Power transmission line icing monitoring data set preprocessing method, device, equipment and medium

Abstract

The invention relates to the technical field of power grid safety, and discloses a power transmission line icing monitoring data set preprocessing method and device, equipment and a medium. Comprising the following steps: acquiring an original icing monitoring data set containing a plurality of monitoring parameters; calculating a correlation coefficient between each monitoring parameter and the target icing state parameter based on the original icing monitoring data set, and screening out key parameters from the original data set according to the correlation coefficient to form a correlation degree data set; wherein the correlation coefficients comprise a grey correlation coefficient, a Pearson correlation coefficient and a Spearman correlation coefficient; performing interpolation completion on the key parameter sequence with missing values in the association degree data set to obtain a complete data set; and performing normalization processing on the complete data set to generate a standardized data set. According to the method, the data availability and representativeness can be improved, so that each parameter can be accurately and consistently input to a subsequent analysis module, and reliable data support is provided for icing risk assessment, prediction and early warning and intelligent decision making.

Description

Technical Field

[0001] This disclosure relates to the field of power grid safety technology, and more specifically, to a method, apparatus, equipment, and medium for preprocessing data sets of transmission line icing monitoring. Background Technology

[0002] Icing is a natural phenomenon where ice forms or accumulates on the surface of power transmission lines under specific meteorological conditions. In severe cases, it can cause accidents such as mechanical overload, flashover, galloping, and even tower collapse, posing a serious threat to the safe and stable operation of the power grid. To promptly grasp the icing status, predict its development trend, and take effective de-icing or ice removal measures, it is essential to monitor icing-related parameters in real-time or near real-time, including diverse information such as ambient temperature and humidity, wind speed and direction, conductor tension, tilt angle, and images and videos. With the widespread application of sensing technology and the Internet of Things (IoT), the scale of data collected by monitoring systems has increased dramatically, forming massive, high-frequency, and multi-dimensional icing monitoring datasets.

[0003] However, raw icing monitoring data generally suffers from problems such as noise interference, missing information, inconsistent dimensions, and imbalanced samples, which directly affect the accuracy of subsequent key analyses such as feature extraction, state identification, risk warning, and ice melting decision-making. Therefore, data preprocessing has become an indispensable basic step in icing state analysis, and its quality directly determines the model performance and the reliability of the analysis results. Summary of the Invention

[0004] In view of the above situation, this application provides a method, apparatus, equipment and medium for preprocessing transmission line icing monitoring datasets, which aims to solve the above problems or at least partially solve the above problems.

[0005] In a first aspect, embodiments of this application provide a method for preprocessing a transmission line icing monitoring dataset, the method comprising: Obtain the raw icing monitoring dataset containing multiple monitoring parameters; Based on the original icing monitoring dataset, the correlation coefficients between each monitoring parameter and the target icing state parameters are calculated, and key parameters are selected from the original dataset according to the correlation coefficients to form a correlation degree dataset; wherein, the correlation coefficients include grey correlation coefficient, Pearson correlation coefficient and Spearman correlation coefficient; The key parameter sequences with missing values ​​in the correlation dataset are interpolated to complete the dataset; The complete dataset is normalized to generate a standardized dataset.

[0006] Secondly, embodiments of this application also provide a preprocessing device for transmission line icing monitoring datasets, the device comprising: The acquisition module is used to acquire the raw icing monitoring dataset containing multiple monitoring parameters; The calculation module is used to calculate the correlation coefficient between each monitoring parameter and the target icing state parameter based on the original icing monitoring dataset; A filtering module is used to filter key parameters from the original dataset based on the correlation coefficients to form a correlation degree dataset; wherein the correlation coefficients include the grey correlation coefficient, the Pearson correlation coefficient, and the Spearman correlation coefficient. The interpolation module is used to interpolate and complete the key parameter sequences with missing values ​​in the correlation degree dataset to obtain a complete dataset. The normalization module is used to normalize the complete dataset to generate a standardized dataset.

[0007] Thirdly, embodiments of this application also provide an electronic device, including: a processor; and a memory arranged to store computer-executable instructions, which, when executed, cause the processor to perform the steps described in the first aspect.

[0008] Fourthly, embodiments of this application also provide a computer-readable storage medium that stores one or more programs, which, when executed by an electronic device including multiple applications, cause the electronic device to perform the steps described in the first aspect.

[0009] The above-mentioned at least one technical solution adopted in the embodiments of this application can achieve the following beneficial effects: by sequentially executing the steps of obtaining the original multi-parameter dataset of transmission line icing monitoring, calculating the grey correlation coefficient, Pearson correlation coefficient and Spearman correlation coefficient between each monitoring parameter and the target icing state parameter and screening key parameters to form a correlation degree dataset, completing the missing data in the correlation degree dataset to obtain a complete dataset, and normalizing the complete dataset to generate a standardized dataset, firstly, the synergistic analysis of the three correlation coefficients can accurately identify and remove redundant and low-correlation parameters in the original data, effectively solving the problem of subsequent analysis interference caused by the large amount and complexity of the original icing monitoring data and the unclear core features, reducing the computing resources occupied by invalid data, and significantly improving data processing efficiency; secondly, by interpolation to complete the data... Missing data segments caused by sensor failures or communication interruptions can ensure the continuity and integrity of key parameter sequences in the time dimension, preventing missing values ​​from damaging the data structure and affecting the reliability of time series analysis models. Furthermore, normalization processing eliminates differences in the dimensions and numerical ranges between different parameters, preventing the problem of some variables dominating the analysis results in subsequent modeling due to scale imbalance of dependent variables, thus ensuring data objectivity and the accuracy of subsequent analysis. The overall process forms a logically rigorous and coherent systematic preprocessing system, overcoming the shortcomings of traditional preprocessing methods that are fragmented and lack specificity. The resulting standardized dataset can provide high-quality and highly available data support for subsequent icing state analysis and decision modeling, effectively improving the power grid's early warning and prevention capabilities during ice disasters and ensuring the safe and stable operation of transmission lines. Attached Figure Description

[0010] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 A flowchart illustrating the preprocessing method for transmission line icing monitoring datasets provided in an embodiment of this application is shown. Figure 2 The diagram shows micrometeorological data of the icing monitoring system provided in this application embodiment; Figure 3 The figure shown is a diagram of the micro-meteorological data interpolation processing results provided in the embodiments of this application; Figure 4 This paper shows a graph illustrating the data normalization results provided in an embodiment of this application. Figure 5 This paper shows a structural diagram of the preprocessing device for transmission line icing monitoring datasets provided in an embodiment of this application. Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown. Detailed Implementation

[0011] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0012] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such use can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the term "comprising" and its variations should be interpreted as open-ended terms meaning "including but not limited to."

[0013] The present application will now be described in detail through specific embodiments.

[0014] Figure 1 This document illustrates a flowchart of a preprocessing method for transmission line icing monitoring datasets provided in an embodiment of this application. Figure 1 It can be seen that this application includes at least steps S101-S103: Step S101: Obtain the original icing monitoring dataset containing multiple monitoring parameters.

[0015] In some embodiments, the monitoring parameters include micrometeorological parameters and conductor condition parameters. Micrometeorological parameters reflect the meteorological conditions of the local environment where the line is located and are external driving factors for icing formation and development. They include at least one of temperature, humidity, wind speed, wind direction, air pressure, solar radiation intensity, rainfall intensity, and precipitation intensity. Conductor condition parameters directly reflect the physical response and load state of the conductor itself and are a direct manifestation of the icing effect. They include at least one of conductor tension and inclination angle.

[0016] In some embodiments, "raw" in the raw icing monitoring dataset specifically refers to the data state before entering the preprocessing flow of this invention. Typical characteristics include: Missing values: blank data records due to sensor malfunction, communication interruption, or power problems. Noise and outliers: errors or non-physically meaningful spikes caused by electromagnetic interference, sensor drift, or transient malfunctions. Inconsistent units: different units for each parameter, with vastly different numerical ranges. Unknown redundancy and correlation among parameters: all collected parameters are included, but which parameters are strongly correlated with the core target of icing status, and which are weakly correlated or redundant, have not yet been quantitatively analyzed.

[0017] The purpose of this step is to provide a complete, authentic, and unmodified data input for subsequent systematic preprocessing. It ensures that the preprocessing workflow starts from the most realistic data conditions to solve problems encountered in actual engineering. The output of this step is a set of raw multi-parameter time series matrices to be processed, where rows typically represent time points and columns represent different monitoring parameters. The matrix may contain null values, outliers, and values ​​with different scales.

[0018] Step S102: Based on the original icing monitoring dataset, calculate the correlation coefficient between each monitoring parameter and the target icing state parameter, and select key parameters from the original dataset according to the correlation coefficient to form a correlation degree dataset.

[0019] The correlation coefficients include the grey relational coefficient, the Pearson correlation coefficient, and the Spearman correlation coefficient.

[0020] 1. The grey relational coefficient is an important concept in grey system theory, used to measure the relative relationship between different variables. It primarily describes the similarity or correlation between each factor in a system and a principal factor. It determines the degree of correlation by calculating the similarity of the changing trends of each factor relative to a reference sequence.

[0021] Specifically, the monitoring coefficients are normalized; the absolute difference between the normalized monitoring coefficients and the target icing state parameters is calculated; and the grey relational coefficient is calculated based on the absolute difference and the resolution coefficient. In some embodiments, the grey relational degree can also be calculated based on the grey relational coefficient, which is a further generalization of the grey relational coefficient.

[0022] Data normalization: In the formula, Indicates the first The factor in the first The value at each time point (or sample point). This represents the normalized value. Calculate the correlation coefficient: ; In the formula, Indicates the first The absolute difference between each factor and the reference series, This represents the resolution coefficient, used to adjust the sensitivity of the correlation coefficient, and its range is generally [0,1]. , This represents the minimum and maximum values ​​among all differences. Calculate the grey relational degree: In the formula, The grey relational degree represents a certain feature, ranging from [0,1]. The larger the value, the stronger the relational degree. Indicates the number of sample points.

[0023] Compared to traditional mathematical statistical analysis methods, such as principal component analysis and factor analysis, grey relational analysis is more adaptable in terms of sample size and sample regularity. This method not only requires less computation but also avoids inconsistencies between quantitative and qualitative analysis results, thus compensating for the shortcomings of using mathematical statistics methods in system analysis.

[0024] 2. The Pearson correlation coefficient is a standardized indicator that measures the degree of linear correlation between two continuous variables, with a value range of [-1, 1]. Essentially, it quantifies the linear covariance trend between variables by normalizing the covariance and standard deviation. r=1: Perfectly positive linear correlation (such as linear growth of height and weight). r=-1: Perfectly negative linear correlation (such as the inverse linear relationship between temperature and heating costs). r=0: No linear correlation (but there may be nonlinear relationships, such as U-shaped curves).

[0025] Specifically, for sample data X=(x 1 , x 2 ,…, x n ), Y=(y 1 , y 2 ,…, y n ) The Pearson correlation coefficient is calculated as follows:

[0026] , This is the sample mean.

[0027] 3. The Spearman correlation coefficient measures monotonicity (i.e., the tendency of one variable to increase or decrease with the other, not limited to linearity) by the rank (or ordinal position) of the variables. The range is also [-1, 1], but it is based on the rank rather than the original value. ρ=1: Completely monotonically increasing (e.g., exam ranking is positively correlated with study time); ρ=-1: Completely monotonically decreasing (e.g., the price of a product is negatively correlated with its sales volume); ρ=0: No monotonic relationship (but there may be nonlinear correlation).

[0028] Calculation method Unrepeated ranks: Pearson correlation coefficients are calculated directly for the ranks; For repeated ranks: a modified formula is used to consider the average rank of repeated ranks.

[0029] Furthermore, after calculating the three coefficients, key parameter subsets are selected based on the grey relational coefficient, Pearson correlation coefficient, and Spearman correlation coefficient, respectively, according to the preset correlation threshold; the intersection of the three key parameter subsets constitutes the correlation degree dataset.

[0030] Specifically, scientific correlation thresholds are set for the three types of coefficients (e.g., grey correlation coefficient > 0.6, Pearson correlation coefficient > 0.5, Spearman correlation coefficient > 0.5). The thresholds can be determined based on domain knowledge or historical data statistics.

[0031] Generate subsets: Set A = {parameter | grey relational coefficient of the parameter > threshold α} Set B = {parameter | Pearson correlation coefficient of the parameter > threshold β} Set C = {parameters | Spearman correlation coefficient of the parameter > threshold γ} The core set is formed by taking the intersection of the sets: the degree of association dataset D = A∩B∩C The advantage of the intersection strategy in this step is that a parameter is only identified as a key parameter if it exhibits a consistent and significant correlation across the trend, linearity, and monotonicity dimensions. This is an extremely rigorous screening criterion that can exclude parameters with accidental or spurious correlations to the greatest extent possible, ensuring high confidence and explanatory power for the selected parameters. For example, a parameter may show a transient Gaussian-Pearlman correlation with the target sequence due to accidental fluctuations (passing the monotonicity test), but its trend (grey correlation) and linear relationship (Pearson) are weak, and it will be excluded by this method.

[0032] In addition to taking the intersection to form a dataset of correlation degree, other methods such as union, weighted comprehensive scoring, majority decision mechanism, or segmented screening mechanism can also be adopted.

[0033] For example, the union method involves selecting from the original dataset at least one of the three correlation coefficients (grey correlation coefficient, Pearson correlation coefficient, and Spearman correlation coefficient) whose value reaches or exceeds a preset threshold, and using the set of these parameters as the correlation degree dataset. This strategy relaxes the selection criteria and can retain potentially correlated features to the greatest extent.

[0034] For example, a weighted scoring mechanism is used: weights are assigned to the grey relational coefficient, Pearson correlation coefficient, and Spearman correlation coefficient, and a weighted comprehensive correlation score is calculated for each monitored parameter. Then, all parameters are sorted according to their comprehensive scores, and parameters with scores exceeding a preset total threshold, or the top N parameters, are selected to form a correlation degree dataset. This method incorporates domain knowledge or optimization objectives. For instance, if linear physical relationships are considered most reliable, the Pearson coefficient can be given a higher weight; if the synchronicity of changing trends is more important, the weight of the grey relational coefficient can be increased, achieving a balanced consideration of correlations across different dimensions.

[0035] For example, the majority decision mechanism: For each monitored parameter, determine the number of times it reaches a preset threshold among the three correlation coefficients. Parameters with at least two coefficients reaching the threshold are selected to form a correlation degree dataset. This approach requires a parameter to be significant on at least two different correlation measures, avoiding the randomness that may arise from a single measure, and is more tolerant than the triple intersection, improving the robustness of the selection results while maintaining a good parameter recall rate.

[0036] Another example is the phased screening method, which involves multiple rounds of screening in a sequential manner. For instance, a computationally efficient correlation coefficient (such as the Pearson coefficient) is first used for rapid initial screening to eliminate obviously irrelevant parameters. Then, on the narrowed candidate set, two other correlation coefficients are calculated for finer screening to ultimately determine the key parameters. This method balances computational efficiency and screening accuracy. It is particularly suitable for situations with extremely high initial parameter dimensionality, significantly reducing the computational overhead of subsequent, more computationally intensive association analyses (such as grey relational analysis). It is a practical, engineering optimization-oriented strategy.

[0037] Step S103: Interpolate and complete the key parameter sequences with missing values ​​in the correlation dataset to obtain the complete dataset.

[0038] Specifically, for the key data sequences after screening, missing data points or segments caused by sensor failure or transmission interruption are identified, and the nearest neighbor interpolation method is used to reconstruct these missing parts.

[0039] Data loss is typically identified automatically by the system through one or more of the following methods: packet loss flags: error flags returned by the communication protocol; discontinuous timestamps: in fixed-frequency acquisition, the time interval between adjacent data points is much longer than the set period; numerical domain anomalies: receiving specific invalid values ​​indicating sensor malfunction. Missing patterns include, for example, random single-point missing data due to brief interference, and continuous missing segments caused by prolonged sensor malfunction or communication interruption.

[0040] The reason for choosing the nearest neighbor interpolation method for interpolation completion is that within a short period of relatively stable changes in meteorological and state parameters, the values ​​at adjacent times are usually closest to the true values. Compared to complex model interpolation, the nearest neighbor method assumes that the nearest data point is the most reliable, which is more in line with engineering intuition and less likely to introduce non-physical oscillations or trends. Furthermore, the algorithm is simple, requiring only the location of the nearest valid data before and after the missing point, resulting in minimal computational overhead, making it suitable for real-time or near-real-time preprocessing needs of massive monitoring stations.

[0041] Specifically, the key parameter sequence is scanned chronologically to identify data points with empty or invalid values. On the time axis before and after these empty or invalid data points, the nearest valid data point is found. The valid data point on the shorter time distance side of the time axis is selected as the nearest valid value, and this process continues until all identified missing points in the sequence are filled. If the missing value occurs at the beginning or end of the sequence, the only available nearest valid value is used directly.

[0042] This step ensures the continuity and integrity of the data over time, laying the foundation for time series analysis models that rely on complete sequences.

[0043] Step S104: Normalize the complete dataset to generate a standardized dataset.

[0044] In some embodiments, the normalization process employs the Min-Max standardization method to map parameter values ​​to the [0,1] interval, or the Z-Score standardization method to convert the parameters into standard normal distribution data with a mean of 0 and a standard deviation of 1.

[0045] In this step, the interpolated, multi-source data with different dimensions and numerical ranges are normalized. By mapping them to a unified standard interval, the weight imbalance caused by differences in the dimensions and scales of the dependent variables is eliminated. After this step, all parameters will have an equal starting point in subsequent machine learning or statistical models, preventing a single variable from dominating model training due to its larger value, thereby ensuring the objectivity and accuracy of the analysis results.

[0046] from Figure 1As shown in the diagram, this application overcomes the shortcomings of traditional methods, such as fragmented steps and inconsistent processing, by integrating data association analysis, data filtering, interpolation completion, and normalization into a coherent preprocessing workflow. Introducing three association analysis techniques in the early stages of preprocessing provides a basis for data filtering, enhancing the scientific rigor and interpretability of the method and avoiding the computational burden and noise interference caused by blindly retaining all data. Through a combination of interpolation and normalization, the authenticity of the data information is ensured while significantly improving the quality and usability of the dataset, enabling it to be safely and reliably input into subsequent state identification, risk prediction, or intelligent decision-making systems.

[0047] The technical solution of this application will be further described in detail below with reference to specific embodiments.

[0048] The various meteorological sensors on the monitoring terminal collect micro-meteorological data approximately every 10 minutes, such as... Figure 2 As shown.

[0049] Grey relational analysis was used to calculate the correlation degree of these characteristic parameters, resulting in a simplified model of transmission line icing data. The correlation degree of five characteristic parameters—temperature, humidity, wind speed, air pressure, and solar radiation intensity—was greater than 0.6. The other four characteristic vectors had low correlation with transmission line icing formation; therefore, these five were considered weakly correlated and redundant vectors and were not considered. The specific correlation degrees of micrometeorological factors are shown in Table 1.

[0050] Table 1

[0051] To address the issue of missing data during sensor data acquisition, a nearest neighbor interpolation method is used to supplement the missing data to ensure data continuity and integrity. This method fully utilizes adjacent values ​​to the missing data for reasonable estimation and supplementation. The results are as follows: Figure 3 As shown.

[0052] Because the values ​​and units of the input variables in the dataset vary significantly, data normalization is necessary. Min-Max standardization is used, and the normalized data is as follows: Figure 4 As shown.

[0053] In summary, this application constructs a multi-level icing monitoring data preprocessing workflow centered on data quality and analysis orientation. Its core idea is not simply to stack existing data processing technologies, but rather to filter, repair, and standardize data through an organic and logically rigorous sequence, making it particularly suitable for complex scenarios with multiple parameters and strong coupling, such as icing state analysis.

[0054] This application emphasizes the irreversible execution sequence of several key steps and their synergistic effects. First, redundant parameters are eliminated through three types of data correlation analysis, and then key parameters are interpolated to complete them. This avoids wasting computational resources on useless or low-correlation missing data. Normalization on the complete data sequence more accurately reflects the global distribution of the data and prevents missing values ​​from interfering with the data scale. Each step precisely addresses the unique pain points of icing monitoring data: data correlation analysis solves the problem of abundant and complex data, making it difficult to choose the appropriate method; nearest neighbor interpolation addresses the problems of missing data and discontinuous sequences; and normalization addresses the problem of inconsistent parameter dimensions, which can lead to model deviations.

[0055] In some embodiments of this application, a preprocessing device for transmission line icing monitoring datasets is provided, which corresponds one-to-one with the preprocessing methods for transmission line icing monitoring datasets described in the above embodiments. For example... Figure 5 As shown, the preprocessing device for the transmission line icing monitoring dataset includes an acquisition module 101, a calculation module 102, a filtering module 103, an interpolation module 104, and a normalization module 105.

[0056] The acquisition module 101 is used to acquire the original icing monitoring dataset containing multiple monitoring parameters; Calculation module 102 is used to calculate the correlation coefficient between each monitoring parameter and the target icing state parameter based on the original icing monitoring dataset; The filtering module 103 is used to filter key parameters from the original dataset based on the correlation coefficients to form a correlation degree dataset; wherein the correlation coefficients include the grey correlation coefficient, the Pearson correlation coefficient, and the Spearman correlation coefficient. Interpolation module 104 is used to interpolate and complete the key parameter sequence with missing values ​​in the correlation degree dataset to obtain a complete dataset; The normalization module 105 is used to normalize the complete dataset to generate a standardized dataset.

[0057] In some embodiments of this application, in the above-described apparatus, the calculation module 102 is specifically used to normalize the monitoring coefficients; calculate the absolute difference between the normalized monitoring coefficients and the target icing state parameters; calculate the grey relational coefficient based on the absolute difference and the resolution coefficient; and calculate the grey relational degree based on the grey relational coefficient.

[0058] In some embodiments of this application, the Spearman correlation coefficient is calculated in the above-described apparatus as follows: when the monitored parameter has no repeating rank, the Pearson correlation coefficient of the rank is calculated; when the monitored parameter has repeating rank, the rank correlation coefficient is calculated using a modified formula.

[0059] In some embodiments of this application, in the above-described apparatus, the filtering module 103 is specifically used to filter out a subset of key parameters based on the grey relational coefficient, Pearson correlation coefficient and Spearman correlation coefficient according to a preset correlation threshold; and to take the intersection of the three subsets of key parameters to form the correlation degree dataset.

[0060] In some embodiments of this application, the interpolation in the above-described apparatus employs the nearest neighbor interpolation method.

[0061] In some embodiments of this application, in the above-described apparatus, the normalization process employs the Min-Max standardization method to map the parameter values ​​to the [0,1] interval, or employs the Z-Score standardization method to convert the parameters into standard normal distribution data with a mean of 0 and a standard deviation of 1.

[0062] In some embodiments of this application, in the above-described device, the monitoring parameters include micro-meteorological parameters and conductor status parameters; wherein, the micro-meteorological parameters include at least one of temperature, humidity, wind speed, wind direction, air pressure, solar radiation intensity, rainfall intensity, and precipitation intensity; and the conductor status parameters include at least one of conductor tension and inclination angle.

[0063] It should be noted that any of the above-mentioned transmission line icing monitoring dataset preprocessing devices can implement the aforementioned transmission line icing monitoring dataset preprocessing method one by one, which will not be elaborated here.

[0064] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown. Figure 6 As shown, at the hardware level, this electronic device includes a processor, and optionally also includes an internal bus, a network interface, and memory. The memory may include main memory, such as high-speed random-access memory (RAM), or it may include non-volatile memory, such as at least one disk drive. Of course, this electronic device may also include other hardware required for other business operations.

[0065] The processor, network interface, and memory can be interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 6 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0066] Memory is used to store programs. Specifically, programs may include program code, which includes computer operation instructions. Memory may include main memory and non-volatile memory, and provides instructions and data to the processor.

[0067] The processor reads the corresponding computer program from non-volatile memory into main memory and then runs it, forming a preprocessing device for the transmission line icing monitoring dataset at the logical level. The processor executes the program stored in memory and specifically performs the aforementioned methods.

[0068] The processor may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in the memory, and the processor reads the information in the memory and, in conjunction with its hardware, completes the steps of the above method.

[0069] This electronic device can execute the transmission line icing monitoring dataset preprocessing method provided in several embodiments of this application, and is implemented as a transmission line icing monitoring dataset preprocessing device. Figure 5 The functions of the embodiments shown are not described in detail here.

[0070] This application also proposes a computer-readable storage medium that stores one or more programs, the programs including instructions that, when executed by an electronic device including multiple applications, enable the electronic device to perform the transmission line icing monitoring dataset preprocessing method provided in several embodiments of this application.

[0071] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0072] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0073] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0074] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0075] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0076] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0077] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0078] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0079] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0080] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for preprocessing a data set for monitoring icing on power transmission lines, characterized in that, The method includes: Obtain the raw icing monitoring dataset containing multiple monitoring parameters; Based on the original icing monitoring dataset, the correlation coefficients between each monitoring parameter and the target icing state parameters are calculated, and key parameters are selected from the original dataset according to the correlation coefficients to form a correlation degree dataset; wherein, the correlation coefficients include grey correlation coefficient, Pearson correlation coefficient and Spearman correlation coefficient; The key parameter sequences with missing values ​​in the correlation dataset are interpolated to complete the dataset; The complete dataset is normalized to generate a standardized dataset.

2. The method according to claim 1, characterized in that, The calculation of the grey correlation coefficient between each monitoring coefficient and the target icing state parameter includes: The monitoring coefficients were normalized. The absolute difference between the monitoring coefficients after normalization and the target icing state parameters is calculated. The grey relational coefficient is calculated based on the absolute difference and the resolution coefficient. Calculate the grey relational degree based on the grey relational coefficient.

3. The method according to claim 1, characterized in that, The Spearman correlation coefficient is calculated as follows: when the monitored parameter has no repeating rank, the Pearson correlation coefficient of the rank is calculated; when the monitored parameter has repeating rank, the rank correlation coefficient is calculated using a modified formula.

4. The method according to claim 1, characterized in that, The step of filtering key parameters from the original dataset based on the correlation coefficient to form a correlation degree dataset includes: Based on the gray relational coefficient, Pearson correlation coefficient and Spearman correlation coefficient respectively, a subset of key parameters is selected according to a preset correlation threshold. The intersection of the three subsets of key parameters constitutes the correlation degree dataset.

5. The method according to claim 1, characterized in that, The interpolation method used is nearest neighbor interpolation.

6. The method according to claim 1, characterized in that, The normalization process employs the Min-Max standardization method to map parameter values ​​to the [0,1] interval, or the Z-Score standardization method to convert the parameters into standard normal distribution data with a mean of 0 and a standard deviation of 1.

7. The method according to any one of claims 1-6, characterized in that, The monitoring parameters include micrometeorological parameters and conductor status parameters; wherein, the micrometeorological parameters include at least one of temperature, humidity, wind speed, wind direction, air pressure, solar radiation intensity, rainfall intensity, and precipitation intensity; and the conductor status parameters include at least one of conductor tension and inclination angle.

8. A preprocessing device for transmission line icing monitoring datasets, characterized in that, The device includes: The acquisition module is used to acquire the raw icing monitoring dataset containing multiple monitoring parameters; The calculation module is used to calculate the correlation coefficient between each monitoring parameter and the target icing state parameter based on the original icing monitoring dataset; A filtering module is used to filter key parameters from the original dataset based on the correlation coefficients to form a correlation degree dataset; wherein the correlation coefficients include the grey correlation coefficient, the Pearson correlation coefficient, and the Spearman correlation coefficient. The interpolation module is used to interpolate and complete the key parameter sequences with missing values ​​in the correlation degree dataset to obtain a complete dataset. The normalization module is used to normalize the complete dataset to generate a standardized dataset.

9. An electronic device, comprising: processor; as well as A memory is configured to store computer-executable instructions, which, when executed, cause the processor to perform the steps of the transmission line icing monitoring dataset preprocessing method as described in any one of claims 1-7.

10. A computer-readable storage medium storing one or more programs that, when executed by an electronic device including a plurality of applications, cause the electronic device to perform the steps of the transmission line icing monitoring dataset preprocessing method as described in any one of claims 1-7.

Images