CN115879616A - High-risk meteorological identification method and device based on power transmission line microclimate station monitoring data - Google Patents
High-risk meteorological identification method and device based on power transmission line microclimate station monitoring data Download PDFInfo
- Publication number
- CN115879616A CN115879616A CN202211543402.7A CN202211543402A CN115879616A CN 115879616 A CN115879616 A CN 115879616A CN 202211543402 A CN202211543402 A CN 202211543402A CN 115879616 A CN115879616 A CN 115879616A
- Authority
- CN
- China
- Prior art keywords
- meteorological
- data
- risk
- transmission line
- events
- 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.)
- Pending
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Alarm Systems (AREA)
Abstract
The invention discloses a high-risk weather identification method and a high-risk weather identification device based on monitoring data of a power transmission line micro-weather station, wherein the method comprises the following steps: collecting monitoring data of the power transmission line micro meteorological station, segmenting the monitoring data into a plurality of data segments through a time sequence, and extracting meteorological events in each data segment; marking the meteorological events in the extracted data segments according to a high-risk meteorological event marking strategy, and acquiring a part of high-risk meteorological event data segments; extracting the description features of all the data segments, and analyzing and processing to form a core feature set; performing cluster analysis on the high-risk meteorological events by combining the core feature set and the marked partial quantity of data sections containing the high-risk meteorological events; and acquiring characteristic parameters of the high-risk meteorological events in time and space, and completing the high-risk meteorological identification based on the monitoring data of the power transmission line micro meteorological station. The method provided by the invention can be used for evaluating the influence of meteorological events on the power system in a small-scale dimension, effectively guiding disaster early warning and allocation processing, and has a wide application range.
Description
Technical Field
The invention belongs to the technical field of power equipment monitoring and early warning, and particularly relates to a high-risk meteorological identification method and device based on power transmission line microclimate station monitoring data.
Background
The transmission tower is used as the most important infrastructure in the transmission network and takes charge of the tasks of supporting the conducting wire to transmit electric energy and construct the power network. Pylons are typically wind sensitive structures and their damage is often associated with extreme wind conditions. In the aspect of high-risk meteorological analysis, the power department mainly uses open meteorological information in the aspect of strong storm analysis and is assisted by a meteorological monitoring site at present.
For example, a power transmission line meteorological disaster fault risk assessment method is provided in patent CN114626629A, an analytic hierarchy process assessment model is established according to meteorological disaster influence factors, and risk weights of the meteorological disaster influence factors are calculated; establishing an algorithm evaluation model by adopting a PageRank algorithm according to the meteorological disaster influence factors, and calculating risk consequences corresponding to the meteorological disaster influence factors; and establishing a comprehensive operation risk evaluation model of the power transmission line according to the risk weight and the risk result. The accuracy of transmission line meteorological disaster risk assessment is improved, the risk state of the line can be accurately grasped, and the safety level of line operation under multiple meteorological disasters can be timely known.
For example, patent CN114330061A provides a method for analyzing weak links of a typical tower of a power transmission line, which obtains data information of a geographic environment, and establishes a corresponding geographic environment model according to the obtained data information of the geographic environment; acquiring data information of a power transmission line tower and an erected cable, and establishing a corresponding power transmission line tower model and a corresponding cable model according to the acquired data information of the power transmission line tower and the cable; acquiring meteorological data information corresponding to the geographic position, and establishing a corresponding meteorological model according to the acquired meteorological data information; and analyzing and judging weak links of the power transmission line tower according to the influence of the meteorological model on the power transmission line tower model and the cable model and the influence of the meteorological model and the geographic environment model which are matched with the meteorological model on the power transmission line tower model and the cable model. The scheme provides a multi-factor analysis method for different regional meteorological conditions, is suitable for searching and analyzing mechanical weak links of a typical power transmission tower, timely and effectively discovers the weak links of the power transmission tower, and improves the use safety of the power transmission tower.
However, in the meteorological field in the prior art, strong wind is identified from a mesoscale range, and a strong storm early warning method based on mesoscale meteorological numerical prediction is researched, so that the data early warning information only stays on a mesoscale level, the influence degree of meteorological events on an electric power system cannot be evaluated from a small scale, and pre-disaster early warning and post-disaster deployment cannot be effectively guided. Based on the iron tower wind-response data acquired by the mechanical sensor, the response data acquisition equipment is high in cost, complex in design and poor in stability, and the research scheme has strong correlation with the model and the structure of the iron tower and is difficult to popularize and apply in a large range.
The transmission line microclimate station is a meteorological monitoring technology which utilizes a transmission tower, and realizes real-time monitoring of the meteorological phenomena of the transmission tower with the position 10m away from the ground by collecting wind speed, precipitation and temperature. At present, some researchers begin to research and analyze data of the micro-meteorological station of the power transmission line, so as to provide decision support for planning operation, meteorological modeling and post-disaster analysis of the overhead power transmission line of the power system.
For example, patent CN113408788A provides a high-dimensional construction and completion method, system, device and medium for a microclimate monitoring device, and the method includes the following steps: acquiring geographic longitude and latitude information of the distribution of the microclimate monitoring device, and analyzing the regional and chronological characteristics of microclimate; clustering analysis based on longitude and latitude two-dimensional information is carried out on the microclimate monitoring devices according to the geographic longitude and latitude information, and the microclimate monitoring devices with similar spatial geographic distances are divided into the same class; the method comprises the steps of obtaining monitoring information of the microclimate monitoring devices which are divided into the same class, constructing a three-dimensional missing tensor according to the monitoring information, and filling missing values of the microclimate monitoring devices according to the three-dimensional missing tensor and a low-rank tensor completion algorithm. According to the method, missing values of the microclimate monitoring information with wrong and missed information are filled according to the time-space correlation of the microclimate monitoring information, and the method can be widely applied to the technical field of meteorological disaster early warning.
However, in the prior art, how to process microclimate data to accurately adapt to high-risk meteorological identification of a power transmission tower is not studied.
Therefore, a problem to be solved by the technical personnel in the art is how to design a high-risk meteorological identification method based on the power transmission line micro-meteorological station monitoring data, and to associate the power transmission line micro-meteorological station monitoring data with high-risk meteorological data so as to evaluate the influence of meteorological events on an electric power system in a small-scale dimension.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a high-risk meteorological identification method and device based on monitoring data of a power transmission line micro-meteorological station.
In a first aspect, the invention provides a high-risk meteorological identification method based on power transmission line microclimate station monitoring data, which comprises the following steps:
collecting monitoring data of the power transmission line micro meteorological station, segmenting the monitoring data into a plurality of data segments through a time sequence, and extracting meteorological events in each data segment;
marking the meteorological events in the extracted data segments according to a high-risk meteorological event marking strategy, and acquiring a part of high-risk meteorological event data segments;
extracting the description features of all the data segments, and analyzing and processing to form a core feature set;
performing cluster analysis on each high-risk meteorological event by combining the core feature set and the marked partial quantity of data segments containing the high-risk meteorological events;
and acquiring characteristic parameters of the high-risk meteorological events in time and space, and completing the high-risk meteorological identification based on the monitoring data of the power transmission line micro meteorological station.
Furthermore, a plurality of data segments are formed through time series segmentation, and the meteorological event in each data segment is extracted, which specifically comprises the following steps:
setting the monitoring data of the power transmission line microclimate station of each data section to be in normal distribution;
according to the sequence of the time sequence, carrying out breakpoint search on the monitoring data of the power transmission line microclimate station, and determining a final breakpoint set through a maximum threshold value of probability likelihood estimation;
based on the breakpoint set, the monitoring data of the power transmission line micro meteorological station are segmented into a plurality of data segments, and corresponding meteorological events are determined and extracted from each data segment;
the method comprises the following steps of carrying out breakpoint search on monitoring data of the power transmission line microclimate station according to the sequence of a time sequence, and determining a final breakpoint set through a maximum threshold value of probability likelihood estimation, wherein the method comprises the following specific steps:
randomly generating a breakpoint combination consisting of each initial breakpoint through the sequence of the time sequence;
the method comprises the steps of conducting global and local search on monitoring data to conduct breakpoint updating, and determining a final breakpoint set;
the global search generates candidate breakpoints, and the local search performs probability likelihood estimation on the candidate breakpoints one by one to determine the candidate breakpoints as final breakpoints.
Further, a high-risk meteorological event marking strategy specifically includes:
and acquiring time and longitude and latitude data of the actual disaster event, comparing the time and longitude and latitude data with the meteorological events in the data section, and determining that the corresponding data section is the data section containing the high-risk meteorological event.
Further, the description features include static time-frequency domain features and dynamic warping similarity features.
Further, the method comprises the following steps of extracting description features of all data segments, analyzing and processing the description features to form a core feature set:
analyzing the time-frequency domain characteristics of the meteorological events in the extracted data segment to obtain an index characteristic set;
acquiring a morphological feature set based on the dynamic distortion similarity of the meteorological events in the two data sections;
fusing the index feature set and the morphological feature set to form an initial feature set, and giving the similarity of each meteorological event;
clustering all weather events through clustering analysis, and obtaining a pseudo label corresponding to each weather event;
and screening the initial feature set by using a random forest according to the pseudo label to obtain a core feature set of the meteorological event.
Further, analyzing the time-frequency domain characteristics of the meteorological events in the extracted data segment to obtain an index characteristic set, and carrying out dimensionless processing on the data of the index characteristic set, wherein the processing formula is as follows:
wherein, x is the original data of the index characteristic,
dimensionless data for x index feature>
Is the mean of the x index characteristic>
The standard deviation of the index features is x.
Further, the index feature set comprises a time domain feature set and a frequency domain feature set, wherein the time domain feature set comprises a waveform index, a peak index, a pulse index, a margin index, a skewness index and a kurtosis index, and the frequency domain feature set comprises a center of gravity frequency, a mean square frequency, a root mean square frequency, a frequency variance and a frequency standard deviation.
Further, the index feature set and the morphological feature set are fused to form an initial feature set, and the similarity of each meteorological event is given, specifically: the similarity of each meteorological event is measured through the distance between the data segments, and the distance relationship between the data segments is as follows:
D[x w,1 (t),x w,2 (t)]
wherein D is t [x w,1 (t),x w,2 (t)]For the distance, D, of two data segments in the time-frequency domain feature space dtw [x w,1 (t),x w,2 (t)]For the morphological transformation costs, x, of two data segments w,i And (t) is a data segment, and n is the number of the data segments.
Further, the high-risk meteorological events are subjected to cluster analysis by combining the core feature set and the marked partial quantity of data sections containing the high-risk meteorological events, and the method specifically comprises the following steps:
giving out a part of marked core feature sets containing high-risk meteorological event data segments, and acquiring the core feature set of the high-risk meteorological event;
and comparing the similarity of all the core data sets with the core data sets of the high-risk meteorological events, and giving out clustering results of other high-risk meteorological events in the core data sets.
In a second aspect, the present invention further provides a high-risk weather identification device based on the monitoring data of the power transmission line microclimate station, which adopts the above-mentioned high-risk weather identification method based on the monitoring data of the power transmission line microclimate station, and includes:
the acquisition module acquires monitoring data of the power transmission line micro meteorological station and forms a plurality of data segments through time sequence segmentation;
the marking module is used for extracting the meteorological events in each data segment, marking the meteorological events in the extracted data segments according to a high-risk meteorological event marking strategy and acquiring partial high-risk meteorological event data segments;
and the analysis processing module extracts the description characteristics of all the data sections, analyzes and processes the description characteristics to form a core characteristic set, and combines the core characteristic set and the marked partial quantity of data sections containing the high-risk meteorological events to perform cluster analysis on each high-risk meteorological event, so as to obtain characteristic parameters of the high-risk meteorological events in time and space and complete the high-risk meteorological identification based on the monitoring data of the power transmission line micro-meteorological station.
The invention provides a high-risk weather identification method and device based on monitoring data of a power transmission line micro-weather station, which at least have the following beneficial effects:
(1) The method comprises the steps of extracting meteorological events by time sequence segmentation, labeling meteorological data according to meteorological disaster information, further extracting characteristics of high-risk meteorological events, detecting the high-risk meteorological events which possibly damage power transmission iron tower caused by the meteorological disasters in history by using a cluster analysis method, evaluating the influence of the meteorological events on a power system in a small-scale dimension, effectively guiding disaster early warning and allocation processing, and having a wide application range.
(2) The clustering analysis is carried out through the similarity of the distance and the shape of the data segments in the time-frequency domain characteristic space, the prediction judgment of the high-risk meteorological events existing in each data segment is given, the accuracy is high, and the data operability is strong.
(3) By arranging and analyzing data of the power transmission line micro-meteorological station and combining meteorological events, accurate positioning can be realized through extraction and detection of high-risk weather from two dimensional layers of time and longitude and latitude.
Drawings
FIG. 1 is a schematic flow chart of a high-risk weather identification method based on monitoring data of a power transmission line micro-weather station according to the present invention;
FIG. 2 is a schematic flow chart of a meteorological event for extracting data segments according to an embodiment of the present invention;
FIG. 3 is a graph of the results of extracting curves containing high-risk meteorological events from a data segment according to an embodiment of the present invention;
FIG. 4 is a graph of the result of extracting a curve containing no high-risk meteorological events from the data segment according to an embodiment of the present invention;
FIG. 5 is a schematic flow chart of data segment description feature extraction according to an embodiment of the present invention;
FIG. 6 is a graph of a result of a cluster analysis performed on a data segment according to an embodiment of the present invention;
FIG. 7 is a graph illustrating the time distribution of high-risk meteorological events according to an embodiment of the present invention;
FIG. 8 is a graph illustrating the spatial distribution of high-risk meteorological events according to an embodiment of the present invention;
fig. 9 is a schematic structural diagram of a high-risk weather identification device based on power transmission line microclimate station monitoring data.
Detailed Description
In order to better understand the technical solution, the technical solution will be described in detail with reference to the drawings and the specific embodiments. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The terminology used in the embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the description of the invention and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise, and "the plural" typically includes at least two.
It is also noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that an article or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such article or apparatus. Without further limitation, an element defined by the phrases "comprising one of \8230;" does not exclude the presence of additional like elements in an article or device comprising the element.
And correlating the monitoring data of the power transmission line micro meteorological station with high-risk meteorology so as to realize the evaluation of the influence of meteorological events on the power system in a small-scale dimension. The microclimate monitoring data of the power transmission line microclimate station are analyzed, high-risk meteorological events which can cause disasters to a power transmission system are extracted according to disaster information of collapse of a wind-induced iron tower, and high-risk identification and statistics are carried out on the meteorological events during the operation period of the power transmission line microclimate station according to the high-risk meteorological events.
As shown in fig. 1, the invention provides a high-risk weather identification method based on monitoring data of a power transmission line microclimate station, which comprises the following steps:
collecting monitoring data of the power transmission line micro meteorological station, segmenting the monitoring data into a plurality of data segments through a time sequence, and extracting meteorological events in each data segment;
marking the meteorological events in the extracted data segments according to a high-risk meteorological event marking strategy, and acquiring a part of high-risk meteorological event data segments;
extracting the description features of all the data segments, and analyzing and processing to form a core feature set;
performing cluster analysis on each high-risk meteorological event by combining the core feature set and the marked partial quantity of data sections containing the high-risk meteorological events;
and acquiring characteristic parameters of the high-risk meteorological events in time and space, and completing high-risk meteorological identification based on monitoring data of the power transmission line micro meteorological station.
According to the statistical result of the invention, a targeted operation and maintenance guidance suggestion can be provided for the power transmission tower to guide relevant departments to reasonably allocate resources and eliminate potential risks of the power transmission tower in time. The method can be popularized on various types of transmission towers in various regions due to the universality of the analysis object.
The meteorological event extraction uses time series segmentation to segment the monitoring data of the power transmission line micro meteorological station into smaller interpretable data segments, each data segment corresponds to one meteorological event and has a more consistent data mode.
As shown in fig. 2, a plurality of data segments are formed by time-series segmentation, and the method for extracting the meteorological event in each data segment specifically includes the following steps:
setting the monitoring data of the power transmission line microclimate station of each data section to be in normal distribution;
according to the sequence of the time sequence, carrying out breakpoint search on the monitoring data of the power transmission line microclimate station, and determining a final breakpoint set through a maximum threshold value of probability likelihood estimation;
based on the breakpoint set, the monitoring data of the power transmission line micro-meteorological station are segmented into a plurality of data segments, and corresponding meteorological events are determined and extracted from each data segment.
The method comprises the following steps of carrying out breakpoint search on monitoring data of the power transmission line microclimate station according to the sequence of a time sequence, and determining a final breakpoint set through a maximum threshold value of probability likelihood estimation, wherein the method comprises the following specific steps:
randomly generating a breakpoint combination consisting of each initial breakpoint through the sequence of the time sequence;
the method comprises the steps of conducting global and local search on monitoring data to conduct breakpoint updating, and determining a final breakpoint set;
the global search generates candidate breakpoints, and the local search performs probability likelihood estimation on the candidate breakpoints one by one to determine the candidate breakpoints as final breakpoints.
The maximum threshold value can be preset in advance before judgment, and different values can be selected according to different specific application scenarios without further limitation.
As shown in fig. 3, the third segment corresponds to data of meteorological events causing a collapse of the pylon, in which the wind speed rises rapidly in a short time and falls rapidly after reaching a maximum value and causing damage to the pylon, and this data characteristic corresponds to the process of leaving and harming the strong convection currents from passing through the environment. The other segments correspond to other meteorological events which occur successively in the period, and each data segment also corresponds to the whole occurrence process of the meteorological events from the beginning to the final end.
As shown in fig. 4, no severe weather events occurred in the vicinity of the power line microclimate station within the corresponding date. The time sequence segmentation result can not only completely identify the meteorological event with longer duration, but also accurately detect the meteorological event with shorter duration of the fifth segment and small time scale, and each data segment corresponds to the occurrence process of the meteorological event that the wind speed is changed from small to large and then from large to small.
The high-risk meteorological event marking strategy specifically comprises the following steps:
and acquiring time and longitude and latitude data of the actual disaster event, comparing the time and longitude and latitude data with the meteorological events in the data section, and determining that the corresponding data section is the data section containing the high-risk meteorological event.
And a power transmission iron tower collapse event caused by strong convection weather occurs near the power transmission iron tower in the corresponding data acquisition time period. The power transmission line micro-meteorological station acquires corresponding data fluctuation at corresponding time, and the data is intercepted and marked as a high-risk meteorological event waveform. After the meteorological events are extracted, high-risk meteorological event marking needs to be carried out according to actual disasters. The disaster event is derived from wind-induced iron tower collapse events reported by departments in each part of the power system, the disaster degree is high, and the damage of the corresponding meteorological event is large. High-risk meteorological events of a disaster actual site often correspond to tornadoes, strong convection monomers and typhoons in strong heat zones, the action range of wind speed at the moment of collapse is often too small, and the maximum wind speed is difficult to directly capture by a microclimate station of a power transmission line. However, the wind speed waveforms of the microclimate stations close to the power transmission line are often similar in characteristics, and in the embodiment, the related meteorological events are marked as high-risk meteorological events according to the information of the microclimate stations of the power transmission line around the disaster site.
The description features comprise static time-frequency domain features and dynamic distortion similarity features. Static time-frequency domain features include mean, absolute mean, effective value, average power, square root amplitude, peak-to-peak, variance, standard deviation, skewness, and kurtosis, as well as barycentric frequency, mean-squared frequency, root-mean-squared frequency, frequency variance, and frequency standard deviation.
As shown in fig. 5, performing description feature extraction on all data segments, analyzing and processing to form a core feature set, specifically includes the following steps:
analyzing the time-frequency domain characteristics of the meteorological events in the extracted data segment to obtain an index characteristic set;
acquiring a morphological feature set based on the dynamic distortion similarity of the meteorological events in the two data segments;
fusing the index feature set and the morphological feature set to form an initial feature set, and giving the similarity of each meteorological event;
clustering all weather events through clustering analysis, and obtaining a pseudo label corresponding to each weather event;
and screening the initial feature set by using a random forest according to the pseudo label to obtain a core feature set of the meteorological event.
Because the value ranges of all dimensions are different, dimensions need to be removed before the data are used, and the data are uniformly converted into a unitless data set.
Analyzing the time-frequency domain characteristics of the meteorological events in the extracted data segment to obtain an index characteristic set, and carrying out dimensionless processing on the data of the index characteristic set, wherein the processing formula is as follows:
wherein x is the original data of the index features,
dimensionless data for the x index feature>
Is the mean of the x index characteristic>
The standard deviation of the index features is x.
The index feature set comprises a time domain feature set and a frequency domain feature set, wherein the time domain feature set comprises a waveform index, a peak index, a pulse index, a margin index, a skewness index and a kurtosis index, and the frequency domain feature set comprises a center of gravity frequency, a mean square frequency, a root mean square frequency, a frequency variance and a frequency standard deviation. The specific relationship of the parameter representation of the time domain feature set and the frequency domain feature set is as follows:
the relation formula of the waveform index is as follows:
the relational formula of the peak index is as follows:
the pulse index is expressed by the following relation formula:
the relation formula of the margin indexes is as follows:
the skewness index has the following relational formula:
the kurtosis index is related as follows:
wherein n is the number of data segments, x w And (t) is a data segment.
Besides the time-frequency domain characteristics, morphological similarity of each data segment needs to be investigated, the index feature set and the morphological feature set are fused to form an initial feature set, and the similarity of each meteorological event is given, which specifically comprises the following steps: the similarity of each meteorological event is measured through the distance between the data segments, and the distance relationship between the data segments is as follows:
D[x w,1 (t),x w,2 (t)]
wherein D is t [x w,1 (t),x w,2 (t)]For the distance, D, of two data segments in the time-frequency domain feature space dtw [x w,1 (t),x w,2 (t)]For the morphological transformation costs, x, of two data segments w,i (t) is the data segment, and n is the number of data segments.
And (3) performing cluster analysis on each high-risk meteorological event by combining the core feature set and the marked partial quantity of data sections containing the high-risk meteorological events, and specifically comprising the following steps:
giving out part of marked core feature sets containing high-risk meteorological event data sections, and acquiring the high-risk meteorological event core feature sets;
and comparing the similarity of all the core data sets with the core data sets of the high-risk meteorological events, and giving out clustering results of other high-risk meteorological events in the core data sets.
As shown in FIG. 6, clustering analysis is performed on certain data segments to obtain clustering results of high-risk meteorological events.
And acquiring characteristic parameters of the high-risk meteorological events in time and space, and completing the high-risk meteorological identification based on the monitoring data of the power transmission line micro meteorological station.
As shown in fig. 7, a time dimension result is given, each meteorological event is classified, the meteorological events in the category corresponding to the meteorological event causing the power transmission tower to collapse are counted, and high-risk meteorological data segments are mainly distributed in the fourth, fifth, seventh and eighth months and are consistent with the occurrence frequency of the abnormal weather condition of strong wind, which indicates that disaster relief preparation needs to be strengthened in the corresponding month.
As shown in fig. 8, a result on the spatial dimension (i.e., longitude and latitude) is given, and a spatial thermodynamic diagram is obtained according to the occurrence frequency of the high-risk meteorological events corresponding to the microclimate stations of each power transmission line. The region with higher heat is mainly concentrated in the east part and the south part of Jiangsu, the east part of Jiangsu belongs to coastal regions, the low altitude at sea is shielded without obstacles, the cyclone is less blocked, the wind speed loss is less, and high-risk weather threatening an electric network system is easy to form. The dimensionality of the south of Jiangsu is low, the movement track of the tropical low-pressure cyclone approaches Jiangsu is from south to north, the probability of damage of the south of Jiangsu by the tropical low-pressure cyclone is higher, and the corresponding high-risk weather is more. High-risk meteorological events in areas with high heating power are more, potential safety hazard risks of nearby power transmission towers are also higher, and risk investigation and daily maintenance need to be enhanced for related areas.
As shown in fig. 9, the present invention further provides a high-risk weather identification device based on the monitoring data of the power transmission line microclimate station, and the high-risk weather identification method based on the monitoring data of the power transmission line microclimate station is adopted, and includes:
the acquisition module acquires monitoring data of the power transmission line microclimate station and forms a plurality of data segments through time sequence segmentation;
the marking module is used for extracting the meteorological events in each data segment, marking the meteorological events in the extracted data segments according to a high-risk meteorological event marking strategy and acquiring partial high-risk meteorological event data segments;
and the analysis processing module extracts the description characteristics of all the data sections, analyzes and processes the description characteristics to form a core characteristic set, and combines the core characteristic set and the marked partial quantity of data sections containing the high-risk meteorological events to perform cluster analysis on each high-risk meteorological event, so as to obtain characteristic parameters of the high-risk meteorological events in time and space and complete the high-risk meteorological identification based on the monitoring data of the power transmission line micro-meteorological station.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention. It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. A high-risk weather identification method based on monitoring data of a power transmission line micro-weather station is characterized by comprising the following steps:
collecting monitoring data of the power transmission line micro meteorological station, segmenting the monitoring data into a plurality of data segments through a time sequence, and extracting meteorological events in each data segment;
according to the high-risk meteorological event marking strategy, marking the meteorological events in the extracted data segment, and acquiring partial high-risk meteorological event data segments;
extracting the description features of all the data segments, and analyzing and processing to form a core feature set;
performing cluster analysis on each high-risk meteorological event by combining the core feature set and the marked partial quantity of data sections containing the high-risk meteorological events;
and acquiring characteristic parameters of the high-risk meteorological events in time and space, and completing the high-risk meteorological identification based on the monitoring data of the power transmission line micro meteorological station.
2. The high-risk weather identification method based on the monitoring data of the electric transmission line microclimate station is characterized in that a plurality of data segments are formed through time sequence segmentation, weather events in each data segment are extracted, and the method specifically comprises the following steps:
setting the monitoring data of the power transmission line micro meteorological station of each data section to be in normal distribution;
according to the sequence of the time sequence, carrying out breakpoint search on the monitoring data of the power transmission line microclimate station, and determining a final breakpoint set through a maximum threshold value of probability likelihood estimation;
based on the breakpoint set, the monitoring data of the power transmission line micro meteorological station are segmented into a plurality of data sections, and corresponding meteorological events are determined and extracted from each data section;
the method comprises the following steps of carrying out breakpoint search on monitoring data of the power transmission line microclimate station according to the sequence of a time sequence, and determining a final breakpoint set through a maximum threshold value of probability likelihood estimation, wherein the method comprises the following specific steps:
randomly generating a breakpoint combination consisting of each initial breakpoint through the sequence of the time sequence;
the method comprises the steps of conducting global and local search on monitoring data to conduct breakpoint updating, and determining a final breakpoint set;
the global search generates candidate breakpoints, and the local search carries out probability likelihood estimation on the candidate breakpoints one by one to determine the candidate breakpoints as final breakpoints.
3. The high-risk weather identification method based on the monitoring data of the electric transmission line microclimate station is characterized in that a high-risk weather event marking strategy specifically comprises the following steps:
and acquiring time and longitude and latitude data of the actual disaster event, comparing the time and longitude and latitude data with the meteorological events in the data section, and determining that the corresponding data section is the data section containing the high-risk meteorological event.
4. The method for identifying high-risk weather based on the monitoring data of the transmission line microclimate station is characterized in that the description features comprise static time-frequency domain features and dynamic distortion similarity features.
5. The high-risk meteorological identification method based on power transmission line microclimate station monitoring data, according to claim 4, characterized in that descriptive features of all data segments are extracted and analyzed to form a core feature set, and the method specifically comprises the following steps:
analyzing the time-frequency domain characteristics of the meteorological events in the extracted data segment to obtain an index characteristic set;
acquiring a morphological feature set based on the dynamic distortion similarity of the meteorological events in the two data sections;
fusing the index feature set and the morphological feature set to form an initial feature set, and giving the similarity of each meteorological event;
clustering all weather events through clustering analysis, and obtaining a pseudo label corresponding to each weather event;
and screening the initial feature set by using a random forest according to the pseudo label to obtain a core feature set of the meteorological event.
6. The method for identifying high-risk weather based on the monitoring data of the microclimate station of the power transmission line according to claim 5, characterized in that the time-frequency domain characteristics of the meteorological events in the extracted data segment are analyzed to obtain an index characteristic set, the method further comprises the step of carrying out dimensionless processing on the data of the index characteristic set, and the processing formula is as follows:
wherein x is the original data of the index features,
dimensionless data for the x index feature>
Is the mean of the x index characteristic>
Is the standard deviation of the x index features.
7. The method for identifying high-risk weather based on monitoring data of the electric transmission line microclimate station is characterized in that the index feature set comprises a time domain feature set and a frequency domain feature set, wherein the time domain feature set comprises a waveform index, a peak index, a pulse index, a margin index, a skewness index and a kurtosis index, and the frequency domain feature set comprises a center-of-gravity frequency, a mean-square frequency, a root-mean-square frequency, a frequency variance and a frequency standard deviation.
8. The high-risk weather identification method based on the monitoring data of the electric transmission line microclimate station is characterized in that the index feature set and the morphological feature set are fused to form an initial feature set, the similarity of each weather event is given, and the method specifically comprises the following steps: the similarity of each meteorological event is measured through the distance between the data segments, and the distance relationship between the data segments is as follows:
wherein D is t [x w,1 (t),x w,2 (t)]For the distance, D, of two data segments in the time-frequency domain feature space dtw [x w,1 (t),x w,2 (t)]For a morphological transformation cost, x, of two data segments w,i And (t) is a data segment, and n is the number of the data segments.
9. The method for identifying high-risk weather based on the monitoring data of the electric transmission line microclimate station according to claim 1, characterized in that the method for cluster-analyzing each high-risk weather event by combining a core feature set and a part of marked high-risk weather event-containing data segments specifically comprises the following steps:
giving out part of marked core feature sets containing high-risk meteorological event data sections, and acquiring the high-risk meteorological event core feature sets;
and comparing the similarity of all the core data sets with the core data sets of the high-risk meteorological events, and giving out clustering results of other high-risk meteorological events in the core data sets.
10. A high-risk weather identification device based on transmission line microclimate station monitoring data is characterized in that the high-risk weather identification method based on transmission line microclimate station monitoring data as claimed in any one of claims 1-9 is adopted, and the method comprises the following steps:
the acquisition module acquires monitoring data of the power transmission line micro meteorological station and forms a plurality of data segments through time sequence segmentation;
the marking module is used for extracting the meteorological events in each data segment, marking the meteorological events in the extracted data segments according to a high-risk meteorological event marking strategy and acquiring partial high-risk meteorological event data segments;
and the analysis processing module extracts the description characteristics of all the data sections, analyzes and processes the description characteristics to form a core characteristic set, combines the core characteristic set and the marked partial quantity of data sections containing the high-risk meteorological events, performs cluster analysis on each high-risk meteorological event, acquires characteristic parameters of the high-risk meteorological events in time and space, and completes the high-risk meteorological identification based on the monitoring data of the power transmission line micro-meteorological station.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211543402.7A CN115879616A (en) | 2022-12-02 | 2022-12-02 | High-risk meteorological identification method and device based on power transmission line microclimate station monitoring data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211543402.7A CN115879616A (en) | 2022-12-02 | 2022-12-02 | High-risk meteorological identification method and device based on power transmission line microclimate station monitoring data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115879616A true CN115879616A (en) | 2023-03-31 |
Family
ID=85765738
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211543402.7A Pending CN115879616A (en) | 2022-12-02 | 2022-12-02 | High-risk meteorological identification method and device based on power transmission line microclimate station monitoring data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115879616A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116595425A (en) * | 2023-07-13 | 2023-08-15 | 浙江大有实业有限公司杭州科技发展分公司 | Defect identification method based on power grid dispatching multi-source data fusion |
| CN118295045A (en) * | 2024-06-06 | 2024-07-05 | 贵州省邮电规划设计院有限公司 | Meteorological monitoring alarm system and method based on big data |
-
2022
- 2022-12-02 CN CN202211543402.7A patent/CN115879616A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116595425A (en) * | 2023-07-13 | 2023-08-15 | 浙江大有实业有限公司杭州科技发展分公司 | Defect identification method based on power grid dispatching multi-source data fusion |
| CN116595425B (en) * | 2023-07-13 | 2023-11-10 | 浙江大有实业有限公司杭州科技发展分公司 | Defect identification method based on power grid dispatching multi-source data fusion |
| CN118295045A (en) * | 2024-06-06 | 2024-07-05 | 贵州省邮电规划设计院有限公司 | Meteorological monitoring alarm system and method based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115879616A (en) | High-risk meteorological identification method and device based on power transmission line microclimate station monitoring data | |
| CN105182450B (en) | A kind of strong convective weather nowcasting warning system | |
| Gugliani et al. | New methods to assess wind resources in terms of wind speed, load, power and direction | |
| CN106526708A (en) | Intelligent early-warning analysis method for meteorological severe convection weather based on machine learning | |
| CN108957595A (en) | A kind of lightning forecasting method and system | |
| CN108509850B (en) | Intrusion signal identification method based on distributed optical fiber system | |
| Lakshmanan et al. | Data mining storm attributes from spatial grids | |
| CN113298295B (en) | Meteorological forecast system for power production | |
| CN101975909A (en) | Method for judging failure properties of shielding failure and counterattack of transmission line | |
| CN109407177B (en) | Machine learning and conventional meteorological observation-based fog identification system and application method | |
| CN102663032A (en) | Fiber grating fence invasion event mode recognition method | |
| CN115994325B (en) | Fan icing power generation data enhancement method based on TimeGAN deep learning method | |
| CN105279612A (en) | Poisson distribution-based power transmission line tripping risk assessment method | |
| CN109917394A (en) | A kind of short based on weather radar faces intelligent Extrapolation method | |
| CN110985310A (en) | Wind driven generator blade fault monitoring method and device based on acoustic sensor array | |
| CN105632059A (en) | Distributed optical fiber perimeter security system | |
| CN110619345A (en) | Cable-stayed bridge monitoring data validity-oriented label reliability comprehensive verification method | |
| Arul et al. | Machine learning based automated identification of thunderstorms from anemometric records using shapelet transform | |
| CN107944188A (en) | Typhoon eye of wind radius discrimination method near the ground based on weather station measured data | |
| CN107403004A (en) | A kind of suspicious numerical examination method of remote gauged rainfall website based on terrain data | |
| CN117523420A (en) | Lightning falling area identification method and system based on radar product data | |
| CN117517868A (en) | Lightning stroke fault matching method and system based on distributed measurement data | |
| CN106651131A (en) | Power-transmission-line anti-typhoon early warning method and system thereof | |
| CN112016739B (en) | Fault detection method and device, electronic equipment and storage medium | |
| CN114384534A (en) | Tree barrier growth prediction analysis method for unmanned aerial vehicle line patrol |
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 |