CN118582357B - Power grid new energy abnormal data detection method and system - Google Patents
Power grid new energy abnormal data detection method and system Download PDFInfo
- Publication number
- CN118582357B CN118582357B CN202411075263.9A CN202411075263A CN118582357B CN 118582357 B CN118582357 B CN 118582357B CN 202411075263 A CN202411075263 A CN 202411075263A CN 118582357 B CN118582357 B CN 118582357B
- Authority
- CN
- China
- Prior art keywords
- turbine generator
- wind
- wind turbine
- abnormal
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 185
- 238000001514 detection method Methods 0.000 title description 5
- 238000006243 chemical reaction Methods 0.000 claims abstract description 98
- 238000000034 method Methods 0.000 claims abstract description 47
- 238000012216 screening Methods 0.000 claims abstract description 6
- 230000006870 function Effects 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000010606 normalization Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 abstract description 3
- 238000010248 power generation Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000003064 k means clustering Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000002547 anomalous effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Wind Motors (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to a method and a system for detecting abnormal data of new energy sources of a power grid, comprising the following steps: and obtaining a plurality of association groups of the wind turbine generator, wherein the association groups comprise wind speed, output power, rotation speed of blades, rotation speed of a generator rotor, included angles between the blades and wind direction and electric energy converted in real time, and screening out abnormal association groups. And calculating a wind energy conversion coefficient according to the difference between the rotating speed and the wind speed of the blades of the abnormal association group and the included angle between the blades and the wind direction, so as to obtain mechanical energy. And obtaining a mechanical energy conversion coefficient according to the blade rotating speed and the generator rotor rotating speed of each abnormal associated group, and further obtaining a theoretical electric energy conversion value of each abnormal associated group. And obtaining a fault position coefficient according to the theoretical electric energy conversion value of each abnormal association group and the electric energy converted in real time, and finally obtaining a fault occurrence position. According to the invention, by analyzing each association group of the wind turbine generator, the accuracy of judging the fault occurrence position is improved.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a method and a system for detecting abnormal data of new energy sources of a power grid.
Background
Wind power new energy grids generally refer to integrating large-scale wind power generation systems into existing power networks or establishing specialized wind power generation networks in order to efficiently capture and distribute wind-generated power. The volatility and uncertainty of wind power generation is a challenge in grid operation. The anomaly data detection may help to discover possible faults or anomalies in the wind power generation system. The power grid can be ensured to run safely and reliably by timely detecting and processing the abnormal data.
At present, when the reason of abnormal output power is detected based on abnormal operation data of a wind turbine generator, the abnormal output power is caused by faults at different energy conversion positions of the turbine generator, so that the actual fault occurrence position cannot be accurately distinguished through new energy abnormal data of a power grid.
Disclosure of Invention
The invention provides a method and a system for detecting abnormal data of new energy sources of a power grid, which are used for solving the existing problems.
The invention relates to a method and a system for detecting abnormal data of new energy sources of a power grid, which adopts the following technical scheme:
the embodiment of the invention provides a method for detecting abnormal data of new energy sources of a power grid, which comprises the following steps:
in the power grid, obtaining an optimal included angle between a turbine blade and the wind direction and a plurality of associated groups of each wind turbine generator; each association group comprises a wind speed sequence section, an output power sequence section, a real-time turbine blade rotating speed sequence section, a real-time generator rotor rotating speed sequence section, a real-time included angle sequence section of the turbine blade and the wind direction and a real-time converted electric energy sequence section in the same time interval;
Screening a plurality of abnormal association groups according to the difference between the data of the wind speed sequence section and the output power sequence section of each association group of each wind turbine generator;
obtaining wind energy conversion coefficients of each abnormal association group according to the difference between the optimal included angle between the turbine blade and the wind direction and the data of the real-time turbine blade rotating speed sequence section, the wind speed sequence section and the real-time included angle sequence section between the turbine blade and the wind direction of each abnormal association group of each wind turbine generator;
Obtaining the mechanical energy of each abnormal association group according to the wind energy conversion coefficient of each abnormal association group of each wind turbine generator and all data of the wind speed sequence section;
Obtaining a mechanical energy conversion coefficient of each abnormal association group according to the difference between the data of the real-time turbine blade rotating speed sequence section and the real-time generator rotor rotating speed sequence section of each abnormal association group of each wind turbine generator; obtaining a theoretical electric energy conversion value of each abnormal association group according to the mechanical energy conversion coefficient and the mechanical energy of each abnormal association group of each wind turbine generator;
Obtaining fault position coefficients of each abnormal associated group according to all data of the real-time converted electric energy sequence segments of each abnormal associated group of each wind turbine generator and theoretical electric energy conversion values; and obtaining the fault occurrence position of each abnormal association group according to the fault position coefficient of each abnormal association group of each wind turbine generator.
Further, the screening of the plurality of abnormal association groups according to the difference between the data of the wind speed sequence section and the output power sequence section of each association group of each wind turbine generator comprises the following specific steps:
Obtaining the matching degree of the wind speed sequence section and the output power sequence section of each association group of each wind turbine generator according to the difference between the data of the wind speed sequence section and the output power sequence section of each association group of each wind turbine generator;
when (when) When the test value is smaller than or equal to a preset first test threshold value, will be the firstFirst wind turbine generatorA plurality of association groups, which are marked as abnormal association groups; wherein, Represent the firstFirst wind turbine generatorAnd matching degree of the wind speed sequence section and the output power sequence section of each association group.
Further, according to the difference between the data of the wind speed sequence section and the output power sequence section of each associated group of each wind turbine generator, a specific calculation formula corresponding to the matching degree of the wind speed sequence section and the output power sequence section of each associated group of each wind turbine generator is obtained as follows:
Wherein, Represent the firstFirst wind turbine generatorThe number of data for each sequence segment of the respective association group; Represent the first First wind turbine generatorWind speed sequence segment of each association groupData; Represent the first First wind turbine generatorWind speed sequence segment of each association groupData; Represent the first First wind turbine generatorOutput power sequence segment of each association groupData; Represent the first First wind turbine generatorOutput power sequence segment of each association groupData; Represent the first First wind turbine generatorDTW minimum matching distances of the wind speed sequence sections and the output power sequence sections of the correlation groups; Representing a linear normalization function.
Further, according to the difference between the optimal included angle between the turbine blade and the wind direction and the data of the real-time turbine blade rotating speed sequence section, the wind speed sequence section and the real-time included angle sequence section between the turbine blade and the wind direction of each abnormal association group of each wind turbine generator, a specific calculation formula corresponding to the wind energy conversion coefficient of each abnormal association group is obtained:
Wherein, Represent the firstFirst wind turbine generatorWind energy conversion coefficients of the abnormal association groups; Represent the first First wind turbine generatorThe number of data for each sequence segment of the anomaly association group; Represent the first First wind turbine generatorThe first of the real-time turbine blade speed sequence segments of the anomaly correlation setData; First, the First wind turbine generatorWind speed sequence segment of each anomaly association groupData; Represent the first First wind turbine generatorReal-time angular sequence of turbine blades of each anomaly-related group with wind directionData; representing an optimal angle of the turbine blades to the wind direction; Representing an absolute value function; Representing the normalization function.
Further, the method obtains the mechanical energy of each abnormal association group according to all the data of the wind energy conversion coefficient and the wind speed sequence section of each abnormal association group of each wind turbine generator, and comprises the following specific steps:
calculate the first First wind turbine generatorWind speed sequence segment of each anomaly association groupData and the firstFirst wind turbine generatorThe product of the wind energy conversion coefficients of the abnormal association group is the firstFirst wind turbine generatorAll data of wind speed sequence section of each abnormal association group and the firstFirst wind turbine generatorThe sum of the products of the wind energy conversion coefficients of the abnormal associated groups is recorded as the firstFirst wind turbine generatorMechanical energy of the abnormal association group.
Further, the method for obtaining the mechanical energy conversion coefficient of each abnormal associated group according to the difference between the data of the real-time turbine blade rotating speed sequence section and the real-time generator rotor rotating speed sequence section of each abnormal associated group of each wind turbine generator comprises the following specific steps:
In the first place First wind turbine generatorCalculating the average value of the difference values of all the data of the same order values in the real-time turbine blade rotating speed sequence section and the real-time generator rotor rotating speed sequence section of each abnormal association group, and recording the normalized value of the reciprocal of the average value as the firstFirst wind turbine generatorThe mechanical energy conversion coefficients of the respective anomaly-related groups.
Further, the theoretical electric energy conversion value of each abnormal association group is obtained according to the mechanical energy conversion coefficient and the mechanical energy of each abnormal association group of each wind turbine generator, and the method comprises the following specific steps:
Will be the first First wind turbine generatorThe product of the mechanical energy conversion coefficient and the mechanical energy of the abnormal associated group is recorded as the firstFirst wind turbine generatorTheoretical electrical energy conversion values for each abnormal association.
Further, the fault location coefficient of each abnormal association group is obtained according to all data and theoretical electric energy conversion values of the electric energy sequence segments converted in real time of each abnormal association group of each wind turbine generator, and the specific steps are as follows:
Will be the first First wind turbine generatorThe difference of the last data minus the first data of the real-time converted electric energy sequence segments of the abnormal association group is recorded as the firstFirst wind turbine generatorActual power conversion values of the abnormal association groups;
Will be the first First wind turbine generatorNormalized values of absolute values of differences between theoretical power conversion values and actual power conversion values of the abnormal correlation groups are recorded as the firstFirst wind turbine generatorFault location coefficients for the respective anomaly association groups.
Further, the step of obtaining the fault occurrence position of each abnormal association group according to the fault position coefficient of each abnormal association group of each wind turbine generator comprises the following specific steps:
If it is Less than or equal to a preset second experience threshold value, judging the first experience threshold valueFirst wind turbine generatorThe mechanical energy of the abnormal association group is converted into electric energy to generate faults; if it isGreater than a preset second experience threshold, then the first is judgedFirst wind turbine generatorThe position where wind energy of the abnormal association group is converted into mechanical energy is failed; wherein, Represent the firstFirst wind turbine generatorFault location coefficients for the respective anomaly association groups.
The invention also provides a system for detecting the abnormal data of the new energy source of the power grid, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the computer program stored in the memory so as to realize the steps of the method for detecting the abnormal data of the new energy source of the power grid.
The technical scheme of the invention has the beneficial effects that:
According to the embodiment of the invention, a plurality of abnormal association groups are screened according to the difference between the data of the wind speed sequence section and the output power sequence section of each association group of each wind turbine generator, so that the time period in which the abnormality is likely to occur can be accurately positioned. According to the difference between the optimal included angle between the turbine blade and the wind direction and the data of the real-time turbine blade rotating speed sequence section, the wind speed sequence section and the real-time included angle sequence section of the turbine blade and the wind direction of each abnormal association group of each wind turbine generator, the wind energy conversion coefficient of each abnormal association group is obtained, so that the accuracy of wind energy utilization efficiency evaluation is improved, the mechanical energy of each abnormal association group is obtained, and the accuracy and the reliability of mechanical energy evaluation are ensured. According to the difference between the data of the real-time turbine blade rotating speed sequence section and the real-time generator rotor rotating speed sequence section of each abnormal association group of each wind turbine generator, the mechanical energy conversion coefficient of each abnormal association group is obtained, and an accurate basis is provided for the subsequent theoretical electric energy conversion value. According to the mechanical energy conversion coefficient and the mechanical energy of each abnormal associated group of each wind turbine generator, the theoretical electric energy conversion value of each abnormal associated group is obtained, and the accuracy of electric energy conversion process evaluation is ensured. According to all data of the real-time converted electric energy sequence segments of each abnormal association group of each wind turbine generator and the theoretical electric energy conversion value, the fault position coefficient of each abnormal association group is obtained, the accuracy of fault detection is improved, and therefore the fault occurrence position of each abnormal association group is accurately obtained. The invention improves the accuracy of judging the fault occurrence position by analyzing each association group of the wind turbine generator.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of steps of a method for detecting abnormal data of new energy of a power grid.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following is a detailed description of specific implementation, structure, characteristics and effects thereof of the method and system for detecting abnormal data of new energy sources of a power grid according to the invention in combination with the accompanying drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The invention provides a method and a system for detecting abnormal data of new energy of a power grid, and a specific scheme thereof are specifically described below with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of steps of a method for detecting abnormal data of new energy of a power grid according to an embodiment of the present invention is shown, where the method includes the following steps:
Step S001: in the power grid, obtaining an optimal included angle between a turbine blade and the wind direction and a plurality of associated groups of each wind turbine generator; each association group comprises a wind speed sequence section, an output power sequence section, a real-time turbine blade rotating speed sequence section, a real-time generator rotor rotating speed sequence section, a real-time included angle sequence section of the turbine blade and the wind direction and a real-time converted electric energy sequence section in the same time interval.
What needs to be described is: wind turbine generators convert wind energy into mechanical energy, which is then converted into electrical energy, which is then transported through a power grid to ensure the supply of electrical power. The wind turbine generator is composed of a turbine, a generator and other parts, and the basic principle is that wind power drives blades of the turbine to rotate, wind energy is converted into mechanical energy at the moment, and then the turbine drives the generator to rotate so as to convert the mechanical energy into electric energy.
In the power grid, the optimal included angle between the turbine blade and the wind direction is obtained, and the sampling interval is taken asAnd second, the sampling period is 3 hours, and the wind speed value, the output power value of each wind turbine generator, the real-time turbine blade rotating speed, the real-time generator rotor rotating speed, the real-time included angle between the turbine blades and the wind direction and the real-time converted electric energy are collected. And obtaining a wind speed sequence, an output power sequence, a real-time turbine blade rotating speed sequence, a real-time generator rotor rotating speed sequence, a real-time included angle sequence of the turbine blades and the wind direction and a real-time converted electric energy sequence of each wind turbine generator respectively formed by corresponding continuous data points. Wherein, For the preset time interval threshold, the preset time interval threshold of the present embodimentThis is exemplified by 0.5.
What needs to be described is: at the same time, the consistency of the interval and the period of different types of data acquisition needs to be ensured.
And calculating the data in the wind speed sequence of each wind turbine generator by using a K-means clustering algorithm and a preset clustering number, and marking a plurality of obtained clusters of each wind turbine generator as a wind speed sequence segment. The K-means clustering algorithm is a known technique, and the specific method is not described here, and the preset number of clusters is 10, which is described as an example.
It should be noted that, clustering the wind speed sequence of each wind turbine generator, the data in the obtained cluster are continuous in time, which is equivalent to dividing the wind speed sequence of each wind turbine generator into a plurality of sequence segments.
In the first placeFor example, a wind turbine generator according to the firstA segmented interval of all wind speed sequence segments of the individual wind turbine generators, segmenting a wind speed sequence, an output power sequence, a real-time turbine blade rotating speed sequence, a real-time generator rotor rotating speed sequence, a real-time included angle sequence of turbine blades and wind direction and a real-time converted electric energy sequence of each wind turbine generator to obtain a first segmentThe system comprises a plurality of wind speed sequence sections, an output power sequence section, a real-time turbine blade rotating speed sequence section, a real-time generator rotor rotating speed sequence section, a real-time included angle sequence section of the turbine blades and the wind direction and a real-time converted electric energy sequence section of the wind turbine generator.
Will be the firstThe wind speed sequence section, the output power sequence section, the real-time turbine blade rotating speed sequence section, the real-time generator rotor rotating speed sequence section, the real-time included angle sequence section of the turbine blade and the wind direction and the real-time converted electric energy sequence section of the same time interval of the wind turbine generator are constructed into a correlation group.
Through the above process, the first step is obtainedSeveral associated groups of wind turbine generators.
And calculating each wind turbine generator according to the process to obtain a plurality of associated groups of each wind turbine generator.
Step S002: and screening a plurality of abnormal association groups according to the difference between the data of the wind speed sequence section and the output power sequence section of each association group of each wind turbine generator.
What needs to be described is: for wind turbine generators, since they convert wind energy into mechanical energy to generate electricity, if there is a fault inside, a huge difference occurs between the input energy level and the output energy level of the corresponding wind turbine generator, and thus this step determines the period of time in which the fault is likely to occur by analyzing the magnitude of the difference.
What is further to be described is: because the input energy level and the output energy level are seriously mismatched due to the failure of the wind turbine generator, the input energy of the wind turbine generator is wind energy and can be measured by measuring real-time wind speed data, and the output energy of the wind turbine generator is electric energy and can be measured by analyzing real-time output power data values. The likely anomalous data period can be determined by analyzing the degree of match of the two sequences.
In the first placeFirst wind turbine generatorFor example, the first association groupFirst wind turbine generatorThe specific calculation formula corresponding to the matching degree of the wind speed sequence segments and the output power sequence segments of each association group is as follows:
Wherein, Represent the firstFirst wind turbine generatorMatching degree of the wind speed sequence sections and the output power sequence sections of the correlation groups; Represent the first First wind turbine generatorThe number of data for each sequence segment of the respective association group; Represent the first First wind turbine generatorWind speed sequence segment of each association groupData; Represent the first First wind turbine generatorWind speed sequence segment of each association groupData; Represent the first First wind turbine generatorOutput power sequence segment of each association groupData; Represent the first First wind turbine generatorOutput power sequence segment of each association groupData; Represent the first First wind turbine generatorDTW minimum matching distances of the wind speed sequence sections and the output power sequence sections of the correlation groups; Representing a linear normalization function.
What needs to be described is: The larger the value of (2), the description of the (1) First wind turbine generatorThe more similar the trend of variation between the data of the wind speed sequence segments and the output power sequence segments of the respective correlation groups, the less likely it is a time period for failure to occur; The smaller the value of (2), the description of the (1) First wind turbine generatorThe more similar the development trend between the wind speed sequence section and the output power sequence section of each association group is, thenFirst wind turbine generatorThe greater the degree of matching of the wind speed sequence segments and the output power sequence segments of the respective correlation groups. The smaller the minimum matching distance of the DTW, the more similar the data sequence, the DTW algorithm is a known technique, and the specific method is not described herein.
Through the above process, the first step is obtainedFirst wind turbine generatorAnd matching degree of the wind speed sequence section and the output power sequence section of each association group.
And calculating each association group of each wind turbine generator according to the process to obtain the matching degree of the wind speed sequence section and the output power sequence section of each association group of each wind turbine generator.
When (when)When the test value is smaller than or equal to a preset first test threshold value, will be the firstFirst wind turbine generatorAnd the association groups are marked as abnormal association groups. The first threshold value is 0.25, which is preset in this embodiment, and this is described as an example.
Through the above process, several abnormal association groups of each wind turbine generator are obtained.
Step S003: and obtaining the wind energy conversion coefficient of each abnormal association group according to the difference between the optimal included angle between the turbine blade and the wind direction and the data of the real-time turbine blade rotating speed sequence section, the wind speed sequence section and the real-time included angle sequence section between the turbine blade and the wind direction of each abnormal association group of each wind turbine generator.
What needs to be described is: after obtaining several anomaly associations, it is most likely to occur at two energy conversion stages due to the anomalies in the data. This step therefore entails analyzing the energy conversion rate of the wind turbine generator in the process of converting energy from wind energy into mechanical energy and vice versa, and then determining the location of the fault by comparing the theoretical amount of energy conversion with the actual measured amount of energy.
What is further to be described is: firstly, the energy conversion efficiency in the process of converting wind energy into mechanical energy in a wind turbine generator is analyzed. If the efficiency of conversion of wind energy into mechanical energy in the abnormal set of associations is low relative to normal, it is indicated that the wind turbine generator may malfunction here.
What is further to be described is: because wind turbine generators convert wind energy into mechanical energy through turbines, corresponding wind energy conversion coefficients can be calculated by comparing the correlation of real-time wind speed data with turbine blade rotational speed data. However, the angle between the turbine blades and the wind direction affects the rotational speed of the blades and thus the wind energy conversion factor, and therefore this factor needs to be combined for calculation.
In the first placeFirst wind turbine generatorFor example, the abnormal association group is the firstFirst wind turbine generatorThe specific calculation formula corresponding to the wind energy conversion coefficient of each abnormal association group is as follows:
Wherein, Represent the firstFirst wind turbine generatorWind energy conversion coefficients of the abnormal association groups; Represent the first First wind turbine generatorThe number of data for each sequence segment of the anomaly association group; Represent the first First wind turbine generatorThe first of the real-time turbine blade speed sequence segments of the anomaly correlation setData; First, the First wind turbine generatorWind speed sequence segment of each anomaly association groupData; Represent the first First wind turbine generatorReal-time angular sequence of turbine blades of each anomaly-related group with wind directionData; representing an optimal angle of the turbine blades to the wind direction; Representing an absolute value function; Representing the normalization function.
What needs to be described is: representing the wind energy conversion rate of the abnormal association, And (3) withIn direct proportion to each other,The greater the value of (2)First wind turbine generatorThe greater the wind energy conversion coefficient of the respective anomaly association.The smaller the value of (c) is, the more the included angle at the corresponding moment is at the optimal angle, the moreFirst wind turbine generatorThe greater the wind energy conversion coefficient of the respective anomaly association.
Through the above process, the first step is obtainedFirst wind turbine generatorWind energy conversion coefficients of the abnormal association groups.
And calculating each abnormal association group of each wind turbine generator according to the process to obtain the wind energy conversion coefficient of each abnormal association group of each wind turbine generator.
Step S004: and obtaining the mechanical energy of each abnormal association group according to the wind energy conversion coefficient and all data of the wind speed sequence section of each abnormal association group of each wind turbine generator.
What needs to be described is: to locate the location of the fault, it is then necessary to calculate the actual mechanical energy converted at this time based on the wind energy conversion coefficient.
Still according to the firstFirst wind turbine generatorFor example, the abnormal association group is the firstFirst wind turbine generatorThe specific calculation formula corresponding to the mechanical energy of each abnormal association group is as follows:
Wherein, Represent the firstFirst wind turbine generatorMechanical energy of the abnormal association group; Represent the first First wind turbine generatorThe number of data for each sequence segment of the anomaly association group; First, the First wind turbine generatorWind speed sequence segment of each anomaly association groupData; Represent the first First wind turbine generatorWind energy conversion coefficients of the abnormal association groups.
What needs to be described is: And (3) with In direct proportion to each other,The greater the value of (2)First wind turbine generatorThe greater the mechanical energy of the individual anomaly association groups.
Through the above process, the first step is obtainedFirst wind turbine generatorMechanical energy of the abnormal association group.
And calculating each abnormal association group of each wind turbine generator according to the process to obtain the mechanical energy of each abnormal association group of each wind turbine generator.
Step S005: obtaining a mechanical energy conversion coefficient of each abnormal association group according to the difference between the data of the real-time turbine blade rotating speed sequence section and the real-time generator rotor rotating speed sequence section of each abnormal association group of each wind turbine generator; and obtaining a theoretical electric energy conversion value of each abnormal associated group according to the mechanical energy conversion coefficient and the mechanical energy of each abnormal associated group of each wind turbine generator.
What needs to be described is: the wind energy of the wind turbine generator is converted into mechanical energy to obtain a corresponding wind energy conversion coefficient, but because the wind turbine generator drives the generator rotor to rotate through the turbine so as to achieve the purpose of generating power, if a fault occurs in the transmission process of the turbine, namely, the process of converting the mechanical energy into electric energy, abnormal output power can be caused. Therefore, the mechanical energy conversion coefficient needs to be analyzed in the next step, so that the position where the fault occurs can be accurately determined.
What is further to be described is: because the turbine drives the generator to rotate, the rotation speed of the turbine blades is similar to the rotation speed of the rotor of the generator under normal conditions, if the position fails, the rotation speeds of the turbine blades and the rotor of the generator are different, and therefore the rotation speed similarity of the turbine blades and the rotor of the generator can be analyzed to measure the mechanical energy conversion coefficient of the corresponding period.
Still according to the firstFirst wind turbine generatorFor example, the abnormal association group is the firstFirst wind turbine generatorThe specific calculation formula corresponding to the mechanical energy conversion coefficient of each abnormal association group is as follows:
Wherein, Represent the firstFirst wind turbine generatorMechanical energy conversion coefficients of the abnormal associated groups; Represent the first First wind turbine generatorThe first of the real-time turbine blade speed sequence segments of the anomaly correlation setData; Represent the first First wind turbine generatorThe number of data for each sequence segment of the anomaly association group; Represent the first First wind turbine generatorThe first abnormal associated set of real-time generator rotor speed sequence segmentsData; Representing the normalization function.
What needs to be described is: And (3) with In direct proportion to each other,The greater the value of (2)First wind turbine generatorThe greater the mechanical energy conversion coefficient of the abnormal association group;
through the above process, the first step is obtained First wind turbine generatorMechanical energy conversion coefficients of the abnormal associated groups;
And calculating each abnormal association group of each wind turbine generator according to the process to obtain the mechanical energy conversion coefficient of each abnormal association group of each wind turbine generator.
What needs to be described is: and calculating the electric quantity converted by the abnormal correlation group under the theoretical condition by combining the mechanical energy conversion coefficient and the mechanical energy of the abnormal correlation group.
Will be the firstFirst wind turbine generatorThe product of the mechanical energy conversion coefficient and the mechanical energy of the abnormal associated group is recorded as the firstFirst wind turbine generatorTheoretical electrical energy conversion values for each abnormal association.
Through the above process, a theoretical power conversion value for each abnormal-related group of each wind turbine generator is obtained.
Step S006: obtaining fault position coefficients of each abnormal associated group according to all data of the real-time converted electric energy sequence segments of each abnormal associated group of each wind turbine generator and theoretical electric energy conversion values; and obtaining the fault occurrence position of each abnormal association group according to the fault position coefficient of each abnormal association group of each wind turbine generator.
What needs to be described is: the theoretical electric energy conversion value of the abnormal association group is obtained, and then the theoretical electric energy conversion value can be compared with the actually measured electric energy, and if the difference between the theoretical electric energy conversion value and the actually measured electric energy is not large, the fact that no large energy loss occurs in the process of converting mechanical energy into electric energy is indicated, so that the fault can occur at the position where wind energy is converted into mechanical energy. If the two are greatly different, the fault occurs at the position where the mechanical energy is converted into the electric energy.
Still according to the firstFirst wind turbine generatorTake the abnormal association group as an example, the firstFirst wind turbine generatorThe difference of the last data minus the first data of the real-time converted electric energy sequence segments of the abnormal association group is recorded as the firstFirst wind turbine generatorActual power conversion values of the respective abnormal association groups.
Through the above process, the actual power conversion value of each abnormal association group of each wind turbine generator is obtained.
Still according to the firstFirst wind turbine generatorFor example, the abnormal association group is the firstFirst wind turbine generatorThe specific calculation formula corresponding to the fault location coefficients of the abnormal association groups is as follows:
Wherein, Represent the firstFirst wind turbine generatorFault location coefficients for the respective abnormal association groups; Represent the first First wind turbine generatorTheoretical electric energy conversion values of the abnormal association groups; Represent the first First wind turbine generatorActual power conversion values of the abnormal association groups; Representing a linear normalization function; Representing an absolute value function.
What needs to be described is: And (3) with In direct proportion to each other,The greater the value of (2)First wind turbine generatorThe greater the fault location coefficient for the respective anomaly association groups.
Through the above process, the first step is obtainedFirst wind turbine generatorFault location coefficients for the respective anomaly association groups.
And calculating each abnormal association group of each wind turbine generator according to the process to obtain the fault location coefficient of each abnormal association group of each wind turbine generator.
If it isLess than or equal to a preset second experience threshold value, judging the first experience threshold valueFirst wind turbine generatorThe mechanical energy of the abnormal association group is converted into electric energy to generate faults; if it isGreater than a preset second experience threshold, then the first is judgedFirst wind turbine generatorThe wind energy of the abnormal association group is converted into mechanical energy to be in fault. The second empirical threshold value preset in this embodiment is 0.22, which is described as an example.
Through the above process, the fault location of the wind turbine generator is determined according to the fault location coefficient of each abnormal association group of each wind turbine generator.
Based on the principle of the steps, relevant maintenance personnel can overhaul relevant positions according to different fault detection signals, and the method only provides an auxiliary fault position positioning function, so that the actual situation is complicated, the relevant maintenance personnel are required to comprehensively consider and maintain in time, and the stability and reliability of a power grid are ensured.
What needs to be described is: in this embodiment, when the denominator in the formula is 0, let the denominator be 1, and ensure that the formula is established, this will be described as an example.
The present invention has been completed.
In summary, in the embodiment of the present invention, a plurality of association groups of the wind turbine generator are obtained, including wind speed, output power, rotation speed of blades, rotation speed of generator rotor, included angle between blades and wind direction, and converted electric energy in real time, and abnormal association groups are screened out. And calculating a wind energy conversion coefficient according to the difference between the rotating speed and the wind speed of the blades of the abnormal association group and the included angle between the blades and the wind direction, so as to obtain mechanical energy. And obtaining a mechanical energy conversion coefficient according to the blade rotating speed and the generator rotor rotating speed of each abnormal associated group, and further obtaining a theoretical electric energy conversion value of each abnormal associated group. And obtaining a fault position coefficient according to the theoretical electric energy conversion value of each abnormal association group and the electric energy converted in real time, and finally obtaining a fault occurrence position. According to the invention, by analyzing each association group of the wind turbine generator, the accuracy of judging the fault occurrence position is improved.
The invention also provides a system for detecting the abnormal data of the new energy source of the power grid, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the computer program stored in the memory so as to realize the steps of the method for detecting the abnormal data of the new energy source of the power grid.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the invention, but any modifications, equivalent substitutions, improvements, etc. within the principles of the present invention should be included in the scope of the present invention.
Claims (2)
1. The method for detecting the abnormal data of the new energy source of the power grid is characterized by comprising the following steps of:
in the power grid, obtaining an optimal included angle between a turbine blade and the wind direction and a plurality of associated groups of each wind turbine generator; each association group comprises a wind speed sequence section, an output power sequence section, a real-time turbine blade rotating speed sequence section, a real-time generator rotor rotating speed sequence section, a real-time included angle sequence section of the turbine blade and the wind direction and a real-time converted electric energy sequence section in the same time interval;
Screening a plurality of abnormal association groups according to the difference between the data of the wind speed sequence section and the output power sequence section of each association group of each wind turbine generator;
obtaining wind energy conversion coefficients of each abnormal association group according to the difference between the optimal included angle between the turbine blade and the wind direction and the data of the real-time turbine blade rotating speed sequence section, the wind speed sequence section and the real-time included angle sequence section between the turbine blade and the wind direction of each abnormal association group of each wind turbine generator;
Obtaining the mechanical energy of each abnormal association group according to the wind energy conversion coefficient of each abnormal association group of each wind turbine generator and all data of the wind speed sequence section;
Obtaining a mechanical energy conversion coefficient of each abnormal association group according to the difference between the data of the real-time turbine blade rotating speed sequence section and the real-time generator rotor rotating speed sequence section of each abnormal association group of each wind turbine generator; obtaining a theoretical electric energy conversion value of each abnormal association group according to the mechanical energy conversion coefficient and the mechanical energy of each abnormal association group of each wind turbine generator;
obtaining fault position coefficients of each abnormal associated group according to all data of the real-time converted electric energy sequence segments of each abnormal associated group of each wind turbine generator and theoretical electric energy conversion values; obtaining the fault occurrence position of each abnormal association group according to the fault position coefficient of each abnormal association group of each wind turbine generator;
the method comprises the following specific steps of screening out a plurality of abnormal association groups according to the difference between the data of the wind speed sequence section and the output power sequence section of each association group of each wind turbine generator:
obtaining the matching degree of the wind speed sequence section and the output power sequence section of each associated group of each wind turbine generator according to the difference between the data of the wind speed sequence section and the output power sequence section of each associated group of each wind turbine generator;
when (when) When the test value is smaller than or equal to a preset first test threshold value, will be the firstFirst wind turbine generatorA plurality of association groups, which are marked as abnormal association groups; wherein, Represent the firstFirst wind turbine generatorMatching degree of the wind speed sequence sections and the output power sequence sections of the correlation groups;
According to the difference between the data of the wind speed sequence section and the output power sequence section of each associated group of each wind turbine generator, a specific calculation formula corresponding to the matching degree of the wind speed sequence section and the output power sequence section of each associated group of each wind turbine generator is obtained:
Wherein, Represent the firstFirst wind turbine generatorThe number of data for each sequence segment of the respective association group; Represent the first First wind turbine generatorWind speed sequence segment of each association groupData; Represent the first First wind turbine generatorWind speed sequence segment of each association groupData; Represent the first First wind turbine generatorOutput power sequence segment of each association groupData; Represent the first First wind turbine generatorOutput power sequence segment of each association groupData; Represent the first First wind turbine generatorDTW minimum matching distances of the wind speed sequence sections and the output power sequence sections of the correlation groups; Representing a linear normalization function;
according to the difference between the data of the optimal included angle between the turbine blade and the wind direction and the real-time turbine blade rotating speed sequence section, the wind speed sequence section and the real-time included angle sequence section between the turbine blade and the wind direction of each abnormal association group of each wind turbine generator, a specific calculation formula corresponding to the wind energy conversion coefficient of each abnormal association group is obtained:
Wherein, Represent the firstFirst wind turbine generatorWind energy conversion coefficients of the abnormal association groups; Represent the first First wind turbine generatorThe number of data for each sequence segment of the anomaly association group; Represent the first First wind turbine generatorThe first of the real-time turbine blade speed sequence segments of the anomaly correlation setData; First, the First wind turbine generatorWind speed sequence segment of each anomaly association groupData; Represent the first First wind turbine generatorReal-time angular sequence of turbine blades of each anomaly-related group with wind directionData; representing an optimal angle of the turbine blades to the wind direction; Representing an absolute value function; Representing a normalization function;
The method for obtaining the mechanical energy of each abnormal association group according to the wind energy conversion coefficient and all data of the wind speed sequence segments of each abnormal association group of each wind turbine generator comprises the following specific steps:
calculate the first First wind turbine generatorWind speed sequence segment of each anomaly association groupData and the firstFirst wind turbine generatorThe product of the wind energy conversion coefficients of the abnormal association group is the firstFirst wind turbine generatorAll data of wind speed sequence section of each abnormal association group and the firstFirst wind turbine generatorThe sum of the products of the wind energy conversion coefficients of the abnormal associated groups is recorded as the firstFirst wind turbine generatorMechanical energy of the abnormal association group;
The method comprises the following specific steps of obtaining the mechanical energy conversion coefficient of each abnormal association group according to the difference between the data of the real-time turbine blade rotating speed sequence section and the real-time generator rotor rotating speed sequence section of each abnormal association group of each wind turbine generator:
In the first place First wind turbine generatorCalculating the average value of the difference values of all the data of the same order values in the real-time turbine blade rotating speed sequence section and the real-time generator rotor rotating speed sequence section of each abnormal association group, and recording the normalized value of the reciprocal of the average value as the firstFirst wind turbine generatorMechanical energy conversion coefficients of the abnormal associated groups;
According to the mechanical energy conversion coefficient and mechanical energy of each abnormal associated group of each wind turbine generator, obtaining a theoretical electric energy conversion value of each abnormal associated group, comprising the following specific steps:
Will be the first First wind turbine generatorThe product of the mechanical energy conversion coefficient and the mechanical energy of the abnormal associated group is recorded as the firstFirst wind turbine generatorTheoretical electric energy conversion values of the abnormal association groups;
All data and theoretical power conversion values of the power sequence segments converted in real time according to each abnormal correlation group of each wind turbine generator, obtaining the fault location coefficient of each abnormal association group, which comprises the following specific steps:
Will be the first First wind turbine generatorThe difference of the last data minus the first data of the real-time converted electric energy sequence segments of the abnormal association group is recorded as the firstFirst wind turbine generatorActual power conversion values of the abnormal association groups;
Will be the first First wind turbine generatorNormalized values of absolute values of differences between theoretical power conversion values and actual power conversion values of the abnormal correlation groups are recorded as the firstFirst wind turbine generatorFault location coefficients for the respective abnormal association groups;
The method for obtaining the fault occurrence position of each abnormal association group according to the fault position coefficient of each abnormal association group of each wind turbine generator comprises the following specific steps:
If it is Less than or equal to a preset second experience threshold value, judging the first experience threshold valueFirst wind turbine generatorThe mechanical energy of the abnormal association group is converted into electric energy to generate faults; if it isGreater than a preset second experience threshold, then the first is judgedFirst wind turbine generatorThe position where wind energy of the abnormal association group is converted into mechanical energy is failed; wherein, Represent the firstFirst wind turbine generatorFault location coefficients for the respective anomaly association groups.
2. A system for detecting abnormal data of new energy of a power grid, comprising a memory, a processor and a computer program stored on the memory and operable on the processor, wherein the computer program when executed by the processor implements the steps of a method for detecting abnormal data of new energy of a power grid as claimed in claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411075263.9A CN118582357B (en) | 2024-08-07 | 2024-08-07 | Power grid new energy abnormal data detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411075263.9A CN118582357B (en) | 2024-08-07 | 2024-08-07 | Power grid new energy abnormal data detection method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118582357A CN118582357A (en) | 2024-09-03 |
| CN118582357B true CN118582357B (en) | 2024-10-18 |
Family
ID=92526830
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411075263.9A Active CN118582357B (en) | 2024-08-07 | 2024-08-07 | Power grid new energy abnormal data detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118582357B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102236060A (en) * | 2010-04-30 | 2011-11-09 | 通用电气公司 | Fault detection device and method for detecting an electrical fault |
| CN102654100A (en) * | 2011-03-02 | 2012-09-05 | 通用电气公司 | Method and system for operating a wind turbine |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| SE0303574D0 (en) * | 2003-12-23 | 2003-12-23 | Abb Research Ltd | Elictric power network |
| WO2012097825A1 (en) * | 2011-01-21 | 2012-07-26 | Vestas Wind Systems A/S | A wind turbine fault detection circuit and method |
| CN105508149B (en) * | 2015-12-31 | 2018-12-07 | 北京金风科创风电设备有限公司 | Fault detection method and device for wind generating set |
| CN116186620A (en) * | 2023-01-16 | 2023-05-30 | 蒙东协合开鲁风力发电有限公司 | Energy efficiency diagnosis method and device and terminal equipment |
-
2024
- 2024-08-07 CN CN202411075263.9A patent/CN118582357B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102236060A (en) * | 2010-04-30 | 2011-11-09 | 通用电气公司 | Fault detection device and method for detecting an electrical fault |
| CN102654100A (en) * | 2011-03-02 | 2012-09-05 | 通用电气公司 | Method and system for operating a wind turbine |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118582357A (en) | 2024-09-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111091298B (en) | Wind power plant flow field coupling characteristic evaluation and intelligent grouping method and system | |
| CN106762452B (en) | Fan master control system fault diagnosis and on-line monitoring method based on data-driven | |
| CN110067708B (en) | Method for identifying yaw wind disharmony by using power curve | |
| CN112462736B (en) | Wind turbine generator fault diagnosis method based on data analysis | |
| CN105891546A (en) | Wind vane fault diagnosis method in wind turbine yaw system based on big data | |
| CN112231361A (en) | Wind power project generating capacity evaluation method based on fan operation data | |
| CN108869174B (en) | Nonlinear modeling wind driven generator blade natural frequency working condition compensation method | |
| CN112065668A (en) | Wind turbine generator state abnormity assessment method and system | |
| CN113153633A (en) | Static deviation calibration method for wind direction instrument of wind turbine generator | |
| CN116771610A (en) | Method for adjusting fault evaluation value of variable pitch system of wind turbine | |
| CN113468728B (en) | Variable pitch system fault prediction method based on neural network | |
| Yan et al. | Wind turbine generator fault detection based on multi-layer neural network and random forest algorithm | |
| CN111894814A (en) | Fault processing system and method for power generation system | |
| CN113915078B (en) | Intelligent recognition method and system for working conditions of blades of fiber bragg grating type wind turbine generator | |
| CN113777351B (en) | Fault diagnosis method and device for wind speed sensor of wind power plant | |
| CN118582357B (en) | Power grid new energy abnormal data detection method and system | |
| CN113374634B (en) | Wind turbine yaw wind alignment method under anemoscope fault mode | |
| CN118481905A (en) | Adjusting method of variable pitch system of wind driven generator | |
| CN117195136B (en) | Power grid new energy abnormal data monitoring method | |
| Xie et al. | Data Cleaning and Modeling of Wind Power Curves | |
| CN111794921B (en) | Onshore wind turbine blade icing diagnosis method based on migration component analysis | |
| CN113283035B (en) | Method, system, equipment and storage medium for constructing double-parameter wind turbine engine room transfer function | |
| CN114912807A (en) | Method and system for evaluating generated energy improving effect of technically improved wind turbine generator | |
| CN114607571A (en) | Offshore wind power gear box fault identification method and system based on lubricating system monitoring | |
| CN113915077A (en) | Fiber grating type wind turbine generator variable pitch flange, blade intelligent diagnosis method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |