is the natural constant.

10. A wind turbine operating performance monitoring method based on a PLC hardware platform, characterized in that: The following steps are involved: S1, collecting wind turbine operating parameters and inputting them into the central processing unit of the PLC hardware platform to analyze and process the wind turbine operating parameters to obtain wind turbine operating performance evaluation data; S2, based on the wind turbine operating performance evaluation data, synchronously obtain the historical operating data of the wind turbine, and analyze and process to obtain the wind turbine operating performance evaluation index; S3, obtaining basic operating parameters of the wind turbine generator set, and analyzing the wind turbine generator set operating performance correction index in combination with the wind turbine generator set operating performance evaluation index, generating early warning information based on the wind turbine generator set operating performance correction index, and simultaneously determining the drone inspection demand information, wherein the drone inspection demand information includes inspection demand and inspection not required; S4, when the UAV inspection demand information is determined to be a demand inspection, the wind turbine UAV inspection data is collected, the wind turbine UAV inspection verification indicator coefficient is analyzed, and the wind turbine operating performance correction index is combined to determine the wind turbine remote warning demand information, and the UAV inspection cycle is adaptively adjusted based on the wind turbine UAV inspection verification indicator coefficient.

Images