Power transmission line hidden danger signal identification method and device, equipment and storage medium

Abstract

The invention relates to a power transmission line hidden danger signal identification method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring a to-be-identified discharge current signal of a power transmission line by using a signal acquisition terminal; the signal acquisition terminals are distributed on a power transmission line according to a preset interval; obtaining key feature parameters according to the discharge current signal to be identified, and obtaining a multi-dimensional feature vector according to the key feature parameters; obtaining the distance between the multi-dimensional feature vector and each initial clustering center; the initial clustering center is obtained based on historical fault hidden danger discharge current signal clustering analysis; and taking the initial clustering center corresponding to the minimum distance in the distances as a target initial clustering center, obtaining a hidden danger type corresponding to the target initial clustering center, and determining the hidden danger type as a hidden danger identification result of the discharge current signal to be identified. By adopting the method, the hidden danger type of the discharge current signal to be identified can be efficiently and accurately identified.

Description

Technical Field

[0001] The present application relates to the technical field of power transmission line hidden danger monitoring and identification, and in particular to a power transmission line hidden danger signal identification method, device, computer equipment, computer-readable storage medium and computer program product. Background Art

[0002] Traditional overhead transmission line safety detection technology mainly relies on regular patrols and manual inspections. Patrol personnel need to patrol along the transmission lines on foot or with the help of transportation to detect possible fault hazards.

[0003] However, with the expansion of overhead transmission lines, it is more common for transmission lines to cross vast areas. The terrain is complex and the environment is harsh, and manual inspection can no longer meet the needs of safety inspection.

[0004] At present, the safety of transmission lines can be monitored through online monitoring equipment, but the current online monitoring equipment is mainly used to monitor more obvious macro faults, such as line breaks, large-scale arc discharges and other faults, while it is difficult to identify hidden faults in transmission lines, such as excessive vegetation, bird damage, insulator pollution and other hidden faults. Summary of the invention

[0005] Based on this, it is necessary to provide a transmission line hidden danger signal identification method, device, computer equipment, computer readable storage medium and computer program product that can identify fault hazards in transmission lines in response to the above technical problems.

[0006] In a first aspect, the present application provides a method for identifying hidden danger signals of a power transmission line, comprising:

[0007] The discharge current signal to be identified of the power transmission line is obtained by using a signal acquisition terminal; the signal acquisition terminal is distributedly arranged on the power transmission line according to preset intervals;

[0008] Obtain key characteristic parameters according to the discharge current signal to be identified, and obtain a multi-dimensional characteristic vector according to the key characteristic parameters;

[0009] Obtaining the distance between the multidimensional feature vector and each initial cluster center; the initial cluster center is obtained based on cluster analysis of discharge current signals of historical fault hazards;

[0010] An initial cluster center corresponding to the minimum distance among the distances is used as a target initial cluster center, a hidden danger type corresponding to the target initial cluster center is obtained, and the hidden danger type is determined as a hidden danger identification result of the discharge current signal to be identified.

[0011] In one embodiment, the step of obtaining the initial cluster center includes:

[0012] Acquire the historical fault hidden danger discharge current signal of the signal acquisition terminal;

[0013] Obtain historical key characteristic parameters according to the historical fault hidden danger discharge current signal, and obtain historical key characteristic vectors according to the key characteristic parameters;

[0014] Performing cluster analysis based on each of the historical key feature vectors to obtain clustering results corresponding to a preset number of clusters;

[0015] According to the clustering result, an average feature vector corresponding to the cluster is obtained, and the average feature vector is used as an initial clustering center corresponding to the cluster.

[0016] In one embodiment, the method further comprises:

[0017] According to the multidimensional feature vector corresponding to the discharge current signal to be identified, the average feature vector corresponding to the target initial cluster center is updated to obtain an updated target initial cluster center.

[0018] In one embodiment, the key characteristic parameters include discharge frequency, pulse amplitude, pulse width and target frequency; the method further includes:

[0019] generating a characteristic radar chart of the discharge current signal to be identified according to the discharge frequency, the pulse amplitude, the pulse width and the target frequency;

[0020] The characteristic radar chart and the hidden danger identification result are sent to a feedback terminal, and the characteristic radar chart and the hidden danger identification result are displayed through the feedback terminal.

[0021] In one embodiment, after sending the characteristic radar map and the hidden danger identification result to a feedback terminal, the method further includes:

[0022] Obtaining update information returned by the feedback terminal for the hidden danger identification result;

[0023] Determine the actual hidden danger type after the update according to the update information;

[0024] The initial cluster center corresponding to the actual hidden danger type is updated according to the multi-dimensional feature vector.

[0025] In one embodiment, the step of acquiring the target frequency includes:

[0026] Obtaining a spectrum analysis result of the discharge current signal to be identified, obtaining each peak amplitude from the spectrum analysis result, and sorting each peak amplitude in descending order to obtain a peak amplitude sorting result;

[0027] According to the peak amplitude sorting result, a preset number of target peak amplitudes are determined, the peak center frequencies corresponding to the target peak amplitudes are obtained, and the peak center frequencies are used as the target frequencies.

[0028] In a second aspect, the present application also provides a transmission line hidden danger signal identification device, comprising:

[0029] A signal acquisition module, used to acquire the discharge current signal to be identified of the transmission line by using a signal acquisition terminal; the signal acquisition terminal is distributedly arranged on the transmission line according to preset intervals;

[0030] A feature vector acquisition module, used to obtain key feature parameters according to the discharge current signal to be identified, and obtain a multi-dimensional feature vector according to the key feature parameters;

[0031] A hidden danger identification module is used to obtain the distance between the multidimensional feature vector and each initial cluster center; the initial cluster center is obtained based on the cluster analysis of the discharge current signal of the historical fault hidden danger; the initial cluster center corresponding to the minimum distance among the distances is used as the target initial cluster center, the hidden danger type corresponding to the target initial cluster center is obtained, and the hidden danger type is determined as the hidden danger identification result of the discharge current signal to be identified.

[0032] In a third aspect, the present application further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method described in the first aspect when executing the computer program.

[0033] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method described in the first aspect.

[0034] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which implements the steps of the method described in the first aspect when executed by a processor.

[0035] The above-mentioned transmission line hidden danger signal identification method, device, computer equipment, computer-readable storage medium and computer program product first use a signal acquisition terminal to obtain the discharge current signal to be identified of the transmission line; the signal acquisition terminal is distributedly arranged on the transmission line according to preset intervals; then key feature parameters are obtained according to the discharge current signal to be identified, and a multidimensional feature vector is obtained according to the key feature parameters; then the distance between the multidimensional feature vector and each initial clustering center is obtained; the initial clustering center is obtained based on the clustering analysis of the discharge current signal of the historical fault hidden danger; finally, the initial clustering center corresponding to the minimum distance among the distances is used as the target initial clustering center. The present invention obtains the hidden danger type corresponding to the target initial clustering center, and determines the hidden danger type as the hidden danger identification result of the discharge current signal to be identified; the present application can monitor the current signals of various parts of the transmission line in an all-round manner by distributing and installing signal acquisition terminals at multiple locations of the transmission line, thereby ensuring the comprehensiveness and accuracy of data acquisition, simplifying signal data by extracting key feature parameters, and extracting multidimensional feature vectors that can reflect the essential characteristics of the discharge current signal. The initial clustering center is determined by using the discharge current signal of historical fault hidden dangers, and then the multidimensional feature vectors are clustered, so that the hidden danger type of the discharge current signal to be identified can be efficiently and accurately identified. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0037] FIG1 is a diagram showing an application environment of a method for identifying hidden danger signals of power transmission lines according to an embodiment;

[0038] FIG2 is a schematic diagram of a flow chart of a method for identifying a hidden danger signal of a power transmission line in one embodiment;

[0039] FIG3 is a schematic diagram of a process of obtaining an initial cluster center in one embodiment;

[0040] FIG4 is a schematic diagram of signal frequency distribution characteristics corresponding to a typical tree obstacle hazard in one embodiment;

[0041] FIG5 is a schematic diagram of signal frequency distribution characteristics corresponding to a typical bird damage hazard in one embodiment;

[0042] FIG6 is a schematic diagram of signal frequency distribution characteristics corresponding to a typical insulator contamination hazard in one embodiment;

[0043] FIG7 is a typical tree obstacle hidden danger fingerprint radar diagram in one embodiment;

[0044] FIG8 is a typical bird damage potential fingerprint radar diagram in one embodiment;

[0045] FIG9 is a radar diagram of a typical contamination hazard fingerprint in one embodiment;

[0046] FIG10 is a radar diagram of a newly collected discharge signal in one embodiment;

[0047] FIG11 is a structural block diagram of a device for identifying hidden danger signals of power transmission lines in one embodiment;

[0048] FIG. 12 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0050] The method for identifying hidden danger signals of power transmission lines provided in the embodiment of the present application can be applied in the application environment as shown in FIG1. ​​Among them, a plurality of signal acquisition terminals 102 are distributedly arranged on the transmission line according to preset intervals. Taking any one of the signal acquisition terminals 102 as an example, the signal acquisition terminal 102 communicates with the server 104 through the network. The data storage system can store data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The server 104 uses the signal acquisition terminal 102 to obtain the discharge current signal to be identified of the transmission line; the signal acquisition terminal 102 is distributedly arranged on the transmission line according to the preset interval; the server 104 obtains the key characteristic parameters according to the discharge current signal to be identified, and obtains the multidimensional characteristic vector according to the key characteristic parameters; the server 104 obtains the distance between the multidimensional characteristic vector and each initial clustering center; the initial clustering center is obtained based on the clustering analysis of the discharge current signal of the historical fault hidden danger; the server 104 uses the initial clustering center corresponding to the minimum distance among the distances as the target initial clustering center, obtains the hidden danger type corresponding to the target initial clustering center, and determines the hidden danger type as the hidden danger identification result of the discharge current signal to be identified. Among them, the server 104 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0051] As a key component of the power transmission system, overhead transmission lines are responsible for transmitting electricity from power plants to users. Due to their wide coverage, overhead transmission lines often cross various geographical areas and face diverse and complex environmental conditions. These environmental conditions include terrain changes such as mountains, forests, plains, and rivers, as well as different climatic conditions such as high temperature, cold, humidity, and wind and sand. In these complex operating environments, overhead transmission lines will inevitably face many potential safety hazards, which may seriously affect the normal operation of the power system and even threaten the safety of the entire power grid.

[0052] Common safety hazards include but are not limited to the following:

[0053] Excessive vegetation: Transmission lines often pass through forested and grassland areas, and over time, natural plant growth can cause vegetation to grow too close to transmission lines, increasing the risk of short circuits and fires.

[0054] Bird damage: Birds frequently move around transmission lines, and their nesting and defecation behaviors may cause local discharge and insulation damage to the transmission lines, and even lead to faults and tripping.

[0055] Insulator contamination: Due to long-term exposure to the outdoors, dust, salt, pollutants, etc. are easily accumulated on the surface of insulators, especially in coastal and industrial areas. These contaminants will reduce the electrical strength of the insulators and increase the possibility of discharge.

[0056] Insulator Deterioration: Over time and due to deteriorating environmental conditions, the material properties of insulators will gradually deteriorate, resulting in their inability to effectively isolate current, leading to electrical failures.

[0057] Suspended hardware: In severe weather or mechanical damage, the hardware of the transmission line may become loose or broken, resulting in a suspended potential between the hardware and the transmission line, which may cause safety hazards during the discharge process.

[0058] These hidden dangers will not only reduce the reliability of transmission lines, but may also lead to serious power failures such as line tripping, large-scale power outages, and even trigger chain reactions, posing a threat to the overall stability of the power grid.

[0059] Traditional overhead transmission line safety monitoring technology mainly relies on regular patrols and manual inspections. Patrol personnel need to patrol along the line on foot or with the help of transportation to find possible hidden dangers. However, since the lines often span a wide area, the terrain is complex and the environment is harsh, this manual inspection method has obvious shortcomings. On the one hand, the patrol frequency is difficult to be high enough, resulting in the gradual formation of hidden dangers during the patrol intervals; on the other hand, manual inspections are inefficient, especially when facing hidden early hidden dangers, which are difficult to detect with the naked eye. In addition, some hidden dangers do not show obvious physical changes in the early stages, and the hidden dangers mainly exist in the form of weak discharge signals. In this case, even if patrols are carried out, it is difficult to detect these potential sources of faults.

[0060] In recent years, with the development of sensor technology, online monitoring equipment has gradually been introduced into transmission line systems. These devices can realize real-time monitoring of transmission lines, effectively improving the timeliness of hidden danger discovery. However, most of the current online monitoring equipment mainly focuses on detecting more obvious macroscopic faults, such as line breaks, large-scale arc discharges, etc. When dealing with overhead transmission line systems with complex environments and various types of hidden dangers, these devices often have difficulty identifying discharge signals in the early stages. Due to the nonlinear and non-stationary characteristics of discharge signals, existing signal analysis methods are still insufficient in extracting and classifying the characteristic parameters of these signals. This leads to the fact that in practical applications, existing technologies are prone to false alarms or missed alarms, thereby reducing the reliability and effectiveness of the monitoring system.

[0061] Therefore, there is an urgent need for an efficient and accurate hidden danger signal identification method that can combine the operating characteristics and actual environment of overhead transmission lines to comprehensively analyze and process discharge signal characteristics, so as to realize automatic identification and early warning of various safety hazards and ensure the safe and stable operation of the power system.

[0062] In an exemplary embodiment, as shown in FIG2 , a method for identifying a hidden danger signal of a power transmission line is provided, and the method is applied to the server 104 in FIG1 as an example for explanation, and includes the following steps:

[0063] Step S202: using a signal acquisition terminal to obtain a discharge current signal to be identified of a transmission line.

[0064] Among them, the signal acquisition terminals can be distributed on the transmission lines according to preset intervals. For example, the preset intervals can be 200 meters, 500 meters, 2000 meters, etc., which are set according to actual needs and are not specifically limited here.

[0065] The discharge current signal to be identified may refer to a traveling wave current signal in a transmission line, such as an abnormal discharge current signal associated with safety hazards such as excessive vegetation, bird damage, and dirty insulators.

[0066] The signal acquisition terminal may be used for real-time monitoring and acquisition of traveling wave current signals, and the signal acquisition terminal may include a sensor and a data processing unit.

[0067] Specifically, the server uses each signal acquisition terminal on the transmission line to acquire the discharge current signal to be identified of the transmission line section covered by each signal acquisition terminal.

[0068] Step S204, obtaining key characteristic parameters according to the discharge current signal to be identified, and obtaining a multi-dimensional characteristic vector according to the key characteristic parameters.

[0069] Among them, key characteristic parameters may refer to representative parameters in the collected signal data, such as current intensity, frequency component, waveform characteristics and other parameters, which can be used to describe the key characteristics of the signal.

[0070] The multi-dimensional feature vector may be a vector composed of multiple key feature parameters, and may be used to represent the feature state of the discharge current signal to be identified.

[0071] Specifically, the server processes the collected discharge current signal to be identified, and uses data analysis methods to extract key characteristic parameters, such as discharge frequency, pulse amplitude, pulse width and other parameters, and then uses the above key characteristic parameters to construct a multi-dimensional feature vector to represent the properties of the discharge current signal to be identified.

[0072] Step S206, obtaining the distance between the multi-dimensional feature vector and each initial cluster center.

[0073] The initial cluster center is obtained based on the cluster analysis of the discharge current signal of the historical fault hidden danger. The initial cluster center may specifically refer to the center vector of a group of feature vectors representing the fault hidden danger state.

[0074] The distance may be a method for calculating the similarity between the multidimensional feature vector corresponding to the discharge current signal to be identified and each initial cluster center, and the distance may be determined by methods such as Euclidean distance and Manhattan distance.

[0075] Specifically, the server first obtains each initial cluster center, and then obtains the distance between the multidimensional feature vector and each initial cluster center through a preset distance algorithm.

[0076] Step S208, taking the initial cluster center corresponding to the minimum distance among the distances as the target initial cluster center, obtaining the hidden danger type corresponding to the target initial cluster center, and determining the hidden danger type as the hidden danger identification result of the discharge current signal to be identified.

[0077] The hidden danger type may refer to the type information of the cluster corresponding to each initial cluster center, and the hidden danger type may include bird damage, insulator contamination, insulator degradation, hardware suspension and other hidden dangers.

[0078] Specifically, the server determines the minimum distance between the multidimensional feature vector and each initial cluster center, and takes the initial cluster center corresponding to the minimum distance, that is, the initial cluster center that is most similar to the multidimensional feature vector as the target initial cluster center, and then obtains the type information of the cluster where the target initial cluster center is located, obtains the hidden danger type represented by the type information, and determines the hidden danger type as the hidden danger identification result of the discharge current signal to be identified.

[0079] In the above-mentioned transmission line hidden danger signal identification method, by distributing and installing signal acquisition terminals at multiple locations of the transmission line, the current signals of various parts of the transmission line can be monitored in all directions, ensuring the comprehensiveness and accuracy of data acquisition. The signal data can be simplified by extracting key feature parameters, and the extracted multidimensional feature vector can reflect the essential characteristics of the discharge current signal. The initial clustering center is determined by using the discharge current signal of historical fault hidden dangers, and then the multidimensional feature vector is clustered, so that the hidden danger type of the discharge current signal to be identified can be efficiently and accurately identified.

[0080] In an exemplary embodiment, as shown in FIG3 , the step of obtaining the initial cluster center may specifically include:

[0081] Step S302, obtaining the historical fault potential discharge current signal of the signal acquisition terminal.

[0082] The historical fault hidden danger discharge current signal may refer to the previously recorded current signal data generated by the transmission line under specific circumstances due to faults or hidden dangers, and these data may be used to analyze the laws and characteristics of the fault occurrence.

[0083] Specifically, the server obtains the historical fault hidden danger discharge current signal of the signal acquisition terminal through the historical record data.

[0084] Step S304, obtaining historical key characteristic parameters according to the historical fault hidden danger discharge current signal, and obtaining historical key characteristic vectors according to the key characteristic parameters.

[0085] The historical key characteristic parameter may refer to an indicator reflecting the signal characteristics extracted from the historical fault hidden danger discharge current signal.

[0086] The historical key feature vector may refer to a vector composed of multiple historical key feature parameters.

[0087] Step S306: Perform cluster analysis based on each historical key feature vector to obtain clustering results corresponding to a preset number of clusters.

[0088] Among them, cluster analysis can refer to dividing the data set into several categories so that the data points in the same category are as similar as possible, and the differences between data points in different categories are as large as possible, so as to classify and manage the data. The clustering algorithms used may include K-Means clustering algorithm, hierarchical clustering algorithm, DBSCAN clustering algorithm, etc.

[0089] Among them, the preset number of clusters may refer to the number of cluster categories that are pre-set to be identified in the cluster analysis. In this embodiment, it may be the corresponding preset number of cluster categories determined according to the number of pre-assessed safety hazard types. For example, if the number of safety hazard types is 6, then the corresponding preset number of clusters can also be set to 6.

[0090] Exemplarily, the number of clusters is preset to K, and the server performs cluster analysis on each historical key feature vector to obtain clustering results of K categories.

[0091] Step S308: According to the clustering result, the average feature vector corresponding to the cluster is obtained, and the average feature vector is used as the initial cluster center corresponding to the cluster.

[0092] The clustering result may refer to the data classification result after the analysis by the clustering algorithm, that is, the number of clusters classified and the data of each cluster.

[0093] The average eigenvector may refer to the average value of the eigenvectors of all data in each cluster, which is used to characterize the characteristics of the cluster and serves as the initial cluster center.

[0094] Specifically, the server calculates the average feature vector corresponding to each cluster according to each cluster in the clustering result and the historical key feature vector in each cluster, and uses the average feature vector as the initial cluster center corresponding to the cluster.

[0095] In this embodiment, by clustering the historical fault hidden danger discharge current signals of the signal acquisition terminal, the effective features of the discharge current signals of different hidden danger types can be extracted, and then the initial cluster center corresponding to each hidden danger type can be accurately obtained, thereby improving the accuracy of subsequent identification of new signal hidden danger types through the initial cluster center.

[0096] In an exemplary embodiment, the method for identifying hidden danger signals of power transmission lines further includes: updating the average feature vector corresponding to the target initial clustering center according to the multidimensional feature vector corresponding to the discharge current signal to be identified, to obtain an updated target initial clustering center.

[0097] Exemplarily, when the server obtains the hidden danger identification result corresponding to the discharge current signal to be identified, that is, the multidimensional feature vector A corresponding to the discharge current signal to be identified belongs to the target initial clustering center a, the server can put the multidimensional feature vector A corresponding to the discharge current signal to be identified into the target initial clustering center a, and then recalculate all feature vectors in the target initial clustering center a to obtain a new average feature vector, and finally use the new average feature vector as the updated target initial clustering center a.

[0098] In this embodiment, the average feature vector corresponding to the target initial clustering center is updated through the multidimensional feature vector corresponding to the discharge current signal to be identified, and the updated target initial clustering center is obtained. The initial clustering center can be continuously learned and improved with the new data in actual operation, so as to maintain the effectiveness and accuracy of the clustering model, and improve the reliability of the transmission line hidden danger signal identification process.

[0099] In an exemplary embodiment, the key characteristic parameters include discharge frequency, pulse amplitude, pulse width and target frequency; the above method may also include:

[0100] Step S11, generating a characteristic radar chart of the discharge current signal to be identified according to the discharge frequency, pulse amplitude, pulse width and target frequency.

[0101] The target frequency may refer to the frequency extracted after the spectrum analysis of the discharge current signal to be identified.

[0102] Specifically, the server takes the parameter values ​​of the discharge frequency, pulse amplitude, pulse width and target frequency as the edges of the radar chart, and generates a characteristic radar chart of the discharge current signal to be identified.

[0103] Step S22, sending the characteristic radar map and the hidden danger identification result to the feedback terminal, and displaying the characteristic radar map and the hidden danger identification result through the feedback terminal.

[0104] The feedback terminal may refer to a terminal used by relevant technical personnel.

[0105] Specifically, the server sends the characteristic radar map and the hidden danger identification result to the feedback terminal, and displays the characteristic radar map and the hidden danger identification result through the feedback terminal, so that the technical personnel can judge and analyze the characteristic radar map and the hidden danger identification result.

[0106] In this embodiment, by combining key characteristic parameters such as discharge frequency, pulse amplitude, pulse width and target frequency, a characteristic radar chart is generated, which can comprehensively describe the characteristics of the discharge current signal to be identified. By sending the characteristic radar chart and the hidden danger identification results to the feedback terminal, the technicians using the feedback terminal can intuitively see the specific numerical performance through the characteristic radar chart, thereby assisting the technicians to make quick and efficient judgments on the hidden danger identification results.

[0107] In an exemplary embodiment, after sending the characteristic radar map and the hidden danger identification result to the feedback terminal, the following steps may also be included:

[0108] Step S33, obtaining update information returned by the feedback terminal for the hidden danger identification result;

[0109] Step S44, determining the actual hidden danger type after the update according to the update information;

[0110] Step S55: updating the initial cluster center corresponding to the actual hidden danger type according to the multi-dimensional feature vector.

[0111] The update information may refer to information on update operations performed on the hidden danger identification results by a technician using the feedback terminal.

[0112] For example, after checking the characteristic radar chart and the hidden danger identification results, the technician determines that there is an error in the hidden danger identification result based on the characteristic radar chart, so the hidden danger type A in the hidden danger identification result is modified to hidden danger type B, and then the modified hidden danger type B is sent to the server. The server obtains the update information returned by the feedback terminal, and determines from the update information that the actual hidden danger type after the update is hidden danger type B, and then updates the initial cluster center corresponding to hidden danger type B based on the multi-dimensional feature vector corresponding to the discharge current signal to be identified.

[0113] In this embodiment, by obtaining the update information returned by the feedback terminal, the system can continuously adjust its model parameters (such as the initial cluster center) according to the actual situation, which can improve the accuracy of hidden danger identification in the future.

[0114] In an exemplary embodiment, the step of acquiring the target frequency may specifically include:

[0115] Step S61, obtaining a spectrum analysis result of the discharge current signal to be identified, obtaining each peak amplitude from the spectrum analysis result, and sorting each peak amplitude in descending order to obtain a peak amplitude sorting result.

[0116] Step S62, according to the peak amplitude sorting result, determine the target peak amplitudes of the first preset number, obtain the peak center frequencies corresponding to the target peak amplitudes, and use the peak center frequencies as the target frequencies.

[0117] The spectrum analysis result may refer to the result obtained after Fourier transform or other frequency domain analysis methods are performed on the discharge current signal to be identified, which shows the energy distribution of the signal at different frequencies. Spectrum analysis can help identify the main frequency components in the signal. In the spectrum diagram of the spectrum analysis result, each frequency point has a corresponding amplitude (or intensity), indicating the size of the frequency component. The peak refers to the local maximum value among these amplitudes, which usually corresponds to the main frequency component of the signal.

[0118] The peak center frequency may refer to the frequency corresponding to the position of the peak in the spectrum diagram.

[0119] Specifically, the server obtains the spectrum analysis result of the discharge current signal to be identified after frequency domain analysis, obtains the amplitude of each peak from the spectrum diagram of the spectrum analysis result, and sorts the peak amplitudes in descending order to obtain the peak amplitude sorting result, and then determines the target peak amplitudes of the first preset number in the sorting result according to the peak amplitude sorting result. For example, the preset number is 5, that is, the first 5 peak amplitudes in the sorting result are determined as the target peak amplitudes, that is, the largest 5 peak amplitudes among the peak amplitudes are obtained as the target peak amplitudes; then, the peak center frequencies corresponding to these target peak amplitudes are obtained through the spectrum diagram, and these peak center frequencies are used as target frequencies.

[0120] In this embodiment, by carefully analyzing the frequency spectrum of the discharge current signal to be identified, the main frequency components in the signal can be accurately extracted, the characteristics of the discharge current signal can be more accurately characterized, and the accuracy of subsequent hidden danger identification can be improved through more precise feature extraction.

[0121] In another exemplary embodiment, a method for identifying hidden danger signals of transmission lines is provided. The key features of the discharge signals of overhead transmission lines are extracted to form a fingerprint of typical hidden danger types, and a clustering algorithm is used to quickly classify and identify newly emerging discharge signals. This embodiment can be implemented through a signal acquisition module, a data preprocessing module, a hidden danger type analysis module and a hidden danger warning module.

[0122] This embodiment focuses on the discharge current signal accompanying the hidden danger process, so the signal acquisition module (i.e., the signal acquisition terminal) needs to first collect the traveling wave current signal on the overhead transmission line. Since the hidden danger discharge signal has the characteristics of small amplitude and high frequency, the signal acquisition module should have high accuracy and a wide frequency range, and should be distributed and installed at equal intervals on each section of the overhead line to prevent the attenuation and distortion of the hidden danger current signal during long-distance transmission.

[0123] The data preprocessing module mainly realizes the preprocessing of the discharge signal. The data processing module first performs denoising, smoothing, normalization and other operations on the original signal to eliminate the interference of environmental noise and other irrelevant signals, improve the quality of the signal, so as to more accurately reflect the actual discharge situation of the line, and provide a more reliable basis for subsequent feature extraction and identification; thereafter, the data processing module will extract key feature parameters from the preprocessed signal, which include but are not limited to the amplitude, frequency, duration, energy distribution, phase information, etc. of the discharge signal, and all the extracted feature parameters will be organized into a multidimensional vector as the fingerprint feature of the corresponding discharge signal.

[0124] The fingerprint features of typical hidden danger types need to be formed in advance through data set training. The data set used for training is preferably from the real data of the corresponding signal acquisition device deployment location to ensure that the training results match the actual situation of the location. By extracting and sorting the feature parameters of a large amount of discharge signal data of each hidden danger type, the typical multi-dimensional feature parameter vector of each hidden danger type is obtained as the basis for completing real-time discharge signal monitoring and hidden danger type identification at this location in the future.

[0125] The clustering algorithm uses known data for cluster analysis. After generating the category center point, the multidimensional vector of the new data is compared with various typical data, and then the nearest category is selected to achieve type determination. The advantage of this algorithm is that it can automatically complete effective classification without supervision. Common clustering algorithms include K-Means clustering algorithm, hierarchical clustering algorithm and DBSCAN clustering algorithm, etc. Its application logic includes the following process:

[0126] (1) Determination of the initial cluster center: The system first needs to perform cluster analysis on the existing discharge signal data and classify similar signals into the same category. These categories correspond to different types of hidden dangers. The average feature vector of each type of signal is regarded as the "fingerprint feature" of the category and serves as the initial cluster center.

[0127] (2) Classification of new signals: For each newly generated discharge signal, the system first extracts its feature vector and then calculates the distance between the vector and each cluster center. The system classifies the signal into the hidden danger type corresponding to the cluster center closest to it. This process can quickly identify the potential hidden danger type of the signal.

[0128] (3) Clustering result update: As time goes by and more data is accumulated, the system will continuously update and optimize the cluster center to better reflect the actual situation in the current operating environment. This dynamic adjustment mechanism ensures that the recognition ability of the clustering algorithm can be continuously improved as the environment and potential danger types change.

[0129] Combined with the characteristic parameter range of typical hidden danger types and the clustering analysis algorithm, the hidden danger type analysis module will further process the characteristic parameter vector extracted from the discharge signal. Finally, the characteristic parameter vector of the discharge signal is compared with the characteristic parameter vector of the typical hidden danger type through the clustering algorithm, and the determination and classification are completed. At the same time, the hidden danger analysis module takes the parameters of each dimension of the multidimensional characteristic parameter as the edge, and intuitively presents the fingerprint characteristics of various typical hidden danger discharge signals in the form of radar charts, and outputs the hidden danger type of the measured discharge signal determined by the clustering analysis and its corresponding radar chart.

[0130] The hidden danger warning module transmits the output results of the hidden danger type analysis module and the location information of the hidden danger occurrence point for early warning, and then notifies the technical personnel to respond to the specific hidden danger situation at the specific location. At the same time, the technical personnel can feedback and correct the analysis results by judging the visual radar map and the on-site situation, and gradually optimize the accuracy of the identification results.

[0131] Through the implementation of the above technical solutions, the hidden danger signal identification and early warning of overhead lines can be realized, thereby improving the safety and stability of the power system. Through the real-time collection of discharge signal data by online monitoring equipment, it can analyze and process the discharge signal at the moment of generation. This real-time nature enables the system to capture the hidden danger signal in time, avoiding the hidden danger missed due to time delay in traditional inspections; at the same time, the use of automated feature extraction and cluster analysis methods can process a large amount of data in a short time and quickly identify the hidden danger type. Compared with the traditional inspection method, it reduces the probability of false alarms and missed alarms, and greatly improves the efficiency; not only that, by integrating the characteristic parameters of multiple hidden danger types, the system can comprehensively reflect the characteristic differences of different hidden danger types. This comprehensiveness enables the system to cover more types of hidden dangers; finally, the method covers the entire process from data acquisition, signal processing, feature extraction to hidden danger identification and early warning, forming a complete monitoring and early warning system, which can greatly reduce the frequency and severity of power failures, reduce the economic losses caused by maintenance and power outages, reduce the cost of manual inspections, and also improve the reliability and stability of the power system.

[0132] In an exemplary specific embodiment, the K-Means clustering algorithm was used to establish fingerprint characteristics of three typical hidden danger types, namely, vegetation overheight, bird damage, and insulator contamination, under simulated test conditions based on the simulated test data set, and the clustering algorithm was used to analyze and identify a single hidden danger discharge signal. The identification results were compared with the test conditions to verify the feasibility of the clustering algorithm and the accuracy of the identification results. The specific process is as follows:

[0133] The first step is to train the data set and establish the fingerprint feature reference of the discharge signal of typical hidden danger types. The simulation test platform was designed to conduct simulation tests at a voltage level of 35kV on the hidden dangers of vegetation overheight, bird damage and insulator contamination faced by real overhead transmission lines, and 120 discharge data of vegetation overheight, 88 discharge data of bird damage and 118 discharge data of insulator contamination were obtained as data sets.

[0134] For this example, the characteristic parameters selected are as follows (not limited to the following parameters, for example only):

[0135] 1) Discharge frequency: the number of times discharge occurs per unit time. The specific method is as follows:

[0136]

[0137] Where n is the number of high-frequency current pulses occurring within the measurement time, and T is the measurement time (s).

[0138] 2) Pulse amplitude: The amplitude of the discharge current signal. The maximum and minimum values ​​of the discharge signal amplitude of the same type of hidden dangers are taken to define the value range of the high-frequency current signal amplitude, which is of great significance for the fingerprint feature characterization of each type of hidden danger.

[0139] 3) Pulse width: the duration of a single discharge current signal.

[0140] 4) Dominant frequency (target frequency): Perform FFT analysis on the signal, focus on the high frequency part, and take the first three amplitude wave center frequencies above 1kHz (except for pollution hazards, the frequency of pollution hazard discharge signals is low) and with the largest amplitude as the dominant frequency of this group of data. These three frequency values ​​define the frequency distribution characteristics of the discharge signal corresponding to this hazard type, which is of great significance for the identification of hazards. As shown in Figure 4, it is a schematic diagram of the signal frequency distribution characteristics corresponding to a typical tree barrier (vegetation overheight) hazard; as shown in Figure 5, it is a schematic diagram of the signal frequency distribution characteristics corresponding to a typical bird damage hazard; as shown in Figure 6, it is a schematic diagram of the signal frequency distribution characteristics corresponding to a typical insulator pollution hazard; in Figures 4-6, FFT is fast Fourier transform, FFT Denoise is fast Fourier transform denoising, that is, using FFT technology to remove or reduce noise in the signal; Current / A means current / ampere, Amplitude means amplitude, Time / s means time / second, Frequency / Hz means frequency / Hz; WaveletDenoise means wavelet denoising, that is, using wavelet transform to denoise the signal.

[0141] The simulation test data of three typical hidden dangers, namely, high vegetation, bird damage and insulator contamination, are taken according to the above characteristic parameters, and the statistical results are shown in the following table:

[0142]

[0143] The three types of hidden danger fingerprint characteristics are intuitively represented by radar charts (where the maximum, average and minimum values ​​of the dominant frequencies are recorded as frequency one, frequency two and frequency three respectively). Figure 7 shows a typical tree obstacle hidden danger fingerprint radar chart, Figure 8 shows a typical bird damage hidden danger fingerprint radar chart, and Figure 9 shows a typical pollution hidden danger fingerprint radar chart.

[0144] Next, data preprocessing and feature parameter extraction are performed. The simulated experimental data of the insulator pollution hazard is taken as the newly collected discharge signal. After preprocessing, the above feature parameters are also taken. The results are shown in the following table:

[0145]

[0146] As shown in Figure 10, in order to take the simulated experimental data of the insulator pollution hidden danger as the radar chart of the newly collected discharge signal, from the radar chart, it can be preliminarily judged that the fingerprint characteristics of the discharge signal are closer to the type of insulator pollution hidden danger. Next, the K-Means clustering algorithm is used to analyze the above single discharge data. First, the selected seven feature parameters are sorted into a seven-dimensional vector, and the feature parameter vectors of the three known typical hidden danger types and the feature parameter vectors of the single discharge signal are input into the algorithm, and K-Means clustering is performed to obtain the classification results. In this example, the algorithm is implemented with the help of MATLAB. The program algorithm process may include: first define the known data characteristic parameter vector: A is the vegetation overheight hazard, B is the bird damage hazard, and C is the insulator pollution hazard; then combine the seven-dimensional vectors of all known things into a matrix; then define the seven-dimensional parameters of the new thing (discharge current signal to be identified); then combine the seven-dimensional vector of the new thing with the seven-dimensional vector of the known thing into a matrix for clustering; later specify the initial cluster center to control the clustering order, set the initial cluster center to the vector of the known thing, and the order is A, B, C; then perform K-Means clustering and specify the initial cluster center; then output the result, the index of the new thing in the matrix is ​​the last one, and then print the cluster number to which the new thing belongs; the cluster center can be displayed through MATLAB, and the cluster index of all things can also be displayed. Through the above algorithm process, the clustering result of the new thing can be obtained, that is, which cluster category the new thing belongs to, and the cluster index of all things can also be displayed.

[0147] The analysis results show that this single hidden danger discharge signal belongs to the type of hidden danger of insulator contamination, which is consistent with the actual experimental conditions. This is the end of the demonstration of this example.

[0148] In actual operation, after the recognition result is generated, the hidden danger warning module transmits the coordinates of the hidden danger location and the type of hidden danger to the relevant departments, and then the technical personnel respond to the warning and deal with the hidden danger, and feedback the recognition result at the same time. At this point, the recognition and warning of the hidden danger signal of the transmission line based on the fingerprint characteristics of the discharge signal is completed.

[0149] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0150] Based on the same inventive concept, the embodiment of the present application also provides a transmission line hidden danger signal identification device for implementing the transmission line hidden danger signal identification method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more transmission line hidden danger signal identification device embodiments provided below can refer to the limitations of the transmission line hidden danger signal identification method above, and will not be repeated here.

[0151] In an exemplary embodiment, as shown in FIG11 , a transmission line hidden danger signal identification device 900 is provided, comprising: a signal acquisition module 901, a feature vector acquisition module 902 and a hidden danger identification module 903, wherein:

[0152] The signal acquisition module 901 is used to acquire the discharge current signal to be identified of the transmission line by using the signal acquisition terminal; the signal acquisition terminal is distributedly arranged on the transmission line according to preset intervals;

[0153] A feature vector acquisition module 902 is used to obtain key feature parameters according to the discharge current signal to be identified, and obtain a multi-dimensional feature vector according to the key feature parameters;

[0154] The hidden danger identification module 903 is used to obtain the distance between the multidimensional feature vector and each initial cluster center; the initial cluster center is obtained based on the cluster analysis of the discharge current signal of the historical fault hidden danger; the initial cluster center corresponding to the minimum distance among the distances is used as the target initial cluster center, the hidden danger type corresponding to the target initial cluster center is obtained, and the hidden danger type is determined as the hidden danger identification result of the discharge current signal to be identified.

[0155] In an exemplary embodiment, the above-mentioned feature vector acquisition module 902 is also used to obtain the historical fault hidden danger discharge current signal of the signal acquisition terminal; obtain the historical key feature parameters according to the historical fault hidden danger discharge current signal, and obtain the historical key feature vector according to the key feature parameters; perform cluster analysis according to each historical key feature vector to obtain the clustering result corresponding to the preset number of clusters; according to the clustering result, obtain the average feature vector corresponding to the cluster, and use the average feature vector as the initial clustering center corresponding to the cluster.

[0156] In an exemplary embodiment, the above-mentioned transmission line hidden danger signal identification device also includes a cluster center updating module, which is used to update the average feature vector corresponding to the target initial cluster center according to the multidimensional feature vector corresponding to the discharge current signal to be identified, so as to obtain an updated target initial cluster center.

[0157] In an exemplary embodiment, the key characteristic parameters include discharge frequency, pulse amplitude, pulse width and target frequency; the transmission line hidden danger signal identification device also includes a display module, which is used to generate a characteristic radar map of the discharge current signal to be identified according to the discharge frequency, pulse amplitude, pulse width and target frequency; the characteristic radar map and the hidden danger identification result are sent to the feedback terminal, and the characteristic radar map and the hidden danger identification result are displayed through the feedback terminal.

[0158] In an exemplary embodiment, the cluster center update module is also used to obtain update information returned by the feedback terminal for the hidden danger identification result; determine the updated actual hidden danger type according to the update information; and update the initial cluster center corresponding to the actual hidden danger type according to the multidimensional feature vector.

[0159] In an exemplary embodiment, the feature vector acquisition module 902 is also used to obtain the spectrum analysis results of the discharge current signal to be identified, obtain each peak amplitude from the spectrum analysis results, and sort each peak amplitude in descending order to obtain a peak amplitude sorting result; according to the peak amplitude sorting result, determine the target peak amplitudes that are ranked in the front preset number, obtain the peak center frequency corresponding to the target peak amplitude, and use the peak center frequency as the target frequency.

[0160] Each module in the above-mentioned power transmission line hidden danger signal identification device can be implemented in whole or in part by software, hardware and their combination. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0161] In an exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in FIG12. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for identifying hidden danger signals of a power transmission line is implemented.

[0162] Those skilled in the art will understand that the structure shown in FIG. 12 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0163] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0164] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0165] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0166] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0167] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0168] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for identifying hidden danger signals of power transmission lines, characterized in that: The method comprises: The signal acquisition terminal is used to obtain the discharge current signal to be identified of the transmission line; the signal acquisition terminal is distributedly arranged on the transmission line according to preset intervals; Obtain key characteristic parameters according to the discharge current signal to be identified, and obtain a multi-dimensional characteristic vector according to the key characteristic parameters; Obtaining the distance between the multidimensional feature vector and each initial cluster center; the initial cluster center is obtained based on cluster analysis of discharge current signals of historical fault hazards; An initial cluster center corresponding to the minimum distance among the distances is used as a target initial cluster center, a hidden danger type corresponding to the target initial cluster center is obtained, and the hidden danger type is determined as a hidden danger identification result of the discharge current signal to be identified.

2. The method according to claim 1, characterized in that: The step of obtaining the initial cluster center includes: Acquire the historical fault hidden danger discharge current signal of the signal acquisition terminal; Obtain historical key characteristic parameters according to the historical fault hidden danger discharge current signal, and obtain historical key characteristic vectors according to the key characteristic parameters; Performing cluster analysis based on each of the historical key feature vectors to obtain clustering results corresponding to a preset number of clusters; According to the clustering result, an average feature vector corresponding to the cluster is obtained, and the average feature vector is used as an initial clustering center corresponding to the cluster.

3. The method according to claim 2, characterized in that The method further comprises: According to the multidimensional feature vector corresponding to the discharge current signal to be identified, the average feature vector corresponding to the target initial cluster center is updated to obtain an updated target initial cluster center.

4. The method according to claim 1, characterized in that: The key characteristic parameters include discharge frequency, pulse amplitude, pulse width and target frequency; the method also includes: generating a characteristic radar chart of the discharge current signal to be identified according to the discharge frequency, the pulse amplitude, the pulse width and the target frequency; The characteristic radar chart and the hidden danger identification result are sent to a feedback terminal, and the characteristic radar chart and the hidden danger identification result are displayed through the feedback terminal.

5. The method according to claim 4, characterized in that After sending the characteristic radar map and the hidden danger identification result to the feedback terminal, the method further includes: Obtaining update information returned by the feedback terminal for the hidden danger identification result; Determine the actual hidden danger type after the update according to the update information; The initial cluster center corresponding to the actual hidden danger type is updated according to the multi-dimensional feature vector.

6. The method according to claim 4, characterized in that The step of acquiring the target frequency comprises: Obtaining a spectrum analysis result of the discharge current signal to be identified, obtaining each peak amplitude from the spectrum analysis result, and sorting each peak amplitude in descending order to obtain a peak amplitude sorting result; According to the peak amplitude sorting result, a preset number of target peak amplitudes are determined, the peak center frequencies corresponding to the target peak amplitudes are obtained, and the peak center frequencies are used as the target frequencies.

7. A transmission line hidden danger signal identification device, characterized in that: The device comprises: A signal acquisition module, used to acquire the discharge current signal to be identified of the transmission line by using a signal acquisition terminal; the signal acquisition terminal is distributedly arranged on the transmission line according to preset intervals; A feature vector acquisition module, used to obtain key feature parameters according to the discharge current signal to be identified, and obtain a multi-dimensional feature vector according to the key feature parameters; A hidden danger identification module is used to obtain the distance between the multidimensional feature vector and each initial cluster center; the initial cluster center is obtained based on the cluster analysis of the discharge current signal of the historical fault hidden danger; the initial cluster center corresponding to the minimum distance among the distances is used as the target initial cluster center, the hidden danger type corresponding to the target initial cluster center is obtained, and the hidden danger type is determined as the hidden danger identification result of the discharge current signal to be identified.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images