A wind power monitoring method, system, medium and electronic device

Abstract

The application provides a wind power monitoring method, system, medium and electronic equipment. The wind power monitoring method comprises: collecting equipment data of a wind turbine generator set to obtain an original monitoring data set, the original monitoring data set comprising mechanical original data, environmental original data and electrical original data; processing the original monitoring data set to obtain a health index value; processing the original monitoring data set to obtain an environmental working condition code; logically determining the health index value and the environmental working condition code to generate a control logic identifier; and generating a monitoring control instruction based on the control logic identifier to obtain a monitoring result of the wind turbine generator set running state. The wind power monitoring method of the application can improve the effectiveness of wind power monitoring.

Description

Technical Field

[0001] This application belongs to the technical field of wind power generation monitoring equipment, and relates to wind power detection, and in particular to a wind power monitoring method, system, medium and electronic equipment. Background Technology

[0002] The field of wind power generation monitoring equipment technology includes real-time monitoring of the operating status of wind turbine generators. The core content is to detect key parameters such as vibration, temperature, and wind speed to ensure equipment safety and performance optimization. However, current wind power generation monitoring technologies have systemic limitations, failing to fully exploit the correlation value of multi-dimensional data, resulting in insufficient accuracy in fault early warning and condition assessment. Furthermore, monitoring systems lack adaptability to complex operating conditions, making it difficult to achieve precise dynamic control and optimized operation. Summary of the Invention

[0003] The purpose of this application is to provide a wind power monitoring method, system, medium, and electronic equipment to improve the effectiveness of wind power monitoring.

[0004] In a first aspect, this application provides a wind power monitoring method, characterized in that the wind power monitoring method includes: collecting equipment data of a wind turbine generator set to obtain a raw monitoring dataset, the raw monitoring dataset including mechanical raw data, environmental raw data, and electrical raw data; performing health parameter processing on the raw monitoring dataset to obtain a health index value; performing environmental condition processing on the raw monitoring dataset to obtain an environmental condition code; performing logical determination on the health index value and the environmental condition code to generate a control logic identifier; and generating a monitoring control command based on the control logic identifier to obtain monitoring results of the operating status of the wind turbine generator set.

[0005] In one implementation of the first aspect, the process of collecting equipment data from a wind turbine generator set to obtain a raw monitoring dataset includes: detecting vibration signal data from vibration sensors and bending moment data from blade root strain gauges to generate mechanical raw data; detecting wind speed data from anemometers and density values ​​from air density sensors to generate environmental raw data; detecting winding temperature data from temperature sensors and power output data from power sensors to generate electrical raw data; and obtaining the raw monitoring dataset based on the mechanical raw data, the environmental raw data, and the electrical raw data.

[0006] In one implementation of the first aspect, the process of processing the original monitoring dataset for health parameters to obtain a health index value includes: processing the original monitoring dataset for health parameter calculations; and performing a health assessment based on the calculated health parameter values ​​to obtain the health index value.

[0007] In one implementation of the first aspect, the process of processing the original monitoring dataset to obtain calculated health parameter values ​​includes: processing the vibration signal data with vibration factors to obtain mechanical wear factor values; processing the temperature data with temperature marking to obtain abnormal gradient marking values; processing the power output data with power coefficients to obtain power fluctuation coefficient values; and obtaining the calculated health parameter values ​​based on the mechanical wear factor values, the abnormal gradient marking values, and the power fluctuation coefficient values.

[0008] In one implementation of the first aspect, the process of performing a health assessment based on the calculated health parameter values ​​to obtain the health index value includes: calling parameters based on the calculated health parameter values ​​to obtain a parameter set value; performing a weighted calculation based on the parameter set values ​​to obtain a weighted parameter value; and generating an index based on the weighted parameter values ​​to obtain the health index value.

[0009] In one implementation of the first aspect, the process of performing environmental condition processing on the original monitoring dataset to obtain an environmental condition code includes: processing the wind speed data in the original monitoring dataset to obtain a wind speed interval code; processing the air density values ​​in the original monitoring dataset to obtain a density interval code; processing the blade root bending moment data in the original monitoring data to obtain a turbulence interval code; and obtaining the environmental condition code based on the wind speed interval code, the density interval code, and the turbulence interval code.

[0010] In one implementation of the first aspect, the process of logically determining the health index value and the environmental condition code to generate a control logic identifier includes: determining a health threshold for the health index value to obtain a health exceeding standard indicator; detecting environmental changes in the environmental condition code to obtain an environmental change indicator; and performing a logical determination based on the health exceeding standard indicator and the environmental change indicator to obtain the control logic identifier.

[0011] Secondly, this application provides a wind power monitoring system comprising: a data acquisition module for acquiring equipment data of a wind turbine generator set to obtain a raw monitoring dataset, the raw monitoring dataset including mechanical raw data, environmental raw data, and electrical raw data; a health parameter processing module for processing the raw monitoring dataset to obtain a health index value; an environmental condition processing module for processing the raw monitoring dataset to obtain an environmental condition code; a logic determination module for performing logical determination on the health index value and the environmental condition code to generate a control logic identifier; and a monitoring control command generation module for generating monitoring control commands based on the control logic identifier to obtain monitoring results of the wind turbine generator set's operating status.

[0012] Thirdly, this application provides an electronic device, the electronic device comprising: a memory storing a computer program thereon; and a processor communicatively connected to the memory for executing the computer program to implement the wind power monitoring method described above.

[0013] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by an electronic device, implements the wind power monitoring method described above.

[0014] As described above, the wind power detection method, system, medium, and electronic equipment described in this application have the following beneficial effects:

[0015] By processing health parameters and environmental conditions in the raw monitoring dataset constructed from the collected equipment data of wind turbine generators, health index values ​​and environmental condition codes are obtained. Combining health parameter processing with environmental condition codes allows for a more accurate assessment of the actual operating status of wind turbine generator equipment. Furthermore, based on the health index values ​​and environmental condition codes, control logic identifiers and monitoring control commands are generated through logical judgment, achieving refined matching between control strategies and operating conditions. This enables differentiated control for different operating conditions, optimizing generator operating efficiency and solving the technical problems of insufficient fault identification accuracy, delayed environmental response, and simplistic control strategies that currently lead to reduced operational safety and power generation efficiency of wind turbine generators. Attached Figure Description

[0016] Figure 1 The diagram shown is a schematic representation of the wind power monitoring method described in the embodiments of this application.

[0017] Figure 2 The diagram shown is a schematic representation of the process of obtaining the original monitoring dataset as described in the embodiments of this application.

[0018] Figure 3 This is a schematic diagram illustrating the process of obtaining calculated health parameter values ​​as described in an embodiment of this application.

[0019] Figure 4 The diagram shown is a schematic representation of the process for obtaining health index values ​​as described in an embodiment of this application.

[0020] Figure 5 The diagram shows the process of obtaining environmental condition codes as described in the embodiments of this application.

[0021] Figure 6 The diagram shown is a schematic representation of the process for generating control logic identifiers as described in an embodiment of this application.

[0022] Figure 7 The diagram shown is a flowchart of the wind power monitoring method described in the embodiments of this application.

[0023] Figure 8 The diagram shown is a structural schematic of the wind power monitoring system described in an embodiment of this application.

[0024] Figure 9 The diagram shown is a structural schematic of the electronic device described in an embodiment of this application.

[0025] Component designation explanation

[0026] 1 Wind power monitoring system

[0027] 11 Data Acquisition Module

[0028] 12 Health Parameter Processing Module

[0029] 13 Environmental Condition Processing Module

[0030] 14. Logic Decision Module

[0031] 15 Monitoring and Control Command Generation Module

[0032] 200 electronic devices

[0033] 201 Memory

[0034] 202 processor

[0035] 203 Monitor

[0036] Steps S11 to S15

[0037] Steps S21 to S24

[0038] Steps S31 to S34

[0039] Steps S41 to S43

[0040] Steps S51 to S54

[0041] Steps S61 to S63 Detailed Implementation

[0042] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, unless otherwise specified, the following embodiments and features in the embodiments can be combined with each other.

[0043] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of this application. Therefore, the drawings only show the components related to this application and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0044] The technical field of wind power generation monitoring equipment encompasses the real-time monitoring of wind turbine generator operation. The core content involves detecting key parameters such as vibration, temperature, and wind speed to ensure equipment safety and performance optimization. This comprehensive technical overview systematically introduces sensor deployment, data acquisition, signal processing units, control logic, and the construction of a monitoring network to improve the reliability and efficiency of wind farms.

[0045] The wind power monitoring system based on ARM and FPGA architecture refers to the use of ARM processors to execute system control logic and FPGAs to achieve high-speed parallel data acquisition and processing to solve the technical issues of wind turbine generator condition monitoring, covering real-time acquisition, analysis and feedback of sensor data.

[0046] Existing technologies rely on threshold monitoring of basic parameters. Vibration monitoring only compares the absolute value of amplitude, ignoring the correlation between spectral characteristics and mechanical wear, resulting in a high rate of missed detection for early bearing pitting faults. Temperature monitoring uses fixed threshold alarms, which cannot identify gradual insulation aging. Power fluctuations lack quantitative indicators, making it difficult to distinguish between grid disturbances and unit anomalies. Environmental monitoring focuses on the single parameter of wind speed, without considering the impact of air density on power output. It does not convert blade root bending moment fluctuations into turbulence intensity indicators, causing the control strategy to be unable to respond to complex wind condition changes. The control logic only triggers health over-limit protection, and continues to operate with fixed parameters when the environment changes abruptly. The pitch system does not adjust the angle of attack according to density changes, and the health status assessment results deviate significantly from the actual faults.

[0047] At least in response to the above-mentioned problems, the following embodiments of this application provide a wind power monitoring method.

[0048] The technical solutions in the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0049] Figure 1 The diagram shown is a schematic representation of a wind power monitoring method according to an embodiment of this application. Figure 1 As shown, the wind power monitoring method includes the following steps S11 to S15.

[0050] Step S11: Collect equipment data from the wind turbine generator set to obtain a raw monitoring dataset. The raw monitoring dataset includes mechanical raw data, environmental raw data, and electrical raw data. The raw monitoring dataset includes vibration signal data, winding temperature data, power output data, wind speed data, density values, and bending moment data.

[0051] Figure 2 This is a schematic diagram illustrating the process of obtaining the original monitoring dataset in one embodiment of this application. For example... Figure 2 As shown, the process of collecting equipment data from wind turbine generators to obtain raw monitoring datasets includes the following steps S21 to S24.

[0052] Step S21: Detect the vibration signal data from the vibration sensor and the bending moment data from the blade root strain gauge to generate raw mechanical data.

[0053] For example, a piezoelectric vibration sensor is used to collect radial vibration signals of a gearbox bearing. The sampling frequency of the piezoelectric vibration sensor can be 10kHz, and the sampling time is 1 second to acquire 10,000 data points. The data unit is m / s. 2 For example, the peak value of the vibration waveform was 2.5 m / s² when the operating speed was 1500 rpm. 2 Simultaneously, the blade root bending moment was measured at a frequency of 1kHz using resistance strain gauges. A 5V excitation voltage was applied to the strain gauge bridge, and the measured voltage difference ΔV = 3.2mV was calculated. Based on the calibration coefficient of 0.05με / mV, the strain value was converted to 152με. The vibration signal data and bending moment data were aligned according to the timestamp; for example, the vibration value at t = 500ms was 1.8m / s². 2 The bending moment value is 148με, which is stored as a two-dimensional array of time-mechanical parameters to generate the original mechanical data.

[0054] Step S22: Detect the wind speed data from the anemometer and the density value from the air density sensor to generate raw environmental data.

[0055] For example, an ultrasonic anemometer is used to emit a 40kHz pulse signal to measure the X / Y / Z triaxial acoustic wave propagation time difference Δt. x =0.12ms, Δt y =0.15ms, Δt z =0.03ms, calculate the wind speed component v according to the sound speed formula v = 331.4 + 0.6T (T = 15℃). x =Δt x ×c / d=0.12e-3×340 / 0.2=8.2m / s, similarly we get v y =8.5m / s, v z =0.3m / s, composite scalar wind speed The resistance value of the PT100 temperature probe was simultaneously read as R = 112.8Ω (corresponding to 15℃), and the piezoresistive barometer output was P = 101.3kPa. Substituting these values ​​into the density formula ρ = P / (287×T) = 101300 / (287×288.15) = 1.225kg / m³ 3The four wind speed sequences [8.2, 8.5, 7.9, 8.3] were linked to density values ​​and timestamps to generate raw environmental data.

[0056] Step S23: Detect the temperature data of the temperature sensor winding and the power output data of the power sensor to generate raw electrical data.

[0057] For example, the winding temperature was measured using a four-wire PT100 platinum resistance thermometer. A constant current source I = 1mA was applied, and the voltage drop V = 0.385V was measured. According to the calibration table R = V / I = 385Ω, the corresponding temperature T = 85.5℃ was used. Simultaneously, the instantaneous values ​​of the three-phase voltage U were acquired. a =690V∠0°、U b =690V∠-120°、U c =690V∠120°, instantaneous current I a =1650A∠-30°、I b =1650A∠-150°、I c =1650A∠90°, real-time calculation of single-phase power P a =U a ×I a ×cos(0°-(-30°))=690×1650×cos30°=985.5kW, similarly we get P b =985.5kW, P c =985.5kW, total power P = 2956.5kW (needs correction to P because cosφ = 0.87) true =P×0.87=2572kW), align the temperature value of 85.5℃ and the power value of 2572kW by second to generate the original electrical data.

[0058] Step S24: Obtain the original monitoring dataset based on the original mechanical data, the original environmental data, and the original electrical data.

[0059] For example, based on the original mechanical data of a 10kHz vibration signal, the average of every 10 data points is downsampled to 1kHz. For instance, the original data [1.8, 1.9, 2.0...] is downsampled to [1.85, 1.95...]. The original environmental data of 4Hz wind speed is directly retained. The original electrical data of 1Hz temperature and power values ​​are extended to 4Hz through linear interpolation. For instance, the temperature sequence [85.3, 85.7] is interpolated to [85.3, 85.4, 85.5, 85.6, 85.7]. A unified time axis is constructed (interval of 250ms), and the data is integrated at the t=500ms node: the downsampled vibration value is 1.85m / s. 2 Bending moment: 148 με; wind speed: 8.4 m / s; density: 1.223 kg / m³ 3The interpolated temperature is 85.5℃ and the interpolated power is 1981kW. The data is encapsulated as a six-dimensional vector [1.85,148,8.4,1.223,85.5,1981] to generate the original monitoring dataset.

[0060] Step S12: Perform health parameter processing on the original monitoring dataset to obtain health index values.

[0061] In one embodiment of this application, the process of processing the original monitoring dataset for health parameters to obtain a health index value includes: processing the original monitoring dataset for health parameter calculations; and performing a health assessment based on the health parameter calculations to obtain the health index value.

[0062] For example, based on the mechanical wear factor, abnormal gradient marker, and power fluctuation coefficient in the calculated health parameter values, ARM performs a weighted summation with weights of 0.5, 0.3, and 0.2 to generate a health index value.

[0063] Figure 3 This diagram illustrates the process of obtaining calculated health parameter values ​​in one embodiment of this application. Figure 3 As shown, the process of processing the original monitoring dataset to obtain calculated health parameter values ​​includes the following steps S31 to S34.

[0064] Step S31: Perform vibration factor processing on the vibration signal data to obtain the mechanical wear factor value. Based on the vibration signal data in the original monitoring dataset, use an FPGA (Field Programmable Gate Array) to calculate the proportion of the 3rd to 5th harmonic amplitude in the vibration spectrum to the total amplitude, and generate the mechanical wear factor value.

[0065] For example, the FPGA reads the vibration signal data sequence v from the original monitoring dataset. i (i = 0, 1, ..., 999, unit m / s) 2 Example data: v = [1.8, 2.0, 2.3, 1.9, ...], perform FFT (Fast Fourier Transform) calculation: (N = 1000, k = 0, 1, ..., 499); Extract the fundamental frequency f base Corresponding speed (e.g., 1500rpm → f) base =25"Hz"), calculate the amplitude of the 75-125Hz frequency band: Calculate the sum of amplitudes across the entire frequency band: Calculation ratio: Example calculation: sum 3to5 =15.6,sum total=98.4→r=0.158, which is the mechanical wear factor value.

[0066] Step S32: Perform temperature labeling processing on the temperature data to obtain abnormal gradient label values. Based on the temperature data in the original monitoring dataset, use FPGA to detect whether the change per minute exceeds +2 degrees Celsius or is lower than -2 degrees Celsius. If so, mark it as an abnormal gradient and generate an abnormal gradient label value.

[0067] For example, the FPGA reads the temperature data sequence T t (t = 0, 1, ..., 59, unit: °C), Example data: T = [85.0, 85.1, 85.3, ...], Calculate the current minute average: Calculate the average value of the previous minute Calculate the temperature difference: Judgment conditions:

[0068]

[0069] Example calculation: This is a value used to label abnormal gradients.

[0070] Step S33: Perform power coefficient processing on the power output data to obtain the power fluctuation coefficient value. Based on the power output data in the original monitoring dataset, the FPGA calculates the standard deviation of a 10-second time window to generate the power fluctuation coefficient value.

[0071] For example, the FPGA reads the power data sequence P j (j = 0, 1, ..., 99, unit: kW), instance data: P = [1980, 1982, 1978, ...], calculate window mean: Calculate the standard deviation: Example calculation: Generate power fluctuation coefficient values.

[0072] Step S34: Obtain the calculated health parameter value based on the mechanical wear factor value, the abnormal gradient marker value, and the power fluctuation coefficient value. The mechanical wear factor value, abnormal gradient marker value, and power fluctuation coefficient value are combined using an FPGA as a whole output to generate the calculated health parameter value.

[0073] For example, the FPGA inputs are: mechanical wear factor value r (e.g., 0.158), abnormal gradient flag value flag (e.g., 1), and power fluctuation coefficient value σ (e.g., 1.10). The triplet is constructed as: V = [r flag σ]. The example output is: V = [0.158, 1, 1.10].

[0074] Figure 4This is a schematic diagram illustrating the process of obtaining health index values ​​in one embodiment of this application. For example... Figure 4 As shown, the process of conducting a health assessment based on the calculated values ​​of the health parameters to obtain the health index value includes the following steps S41 to S43.

[0075] Step S41: Based on the calculated health parameter values, parameter sets are obtained by calling parameters. Based on the calculated health parameter values, the mechanical wear factor value, abnormal gradient marker value, and power fluctuation coefficient value are called using an ARM (Advanced RISC Machine) to generate parameter sets.

[0076] For example, based on the calculated health parameter value, the ARM reads the input value. The calculated health parameter value is a triplet array output by the FPGA. Index 0 stores the mechanical wear factor value, index 1 stores the abnormal gradient marker value, and index 2 stores the power fluctuation coefficient value. The data format is floating-point or integer. For example, the input array is [0.158, 1, 1.10]. The ARM directly accesses the array elements through memory address and extracts the value at index 0 as the mechanical wear factor value. This value is dimensionless and refers to the ISO standard for wind turbine bearing wear. 10816 defines the range from 0 to 1, extracts the value at index 1 as the abnormal gradient marker value, which is an integer 0 or 1, where 0 indicates normal and 1 indicates abnormal. Extracts the value at index 2 as the power fluctuation coefficient value, in kW. Referring to the wind farm operation specifications, the normal value is less than 1.5. The extracted values ​​are 0.158, 1, and 1.10 respectively. The combined operation stores the three values ​​in the original order into a new array. The new array index 0 is the mechanical wear factor value of 0.158, index 1 is the abnormal gradient marker value of 1, and index 2 is the power fluctuation coefficient value of 1.10. The array length is fixed at 3, and the data encapsulation uses contiguous memory space to generate parameter set values.

[0077] Step S42: Perform a weighted calculation based on the parameter set values ​​to obtain weighted parameter values. Based on the parameter set values, ARM multiplies the gradient label value by a weight of 0.3 and the power fluctuation coefficient value by a weight of 0.2 to generate weighted parameter values.

[0078] For example, based on the parameter set values, the ARM reads the input array. The parameter set values ​​are the triples output by the previous module. Index 0 is the mechanical wear factor value, index 1 is the abnormal gradient marker value, and index 2 is the power fluctuation coefficient value. The instance array is [0.158, 1, 1.10]. Weight values ​​are set as follows: mechanical wear factor weight 0.5 (this weight is based on the wind power equipment fault statistics report, where mechanical faults account for 50%, hence the highest weight); abnormal gradient marker weight 0.3 (because temperature anomalies account for 30% of total faults); power fluctuation coefficient weight 0.2 (because power fluctuations have a relatively small impact, accounting for 20%). These weight values ​​are stored... In the ARM constant register, the weighted values ​​are calculated as follows: The ARM multiplies the value at index 0 by the weight 0.5. The multiplication operation uses the floating-point unit, for example, 0.158 × 0.5 = 0.079. The value at index 1 is multiplied by the weight 0.3, for example, 1 × 0.3 = 0.3. The value at index 2 is multiplied by the weight 0.2, for example, 1.10 × 0.2 = 0.22. A new array is generated to store the weighted results. In the new array, index 0 is the mechanical wear factor weighted value of 0.079, index 1 is the abnormal gradient marker weighted value of 0.3, and index 2 is the power fluctuation coefficient weighted value of 0.22. The data units are consistent with the input, and the weighted parameter values ​​are generated.

[0079] Step S43: Generate the health index value based on the weighted parameter values. The health index value, i.e., the weighted health index value, is generated based on the weighted parameter values, the ARM summation mechanical wear factor weighted value, the abnormal gradient marker weighted value, and the power fluctuation coefficient weighted value.

[0080] For example, based on the weighted parameter values, the ARM reads the input array. The weighted parameter values ​​are the triplet output by the previous module. Index 0 is the weighted value of the mechanical wear factor, index 1 is the weighted value of the abnormal gradient marker, and index 2 is the weighted value of the power fluctuation coefficient. The instance array is [0.079, 0.3, 0.22]. Summation operation: The ARM calls the adder unit to sequentially accumulate the three element values. First, it adds the values ​​at index 0 and index 1, 0.079 + 0.3 = 0.379, and then adds the value at index 2, 0.379 + 0.22 = 0.599. The summation result is stored as a single-precision floating-point number. The health index value ranges from 0 to 1. The threshold of 0.8 is set based on the IEC 61400-25 standard. A value exceeding 0.8 indicates high risk. The instance value of 0.599 is less than the threshold, so it does not exceed the standard. The health index value is generated.

[0081] Step S13: Perform environmental condition processing on the original monitoring dataset to obtain environmental condition codes. Based on the original monitoring dataset, the FPGA calculates the 10-minute average wind speed and divides it into intervals, reads the air density value and divides it into intervals, analyzes the blade root bending moment to derive the turbulence intensity and divides it into intervals, and combines them to generate environmental condition codes.

[0082] For example, the intervals for the 10-minute average wind speed are specifically less than 6 m / s, 6 to 12 m / s, and greater than 12 m / s; the intervals for the air density are specifically less than 1.15 kg / m³ and 1.15 to 1.22 kg / m³; and the intervals for the turbulence intensity derived from the blade root bending moment are specifically less than 10% and 10% to 20%.

[0083] Figure 5 This is a schematic diagram illustrating the process of obtaining environmental condition codes in one embodiment of this application. For example... Figure 5 As shown, the process of performing environmental condition processing on the original monitoring dataset to obtain environmental condition codes includes the following steps S51 to S54.

[0084] Step S51: Process the wind speed data in the original monitoring dataset to obtain wind speed interval codes. Based on the wind speed data in the original monitoring dataset, the FPGA uses a sliding window to calculate the 10-minute average wind speed value, compares this value with a threshold of 6 meters per second to determine the interval less than 6 meters per second, and compares it with a threshold of 12 meters per second to determine the interval between 6 and 12 meters per second or the interval greater than 12 meters per second, thus generating wind speed interval codes.

[0085] For example, the FPGA reads the wind speed value sequence v from the raw monitoring dataset. i (i = 0, 1, ..., 2399, unit: m / s), instance sequence v = [8.1, 8.3, 7.9, ...], calculate the sliding window average: Example calculation: ∑v i =19440→avg_wind=8.1, comparison threshold:

[0086]

[0087] Example output: Wind speed range code 1.

[0088] Step S52: Process the air density values ​​in the original monitoring dataset to obtain density interval codes. Based on the air density values ​​in the original monitoring dataset, the FPGA reads the air density sensor values, compares these values ​​with a threshold of 1.15 kg / m³ to determine the interval less than 1.15 kg / m³, and compares them with a threshold of 1.22 kg / m³ to determine the interval between 1.15 and 1.22 kg / m³, thus generating density interval codes.

[0089] For example, the FPGA reads the air density value ρ (unit: kg / m³). 3 ), instance value ρ = 1.18, comparison threshold:

[0090]

[0091] Example output: Density interval encoding 1.

[0092] Step S53: Process the blade root bending moment data in the original monitoring data to obtain turbulence interval codes. Based on the blade root bending moment data in the original monitoring dataset, the FPGA analyzes the fluctuation amplitude of the blade root bending moment data to derive the turbulence intensity percentage. This percentage is compared with a 10% threshold to determine the interval less than 10%, and compared with a 20% threshold to determine the interval between 10% and 20%, thus generating turbulence interval codes.

[0093] For example, the FPGA reads the leaf root bending moment sequence m j (j = 0, 1, ..., 599999, unit με), instance m = [150, 152, 149, ...], calculate the standard deviation: Example calculation: μ=150,∑(m j -μ) 2 =90000→σ m ≈0.387, calculate turbulence intensity: TI=0.1×σ m Example: "TI" = 3.87%, comparison threshold:

[0094]

[0095] Example output: Turbulence interval code 0.

[0096] Step S54: Obtain the environmental condition code based on the wind speed interval code, the density interval code, and the turbulence interval code. Based on the wind speed interval code, density interval code, and turbulence interval code, the FPGA combines the three codes to generate 18 operating condition codes, thus generating the environmental condition code.

[0097] For example, FPGA input encoding: - Wind speed encoding W code (Example: 1) - Density encoding D code (Example: 1) - Turbulence coding T code (Example: 0), combined operation: env code =100×W code +10×D code +T code Example: 100×1+10×1+0=110, generating environmental condition code 110.

[0098] Step S14: Perform logical determination on the health index value and the environmental condition code to generate a control logic identifier.

[0099] Figure 6 This is a schematic diagram illustrating the process of generating control logic identifiers in one embodiment of this application. For example... Figure 6As shown, the process of logically determining the health index value and the environmental condition code to generate a control logic identifier includes the following steps S61 to S63.

[0100] Step S61: Perform a health threshold judgment on the health index value to obtain a health exceeding indicator. Based on the health index value, compare whether the value exceeds the 0.8 threshold for three consecutive monitoring periods to generate a health exceeding indicator.

[0101] For example, the ARM reads a sequence H of health index values ​​for three consecutive monitoring periods. t H t-1 H t-2 (Units dimensionless, range 0-1), instance sequence [0.82, 0.83, 0.79], comparison operation: check H t >0.8, H t-1 >0.8, H t-2 Whether the condition is true or false is determined simultaneously. The threshold of 0.8 is set according to the IEC 61400-25 standard, indicating a high-risk state of the equipment. In the example, the value of 0.82 > 0.8 in period t is true, the value of 0.83 > 0.8 in period t-1 is true, and the value of 0.79 < 0.8 in period t-2 is false. Therefore, the continuous condition is not met, and a logic flag is generated: if all three conditions are true, output 1, otherwise output 0. In the example, the health exceeding the standard flag is 0.

[0102] Step S62: Perform environmental change detection on the environmental condition code to obtain an environmental change flag. Based on the environmental condition code, compare whether the current code is different from the stored code of the previous period, and generate an environmental change flag.

[0103] For example, based on environmental condition coding, the ARM reads the current coding C. t The previous cycle encoding C of the storage t-1 (Encoding range 000-222), current code 110 (meaning: medium wind speed / medium density / low turbulence), previous cycle code 105 (medium wind speed / low density / high turbulence), comparison operation: directly determine C. t Is it equal to C? t-1 If instance 110 ≠ 105 is true, generate the logic flag: output 1 if they are not equal, otherwise output 0. This mechanism is used to capture scenarios such as sudden changes in wind speed, density jumps or turbulent transitions. The instance outputs the environmental change flag 1.

[0104] Step S63: Perform logical judgment based on the health exceedance flag and the environmental change flag to obtain the control logic identifier. The control logic identifier includes pitch rate setting, torque output limit, pitch angle offset, and IGBT switching frequency parameters. Based on the health exceedance flag and the environmental change flag, determine whether the health exceedance flag or the environmental change flag is true. If it is true, determine that the switching condition is met. When the health exceeds the limit, set the pitch rate control parameter to 50% of the rated value and the torque output control parameter to 85% of the maximum value. When the environment changes, match the environmental operating condition code to calculate the pitch angle offset control parameter by increasing or decreasing by 0.5 degrees or increasing the IGBT switching frequency control parameter by 2000 Hz, and generate the control logic identifier.

[0105] For example, based on the health exceedance marker F h Environmental change indicator F e ARM performs a logical OR operation: F h ∨F e Example F h =0, F e =1 → The result is true. When the result is true, the switching condition is determined to be met, and the operation is selected according to the trigger source: When the health exceeds the limit: call the preset parameter table and set the pitch rate control parameter θ. rate =50; When the environment changes: Analyze the environmental condition code C t For the hundreds / tens / units digits, match the preset action matrix: Hundreds digit change (wind speed range): If from 0→1 or 1→2, then the pitch angle offset Δβ=-0.5° (reduce angle of attack); Tens digit change (density range): If from 1→2, then the IGBT switching frequency f sw Boost by 2000Hz (typical base frequency 4kHz → 6kHz), Example C t =110 (hundreds digit 1 / tens digit 1 / units digit 0), C t-1 =105 (hundreds digit 1 / tens digit 0 / units digit 5), the tens digit changes from 0 to 1, triggering a density change action, therefore Δβ = +0.5° (increasing the angle of attack to compensate for the decrease in density), and finally merging the output control parameter package: [θ rate ,τ out ,Δβ,f sw = [null,null,+0.5°,null] (fill in null for untriggered items), encapsulated as control logic identifier [0,0,0.5,0].

[0106] Step S15: Generate monitoring and control commands based on the control logic identifier to obtain monitoring results of the wind turbine generator's operating status. Generate and issue monitoring and control commands according to the generated control logic identifier, and set up a detection module for real-time feedback monitoring.

[0107] The wind power monitoring method provided in this application will now be described in detail through a specific example. It should be noted that the content of this example is only for explaining and illustrating the wind power monitoring method provided in this application, and is not intended to limit the scope of protection of this application in any way. In specific applications, appropriate steps can be added or deleted based on this example according to actual needs. Figure 7 This is a flowchart illustrating the wind power monitoring method used in this example. Figure 7 As shown, the wind power monitoring method in this example includes the following steps S100 to S109.

[0108] Step S100: Collect equipment data from the wind turbine generator set to obtain the original monitoring dataset.

[0109] Step S101: Process the original monitoring dataset to obtain calculated values ​​of health parameters.

[0110] Step S102: Perform a health assessment on the calculated health parameters to obtain a health index value.

[0111] Step S103: Perform environmental condition processing on the original monitoring dataset to obtain environmental condition codes.

[0112] Step S104: Determine the health threshold of the health index value to obtain the health exceeding the standard indicator.

[0113] Step S105: Perform environmental change detection on the environmental condition code to obtain environmental change indicators.

[0114] Step S106: Determine whether the switching conditions are met based on the health exceedance sign and the environmental change sign.

[0115] Step S107: When the switching conditions are met and the health exceeds the standard, set the pitch rate to 50% and the torque output to 85%.

[0116] Step S108: When the switching conditions are met and the environment changes, match the environmental operating condition code, calculate the pitch angle offset, or increase the IGBT switching frequency.

[0117] Step S109: Based on the settings of pitch rate 50%, torque output 85%, and matching environmental operating condition code, calculate the pitch angle offset or increase the IGBT switching frequency to generate a control logic identifier.

[0118] It should be noted that the labels S100 to S109 are only used to indicate different steps, and not to restrict the execution order of these steps.

[0119] In summary, the wind power monitoring method of this application solves the technical problems of insufficient fault identification accuracy, delayed environmental response, and single control strategy leading to reduced wind turbine operation safety and power generation efficiency in existing technologies by capturing mechanical wear through real-time calculation of the proportion of vibration spectrum characteristics, dynamically detecting temperature gradients to mark abnormal states, quantifying the standard deviation of power fluctuations, weighted fusion of multi-source parameters to generate a health index, and partitioning and coding environmental conditions and matching control compensation. In this application, by collecting the proportion of 3rd to 5th harmonic amplitude values ​​in the vibration spectrum in real time, the degree of mechanical wear is directly correlated, avoiding the risk of misjudgment from traditional simple threshold alarms and improving fault identification accuracy. Combined with minute-by-minute gradient detection of temperature changes, abnormal temperature rises or drops in windings are captured, compensating for the lag in single-point temperature monitoring. The power output standard deviation is calculated synchronously to quantify fluctuation intensity, forming a multi-dimensional health assessment basis. When weighted and fused with three parameters, mechanical wear is given the highest weight, conforming to the statistical laws of wind turbine faults, and the output continuous health index dynamically reflects the equipment status. Furthermore, the environmental condition classification incorporates turbulence intensity derivation, and aerodynamic load changes are inferred from blade root bending moment fluctuations. This provides a more accurate characterization of wind conditions than simple wind speed zoning. The combined coding mechanism covers 18 operating condition combinations, and control switching responds simultaneously to health exceedances and environmental abrupt changes. In case of health anomalies, the system automatically reduces load and operates protective equipment. When the environment changes, aerodynamic compensation or electrical adjustments are matched according to the coding. Pitch angle offset of ±0.5 degrees compensates for angle of attack deviation caused by density changes. The IGBT switching frequency is increased by 2000 Hz to enhance grid disturbance adaptability, achieving a refined match between control strategy and operating conditions. Feature extraction, state assessment, environmental adaptation, and control execution are formed into a closed loop. The mechanical wear factor reduces the underreporting of bearing damage, the turbulence intensity derivation error is low, the control response delay is shortened, and the unit's aerodynamic efficiency is improved.

[0120] The scope of protection of the wind power monitoring method described in this application is not limited to the execution order of the steps listed in this application. Any solution implemented by adding, subtracting, or replacing steps in the prior art based on the principles of this application is included within the scope of protection of this application.

[0121] This application also provides a wind power monitoring system, which can implement the wind power monitoring method described in this application. However, the implementation device of the wind power monitoring method described in this application includes, but is not limited to, the structure of the wind power monitoring system listed in this embodiment. All structural modifications and substitutions of the prior art made based on the principles of this application are included within the protection scope of this application.

[0122] Figure 8 The diagram shown is a structural schematic of a wind power monitoring system according to one embodiment of this application. Figure 8As shown, the wind power monitoring system 1 includes: a data acquisition module 11, a health parameter processing module 12, an environmental condition processing module 13, a logic determination module 14, and a monitoring and control command generation module 15. The data acquisition module 11 collects equipment data from the wind turbine generator set to obtain a raw monitoring dataset, which includes mechanical raw data, environmental raw data, and electrical raw data. The health parameter processing module 12 processes the raw monitoring dataset to obtain health index values. The environmental condition processing module 13 processes the raw monitoring dataset to obtain environmental condition codes. The logic determination module 14 performs logical determination on the health index values ​​and the environmental condition codes to generate a control logic identifier. The monitoring and control command generation module 15 generates monitoring and control commands based on the control logic identifier to obtain monitoring results of the wind turbine generator set's operating status.

[0123] It should be noted that, Figure 8 The modules in the wind power monitoring system 1 shown are... Figure 1 The steps in the wind power monitoring method are all corresponding and will not be repeated here.

[0124] In the embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, or methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules / units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or units may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection of apparatuses or modules or units may be electrical, mechanical, or other forms.

[0125] The modules / units described as separate components may or may not be physically separate. The components shown as modules / units may or may not be physical modules; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules / units can be selected to achieve the objectives of the embodiments of this application, depending on actual needs. For example, the functional modules / units in the various embodiments of this application may be integrated into one processing module, or each module / unit may exist physically separately, or two or more modules / units may be integrated into one module / unit.

[0126] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0127] This application also provides a computer-readable storage medium storing a computer program thereon. When executed by a processor, this computer program implements the wind power monitoring method provided in this application. Those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing a processor. The program can be stored in a computer-readable storage medium, which is a non-transitory medium, such as random access memory, read-only memory, flash memory, hard disk, solid-state drive, magnetic tape, floppy disk, optical disk, and any combination thereof. The above storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., digital video disc (DVD)), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0128] This application embodiment may also provide an electronic device. Figure 9 The diagram shown is a structural schematic of an electronic device 200 according to an embodiment of this application. Figure 9 As shown, in this embodiment, the electronic device 200 includes a memory 201 and a processor 202.

[0129] The memory 201 is used to store computer programs. In some possible implementations, the memory 201 may include various media capable of storing program code, such as ROM, RAM, magnetic disk, USB flash drive, memory card, or optical disk.

[0130] In this embodiment, memory 201 may include a computer system readable medium in the form of volatile memory, such as RAM and / or cache memory. Electronic device 200 may further include other removable / non-removable, volatile / non-volatile computer system storage media. Memory 201 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of this application.

[0131] The processor 202 is connected to the memory 201 and is used to execute the computer program stored in the memory 201 so that the electronic device 200 performs the wind power monitoring method.

[0132] For example, processor 202 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc. In other embodiments, processor 202 may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0133] In some implementations, the electronic device 200 provided in this application embodiment may further include a display 203. The display 203 is communicatively connected to the memory 201 and the processor 202, and is used to display the relevant graphical user interface (GUI) of the wind power monitoring method.

[0134] In this embodiment, the display 203 may include a display screen (display panel). In some implementations, the display panel may be configured using a liquid crystal display (LCD), an organic light-emitting diode (OLED), or the like. Furthermore, the display 203 may also be a touch panel (touchscreen, touch screen), which may include a display screen and a touch-sensitive surface. When the touch-sensitive surface detects a touch operation on or near it, it transmits the information to the processor 22 to determine the type of touch event. Subsequently, the processor 202 provides corresponding visual output on the display device based on the type of touch event.

[0135] The descriptions of the processes or structures corresponding to the above figures each have their own emphasis. For parts of a process or structure that are not described in detail, please refer to the relevant descriptions of other processes or structures.

[0136] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in this application should still be covered by the claims of this application.

Claims

1. A wind power monitoring method, characterized in that, The wind power monitoring method includes: The process involves collecting equipment data from wind turbine generator sets to obtain raw monitoring datasets, which include mechanical raw data, environmental raw data, and electrical raw data. This includes: detecting vibration signal data from vibration sensors and bending moment data from blade root strain gauges to generate mechanical raw data; detecting wind speed data from anemometers and density values ​​from air density sensors to generate environmental raw data; detecting winding temperature data from temperature sensors and power output data from power sensors to generate electrical raw data; and obtaining the raw monitoring dataset based on the mechanical raw data, the environmental raw data, and the electrical raw data. The original monitoring dataset is processed to obtain a health index value. This process includes: processing the original monitoring dataset to obtain calculated health parameter values; performing a health assessment based on the calculated health parameter values ​​to obtain the health index value; and processing the original monitoring dataset to obtain an environmental condition code. This process includes: processing wind speed data in the original monitoring dataset to obtain a wind speed interval code; processing air density sensor density values ​​in the original monitoring dataset to obtain a density interval code; processing blade root strain gauge bending moment data in the original monitoring dataset to obtain a turbulence interval code; obtaining the environmental condition code based on the wind speed interval code, the density interval code, and the turbulence interval code; and performing logical determination on the health index value and the environmental condition code to generate a control logic identifier. Based on the control logic identifier, a monitoring and control command is generated to obtain the monitoring results of the wind turbine generator's operating status.

2. The wind power monitoring method according to claim 1, characterized in that, The process of processing the original monitoring dataset to obtain calculated health parameter values ​​includes: The vibration signal data is processed by vibration factor to obtain the mechanical wear factor value; The temperature data is subjected to temperature labeling to obtain abnormal gradient label values; The power output data is processed to obtain the power fluctuation coefficient value; The calculated values ​​of the health parameters are obtained based on the mechanical wear factor value, the abnormal gradient marker value, and the power fluctuation coefficient value.

3. The wind power monitoring method according to claim 1, characterized in that, The process of conducting a health assessment based on the calculated values ​​of the health parameters to obtain the health index value includes: Based on the calculated values ​​of the health parameters, parameter calls are performed to obtain the parameter set values; Weighted parameter values ​​are obtained by performing a weighted calculation based on the parameter set values. The health index value is obtained by generating an index based on the weighted parameter values.

4. The wind power monitoring method according to claim 1, characterized in that, The process of logically determining the health index value and the environmental condition code to generate a control logic identifier includes: The health index value is used to determine the health threshold to obtain a health exceeding the standard indicator; Environmental change detection is performed on the environmental condition code to obtain environmental change indicators; Logical determination is performed based on the health exceedance indicator and the environmental change indicator to obtain the control logic identifier.

5. A wind power monitoring system, employing the wind power monitoring method as described in any one of claims 1 to 4, characterized in that, The wind power monitoring system includes: The data acquisition module is used to collect equipment data from the wind turbine generator set to obtain raw monitoring datasets, which include mechanical raw data, environmental raw data, and electrical raw data. The health parameter processing module is used to process the health parameters of the original monitoring dataset to obtain health index values; An environmental condition processing module is used to process the original monitoring dataset to obtain environmental condition codes. The logic determination module is used to perform logical determination on the health index value and the environmental condition code to generate a control logic identifier; The monitoring and control command generation module is used to generate monitoring and control commands based on the control logic identifier in order to obtain the monitoring results of the operating status of the wind turbine generator set.

6. An electronic device, characterized in that, The electronic device includes: A memory on which computer programs are stored; A processor, communicatively connected to the memory, is used to execute the computer program to implement the wind power monitoring method according to any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by an electronic device, the program implements the wind power monitoring method as described in any one of claims 1 to 4.

Images