A wind turbine fatigue load early warning method and system

Abstract

The present invention relates to a method and system for early warning of fatigue load of a wind turbine, comprising: determining the operating values ​​and theoretical values ​​of various load data of the wind turbine according to the operating data of the wind turbine; and performing fatigue load early warning on the wind turbine according to the operating values ​​and theoretical values ​​of various load data of the wind turbine. The technical solution provided by the present invention constructs a load monitoring model of the wind turbine using the monitoring data of the wind farm monitoring system at historical moments and the load test data of the wind turbine, and performs real-time monitoring of the fatigue load of each unit in the wind power plant based on the load monitoring model and the monitoring data of the wind farm monitoring system collected in real time, thereby reducing the time and cost consumed by testing the load of each wind turbine one by one, improving the accuracy of fatigue load monitoring of the wind turbine, and ensuring the safe and stable operation of the wind turbine.

Description

Technical Field

[0001] The present invention relates to the technical field of big data operation control analysis and wind power data analysis, and in particular to a wind turbine fatigue load early warning method and system. Background Art

[0002] In recent years, wind power generation has developed rapidly, and the number of wind power installed has increased significantly. The safety and stability of wind turbines are our focus.

[0003] Wind turbines are power generation equipment that need to operate for 20 years. This continuous and long-term growth has brought huge challenges to the safe and stable operation of wind turbines. The load of wind turbines is a parameter directly related to safety. Most of the wind turbine safety accidents that have occurred in recent years are caused by excessive load.

[0004] According to the GL2010 standard, blade root load, tower top load, yaw load, and tower bottom load are defined. During the design phase of the wind turbine, these load parameters have design limit values. Taking the left and right loads at the bottom of the tower of a certain model of 2.5MW wind turbine (tower bottom load) as an example, its fatigue load (20 years) design value is 16708, which means that loads exceeding this value will affect the life of the wind turbine; its limit design value is 46774, which means that exceeding the instantaneous value of the load will damage the safety of the unit itself and even cause the tower to collapse. Therefore, monitoring the load of the wind turbine can effectively avoid accidents and ensure the safety of the wind turbine.

[0005] The current reality is that wind turbines only conduct load type tests on prototypes during the finalization phase, and generally do not monitor the loads of wind turbines installed in large quantities. Even if some wind farms monitor the loads, they only test individual units, and do not monitor the loads of all wind turbines in the wind farm. Moreover, the monitoring of the existing small amount of load is often a ten-minute data monitoring record, and no attention is paid to the instantaneous changes in the load. This is mainly because the investment in load testing is huge, and the cost of large-scale testing is very high.

[0006] In order to ensure the safe and stable operation of each wind turbine in the wind farm, it is necessary to complete the fatigue load monitoring of each wind turbine in real time.

[0007] Patents with application numbers 201210436487.9 and 201010513594.8 are both wind turbine load test systems, and do not involve real-time load monitoring. Patent application number 201310052643.6 is a system and method for wind turbine load control, and does not involve real-time load monitoring. Patent application number 201210580075.2 is a monitoring system and method for wind turbine vibration, and does not involve fatigue loads of wind turbines. 201010134383.3 is a system for monitoring fatigue loads of wind turbines, and does not involve real-time load monitoring. 201410360695.4 is a method for fatigue monitoring of wind turbines, and does not involve real-time load monitoring. The invention patent "A long-term evaluation method for wind farm loads" (application publication number: CN106815771A) discloses a long-term evaluation method for wind farm loads, but this method is suitable for long-term evaluation of loads and cannot achieve real-time monitoring.

[0008] At present, there is no relevant invention or utility model patent that can complete the fatigue load monitoring of each wind turbine set in real time. Summary of the invention

[0009] In view of the deficiencies in the prior art, the purpose of the present invention is to propose an early warning method for fatigue load of wind turbines. The method constructs a load monitoring model for wind turbines by utilizing monitoring data of a wind farm monitoring system at historical moments and load test data of wind turbines. The method also performs real-time fatigue load monitoring of wind turbines on each unit in a wind power plant based on the load monitoring model and the monitoring data of the wind farm monitoring system collected in real time, thereby reducing the time and cost consumed in testing the load of each wind turbine one by one, improving the accuracy of load monitoring of wind turbines, and ensuring the safe and stable operation of wind turbines.

[0010] The purpose of the present invention is achieved by adopting the following technical solutions:

[0011] The present invention provides an early warning method for fatigue load of a wind turbine generator set, wherein the method comprises:

[0012] Determine the operating values ​​and theoretical values ​​of various load data of the wind turbine generator set according to the operating data of the wind turbine generator set;

[0013] Provide fatigue load warning for wind turbines based on the operating values ​​and theoretical values ​​of various load data of wind turbines;

[0014] The types of wind turbine load data include: blade flapping bending moment, blade shimmy bending moment, yaw torsion moment, tower top overturning bending moment, tower top shimmy bending moment, tower bottom overturning bending moment and tower bottom shimmy bending moment.

[0015] Preferably, the operating data includes: active power, generator speed, pitch angle, yaw deviation, nacelle x-direction acceleration and nacelle y-direction acceleration.

[0016] Preferably, the step of determining the operating values ​​and theoretical values ​​of various load data of the wind turbine generator set according to the operating data of the wind turbine generator set includes:

[0017] The operating data of the wind turbine generator set are respectively substituted into a preset operating load model and a preset theoretical load model to obtain operating values ​​and theoretical values ​​of various load data of the wind turbine generator set.

[0018] Furthermore, the fatigue load warning of the wind turbine generator set according to the operating value and theoretical value of the wind turbine generator set load data includes:

[0019] If the operating value of the i-th type of load data of the wind turbine generator set is greater than the fatigue setting value of the i-th type of load data of the wind turbine generator set, or the deviation between the operating value and the theoretical value of the i-th type of load data of the wind turbine generator set is greater than 5% of the fatigue setting value of the i-th type of load data of the wind turbine generator set, a first-level fatigue load warning of the part of the wind turbine generator set corresponding to the i-th type of load data is issued;

[0020] If the theoretical value of the i-th type of load data of the wind turbine generator set is greater than the fatigue setting value of the i-th type of load data of the wind turbine generator set, a second-level fatigue load warning of the wind turbine generator set part corresponding to the i-th type of load data is issued;

[0021] Among them, i∈(1~7).

[0022] Furthermore, the part of the wind turbine corresponding to the blade flapping bending moment, blade swing bending moment and yaw torsion moment is the blade root of the wind turbine;

[0023] The part of the wind turbine set corresponding to the tower top overturning bending moment and the tower top swing bending moment is the wind turbine set tower top;

[0024] The part of the wind turbine generator set corresponding to the tower bottom overturning bending moment and the tower bottom swing bending moment is the wind turbine generator set tower bottom.

[0025] Furthermore, the training process of the preset operational load model / theoretical load model includes:

[0026] The operating data of the wind turbine group at each historical moment in the operating data set / theoretical data set of the wind turbine group is used as the input layer training sample of the adaptive neural-fuzzy inference system, and the measured value of the load data of the wind turbine group at each historical moment in the operating data set / theoretical data set of the wind turbine group is used as the output layer training sample of the adaptive neural-fuzzy inference system. The adaptive neural-fuzzy inference system is trained to obtain a pre-set operating load model / theoretical load model.

[0027] Furthermore, the operation data set of the wind turbine set is composed of the operation data of the wind turbine set at each historical moment and the measured values ​​of the load data of the wind turbine set, wherein the operation status of the wind turbine set at each historical moment does not include startup, shutdown or idling.

[0028] Furthermore, the process of obtaining the theoretical data set of the wind turbine generator system includes:

[0029] If the deviation between the coordinate point composed of the active power and speed of the wind turbine set corresponding to the j-th historical moment in the operation data set and the active power-speed control curve of the wind turbine set is less than the preset deviation range of the active power-speed control curve of the wind turbine set, the deviation between the coordinate point composed of the pitch angle and speed of the wind turbine set corresponding to the j-th historical moment in the operation data set and the pitch angle-speed control curve of the wind turbine set is less than the preset deviation range of the pitch angle-speed control curve of the wind turbine set, and the deviation between the coordinate point composed of the torque and speed of the wind turbine set corresponding to the j-th historical moment in the operation data set and the torque-speed control curve of the wind turbine set is less than the preset deviation range of the torque-speed control curve of the wind turbine set, then the operation data at the j-th historical moment in the operation data set and the measured values ​​of the wind turbine set load data are filled into the theoretical data set of the wind turbine set;

[0030] Among them, j∈(1~N), N is the total number of historical moments in the running data set.

[0031] Furthermore, the active power-speed control curve of the wind turbine is determined as follows:

[0032]

[0033] Determine the pitch angle-speed control curve of the wind turbine according to the following formula:

[0034]

[0035] Determine the torque-speed control curve of the wind turbine according to the following formula:

[0036]

[0037] Where n is the speed of the wind turbine, n LOS is the minimum speed of the wind turbine when it is connected to the grid, n rated is the rated speed of the wind turbine, n Max is the maximum speed of the wind turbine when it is connected to the grid, T Max1 is the maximum torque corresponding to the lowest speed of the wind turbine, T1 is the maximum torque corresponding to the maximum power tracking of the wind turbine, T rated is the rated torque of the wind turbine, T2 is the maximum torque of the wind turbine under constant power control, P is the active power of the wind turbine, PMax1 The maximum active power corresponding to the lowest speed of the wind turbine, P1 is the maximum active power corresponding to the maximum power tracking of the wind turbine, P rated The rated active power of the wind turbine, β1 is the maximum pitch angle of the wind turbine when it is connected to the grid, and β is the pitch angle of the wind turbine.

[0038] Furthermore, the deviation d between the coordinate point composed of the active power and speed of the wind turbine corresponding to the jth historical moment in the operation data set and the active power-speed control curve of the wind turbine is determined as follows: g :

[0039]

[0040] Where P i is the active power of the wind turbine corresponding to the jth historical moment in the operating data set, n g is any speed of the active power-speed control curve of the wind turbine, P g is the active power-speed control curve of the wind turbine and n g The corresponding active power, C g It is the active power-speed control curve of wind turbine.

[0041] The deviation d between the wind turbine pitch angle and speed control curve of the wind turbine corresponding to the jth historical moment in the operation data set and the wind turbine pitch angle-speed control curve is determined by the following formula: j :

[0042]

[0043] In the formula, β i is the pitch angle of the wind turbine corresponding to the jth historical moment in the operating data set, n j is any speed of the wind turbine’s pitch angle-speed control curve, β j is the wind turbine's pitch angle-speed control curve and n j The corresponding pitch angle, C j is the pitch angle-speed control curve of the wind turbine;

[0044] The deviation d between the torque and speed control curve of the wind turbine set and the coordinate point composed of the torque and speed of the wind turbine set corresponding to the jth historical moment in the operation data set is determined by the following formula: z :

[0045]

[0046] Where n i is the torque of the wind turbine corresponding to the jth historical moment in the operating data set, T iis the torque of the wind turbine at the i-th historical moment in the wind turbine operation data set, n z is any speed of the torque-speed control curve of the wind turbine, T z is the torque-speed control curve of the wind turbine and n z The corresponding torque, C Z is the torque-speed control curve of the wind turbine.

[0047] The present invention provides an early warning system for fatigue load of a wind turbine generator set, the improvement of which lies in that the system comprises:

[0048] A determination module, used to determine the operating values ​​and theoretical values ​​of various load data of the wind turbine generator set according to the operating data of the wind turbine generator set;

[0049] An early warning module is used to provide fatigue load early warning for wind turbines based on the operating values ​​and theoretical values ​​of various load data of wind turbines;

[0050] The types of wind turbine load data include: blade flapping bending moment, blade shimmy bending moment, yaw torsion moment, tower top overturning bending moment, tower top shimmy bending moment, tower bottom overturning bending moment and tower bottom shimmy bending moment.

[0051] Compared with the closest prior art, the present invention has the following beneficial effects:

[0052] The technical solution provided by the present invention determines the operating values ​​and theoretical values ​​of various load data of the wind turbine set according to the operating data of the wind turbine set; and performs fatigue load warning on the wind turbine set according to the operating values ​​and theoretical values ​​of various load data of the wind turbine set; the solution constructs a load monitoring model for the wind turbine set using the monitoring data of the wind farm monitoring system at historical moments and the load test data of the wind turbine set, and performs real-time wind turbine fatigue load monitoring on each unit in the wind power plant based on the load monitoring model and the monitoring data of the wind farm monitoring system collected in real time, thereby reducing the time and cost consumed in testing the load of each wind turbine set one by one, improving the accuracy of fatigue load monitoring of the wind turbine set, and ensuring the safe and stable operation of the wind turbine set.

[0053] The technical solution provided by the present invention is very suitable for long-term real-time load monitoring of a wind farm in operation, especially for an offshore wind farm. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 It is a flow chart of an early warning method for fatigue load of a wind turbine;

[0055] Figure 2 It is a schematic diagram of the loads at key positions of the wind turbine;

[0056] FIG3( a ) is a schematic diagram of a torque-speed control curve of a wind turbine;

[0057] FIG3( b ) is a schematic diagram of the active power-speed control curve of a wind turbine;

[0058] FIG3( c ) is a schematic diagram of a pitch angle-speed control curve of a wind turbine;

[0059] Figure 4 It is a structural diagram of an early warning system for fatigue load of a wind turbine. DETAILED DESCRIPTION

[0060] The specific implementation modes of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0061] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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.

[0062] The present invention provides an early warning method for fatigue load of a wind turbine generator set, such as Figure 1 As shown, the method includes:

[0063] Step 101. Determine the operating values ​​and theoretical values ​​of various load data of the wind turbine generator set according to the operating data of the wind turbine generator set;

[0064] Step 102: Perform fatigue load warning on the wind turbine generator set according to the operating values ​​and theoretical values ​​of various load data of the wind turbine generator set;

[0065] Among them, Figure 2 As shown, the types of wind turbine load data include: blade flapping bending moment, blade shimmy bending moment, yaw torsion moment, tower top overturning bending moment, tower top shimmy bending moment, tower bottom overturning bending moment and tower bottom shimmy bending moment.

[0066] The operating data include: active power, generator speed, pitch angle, yaw deviation, nacelle x-direction acceleration and nacelle y-direction acceleration.

[0067] Specifically, step 101 includes:

[0068] The operating data of the wind turbine generator set are respectively substituted into a preset operating load model and a preset theoretical load model to obtain operating values ​​and theoretical values ​​of various load data of the wind turbine generator set.

[0069] Furthermore, the step 102 includes:

[0070] If the operating value of the i-th type of load data of the wind turbine generator set is greater than the fatigue setting value of the i-th type of load data of the wind turbine generator set, or the deviation between the operating value and the theoretical value of the i-th type of load data of the wind turbine generator set is greater than 5% of the fatigue setting value of the i-th type of load data of the wind turbine generator set, a first-level fatigue load warning of the part of the wind turbine generator set corresponding to the i-th type of load data is issued;

[0071] If the theoretical value of the i-th type of load data of the wind turbine generator set is greater than the fatigue setting value of the i-th type of load data of the wind turbine generator set, a second-level fatigue load warning of the wind turbine generator set part corresponding to the i-th type of load data is issued;

[0072] Among them, i∈(1~7), the level of the second-level warning is higher than the level of the first-level warning.

[0073] Furthermore, the part of the wind turbine corresponding to the blade flapping bending moment, blade swing bending moment and yaw torsion moment is the blade root of the wind turbine;

[0074] The part of the wind turbine set corresponding to the tower top overturning bending moment and the tower top swing bending moment is the wind turbine set tower top;

[0075] The part of the wind turbine generator set corresponding to the tower bottom overturning bending moment and the tower bottom swing bending moment is the wind turbine generator set tower bottom.

[0076] Specifically, the training process of the preset operational load model / theoretical load model includes:

[0077] The operating data of the wind turbine group at each historical moment in the operating data set / theoretical data set of the wind turbine group is used as the input layer training sample of the adaptive neural-fuzzy inference system, and the measured value of the load data of the wind turbine group at each historical moment in the operating data set / theoretical data set of the wind turbine group is used as the output layer training sample of the adaptive neural-fuzzy inference system. The adaptive neural-fuzzy inference system is trained to obtain a pre-set operating load model / theoretical load model.

[0078] Specifically, the operation data set of the wind turbine set is composed of the operation data of the wind turbine set at each historical moment and the measured value of the load data of the wind turbine set, wherein the operation status of the wind turbine set at each historical moment does not include startup, shutdown or idling.

[0079] In the best embodiment of the present invention, the wind farm monitoring system (SCADA system) usually records the time series data of the most important operating parameters of each wind turbine, so the operating data, operating status (startup, shutdown, normal operation or idling) and torque of the wind turbines at each historical moment can be obtained through the wind farm monitoring system (SCADA system), and the wind turbines here can be selected from typical wind turbines in the wind farm.

[0080] The measured values ​​of the wind turbine load data at each historical moment can be collected by strain gauges installed on the blade root, tower top and tower bottom of the wind turbine, where the time interval of each historical moment of the wind turbine is 20ms.

[0081] In addition, the wind farm monitoring system (SCADA system) generally measures digital quantities and switch quantities, including: wind speed, wind direction, temperature of key components, rotation speed of rotating components, active power, etc. of the wind turbine set. After real-time data acquisition, the data is stored and processed on-site by the wind turbine set main control system, and then sent to the SCADA server of the wind farm centralized control center, so its update cycle is respectively at the millisecond level, second level and minute level. It should be noted that the SCADA data (20ms level) used in the present invention must be consistent with the load test data sampling period (20ms). It is worth noting that most of the patents and papers in the past have processed 10min or even 1h level data, which cannot meet the real-time requirements.

[0082] Specifically, the process of obtaining the theoretical data set of a wind turbine includes:

[0083] If the deviation between the coordinate point composed of the active power and speed of the wind turbine set corresponding to the j-th historical moment in the operation data set and the active power-speed control curve of the wind turbine set is less than the preset deviation range of the active power-speed control curve of the wind turbine set, the deviation between the coordinate point composed of the pitch angle and speed of the wind turbine set corresponding to the j-th historical moment in the operation data set and the pitch angle-speed control curve of the wind turbine set is less than the preset deviation range of the pitch angle-speed control curve of the wind turbine set, and the deviation between the coordinate point composed of the torque and speed of the wind turbine set corresponding to the j-th historical moment in the operation data set and the torque-speed control curve of the wind turbine set is less than the preset deviation range of the torque-speed control curve of the wind turbine set, then the operation data at the j-th historical moment in the operation data set and the measured values ​​of the wind turbine set load data are filled into the theoretical data set of the wind turbine set;

[0084] Among them, j∈(1~N), N is the total number of historical moments in the running data set.

[0085] In the preferred embodiment of the present invention, the preset deviation range of each control curve may be 2%.

[0086] Specifically, FIG3(a) shows a schematic diagram of the torque-speed control curve of a wind turbine generator set, and the mathematical model of the control curve is as follows:

[0087]

[0088] Figure 3(b) shows the active power-speed control curve of the wind turbine. The mathematical model of the control curve is as follows:

[0089]

[0090] Figure 3(c) shows the pitch angle-speed control curve of the wind turbine. The mathematical model of the control curve is as follows:

[0091]

[0092] Where n is the speed of the wind turbine, n LOS is the minimum speed of the wind turbine when it is connected to the grid, n rated is the rated speed of the wind turbine, n Max is the maximum speed of the wind turbine when it is connected to the grid, T Max1 is the maximum torque corresponding to the lowest speed of the wind turbine, T1 is the maximum torque corresponding to the maximum power tracking of the wind turbine, T rated is the rated torque of the wind turbine, T2 is the maximum torque of the wind turbine under constant power control, P is the active power of the wind turbine, P Max1 The maximum active power corresponding to the lowest speed of the wind turbine, P1 is the maximum active power corresponding to the maximum power tracking of the wind turbine, P rated The rated active power of the wind turbine, β1 is the maximum pitch angle of the wind turbine when it is connected to the grid, and β is the pitch angle of the wind turbine.

[0093] Specifically, the deviation d between the coordinate point composed of the active power and speed of the wind turbine corresponding to the jth historical moment in the operation data set and the active power-speed control curve of the wind turbine is determined as follows: g :

[0094]

[0095] Where P i is the active power of the wind turbine corresponding to the jth historical moment in the operating data set, n g is any speed of the active power-speed control curve of the wind turbine, P g is the active power-speed control curve of the wind turbine and n g The corresponding active power, C g It is the active power-speed control curve of wind turbine.

[0096] The deviation d between the wind turbine pitch angle and speed control curve of the wind turbine corresponding to the jth historical moment in the operation data set and the wind turbine pitch angle-speed control curve is determined by the following formula: j :

[0097]

[0098] In the formula, β iis the pitch angle of the wind turbine corresponding to the jth historical moment in the operating data set, n j is any speed of the wind turbine’s pitch angle-speed control curve, β j is the wind turbine's pitch angle-speed control curve and n j The corresponding pitch angle, C j is the pitch angle-speed control curve of the wind turbine;

[0099] The deviation d between the torque and speed control curve of the wind turbine set and the coordinate point composed of the torque and speed of the wind turbine set corresponding to the jth historical moment in the operation data set is determined by the following formula: z :

[0100]

[0101] Where n i is the torque of the wind turbine corresponding to the jth historical moment in the operating data set, T i is the torque of the wind turbine at the i-th historical moment in the wind turbine operation data set, n z is any speed of the torque-speed control curve of the wind turbine, T z is the torque-speed control curve of the wind turbine and n z The corresponding torque, C Z is the torque-speed control curve of the wind turbine.

[0102] The present invention provides an early warning system for fatigue load of a wind turbine generator set, such as Figure 4 As shown, the system comprises:

[0103] A determination module, used to determine the operating values ​​and theoretical values ​​of various load data of the wind turbine generator set according to the operating data of the wind turbine generator set;

[0104] An early warning module is used to provide fatigue load early warning for wind turbines based on the operating values ​​and theoretical values ​​of various load data of wind turbines;

[0105] The types of wind turbine load data include: blade flapping bending moment, blade shimmy bending moment, yaw torsion moment, tower top overturning bending moment, tower top shimmy bending moment, tower bottom overturning bending moment and tower bottom shimmy bending moment.

[0106] Specifically, the operating data includes: active power, generator speed, pitch angle, yaw deviation, nacelle x-direction acceleration, and nacelle y-direction acceleration.

[0107] Specifically, the determining module is used to:

[0108] The operating data of the wind turbine generator set are respectively substituted into a preset operating load model and a preset theoretical load model to obtain operating values ​​and theoretical values ​​of various load data of the wind turbine generator set.

[0109] Furthermore, the early warning module is used to:

[0110] If the operating value of the i-th type of load data of the wind turbine generator set is greater than the fatigue setting value of the i-th type of load data of the wind turbine generator set, or the deviation between the operating value and the theoretical value of the i-th type of load data of the wind turbine generator set is greater than 5% of the fatigue setting value of the i-th type of load data of the wind turbine generator set, a first-level fatigue load warning of the part of the wind turbine generator set corresponding to the i-th type of load data is issued;

[0111] If the theoretical value of the i-th type of load data of the wind turbine generator set is greater than the fatigue setting value of the i-th type of load data of the wind turbine generator set, a second-level fatigue load warning of the wind turbine generator set part corresponding to the i-th type of load data is issued;

[0112] Among them, i∈(1~7).

[0113] Specifically, the part of the wind turbine corresponding to the blade flapping bending moment, blade swing bending moment and yaw torsion moment is the blade root of the wind turbine;

[0114] The part of the wind turbine set corresponding to the tower top overturning bending moment and the tower top swing bending moment is the wind turbine set tower top;

[0115] The part of the wind turbine generator set corresponding to the tower bottom overturning bending moment and the tower bottom swing bending moment is the wind turbine generator set tower bottom.

[0116] The specific training process of the preset operational load model / theoretical load model includes:

[0117] The operating data of the wind turbine group at each historical moment in the operating data set / theoretical data set of the wind turbine group is used as the input layer training sample of the adaptive neural-fuzzy inference system, and the measured value of the load data of the wind turbine group at each historical moment in the operating data set / theoretical data set of the wind turbine group is used as the output layer training sample of the adaptive neural-fuzzy inference system. The adaptive neural-fuzzy inference system is trained to obtain a pre-set operating load model / theoretical load model.

[0118] Specifically, the operation data set of the wind turbine set is composed of the operation data of the wind turbine set at each historical moment and the measured value of the load data of the wind turbine set, wherein the operation status of the wind turbine set at each historical moment does not include startup, shutdown or idling.

[0119] Specifically, the process of obtaining the theoretical data set of a wind turbine includes:

[0120] If the deviation between the coordinate point composed of the active power and speed of the wind turbine set corresponding to the j-th historical moment in the operation data set and the active power-speed control curve of the wind turbine set is less than the preset deviation range of the active power-speed control curve of the wind turbine set, the deviation between the coordinate point composed of the pitch angle and speed of the wind turbine set corresponding to the j-th historical moment in the operation data set and the pitch angle-speed control curve of the wind turbine set is less than the preset deviation range of the pitch angle-speed control curve of the wind turbine set, and the deviation between the coordinate point composed of the torque and speed of the wind turbine set corresponding to the j-th historical moment in the operation data set and the torque-speed control curve of the wind turbine set is less than the preset deviation range of the torque-speed control curve of the wind turbine set, then the operation data at the j-th historical moment in the operation data set and the measured values ​​of the wind turbine set load data are filled into the theoretical data set of the wind turbine set;

[0121] Among them, j∈(1~N), N is the total number of historical moments in the running data set.

[0122] Specifically, the active power-speed control curve of the wind turbine is determined according to the following formula:

[0123]

[0124] Determine the pitch angle-speed control curve of the wind turbine according to the following formula:

[0125]

[0126] Determine the torque-speed control curve of the wind turbine according to the following formula:

[0127]

[0128] Where n is the speed of the wind turbine, n LOS is the minimum speed of the wind turbine when it is connected to the grid, n rated is the rated speed of the wind turbine, n Max is the maximum speed of the wind turbine when it is connected to the grid, T Max1 is the maximum torque corresponding to the lowest speed of the wind turbine, T1 is the maximum torque corresponding to the maximum power tracking of the wind turbine, T rated is the rated torque of the wind turbine, T2 is the maximum torque of the wind turbine under constant power control, P is the active power of the wind turbine, P Max1 The maximum active power corresponding to the lowest speed of the wind turbine, P1 is the maximum active power corresponding to the maximum power tracking of the wind turbine, P rated The rated active power of the wind turbine, β1 is the maximum pitch angle of the wind turbine when it is connected to the grid, and β is the pitch angle of the wind turbine.

[0129] Specifically, the deviation d between the coordinate point composed of the active power and speed of the wind turbine corresponding to the jth historical moment in the operation data set and the active power-speed control curve of the wind turbine is determined as follows: g :

[0130]

[0131] Where P i is the active power of the wind turbine corresponding to the jth historical moment in the operating data set, n g is any speed of the active power-speed control curve of the wind turbine, P g is the active power-speed control curve of the wind turbine and n g The corresponding active power, C g It is the active power-speed control curve of wind turbine.

[0132] The deviation d between the wind turbine pitch angle and speed control curve of the wind turbine corresponding to the jth historical moment in the operation data set and the wind turbine pitch angle-speed control curve is determined by the following formula: j :

[0133]

[0134] In the formula, β i is the pitch angle of the wind turbine corresponding to the jth historical moment in the operating data set, n j is any speed of the wind turbine’s pitch angle-speed control curve, β j is the wind turbine's pitch angle-speed control curve and n j The corresponding pitch angle, C j is the pitch angle-speed control curve of the wind turbine;

[0135] The deviation d between the torque and speed control curve of the wind turbine set and the coordinate point composed of the torque and speed of the wind turbine set corresponding to the jth historical moment in the operation data set is determined by the following formula: z :

[0136]

[0137] Where n i is the torque of the wind turbine corresponding to the jth historical moment in the operating data set, T i is the torque of the wind turbine at the i-th historical moment in the wind turbine operation data set, n z is any speed of the torque-speed control curve of the wind turbine, T z is the torque-speed control curve of the wind turbine and n z The corresponding torque, C Z is the torque-speed control curve of the wind turbine.

[0138] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0139] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0140] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0141] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0142] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A wind turbine fatigue load early warning method, characterized in that: The method comprises: Determine the operating values ​​and theoretical values ​​of various load data of the wind turbine generator set according to the operating data of the wind turbine generator set; Provide fatigue load warning for wind turbines based on the operating values ​​and theoretical values ​​of various load data of wind turbines; The types of various load data of the wind turbine generator set include: blade flapping bending moment, blade shimmy bending moment, yaw torsion moment, tower top overturning bending moment, tower top shimmy bending moment, tower bottom overturning bending moment and tower bottom shimmy bending moment; Determining the operating values ​​and theoretical values ​​of various load data of the wind turbine generator set according to the operating data of the wind turbine generator set includes: Substituting the operating data of the wind turbine generator set into a preset operating load model and a preset theoretical load model respectively, to obtain operating values ​​and theoretical values ​​of various load data of the wind turbine generator set; The fatigue load warning of the wind turbine generator set according to the operating value and theoretical value of the wind turbine generator set load data includes: If the operating value of the i-th type of load data of the wind turbine generator set is greater than the fatigue setting value of the i-th type of load data of the wind turbine generator set, or the deviation between the operating value and the theoretical value of the i-th type of load data of the wind turbine generator set is greater than 5% of the fatigue setting value of the i-th type of load data of the wind turbine generator set, a first-level fatigue load warning of the part of the wind turbine generator set corresponding to the i-th type of load data is issued; If the theoretical value of the i-th type of load data of the wind turbine generator set is greater than the fatigue setting value of the i-th type of load data of the wind turbine generator set, a second-level fatigue load warning of the wind turbine generator set part corresponding to the i-th type of load data is issued; Among them, i∈(1~7); The training process of the preset operational load model / theoretical load model includes: The operating data of the wind turbine group at each historical moment in the operating data set / theoretical data set of the wind turbine group is used as the input layer training sample of the adaptive neural-fuzzy inference system, and the measured value of the load data of the wind turbine group at each historical moment in the operating data set / theoretical data set of the wind turbine group is used as the output layer training sample of the adaptive neural-fuzzy inference system. The adaptive neural-fuzzy inference system is trained to obtain a pre-set operating load model / theoretical load model.

2. The method according to claim 1, characterized in that The operating data include: active power, generator speed, pitch angle, yaw deviation, nacelle x-direction acceleration and nacelle y-direction acceleration.

3. The method according to claim 1, characterized in that The part of the wind turbine corresponding to the blade flapping bending moment, blade swing bending moment and yaw torsion moment is the blade root of the wind turbine; The part of the wind turbine set corresponding to the tower top overturning bending moment and the tower top swing bending moment is the wind turbine set tower top; The part of the wind turbine generator set corresponding to the tower bottom overturning bending moment and the tower bottom swing bending moment is the wind turbine generator set tower bottom.

4. The method according to claim 1, characterized in that The wind turbine operation data set is composed of the wind turbine operation data at each historical moment and the measured values ​​of the wind turbine load data, wherein the operation status of the wind turbine at each historical moment does not include startup, shutdown or idling.

5. The method according to claim 4, characterized in that The process of obtaining the theoretical data set of a wind turbine includes: If the deviation between the coordinate point composed of the active power and speed of the wind turbine set corresponding to the j-th historical moment in the operation data set and the active power-speed control curve of the wind turbine set is less than the preset deviation range of the active power-speed control curve of the wind turbine set, the deviation between the coordinate point composed of the pitch angle and speed of the wind turbine set corresponding to the j-th historical moment in the operation data set and the pitch angle-speed control curve of the wind turbine set is less than the preset deviation range of the pitch angle-speed control curve of the wind turbine set, and the deviation between the coordinate point composed of the torque and speed of the wind turbine set corresponding to the j-th historical moment in the operation data set and the torque-speed control curve of the wind turbine set is less than the preset deviation range of the torque-speed control curve of the wind turbine set, then the operation data at the j-th historical moment in the operation data set and the measured values ​​of the wind turbine set load data are filled into the theoretical data set of the wind turbine set; Among them, j∈(1~N), N is the total number of historical moments in the running data set.

6. The method according to claim 5, characterized in that Determine the active power-speed control curve of the wind turbine according to the following formula: Determine the pitch angle-speed control curve of the wind turbine according to the following formula: Determine the torque-speed control curve of the wind turbine according to the following formula: Where n is the speed of the wind turbine, n LOS is the minimum speed of the wind turbine when it is connected to the grid, n rated is the rated speed of the wind turbine, n Max is the maximum speed of the wind turbine when it is connected to the grid, T Max1 is the maximum torque corresponding to the lowest speed of the wind turbine, T1 is the maximum torque corresponding to the maximum power tracking of the wind turbine, T rated is the rated torque of the wind turbine, T2 is the maximum torque of the wind turbine under constant power control, P is the active power of the wind turbine, P Max1 The maximum active power corresponding to the lowest speed of the wind turbine, P1 is the maximum active power corresponding to the maximum power tracking of the wind turbine, P rated The rated active power of the wind turbine, β1 is the maximum pitch angle of the wind turbine when it is connected to the grid, and β is the pitch angle of the wind turbine.

7. The method according to claim 5, characterized in that The deviation d between the coordinate point composed of the active power and speed of the wind turbine corresponding to the jth historical moment in the operation data set and the active power-speed control curve of the wind turbine is determined by the following formula: g : Where P i is the active power of the wind turbine corresponding to the jth historical moment in the operating data set, n g is any speed of the active power-speed control curve of the wind turbine, P g is the active power-speed control curve of the wind turbine and n g The corresponding active power, C g is the active power-speed control curve of the wind turbine; The deviation d between the wind turbine pitch angle and speed control curve of the wind turbine corresponding to the jth historical moment in the operation data set and the wind turbine pitch angle-speed control curve is determined by the following formula: j : In the formula, β i is the pitch angle of the wind turbine corresponding to the jth historical moment in the operating data set, n j is any speed of the wind turbine’s pitch angle-speed control curve, β j is the wind turbine's pitch angle-speed control curve and n j The corresponding pitch angle, C j is the pitch angle-speed control curve of the wind turbine; The deviation d between the torque and speed control curve of the wind turbine set and the coordinate point composed of the torque and speed of the wind turbine set corresponding to the jth historical moment in the operation data set is determined by the following formula: z : Where n i is the speed of the wind turbine corresponding to the jth historical moment in the operation data set, T i is the wind turbine torque at the jth historical moment in the wind turbine operation data set, n z is any speed of the torque-speed control curve of the wind turbine, T z is the torque-speed control curve of the wind turbine and n z The corresponding torque, C Z is the torque-speed control curve of the wind turbine.

8. A wind turbine fatigue load early warning system, characterized in that: The system comprises: A determination module, used to determine the operating values ​​and theoretical values ​​of various load data of the wind turbine generator set according to the operating data of the wind turbine generator set; An early warning module is used to provide fatigue load early warning for wind turbines based on the operating values ​​and theoretical values ​​of various load data of wind turbines; The types of various load data of the wind turbine generator set include: blade flapping bending moment, blade shimmy bending moment, yaw torsion moment, tower top overturning bending moment, tower top shimmy bending moment, tower bottom overturning bending moment and tower bottom shimmy bending moment; The determining module is used to: Substituting the operating data of the wind turbine generator set into a preset operating load model and a preset theoretical load model respectively, to obtain operating values ​​and theoretical values ​​of various load data of the wind turbine generator set; The early warning module is used to: If the operating value of the i-th type of load data of the wind turbine generator set is greater than the fatigue setting value of the i-th type of load data of the wind turbine generator set, or the deviation between the operating value and the theoretical value of the i-th type of load data of the wind turbine generator set is greater than 5% of the fatigue setting value of the i-th type of load data of the wind turbine generator set, a first-level fatigue load warning of the part of the wind turbine generator set corresponding to the i-th type of load data is issued; If the theoretical value of the i-th type of load data of the wind turbine generator set is greater than the fatigue setting value of the i-th type of load data of the wind turbine generator set, a second-level fatigue load warning of the wind turbine generator set part corresponding to the i-th type of load data is issued; Among them, i∈(1~7); The training process of the preset operational load model / theoretical load model includes: The operating data of the wind turbine group at each historical moment in the operating data set / theoretical data set of the wind turbine group is used as the input layer training sample of the adaptive neural-fuzzy inference system, and the measured value of the load data of the wind turbine group at each historical moment in the operating data set / theoretical data set of the wind turbine group is used as the output layer training sample of the adaptive neural-fuzzy inference system. The adaptive neural-fuzzy inference system is trained to obtain a pre-set operating load model / theoretical load model.

9. The system according to claim 8, characterized in that The operating data include: active power, generator speed, pitch angle, yaw deviation, nacelle x-direction acceleration and nacelle y-direction acceleration.

10. The system according to claim 8, characterized in that The part of the wind turbine corresponding to the blade flapping bending moment, blade swing bending moment and yaw torsion moment is the blade root of the wind turbine; The part of the wind turbine set corresponding to the tower top overturning bending moment and the tower top swing bending moment is the wind turbine set tower top; The part of the wind turbine generator set corresponding to the tower bottom overturning bending moment and the tower bottom swing bending moment is the wind turbine generator set tower bottom.

11. The system according to claim 8, characterized in that The wind turbine operation data set is composed of the wind turbine operation data at each historical moment and the measured values ​​of the wind turbine load data, wherein the operation status of the wind turbine at each historical moment does not include startup, shutdown or idling.

12. The system according to claim 11, characterized in that The process of obtaining the theoretical data set of a wind turbine includes: If the deviation between the coordinate point composed of the active power and speed of the wind turbine set corresponding to the j-th historical moment in the operation data set and the active power-speed control curve of the wind turbine set is less than the preset deviation range of the active power-speed control curve of the wind turbine set, the deviation between the coordinate point composed of the pitch angle and speed of the wind turbine set corresponding to the j-th historical moment in the operation data set and the pitch angle-speed control curve of the wind turbine set is less than the preset deviation range of the pitch angle-speed control curve of the wind turbine set, and the deviation between the coordinate point composed of the torque and speed of the wind turbine set corresponding to the j-th historical moment in the operation data set and the torque-speed control curve of the wind turbine set is less than the preset deviation range of the torque-speed control curve of the wind turbine set, then the operation data at the j-th historical moment in the operation data set and the measured values ​​of the wind turbine set load data are filled into the theoretical data set of the wind turbine set; Among them, j∈(1~N), N is the total number of historical moments in the running data set.

13. The system of claim 12, wherein: Determine the active power-speed control curve of the wind turbine according to the following formula: Determine the pitch angle-speed control curve of the wind turbine according to the following formula: Determine the torque-speed control curve of the wind turbine according to the following formula: Where n is the speed of the wind turbine, n LOS is the minimum speed of the wind turbine when it is connected to the grid, n rated is the rated speed of the wind turbine, n Max is the maximum speed of the wind turbine when it is connected to the grid, T Max1 is the maximum torque corresponding to the lowest speed of the wind turbine, T1 is the maximum torque corresponding to the maximum power tracking of the wind turbine, T rated is the rated torque of the wind turbine, T2 is the maximum torque of the wind turbine under constant power control, P is the active power of the wind turbine, P Max1 The maximum active power corresponding to the lowest speed of the wind turbine, P1 is the maximum active power corresponding to the maximum power tracking of the wind turbine, P rated The rated active power of the wind turbine, β1 is the maximum pitch angle of the wind turbine when it is connected to the grid, and β is the pitch angle of the wind turbine.

14. The system of claim 12, wherein: The deviation d between the coordinate point composed of the active power and speed of the wind turbine corresponding to the jth historical moment in the operation data set and the active power-speed control curve of the wind turbine is determined by the following formula: g : Where P i is the active power of the wind turbine corresponding to the jth historical moment in the operating data set, n g is any speed of the active power-speed control curve of the wind turbine, P g is the active power-speed control curve of the wind turbine and n g The corresponding active power, C g is the active power-speed control curve of the wind turbine; The deviation d between the wind turbine pitch angle and speed control curve of the wind turbine corresponding to the jth historical moment in the operation data set and the wind turbine pitch angle-speed control curve is determined by the following formula: j : In the formula, β i is the pitch angle of the wind turbine corresponding to the jth historical moment in the operating data set, n j is any speed of the wind turbine’s pitch angle-speed control curve, β j is the wind turbine's pitch angle-speed control curve and n j The corresponding pitch angle, C j is the pitch angle-speed control curve of the wind turbine; The deviation d between the torque and speed control curve of the wind turbine set and the coordinate point composed of the torque and speed of the wind turbine set corresponding to the jth historical moment in the operation data set is determined by the following formula: z : Where n i is the speed of the wind turbine corresponding to the jth historical moment in the operation data set, T i is the wind turbine torque at the jth historical moment in the wind turbine operation data set, n z is any speed of the torque-speed control curve of the wind turbine, T z is the torque-speed control curve of the wind turbine and n z The corresponding torque, C Z is the torque-speed control curve of the wind turbine.

Images