Wind power parameter processing method, device, equipment and medium

Abstract

The invention relates to the technical field of wind power generation, and discloses a wind power parameter processing method, device and equipment and a medium. According to the SCADA data of the wind turbine generator in a plurality of continuous operation time periods, N target environment parameters and M target operation parameters which have the largest influence on the generated power can be determined in sequence, and the M target operation parameters are determined as key parameters used for identifying whether the generated power of the wind turbine generator is abnormal or not. And then determining a normal upper limit parameter value and a normal lower limit parameter value of each key parameter. The normal upper limit parameter value and the normal lower limit parameter value of each key parameter can be used for monitoring whether the generated power of the wind turbine generator is abnormal or not, and then whether operation of the wind turbine generator is abnormal or not is recognized. According to the invention, the determination modes of the key parameters and the threshold values thereof can be effectively enriched.

Description

Technical Field

[0001] The present invention relates to the technical field of wind power generation, and in particular to a method, device, equipment and medium for processing wind power parameters. Background Art

[0002] With the development of science and technology, wind power generation technology continues to improve.

[0003] Wind turbines are complex systems composed of multiple components and subsystems, and operate in harsh environments. Relevant technologies can determine whether there are abnormalities in the operation of wind turbines by monitoring whether the parameter values ​​of key parameters in the wind turbines exceed the thresholds, so as to identify the abnormalities in time and take corresponding measures to avoid shutdown of the entire machine for maintenance.

[0004] However, the selection and thresholds of key parameters are generally determined by relevant technical personnel based on subjective experience, and there are few ways to determine them. Summary of the invention

[0005] The present invention provides a wind power parameter processing method, device, equipment and medium to solve the defect that the selection and threshold values ​​of key parameters in related technologies are generally determined by relevant technical personnel based on subjective experience, and there are few determination methods. It can effectively enrich the determination methods of key parameters and their threshold values.

[0006] In a first aspect, the present invention provides a wind power parameter processing method, comprising:

[0007] Obtaining monitoring and data acquisition SCADA data of the wind turbine in multiple continuous operating time periods; wherein the SCADA data in each operating time period includes parameter values ​​of multiple natural environment parameters in the operating time period, parameter values ​​of multiple wind turbine operating parameters in the operating time period, and power generation in the operating time period;

[0008] According to the SCADA data in the multiple operating time periods, N target environmental parameters having the greatest impact on the power generation are determined from the multiple natural environmental parameters; wherein N is an integer greater than 1;

[0009] Based on the SCADA data in the multiple operating time periods and the N target environmental parameters, M target operating parameters having the greatest impact on the power generation are determined from the multiple wind turbine operating parameters, and each of the target operating parameters is determined as a key parameter for identifying whether the power generation of the wind turbine set is abnormal; M is an integer greater than 1;

[0010] According to the parameter value of each key parameter in each operating period, a normal upper limit parameter value and a normal lower limit parameter value of each key parameter are determined.

[0011] Optionally, determining N target environmental parameters having the greatest impact on power generation from the multiple natural environmental parameters based on the SCADA data in the multiple operating time periods includes:

[0012] For any of the natural environment parameters, determining the parameter value of the natural environment parameter in all the operating time periods in all the SCADA data, arranging the parameter values ​​of the natural environment parameter in all the operating time periods in order from small to large, to obtain a first arrangement array corresponding to the natural environment parameter, and determining the information gain value of the natural environment parameter according to the first arrangement array corresponding to the natural environment parameter and the generated power in the SCADA data;

[0013] The largest N information gain values ​​are determined from the information gain values ​​of the multiple natural environment parameters, and the natural environment parameters corresponding to the N information gain values ​​are determined as the N target environment parameters.

[0014] Optionally, determining M target operating parameters having the greatest impact on power generation from the multiple wind turbine operating parameters based on the SCADA data in the multiple operating time periods and the N target environmental parameters includes:

[0015] For any of the SCADA data, taking the parameter values ​​of the N target environmental parameters in the SCADA data as a parameter value group as a whole;

[0016] Clustering the SCADA data in the multiple operating time periods based on the parameter value groups to obtain multiple first data groups; wherein each of the first data groups includes at least one of the SCADA data, the parameter value groups of each of the SCADA data in the same first data group are the same, and the parameter value groups of the SCADA data in different first data groups are different;

[0017] For any of the first data groups, determine the maximum power generation in the first data group, and respectively determine the power generation difference value corresponding to each of the SCADA data of the first data group, the power generation difference value corresponding to the SCADA data being the absolute value of the difference between the power generation in the SCADA data and the maximum power generation;

[0018] For any of the wind turbine operating parameters, determine the parameter value of the wind turbine operating parameter in all the operating time periods in all the SCADA data, arrange the parameter values ​​of the wind turbine operating parameter in all the operating time periods in order from small to large, and obtain a second arrangement array corresponding to the wind turbine operating parameter, and determine the information gain value of the wind turbine operating parameter according to the second arrangement array corresponding to the wind turbine operating parameter and the power generation difference value corresponding to the SCADA data;

[0019] The maximum M information gain values ​​are determined from the information gain values ​​of the plurality of wind turbine operating parameters, and the wind turbine operating parameters corresponding to the M information gain values ​​are determined as the M target operating parameters.

[0020] Optionally, determining the information gain value of the target parameter according to the permutation array and the power generation related value corresponding to the target parameter includes:

[0021] Creating a statistical parameter, setting the initial parameter value of the statistical parameter to 1; and, starting from the first element in the permutation array corresponding to the target parameter, traversing all elements in the permutation array in sequence; wherein the target parameter is the natural environment parameter or the wind turbine operating parameter;

[0022] For any of the traversed elements, the SCADA data in the multiple operating time periods are divided into a second data group and a third data group according to the elements; wherein the parameter value of the target parameter in each of the SCADA data in the second data group is not greater than the element, and the parameter value of the target parameter in each of the SCADA data in the third data group is greater than the element; determining a first average value of all the power generation related values ​​corresponding to the second data group, and determining a second average value of all the power generation related values ​​corresponding to the third data group, determining a square difference between the first average value and the second average value, and using it as the square difference corresponding to the element; if it is determined that the square difference corresponding to the element is less than the square difference corresponding to the previous element in the permutation array, adding 1 to the parameter value of the statistical parameter;

[0023] The final parameter value of the statistical parameter is determined and used as the information gain value of the target parameter.

[0024] Optionally, when the target parameter is the natural environment parameter, the permutation array corresponding to the target parameter is the first permutation array corresponding to the natural environment parameter, the elements in the permutation array are the parameter values ​​of the natural environment parameter in the first permutation array, the power generation related value is the power generation in the SCADA data, and all the power generation related values ​​corresponding to the second data group include the power generation in each SCADA data of the second data group;

[0025] When the target parameter is the wind turbine operating parameter, the arrangement array corresponding to the target parameter is the second arrangement array corresponding to the wind turbine operating parameter, the elements in the arrangement array are the parameter values ​​of the wind turbine operating parameter in the second arrangement array, the power generation related values ​​are the power generation difference values ​​corresponding to the SCADA data, and all the power generation related values ​​corresponding to the second data group include the power generation difference values ​​corresponding to each SCADA data of the second data group.

[0026] Optionally, determining a normal upper limit parameter value and a normal lower limit parameter value of each of the key parameters according to the parameter value of each of the key parameters in the SCADA data in the multiple operating time periods includes:

[0027] For any of the key parameters, the parameter values ​​of the key parameter in all the running time periods are arranged in order from small to large to obtain a target arrangement array;

[0028] Determine the elements in the target array whose arrangement order is the first order and the second order respectively, and use them as the first element and the second element respectively; wherein the first order is the product of the total number of elements in the target array and 0.25, and the second order is the product of the total number of elements and 0.75;

[0029] Calculating an element difference obtained by subtracting the first element from the second element, and calculating a target product of the element difference and a preset coefficient;

[0030] Calculate a first value obtained by subtracting the target product from the first element, and calculate a second value obtained by adding the target product to the second element;

[0031] The first value and the second value are respectively determined as a normal lower limit parameter value and a normal upper limit parameter value of the key parameter.

[0032] Optionally, the multiple natural environment parameters include at least three of wind speed, air temperature, wind direction, turbulence intensity and air temperature in the generator collector ring room;

[0033] The multiple wind turbine operating parameters include characteristic tower vibration characteristics, transmission chain vibration characteristics, generator collector ring slide temperature, main shaft speed, pitch setting angle, voltage, current, frequency, torque, gearbox inlet oil pressure, generator collector ring indoor air temperature, gearbox front bearing temperature, gearbox rear bearing temperature, gearbox oil temperature, generator front bearing temperature, generator rear bearing temperature, motor stator winding temperature, inverter cooling air temperature, control cabinet temperature, cabin temperature, pitch motor temperature, wind rotor speed, wind direction-nacelle angle, main shaft bearing temperature, gearbox high-speed shaft speed, generator torque, inverter set torque, actual pitch angle and mechanical brake status. At least three of them.

[0034] In a second aspect, the present invention provides a wind power parameter processing device, comprising:

[0035] An acquisition unit is used to acquire monitoring and data acquisition SCADA data of the wind turbine in a plurality of continuous operation periods; wherein the SCADA data in each operation period includes parameter values ​​of a plurality of natural environment parameters in the operation period, parameter values ​​of a plurality of wind turbine operation parameters in the operation period and the power generation in the operation period;

[0036] A first determining unit is used to determine N target environmental parameters that have the greatest impact on power generation from among the multiple natural environmental parameters based on the SCADA data in the multiple operating time periods; wherein N is an integer greater than 1;

[0037] A second determination unit is configured to determine, based on the SCADA data in the multiple operating time periods and the N target environmental parameters, M target operating parameters having the greatest impact on the power generation from among the multiple wind turbine operating parameters; M is an integer greater than 1;

[0038] A third determining unit, configured to determine each of the target operating parameters as a key parameter for identifying whether the power generation power of the wind turbine generator set is abnormal;

[0039] The fourth determining unit is used to determine a normal upper limit parameter value and a normal lower limit parameter value of each of the key parameters according to the parameter value of each of the key parameters in each of the operating time periods.

[0040] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor are communicatively connected to each other, computer instructions are stored in the memory, and the processor executes the wind power parameter processing method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0041] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the wind power parameter processing method of the first aspect or any corresponding embodiment thereof.

[0042] The wind power parameter processing method, device, equipment and medium provided by the present invention can determine the N target environmental parameters and M target operating parameters that have the greatest impact on the power generation according to the SCADA data of the wind turbine in multiple continuous operating periods, and determine the M target operating parameters as key parameters for identifying whether the power generation of the wind turbine is abnormal, and then determine the normal upper limit parameter value and the normal lower limit parameter value of each key parameter. The normal upper limit parameter value and the normal lower limit parameter value of each key parameter can be used to monitor whether the power generation of the wind turbine is abnormal, and then used to identify whether the operation of the wind turbine is abnormal. The present invention can effectively enrich the method of determining key parameters and their thresholds. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0044] Figure 1 A flow chart of a wind power parameter processing method provided by an embodiment of the present invention;

[0045] Figure 2 A schematic diagram of the structure of a wind power parameter processing device provided by an embodiment of the present invention;

[0046] Figure 3 A schematic diagram of the structure of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings 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.

[0048] like Figure 1 As shown, this embodiment proposes a first wind power parameter processing method, which may include the following steps:

[0049] S101, obtaining the Supervisory Control And Data Acquisition (SCADA) data of the wind turbine in a plurality of continuous operation periods, wherein the SCADA data in each operation period includes parameter values ​​of a plurality of natural environment parameters in the operation period, parameter values ​​of a plurality of wind turbine operation parameters in the operation period, and the power generation in the operation period.

[0050] The operating period may be a period of a certain length during which the wind turbine generator set is in operation.

[0051] Specifically, this embodiment does not limit the duration of the running time period, such as 10 minutes. It should be noted that among the above multiple running time periods, the durations of different running time periods may be the same or different.

[0052] Specifically, the SCADA data in each operation period may be the SCADA data of the wind turbine in the corresponding operation period. The SCADA data may be the wind turbine operation related data collected by the SCADA system.

[0053] Optionally, the multiple natural environment parameters include at least three of wind speed, air temperature, wind direction, turbulence intensity and air temperature inside the generator collector ring room.

[0054] Optionally, the multiple wind turbine operating parameters include characteristic tower vibration characteristics, transmission chain vibration characteristics, generator collector ring slide temperature, main shaft speed, pitch setting angle, voltage, current, frequency, torque, gearbox inlet oil pressure, generator collector ring indoor air temperature, gearbox front bearing temperature, gearbox rear bearing temperature, gearbox oil temperature, generator front bearing temperature, generator rear bearing temperature, motor stator winding temperature, inverter cooling air temperature, control cabinet temperature, cabin temperature, pitch motor temperature, rotor speed, wind direction-nacelle angle, main shaft bearing temperature, gearbox high-speed shaft speed, generator torque, inverter set torque, actual pitch angle and mechanical brake status. At least three of them.

[0055] Specifically, the natural environment parameters may be wind speed, air temperature, wind direction, turbulence intensity, etc. The wind turbine operation parameters may be characteristic tower vibration value, transmission chain vibration value, generator torque value, mechanical brake status, etc.

[0056] Optionally, the parameter value of the natural environment parameter in the operation period can be the parameter value of the natural environment parameter at the last moment in the operation period, or the average parameter value of the natural environment parameter in the operation period, or the maximum parameter value or minimum parameter value of the natural environment parameter in the operation period, or the cumulative parameter value of the natural environment parameter in the operation period, or the standard deviation or variance of the parameter value of the natural environment parameter in the operation period. For example, when the duration of the operation period is ten minutes, the parameter value of the natural environment parameter in the operation period can be ten-minute wind speed, ten-minute air temperature, ten-minute wind direction, turbulence intensity, ten-minute wind speed mean, ten-minute wind speed minimum, ten-minute wind speed maximum, ten-minute wind speed variance, wind direction minimum, wind direction maximum, ten-minute air temperature minimum, ten-minute air temperature maximum, generator collector ring indoor air temperature minimum, or generator collector ring indoor air temperature maximum.

[0057] Optionally, the parameter value of the fan operating parameter during the operating period may be the parameter value of the fan operating parameter at the last moment during the operating period, or the average parameter value of the fan operating parameter during the operating period, or the maximum parameter value or the minimum parameter value of the fan operating parameter during the operating period, or the cumulative parameter value of the fan operating parameter during the operating period, or the standard deviation or variance of the parameter value of the fan operating parameter during the operating period. For example, when the duration of the operating period is ten minutes, the parameter values ​​of the wind turbine operating parameters within the operating period can be the characteristic tower vibration average value within a ten-minute period, the generator collector ring slide temperature, main shaft speed, pitch setting angle, voltage, current, frequency, torque, gearbox inlet oil pressure, generator collector ring indoor air temperature, gearbox front bearing temperature, gearbox rear bearing temperature, gearbox oil temperature, generator front bearing temperature, generator rear bearing temperature, motor stator winding temperature, inverter cooling air temperature, control cabinet temperature, cabin temperature, pitch motor temperature, wind rotor speed, wind direction cabin angle, main shaft bearing temperature, gearbox high-speed shaft speed, generator torque value, inverter set torque, pitch actual angle or mechanical brake status.

[0058] S102: According to the SCADA data in the multiple operating time periods, N target environmental parameters having the greatest impact on the power generation are determined from the multiple natural environmental parameters, where N is an integer greater than 1.

[0059] It should be noted that the power generation of a wind turbine is an important operating parameter, and changes in the power generation can directly reflect whether the power generation of the wind turbine is abnormal. In this embodiment, parameters that have a greater impact on the power generation of the wind turbine can be selected as key parameters, and the power generation of the wind turbine can be monitored based on the parameter values ​​of the key parameters.

[0060] Specifically, this embodiment can determine the natural environment parameters that have a greater impact on the power generation according to the SCADA data in the above-mentioned multiple operating time periods.

[0061] Specifically, the target environmental parameter is the natural environmental parameter determined in this embodiment from among the above-mentioned multiple natural environmental parameters and having a greater impact on the power generation.

[0062] It should be noted that N can be set by technicians according to actual conditions, for example, it can be set to 3, and this embodiment does not limit it.

[0063] S103. Based on the SCADA data in multiple operating time periods and N target environmental parameters, determine M target operating parameters that have the greatest impact on power generation from multiple wind turbine operating parameters; M is an integer greater than 1.

[0064] Specifically, this embodiment can determine the wind turbine operating parameters having a greater impact on the power generation from among the multiple wind turbine operating parameters based on the SCADA data in the multiple operating time periods and the determined N target environmental parameters.

[0065] Specifically, the target operating parameter is the wind turbine operating parameter that has a greater impact on the power generation power and is determined in this embodiment from among the multiple wind turbine operating parameters mentioned above.

[0066] It should be noted that M can be set by technicians according to actual conditions, for example, it can be set to 5, and this embodiment does not limit this.

[0067] S104. Determine each target operating parameter as a key parameter for identifying whether the power generation power of the wind turbine generator set is abnormal.

[0068] Specifically, in this embodiment, each target operating parameter may be determined as a key parameter.

[0069] It is understandable that whether the power generation of the wind turbine is normal is an important factor in determining whether its operating state is normal. In this embodiment, when it is determined that the power generation of the wind turbine is normal in a certain period of time, it is determined that the operating state of the wind turbine in the period of time is normal. In this embodiment, when it is determined that the power generation of the wind turbine in a certain period of time is abnormal, it is determined that the operating state of the wind turbine in the period of time is abnormal.

[0070] S105. Determine a normal upper limit parameter value and a normal lower limit parameter value of each key parameter according to the parameter value of each key parameter in multiple operating time periods.

[0071] The normal upper limit parameter value of the key parameter may be the upper limit parameter value of the key parameter under normal conditions. If the parameter value of the key parameter exceeds the normal upper limit parameter value, it means that the parameter value of the key parameter is too large and the power generation of the wind turbine is abnormal.

[0072] The normal lower limit parameter value of the key parameter may be the lower limit parameter value of the key parameter under normal conditions. If the parameter value of the key parameter is lower than the normal lower limit parameter value, it means that the parameter value of the key parameter is too small and the power generation of the wind turbine is abnormal.

[0073] It should be noted that if the parameter value of at least one key parameter exceeds the corresponding normal upper limit parameter value, or is lower than the corresponding normal lower limit parameter value, it can be determined that the power generation of the wind turbine is abnormal. If the parameter value of each key parameter is not lower than the corresponding normal lower limit parameter value, and does not exceed the corresponding normal upper limit parameter value, it can be determined that the power generation of the wind turbine is normal.

[0074] Specifically, after determining the key parameter, this embodiment can determine the normal upper limit parameter value and the normal lower limit parameter value of the key parameter according to the parameter value of the key parameter in each operating period.

[0075] It can be understood that this embodiment can monitor the parameter values ​​of key parameters during the operation of the wind turbine set, and determine whether the parameter values ​​of the key parameters are abnormal based on the normal upper limit parameter value and the normal lower limit parameter value of the key parameter, so as to determine whether the power generation power of the wind turbine set is abnormal, and then determine whether there is any abnormality in the operation of the wind turbine set, thereby realizing the monitoring of the operating status of the wind turbine set.

[0076] It should be noted that, through steps S101 to S105, this embodiment can effectively realize the intelligent selection of key parameters of wind turbines, and can effectively avoid the problems in related technologies such as the rationality of key parameters selected by technicians being affected by subjective experience, consuming human resources and selection efficiency.

[0077] It should also be noted that this embodiment selects to use an algorithm to study the abnormal power curve of wind turbines, which can only rely on SCADA data to perform power curve abnormality analysis and early warning for different wind turbines and different models, and the results are more accurate.

[0078] The wind power parameter processing method proposed in this embodiment can determine the N target environmental parameters and M target operating parameters that have the greatest impact on the power generation according to the SCADA data of the wind turbine in multiple continuous operating periods, and determine the M target operating parameters as key parameters for identifying whether the power generation of the wind turbine is abnormal, and then determine the normal upper limit parameter value and the normal lower limit parameter value of each key parameter. The normal upper limit parameter value and the normal lower limit parameter value of each key parameter can be used to monitor whether the power generation of the wind turbine is abnormal, and then used to identify whether the operation of the wind turbine is abnormal. This embodiment can effectively enrich the method of determining key parameters and their thresholds.

[0079] based on Figure 1 This embodiment proposes a second wind power parameter processing method, in which step S102 may include:

[0080] For any natural environment parameter, determine the parameter value of the natural environment parameter in all operating time periods in all SCADA data, arrange the parameter values ​​of the natural environment parameter in all operating time periods in order from small to large, and obtain a first arrangement array corresponding to the natural environment parameter, and determine the information gain value of the natural environment parameter according to the first arrangement array corresponding to the natural environment parameter and the power generation in the SCADA data;

[0081] The largest N information gain values ​​are determined from the information gain values ​​of the plurality of natural environment parameters, and the natural environment parameters corresponding to the N information gain values ​​are determined as N target environment parameters.

[0082] Among them, the information gain value of the natural environment parameter can be used to measure the impact of the natural environment parameter on the power generation.

[0083] Specifically, for any natural environment parameter, this embodiment can arrange the parameter values ​​of the natural environment parameter in all operating time periods in order from small to large to obtain a corresponding first arrangement array. Afterwards, this embodiment can determine the information gain value of the natural environment parameter based on the first arrangement array and the power generation power in the SCADA data.

[0084] Optionally, based on the SCADA data in multiple operating time periods and N target environmental parameters, M target operating parameters having the greatest impact on the power generation are determined from among the multiple wind turbine operating parameters, including:

[0085] For any SCADA data, the parameter values ​​of N target environmental parameters in the SCADA data are taken as a parameter value group as a whole;

[0086] Clustering the SCADA data in multiple operating time periods based on the parameter value groups to obtain multiple first data groups; wherein each first data group includes at least one SCADA data, the parameter value groups of each SCADA data in the same first data group are the same, and the parameter value groups of the SCADA data in different first data groups are different;

[0087] For any first data group, determine the maximum power generation in the first data group, and respectively determine the power generation difference value corresponding to each SCADA data of the first data group, the power generation difference value corresponding to the SCADA data being the absolute value of the difference between the power generation in the SCADA data and the maximum power generation;

[0088] For any wind turbine operating parameter, determine the parameter value of the wind turbine operating parameter in all operating time periods in all SCADA data, arrange the parameter values ​​of the wind turbine operating parameter in all operating time periods in order from small to large, and obtain a second arrangement array corresponding to the wind turbine operating parameter, and determine the information gain value of the wind turbine operating parameter according to the second arrangement array corresponding to the wind turbine operating parameter and the power generation difference value corresponding to the SCADA data;

[0089] The maximum M information gain values ​​are determined from the information gain values ​​of the plurality of wind turbine operating parameters, and the wind turbine operating parameters corresponding to the M information gain values ​​are determined as the M target operating parameters.

[0090] Among them, one SCADA data is the SCADA data of the wind turbine in a certain operation period.

[0091] Specifically, the information gain value of the wind turbine operating parameter can be used to measure the influence of the wind turbine operating parameter on the power generation.

[0092] Specifically, this embodiment can take the parameter values ​​of N target environment parameters in one SCADA data as a parameter value group. Afterwards, this embodiment can cluster the SCADA data in all the above operating time periods according to the parameter value group, and divide the SCADA data in all the above operating time periods into multiple first data groups.

[0093] Specifically, in this embodiment, for any wind turbine operating parameter, the parameter values ​​of the wind turbine operating parameter in all operating time periods can be arranged in order from small to large to obtain a corresponding second arrangement array. Thereafter, the information gain value of the wind turbine operating parameter can be determined based on the second arrangement array and the power generation difference value corresponding to the SCADA data.

[0094] Optionally, determining the information gain value of the target parameter according to the permutation array corresponding to the target parameter and the power generation related value includes:

[0095] Create a statistical parameter, set the initial parameter value of the statistical parameter to 1; and, starting from the first element in the permutation array corresponding to the target parameter, traverse all elements in the permutation array in sequence; wherein the target parameter is a natural environment parameter or a fan operation parameter;

[0096] For any element traversed, the SCADA data in multiple operating time periods are divided into a second data group and a third data group according to the element; wherein the parameter value of the target parameter in each SCADA data of the second data group is not greater than the element, and the parameter value of the target parameter in each SCADA data of the third data group is greater than the element; determine the first average value of all power generation related values ​​corresponding to the second data group, and determine the second average value of all power generation related values ​​corresponding to the third data group, determine the square difference between the first average value and the second average value, and use it as the square difference corresponding to the element; if it is determined that the square difference corresponding to the element is less than the square difference corresponding to the previous element in the arrangement array, add 1 to the parameter value of the statistical parameter;

[0097] The final parameter value of the statistical parameter is determined and used as the information gain value of the target parameter.

[0098] Optionally, when the target parameter is a natural environment parameter, the permutation array corresponding to the target parameter is the first permutation array corresponding to the natural environment parameter, the elements in the permutation array are the parameter values ​​of the natural environment parameter in the first permutation array, the power generation related value is the power generation in the SCADA data, and all power generation related values ​​corresponding to the second data group include the power generation in each SCADA data of the second data group.

[0099] Specifically, this embodiment may create a statistical parameter and define its initial parameter value as 1. This embodiment may start from the first parameter value in the first array corresponding to the natural environment parameter and traverse all parameter values ​​in the first array.

[0100] For any parameter value traversed in the first array, this embodiment can divide all SCADA data into two data groups, namely, a second data group and a third data group, according to the parameter value. The second data group and the third data group each include at least one SCADA data, the parameter value of the natural environment parameter in each SCADA data of the second data group is not greater than the parameter value currently traversed, and the parameter value of the natural environment parameter in each SCADA data of the third array is greater than the parameter value currently traversed. Calculate the first average value of the generated power in all SCADA data of the second data group, and calculate the second average value of the generated power in all SCADA data of the third data group, calculate the square difference between the first average value and the second average value, and use it as the square difference corresponding to the parameter value currently traversed.

[0101] Specifically, in this embodiment, during the process of traversing all parameter values ​​in the first arrangement array, if the square difference corresponding to the currently traversed parameter value is smaller than the square difference corresponding to the previous parameter value, 1 is added to the current parameter value of the statistical parameter.

[0102] Specifically, the final parameter value of the statistical parameter is the parameter value of the statistical parameter determined after this embodiment has traversed all parameter values ​​in the first arrangement array and decided whether to add 1 to the current parameter value of the statistical parameter based on the relationship between the square difference corresponding to the last parameter value and the square difference corresponding to the second to last parameter value.

[0103] Optionally, when the target parameter is the fan operating parameter, the permutation array corresponding to the target parameter is the second permutation array corresponding to the fan operating parameter, the elements in the permutation array are the parameter values ​​of the fan operating parameter in the second permutation array, the power generation related values ​​are the power generation difference values ​​corresponding to the SCADA data, and all power generation related values ​​corresponding to the second data group include the power generation difference values ​​corresponding to each SCADA data of the second data group.

[0104] Specifically, this embodiment may create a statistical parameter and define its initial parameter value as 1. This embodiment may start from the first parameter value in the second array corresponding to the wind turbine operating parameter and traverse all parameter values ​​in the second array.

[0105] For any parameter value traversed in the second array, this embodiment can divide all SCADA data into two data groups, namely the second data group and the third data group, according to the parameter value. The second data group and the third data group each include at least one SCADA data, the parameter value of the wind turbine operating parameter in each SCADA data of the second data group is not greater than the parameter value currently traversed, and the parameter value of the wind turbine operating parameter in each SCADA data of the third array is greater than the parameter value currently traversed. Calculate the first average value of the power generation difference value corresponding to all SCADA data of the second data group, and calculate the second average value of the power generation difference value corresponding to all SCADA data of the third data group, calculate the square difference between the first average value and the second average value, and use it as the square difference corresponding to the parameter value currently traversed.

[0106] Specifically, in this embodiment, during the process of traversing all parameter values ​​in the second array, if the square difference corresponding to the currently traversed parameter value is smaller than the square difference corresponding to the previous parameter value, 1 is added to the current parameter value of the statistical parameter.

[0107] Specifically, the final parameter value of the statistical parameter can be the parameter value of the statistical parameter determined after traversing all parameter values ​​in the second arrangement array in this embodiment and deciding whether to add 1 to the current parameter value of the statistical parameter based on the relationship between the square difference corresponding to the last parameter value and the square difference corresponding to the second to last parameter value.

[0108] The wind power parameter processing method proposed in this embodiment can effectively determine the information gain values ​​of natural environment parameters and wind turbine operating parameters.

[0109] based on Figure 1 This embodiment proposes a third wind power parameter processing method. In this method, step S105 may include:

[0110] For any key parameter, the parameter values ​​of the key parameter in all running time periods are arranged in order from small to large to obtain a target arrangement array;

[0111] Determine the elements with the first and second order in the target array respectively, and use them as the first element and the second element respectively; wherein the first order is the product of the total number of elements in the target array and 0.25, and the second order is the product of the total number of elements and 0.75;

[0112] Calculate the element difference obtained by subtracting the first element from the second element, and calculate the target product of the element difference and the preset coefficient;

[0113] Calculate a first value obtained by subtracting the target product from the first element, and calculate a second value obtained by adding the target product to the second element;

[0114] The first numerical value and the second numerical value are respectively determined as the normal lower limit parameter value and the normal upper limit parameter value of the key parameter.

[0115] The preset coefficient may be set by a technician according to actual conditions, for example, it may be set to 1.5 or 2, and this embodiment does not limit this.

[0116] The wind power parameter processing method proposed in this embodiment can effectively realize the intelligent determination of the normal lower limit parameter value and the normal upper limit parameter value of the key parameters, and can avoid the problems of threshold accuracy being affected by subjective experience, consuming human resources and setting efficiency existing in the related technology when the threshold is set by technical personnel.

[0117] based on Figure 1 This embodiment proposes a fourth wind power parameter processing method. After step S104, the method may further include:

[0118] For any key parameter, determine the reliability level corresponding to the key parameter based on all target parameter values ​​of the key parameter and the power generation difference value corresponding to the SCADA data;

[0119] The target parameter value is the parameter value of the key parameter during the running period.

[0120] Specifically, this embodiment can determine the reliability level of each key parameter.

[0121] In practical applications, this embodiment can monitor that the parameter value of a key parameter of a wind turbine exceeds a threshold during its operation, and can output information that the parameter value of the key parameter is abnormal, as well as the reliability level of the key parameter, to provide corresponding alarm information to technicians, providing a basis for technicians to analyze the operating status of the wind turbine.

[0122] Optionally, the reliability level corresponding to the key parameter is determined based on all target parameter values ​​of the key parameter and the power generation difference value corresponding to the SCADA data, including:

[0123] For any target parameter value of the key parameter, the target parameter value is used as the x-axis coordinate value of the data point to be drawn, and the power generation difference value corresponding to the SCADA data including the target parameter value is used as the y-axis coordinate value of the data point to be drawn, and the corresponding data point is drawn to the preset plane rectangular coordinate system according to the x-axis coordinate value and the y-axis coordinate value;

[0124] Classifying all data points corresponding to the key parameters based on the x-axis coordinate values ​​to obtain multiple data point groups corresponding to the key parameters; wherein the data point group includes at least one data point, and the x-axis coordinate values ​​of different data points in the same data point group are equal;

[0125] For any data point group corresponding to the key parameter, the standard deviation of the y-axis coordinate values ​​of all data points in the data point group is calculated. If the calculated standard deviation is greater than the preset threshold, the data point group is discretely controlled to obtain a controlled data point group, and the controlled data point group is used as a new data point group. The standard deviation of the y-axis coordinate values ​​of all data points in the execution data point group is returned until the calculated standard deviation is no greater than the preset threshold, thereby obtaining a discrete data point group and a final standard deviation corresponding to the key parameter;

[0126] For any discrete data point group corresponding to the key parameter, draw a corresponding envelope line in a plane rectangular coordinate system according to the discrete data point group, and determine the number of drawn envelope lines;

[0127] Calculate the first sum of all envelope quantities corresponding to the key parameter, and calculate the second sum of all final standard deviations corresponding to the key parameter;

[0128] Determine the reliability level corresponding to the key parameter according to the first sum value and the second sum value;

[0129] Among them, the reliability level of the key parameter is positively correlated with the size of the first sum value; when the first sum value remains unchanged, the reliability level of the key parameter is negatively correlated with the size of the second sum value.

[0130] Specifically, for any key parameter, this embodiment can use the parameter value of the key parameter in the operating period as the horizontal axis coordinate, i.e., the x-axis coordinate, and the power generation difference value corresponding to the SCADA data in the operating period as the vertical axis coordinate, i.e., the y-axis coordinate, to draw each data point in a plane rectangular coordinate system. Afterwards, this embodiment can regard all data points with the same horizontal axis coordinate as a data point group corresponding to the key parameter, and in this case, multiple data point groups corresponding to the key parameter can be obtained.

[0131] Specifically, for any data point group corresponding to the key parameter, the present embodiment can calculate the standard deviation of all vertical axis coordinate values ​​in the data point group. If the standard deviation is greater than a preset threshold, the data point group is subjected to discrete degree control until a discrete data point group with a standard deviation not greater than the preset threshold and a final standard deviation are obtained. Afterwards, the present embodiment can draw a corresponding envelope line according to the discrete data point group in a plane rectangular coordinate system for any discrete data point group corresponding to the key parameter, and determine the number of drawn envelope lines.

[0132] The preset threshold value may be set by a technician according to actual needs, for example, it may be set to 3, and this embodiment does not limit this.

[0133] Optionally, the discreteness control of the data point group is performed to obtain the controlled data point group, including:

[0134] Calculate the median value of the y-axis coordinate values ​​of all data points in the data point group, calculate the absolute value of the difference between the y-axis coordinate value of each data point in the data point group and the median value, and determine the largest absolute value of the difference, determine the data point corresponding to the largest absolute value of the difference as the target data point, delete the target data point in the data point group, and determine the data point group after deleting the target data point as the controlled data point group.

[0135] The inventor of the present invention has found that due to the variability of the operating state of wind turbines, by analyzing and monitoring the power curve of wind turbines, it is possible to ensure the efficient operation of wind turbines and timely discover the failure of various components. The analysis of abnormal performance of wind turbines has gradually become an important research direction in the development of wind power.

[0136] It is understandable that this embodiment can be applied to the study of abnormal power curves of wind turbines by adopting an algorithm, and can only rely on SCADA data to perform power curve abnormality analysis and early warning for different wind turbines and different models, and the results are more accurate.

[0137] The wind power parameter processing method proposed in this embodiment can effectively determine the reliability level of each key parameter, and provide a basis for technicians to analyze the operating status of wind turbines.

[0138] like Figure 2 As shown, this embodiment provides a wind power parameter processing device, which includes:

[0139] The acquisition unit 201 is used to acquire the monitoring and data acquisition SCADA data of the wind turbine in a plurality of continuous operation periods; wherein the SCADA data in each operation period includes parameter values ​​of a plurality of natural environment parameters in the operation period, parameter values ​​of a plurality of wind turbine operation parameters in the operation period and the power generation in the operation period;

[0140] The first determination unit 202 is used to determine N target environmental parameters that have the greatest impact on the power generation from a plurality of natural environmental parameters according to the SCADA data in a plurality of operating time periods; wherein N is an integer greater than 1;

[0141] The second determination unit 203 is used to determine M target operating parameters that have the greatest impact on the power generation from among the multiple wind turbine operating parameters based on the SCADA data in the multiple operating time periods and the N target environmental parameters; M is an integer greater than 1;

[0142] A third determining unit 204 is used to determine each target operating parameter as a key parameter for identifying whether the power generation power of the wind turbine is abnormal;

[0143] The fourth determining unit 205 is used to determine a normal upper limit parameter value and a normal lower limit parameter value of each key parameter according to the parameter value of each key parameter in each operating period.

[0144] It should be noted that the processing of the acquisition unit 201, the first determination unit 202, the second determination unit 203, the third determination unit 204 and the fourth determination unit 205 and the beneficial effects thereof can be respectively referred to in Figure 1 Steps S101 to S105 in the above are not described in detail.

[0145] Optionally, the first determining unit 202 is further configured to:

[0146] For any natural environment parameter, determine the parameter value of the natural environment parameter in all operating time periods in all SCADA data, arrange the parameter values ​​of the natural environment parameter in all operating time periods in order from small to large, and obtain a first arrangement array corresponding to the natural environment parameter, and determine the information gain value of the natural environment parameter according to the first arrangement array corresponding to the natural environment parameter and the power generation in the SCADA data;

[0147] The largest N information gain values ​​are determined from the information gain values ​​of the plurality of natural environment parameters, and the natural environment parameters corresponding to the N information gain values ​​are determined as N target environment parameters.

[0148] Optionally, the second determining unit 203 is further configured to:

[0149] For any SCADA data, the parameter values ​​of N target environmental parameters in the SCADA data are taken as a parameter value group as a whole;

[0150] Clustering the SCADA data in multiple operating time periods based on the parameter value groups to obtain multiple first data groups; wherein each first data group includes at least one SCADA data, the parameter value groups of each SCADA data in the same first data group are the same, and the parameter value groups of the SCADA data in different first data groups are different;

[0151] For any first data group, determine the maximum power generation in the first data group, and respectively determine the power generation difference value corresponding to each SCADA data of the first data group, the power generation difference value corresponding to the SCADA data being the absolute value of the difference between the power generation in the SCADA data and the maximum power generation;

[0152] For any wind turbine operating parameter, determine the parameter value of the wind turbine operating parameter in all operating time periods in all SCADA data, arrange the parameter values ​​of the wind turbine operating parameter in all operating time periods in order from small to large, and obtain a second arrangement array corresponding to the wind turbine operating parameter, and determine the information gain value of the wind turbine operating parameter according to the second arrangement array corresponding to the wind turbine operating parameter and the power generation difference value corresponding to the SCADA data;

[0153] The maximum M information gain values ​​are determined from the information gain values ​​of the plurality of wind turbine operating parameters, and the wind turbine operating parameters corresponding to the M information gain values ​​are determined as the M target operating parameters.

[0154] Optionally, the information gain value of the target parameter is determined according to the permutation array and the power generation related value corresponding to the target parameter, and is set to:

[0155] Create a statistical parameter, set the initial parameter value of the statistical parameter to 1; and, starting from the first element in the permutation array corresponding to the target parameter, traverse all elements in the permutation array in sequence; wherein the target parameter is a natural environment parameter or a fan operation parameter;

[0156] For any element traversed, the SCADA data in multiple operating time periods are divided into a second data group and a third data group according to the element; wherein the parameter value of the target parameter in each SCADA data of the second data group is not greater than the element, and the parameter value of the target parameter in each SCADA data of the third data group is greater than the element; determine the first average value of all power generation related values ​​corresponding to the second data group, and determine the second average value of all power generation related values ​​corresponding to the third data group, determine the square difference between the first average value and the second average value, and use it as the square difference corresponding to the element; if it is determined that the square difference corresponding to the element is less than the square difference corresponding to the previous element in the arrangement array, add 1 to the parameter value of the statistical parameter;

[0157] The final parameter value of the statistical parameter is determined and used as the information gain value of the target parameter.

[0158] Optionally, when the target parameter is a natural environment parameter, the permutation array corresponding to the target parameter is the first permutation array corresponding to the natural environment parameter, the elements in the permutation array are the parameter values ​​of the natural environment parameter in the first permutation array, the power generation related value is the power generation in the SCADA data, and all power generation related values ​​corresponding to the second data group include the power generation in each SCADA data of the second data group.

[0159] Optionally, when the target parameter is the fan operating parameter, the permutation array corresponding to the target parameter is the second permutation array corresponding to the fan operating parameter, the elements in the permutation array are the parameter values ​​of the fan operating parameter in the second permutation array, the power generation related values ​​are the power generation difference values ​​corresponding to the SCADA data, and all power generation related values ​​corresponding to the second data group include the power generation difference values ​​corresponding to each SCADA data of the second data group.

[0160] Optionally, the fourth determining unit 205 is further configured to:

[0161] For any key parameter, the parameter values ​​of the key parameter in all running time periods are arranged in order from small to large to obtain a target arrangement array;

[0162] Determine the elements with the first and second order in the target array respectively, and use them as the first element and the second element respectively; wherein the first order is the product of the total number of elements in the target array and 0.25, and the second order is the product of the total number of elements and 0.75;

[0163] Calculate the element difference obtained by subtracting the first element from the second element, and calculate the target product of the element difference and the preset coefficient;

[0164] Calculate a first value obtained by subtracting the target product from the first element, and calculate a second value obtained by adding the target product to the second element;

[0165] The first numerical value and the second numerical value are respectively determined as the normal lower limit parameter value and the normal upper limit parameter value of the key parameter.

[0166] Optionally, the plurality of natural environment parameters include at least three of wind speed, air temperature, wind direction, turbulence intensity and air temperature in the generator collector ring room;

[0167] The multiple wind turbine operating parameters include characteristic tower vibration characteristics, transmission chain vibration characteristics, generator collector ring slide temperature, main shaft speed, pitch setting angle, voltage, current, frequency, torque, gearbox inlet oil pressure, generator collector ring indoor air temperature, gearbox front bearing temperature, gearbox rear bearing temperature, gearbox oil temperature, generator front bearing temperature, generator rear bearing temperature, motor stator winding temperature, inverter cooling air temperature, control cabinet temperature, cabin temperature, pitch motor temperature, wind rotor speed, wind direction cabin angle, main shaft bearing temperature, gearbox high-speed shaft speed, generator torque, inverter set torque, actual pitch angle and mechanical brake status. At least three of them.

[0168] The wind power parameter processing device proposed in this embodiment can determine the N target environmental parameters and M target operating parameters that have the greatest impact on the power generation according to the SCADA data of the wind turbine in multiple continuous operating periods, and determine the M target operating parameters as key parameters for identifying whether the power generation of the wind turbine is abnormal, and then determine the normal upper limit parameter value and the normal lower limit parameter value of each key parameter. The normal upper limit parameter value and the normal lower limit parameter value of each key parameter can be used to monitor whether the power generation of the wind turbine is abnormal, and then used to identify whether the operation of the wind turbine is abnormal. This embodiment can effectively enrich the method of determining key parameters and their thresholds.

[0169] The wind power parameter processing device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0170] The embodiment of the present invention also provides a computer device having the above Figure 2 The wind power parameter processing device shown.

[0171] See also Figure 3 , a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are connected to each other using different buses for communication, and can be installed on a common motherboard or installed in other ways as needed. The processor can process instructions executed in the computer device, including instructions stored in or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides part of the necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 3 A processor 10 is taken as an example.

[0172] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0173] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0174] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function. The data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage devices. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0175] The memory 20 may include a volatile memory, such as a random access memory. The memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive. The memory 20 may also include a combination of the above-mentioned types of memory.

[0176] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0177] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0178] 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 aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for processing wind power parameters, characterized in that: include: Obtaining monitoring and data acquisition SCADA data of the wind turbine in multiple continuous operating time periods; wherein the SCADA data in each operating time period includes parameter values ​​of multiple natural environment parameters in the operating time period, parameter values ​​of multiple wind turbine operating parameters in the operating time period, and power generation in the operating time period; According to the SCADA data in the multiple operating time periods, determine N target environmental parameters that have the greatest impact on the power generation from the multiple natural environmental parameters; wherein N is an integer greater than 1; Based on the SCADA data in the multiple operating time periods and the N target environmental parameters, M target operating parameters having the greatest impact on the power generation are determined from the multiple wind turbine operating parameters, and each of the target operating parameters is determined as a key parameter for identifying whether the power generation of the wind turbine set is abnormal; M is an integer greater than 1; According to the parameter value of each key parameter in each operating period, a normal upper limit parameter value and a normal lower limit parameter value of each key parameter are determined.

2. The method according to claim 1, characterized in that Determining, based on the SCADA data in the multiple operating time periods, N target environmental parameters having the greatest impact on the power generation from the multiple natural environmental parameters, includes: For any of the natural environment parameters, determining the parameter value of the natural environment parameter in all the operating time periods in all the SCADA data, arranging the parameter values ​​of the natural environment parameter in all the operating time periods in order from small to large, to obtain a first arrangement array corresponding to the natural environment parameter, and determining the information gain value of the natural environment parameter according to the first arrangement array corresponding to the natural environment parameter and the generated power in the SCADA data; The largest N information gain values ​​are determined from the information gain values ​​of the multiple natural environment parameters, and the natural environment parameters corresponding to the N information gain values ​​are determined as the N target environment parameters.

3. The method according to claim 1, characterized in that The method of determining M target operating parameters having the greatest impact on power generation from among the plurality of wind turbine operating parameters based on the SCADA data in the plurality of operating time periods and the N target environmental parameters includes: For any of the SCADA data, taking the parameter values ​​of the N target environmental parameters in the SCADA data as a parameter value group as a whole; Clustering the SCADA data in the multiple operating time periods based on the parameter value groups to obtain multiple first data groups; wherein each of the first data groups includes at least one of the SCADA data, the parameter value groups of each of the SCADA data in the same first data group are the same, and the parameter value groups of the SCADA data in different first data groups are different; For any of the first data groups, determine the maximum power generation in the first data group, and respectively determine the power generation difference value corresponding to each of the SCADA data of the first data group, the power generation difference value corresponding to the SCADA data being the absolute value of the difference between the power generation in the SCADA data and the maximum power generation; For any of the wind turbine operating parameters, determine the parameter value of the wind turbine operating parameter in all the operating time periods in all the SCADA data, arrange the parameter values ​​of the wind turbine operating parameter in all the operating time periods in order from small to large, and obtain a second arrangement array corresponding to the wind turbine operating parameter, and determine the information gain value of the wind turbine operating parameter according to the second arrangement array corresponding to the wind turbine operating parameter and the power generation difference value corresponding to the SCADA data; The maximum M information gain values ​​are determined from the information gain values ​​of the plurality of wind turbine operating parameters, and the wind turbine operating parameters corresponding to the M information gain values ​​are determined as the M target operating parameters.

4. The method according to claim 2 or 3, characterized in that: Determining the information gain value of the target parameter according to the permutation array and the power generation related value corresponding to the target parameter includes: Creating a statistical parameter, setting the initial parameter value of the statistical parameter to 1; and, starting from the first element in the permutation array corresponding to the target parameter, traversing all elements in the permutation array in sequence; wherein the target parameter is the natural environment parameter or the wind turbine operating parameter; For any of the traversed elements, the SCADA data in the multiple operating time periods are divided into a second data group and a third data group according to the elements; wherein the parameter value of the target parameter in each of the SCADA data in the second data group is not greater than the element, and the parameter value of the target parameter in each of the SCADA data in the third data group is greater than the element; determining a first average value of all the power generation related values ​​corresponding to the second data group, and determining a second average value of all the power generation related values ​​corresponding to the third data group, determining a square difference between the first average value and the second average value, and using it as the square difference corresponding to the element; if it is determined that the square difference corresponding to the element is less than the square difference corresponding to the previous element in the permutation array, adding 1 to the parameter value of the statistical parameter; The final parameter value of the statistical parameter is determined and used as the information gain value of the target parameter.

5. The method according to claim 4, characterized in that When the target parameter is the natural environment parameter, the permutation array corresponding to the target parameter is the first permutation array corresponding to the natural environment parameter, the elements in the permutation array are the parameter values ​​of the natural environment parameter in the first permutation array, the power generation related value is the power generation in the SCADA data, and all the power generation related values ​​corresponding to the second data group include the power generation in each of the SCADA data of the second data group; When the target parameter is the wind turbine operating parameter, the arrangement array corresponding to the target parameter is the second arrangement array corresponding to the wind turbine operating parameter, the elements in the arrangement array are the parameter values ​​of the wind turbine operating parameter in the second arrangement array, the power generation related values ​​are the power generation difference values ​​corresponding to the SCADA data, and all the power generation related values ​​corresponding to the second data group include the power generation difference values ​​corresponding to each SCADA data of the second data group.

6. The method according to claim 1, characterized in that Determining a normal upper limit parameter value and a normal lower limit parameter value of each of the key parameters according to the parameter value of each of the key parameters in the SCADA data in the multiple operating time periods comprises: For any of the key parameters, the parameter values ​​of the key parameter in all the running time periods are arranged in order from small to large to obtain a target arrangement array; Determine the elements in the target array whose arrangement order is the first order and the second order respectively, and use them as the first element and the second element respectively; wherein the first order is the product of the total number of elements in the target array and 0.25, and the second order is the product of the total number of elements and 0.75; Calculating an element difference obtained by subtracting the first element from the second element, and calculating a target product of the element difference and a preset coefficient; Calculate a first value obtained by subtracting the target product from the first element, and calculate a second value obtained by adding the target product to the second element; The first value and the second value are respectively determined as a normal lower limit parameter value and a normal upper limit parameter value of the key parameter.

7. The method according to claim 1, characterized in that The plurality of natural environment parameters include at least three of wind speed, air temperature, wind direction, turbulence intensity and air temperature in the generator collector ring room; The multiple wind turbine operating parameters include characteristic tower vibration characteristics, transmission chain vibration characteristics, generator collector ring slide temperature, main shaft speed, pitch setting angle, voltage, current, frequency, torque, gearbox inlet oil pressure, generator collector ring indoor air temperature, gearbox front bearing temperature, gearbox rear bearing temperature, gearbox oil temperature, generator front bearing temperature, generator rear bearing temperature, motor stator winding temperature, inverter cooling air temperature, control cabinet temperature, cabin temperature, pitch motor temperature, wind rotor speed, wind direction-nacelle angle, main shaft bearing temperature, gearbox high-speed shaft speed, generator torque, inverter set torque, actual pitch angle and mechanical brake status. At least three of them.

8. A wind power parameter processing device, characterized in that: include: An acquisition unit is used to acquire monitoring and data acquisition SCADA data of the wind turbine in a plurality of continuous operation periods; wherein the SCADA data in each operation period includes parameter values ​​of a plurality of natural environment parameters in the operation period, parameter values ​​of a plurality of wind turbine operation parameters in the operation period and the power generation in the operation period; A first determining unit is used to determine N target environmental parameters that have the greatest impact on power generation from among the multiple natural environmental parameters based on the SCADA data in the multiple operating time periods; wherein N is an integer greater than 1; A second determination unit is configured to determine, based on the SCADA data in the multiple operating time periods and the N target environmental parameters, M target operating parameters having the greatest impact on the power generation from among the multiple wind turbine operating parameters; M is an integer greater than 1; A third determining unit, configured to determine each of the target operating parameters as a key parameter for identifying whether the power generation power of the wind turbine generator set is abnormal; The fourth determining unit is used to determine a normal upper limit parameter value and a normal lower limit parameter value of each of the key parameters according to the parameter value of each of the key parameters in each of the operating time periods.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the wind power parameter processing method according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the wind power parameter processing method according to any one of claims 1 to 7.

Images