Cable running state evaluation method, apparatus, device, medium, and program product

Abstract

The application relates to a cable operation state evaluation method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: obtaining operation data of a cable, wherein the operation data comprises temperature data, current data and voltage data; pre-processing the operation data to obtain pre-processed operation data; determining component parameters associated with the cable core temperature according to the pre-processed operation data; performing correlation degree analysis on the component parameters to obtain a correlation degree feature matrix, which is used for evaluating the operation state of the cable. The method can improve the accuracy and efficiency of cable operation state judgment.

Description

Technical Field

[0001] This application relates to the field of cable operating condition assessment technology, and in particular to a cable operating condition assessment method, apparatus, computer equipment, storage medium and computer program product. Background Technology

[0002] With the rapid development of power grids, power cables are widely used in urban power transmission and distribution systems. Considering that most cables are laid underground, maintenance and emergency repairs are difficult. Therefore, online assessment of cable line operating status has become an important auxiliary means of cable maintenance. Cable core temperature is one of the key indicators of cable line operating status. If the cable core temperature exceeds the maximum allowable temperature for long-term operation, the insulation layer will be damaged, leading to line faults.

[0003] During the operation of a cable, various factors such as operating current, soil thermal resistance, air temperature, cable burial depth, distance between adjacent cables, and heat sources can affect the cable core temperature, making the analysis of the core temperature complex and resulting in low accuracy and efficiency in judging the cable's operating status. Summary of the Invention

[0004] Therefore, it is necessary to provide a cable operation status assessment method, device, computer equipment, computer-readable storage medium, and computer program product that can improve the accuracy and efficiency of cable operation status judgment in response to the above-mentioned technical problems.

[0005] In a first aspect, this application provides a method for evaluating the operating status of a cable, the method comprising:

[0006] Acquire cable operating data, including temperature, current, and voltage data;

[0007] The operating data is preprocessed to obtain preprocessed operating data, and the component parameters related to the cable core temperature are determined based on the preprocessed operating data.

[0008] Correlation analysis was performed on each component parameter to obtain the correlation feature matrix, which was used to evaluate the operating status of the cable.

[0009] In one embodiment, the temperature data includes the cable core temperature, cable sheath temperature, and ambient temperature; acquiring the cable's operational data includes:

[0010] The cable core temperature is collected according to the first preset sampling frequency, and the cable sheath temperature is collected according to the second preset sampling frequency.

[0011] The ambient temperature at different locations is collected using a fiber optic sensor according to a second preset sampling frequency.

[0012] The three-phase current and three-phase voltage data of the cable are collected according to the third preset sampling frequency.

[0013] In one embodiment, the running data is preprocessed to obtain preprocessed running data, including:

[0014] Identify blank data in the running data and find out the reasons for the blank data, and clean the running data according to the reasons;

[0015] Calculate the average value of multiple running data collected in each sampling period to obtain running data with a unified frequency;

[0016] An operational data sequence is generated based on the time identifier of the operational data after unification of frequency. The operational data sequence is used to construct the original data matrix, and the original data matrix is ​​used to characterize the features of the operational data.

[0017] In one embodiment, data cleaning is performed on the running data based on the cause of the blank data, including:

[0018] If the cause is cable outage, then the blank data will be removed from the operation data;

[0019] If the cause is data transmission delay, then starting from the sampling time of the blank data, the running data value of the next sampling time will be used as the running data value of the previous sampling time.

[0020] If the cause is a transmission failure, the data value of the sampling time before or after the sampling time of the blank data is used as the data value of the sampling time of the blank data.

[0021] In one embodiment, before performing correlation analysis on the component parameters, the method further includes:

[0022] The sample matrix is ​​determined based on the operating data and the sampling period of the operating data, and the covariance matrix of the sample matrix is ​​also determined.

[0023] The eigenvalues ​​of the sample matrix and the corresponding eigenvectors are calculated based on the covariance matrix. The eigenvalues ​​are used to calculate the contribution rate of the component parameters of each eigenvector, and the eigenvectors are used to construct the feature matrix. The feature matrix is ​​used to characterize the degree of correlation between each running data and the running state.

[0024] In one embodiment, a correlation analysis is performed on each component parameter to obtain a correlation feature matrix, including:

[0025] Calculate the ratio of each eigenvalue to the sum of all eigenvalues ​​to obtain the contribution rate of the component parameters corresponding to each eigenvector;

[0026] The cumulative contribution rate of multiple component parameters is obtained by calculating the ratio of the sum of the contribution rates of multiple different component parameters to the sum of the contribution rates of each component parameter.

[0027] The cumulative contribution rates of multiple component parameters are compared with the second preset threshold. The feature vectors corresponding to the cumulative contribution rates of component parameters that are greater than the second preset threshold are determined as the first feature vectors. Each first feature vector is multiplied by its corresponding feature value to obtain the correlation feature vector. The correlation feature vector is used as the column vector of the feature matrix to construct the feature matrix. The operating status of the cable is evaluated through the feature matrix.

[0028] Secondly, this application also provides a cable operating status assessment device. The device includes:

[0029] The acquisition module is used to acquire the cable's operating data, including temperature, current, and voltage data.

[0030] The preprocessing module is used to preprocess the operating data to obtain preprocessed operating data, and to determine the component parameters related to the cable core temperature based on the preprocessed operating data.

[0031] The analysis module is used to perform correlation analysis on the parameters of each component to obtain the correlation feature matrix, which is used to evaluate the operating status of the cable.

[0032] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0033] Acquire cable operating data, including temperature, current, and voltage data;

[0034] The operating data is preprocessed to obtain preprocessed operating data, and the component parameters related to the cable core temperature are determined based on the preprocessed operating data.

[0035] Correlation analysis was performed on each component parameter to obtain the correlation feature matrix, which was used to evaluate the operating status of the cable.

[0036] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0037] Acquire cable operating data, including temperature, current, and voltage data;

[0038] The operating data is preprocessed to obtain preprocessed operating data, and the component parameters related to the cable core temperature are determined based on the preprocessed operating data.

[0039] Correlation analysis was performed on each component parameter to obtain the correlation feature matrix, which was used to evaluate the operating status of the cable.

[0040] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the following steps:

[0041] Acquire cable operating data, including temperature, current, and voltage data;

[0042] The operating data is preprocessed to obtain preprocessed operating data, and the component parameters related to the cable core temperature are determined based on the preprocessed operating data.

[0043] Correlation analysis was performed on each component parameter to obtain the correlation feature matrix, which was used to evaluate the operating status of the cable.

[0044] The aforementioned cable operation status assessment method acquires cable operation data, including temperature, current, and voltage data. This data reveals key parameters of the cable during actual operation, providing insight into its actual performance and operating environment. This facilitates monitoring cable status changes and predicting future changes. Preprocessing the operation data yields preprocessed data, which is then used to determine component parameters correlated with the cable core temperature. This improves the quality and reliability of the data used for correlation analysis, making it easier to extract effective features. Correlation analysis of each component parameter yields a correlation feature matrix, which is used to assess the cable's operation status. This matrix clarifies the impact of different parameters on the cable's operation status, allowing for the timely detection of potential problems and timely cable maintenance. These methods contribute to improving the accuracy and efficiency of cable operation status assessment. Attached Figure Description

[0045] Figure 1 This is a diagram illustrating the application environment of the cable operating status assessment method in one embodiment;

[0046] Figure 2 This is a flowchart illustrating a cable operation status assessment method in one embodiment;

[0047] Figure 3 This is a flowchart illustrating a cable operation status assessment method in one embodiment;

[0048] Figure 4 This is a structural block diagram of a cable operation status assessment device in one embodiment;

[0049] Figure 5 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0050] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0051] The cable operating status assessment method provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or located in the cloud or on other network servers. Terminal 102 can be a power data acquisition terminal in a power system, such as various sensors, load monitoring equipment, smart meters, transformer monitoring equipment, line monitoring equipment, and SCADA systems (Supervisory Control And Data Acquisition). Server 104 can be implemented using a standalone server or a server cluster consisting of multiple servers; server 104 can be the control server of the power system.

[0052] In one embodiment, such as Figure 2 As shown, a method for evaluating the operating status of a cable is provided, which can be applied to... Figure 1 Taking the application environment in [the document] as an example, the following steps are included:

[0053] Step 202: Obtain the cable's operating data, which includes temperature data, current data, and voltage data.

[0054] Cables, in general, refer to cables used in power systems to transmit electrical energy. From the inside out, they typically consist of a core (conductor), an insulation layer, an insulation protective layer, and an outer protective layer made of materials such as polyvinyl chloride (PVC). They may also include a metallic protective layer for electromagnetic shielding, and a filler layer to maintain the cable's circular cross-section or for waterproofing. When transmitting three-phase alternating current, the cable consists of three cores, each transmitting one of the three phases of the power supply. Each core has its own sheath, and the overall protective layer and outer sheath are wound together. Cable operating data can include core temperature, outer sheath temperature, current, voltage, insulation resistance, partial discharge status, impedance, length, location, vibration and shock data, humidity data, and environmental data. Current data can include steady-state current, peak current, and instantaneous current; voltage data can include AC voltage, peak voltage, and instantaneous voltage; and environmental data can include the temperature and humidity of the cable trench.

[0055] For example, acquiring cable operating data, including temperature, current, and voltage data, can be achieved using sensors or data acquisition devices. Temperature data can be acquired using thermocouple temperature sensors, infrared thermometers, or fiber optic temperature sensors. Current data can be obtained by measuring the secondary current using a current transformer to infer the current on the main conductor, or by using devices such as current clamps, Hall effect sensors, or circuit breakers. Voltage data can be obtained by measuring the secondary voltage using a voltage transformer and inferring the voltage on the main conductor, or by using voltage dividers or contactless voltage sensors. Environmental data can be measured using temperature and humidity sensors or thermal imagers. Since cables are typically buried underground, temperature sensors can also be deployed in the soil near the cable trench or at suitable locations within the trench. Fiber optic temperature sensors can be placed at different locations within the cable trench to monitor temperature changes in real time, improving measurement accuracy and interference resistance.

[0056] Step 204: Preprocess the operating data to obtain preprocessed operating data, and determine the component parameters associated with the core temperature of the cable based on the preprocessed operating data.

[0057] Preprocessing refers to cleaning, transforming, or preparing data to improve its accuracy and usability for better subsequent analysis. Accordingly, preprocessed operational data can be data with errors, missing values, or outliers removed, data conforming to a specific distribution, or data scaled to a uniform range. Component parameters associated with cable core temperature mainly include core temperature, cable sheath temperature, temperature at different locations in the cable trench, and voltage and current of each phase core.

[0058] For example, preprocessing the operating data may involve operations such as data cleaning, data transformation, data smoothing, data standardization, or dataset partitioning. Determining the component parameters associated with the cable core temperature based on the preprocessed operating data may involve calculating the correlation coefficient between each component parameter and the cable core temperature. If a high positive or negative correlation is observed, the Pearson correlation coefficient or other correlation indicators may be used for measurement.

[0059] Step 206: Perform correlation analysis on each component parameter to obtain the correlation feature matrix. The correlation feature matrix is ​​used to evaluate the operating status of the cable.

[0060] Correlation analysis refers to the analysis of data to obtain the relationship between two or more data points, which can reflect the interaction and correlation between data. The analysis results can be represented by parameters such as correlation coefficients. A correlation feature matrix is ​​a two-dimensional matrix composed of multiple samples and their correlation coefficients and other parameters; it can intuitively represent the correlation between data. The operating status of a cable can include multiple aspects, such as electrical performance, temperature, and insulation condition.

[0061] For example, correlation analysis is performed on each component parameter to obtain a correlation feature matrix. This can be achieved by selecting some component parameters that may have a high correlation as correlation features, determining a correlation coefficient threshold, selecting component parameters whose correlation coefficient with the cable operating status is greater than the threshold, and using the product of these component parameters and their correlation coefficients as column vectors of the correlation feature matrix to construct the correlation feature matrix.

[0062] The aforementioned cable operation status assessment method acquires cable operation data, including temperature, current, and voltage data. This data reveals key parameters of the cable during actual operation, providing insight into its actual performance and operating environment. This facilitates monitoring cable status changes and predicting future changes. Preprocessing the operation data yields preprocessed data, which is then used to determine component parameters correlated with the cable core temperature. This improves the quality and reliability of the data used for correlation analysis, making it easier to extract effective features. Correlation analysis of each component parameter yields a correlation feature matrix, which is used to assess the cable's operation status. This matrix clarifies the impact of different parameters on the cable's operation status, allowing for the timely detection of potential problems and timely cable maintenance. These methods contribute to improving the accuracy and efficiency of cable operation status assessment.

[0063] In one embodiment, the temperature data includes the cable core temperature, cable sheath temperature, and ambient temperature. Acquiring the cable's operating data includes: collecting the cable core temperature according to a first preset sampling frequency and collecting the cable sheath temperature according to a second preset sampling frequency; collecting the ambient temperature at different locations using an optical fiber sensor according to the second preset sampling frequency; and collecting the cable's three-phase current data and three-phase voltage data according to a third preset sampling frequency.

[0064] Here, cable core temperature refers to the temperature of the conductor inside the cable, cable sheath temperature refers to the temperature of the surface of the outer insulation layer of the cable, and ambient temperature can be the temperature of the cable installation environment, such as the temperature at different locations in the cable trench. Three-phase current data refers to the current value flowing through each of the three phases (A phase, B phase, and C phase) of the cable, and three-phase voltage data refers to the voltage value of each of the three phases.

[0065] For example, the first preset sampling frequency, the second preset sampling frequency, and the third preset sampling frequency can be determined according to the frequency of the actual sampling device or sensor. These three frequencies can be the same or different; when the frequencies are the same, frequency unification of the data can be avoided. Fiber optic sensors can be installed at different locations in the cable trench, for example, they can be arrayed on the inner wall of the cable trench to more accurately collect ambient temperature data at different locations. Three-phase current data and three-phase voltage data can be collected using a power data acquisition device.

[0066] In one embodiment, the running data is preprocessed to obtain preprocessed running data, including: identifying blank data in the running data and obtaining the cause of the blank data; cleaning the running data according to the cause; calculating the average value of multiple running data collected in each sampling period to obtain running data with a unified frequency; generating a running data sequence according to the time identifier of the running data with a unified frequency, the running data sequence being used to construct an original data matrix, and the original data matrix being used to characterize the features of the running data.

[0067] Blank data refers to data in the collected operational data that contains missing or unrecorded information. Errors in data acquisition, data loss during format conversion, or problems during storage can all lead to blank data in the operational data. The timestamp in the operational data is time-related information used to identify the time point or time period of data acquisition; it can be in the form of a timestamp or other format.

[0068] For example, to determine the cause of blank data, one can traverse the running data and identify any obvious missing patterns, such as specific time periods, locations, or sample categories. Alternatively, the cause can be determined based on the operational information of the data acquisition device and the data acquisition process. Data cleaning of the running data can involve deleting blank data, filling in blank data using statistical measures, or performing model-based predictions. Calculating the average of multiple running data collected in each sampling period to obtain running data with a unified frequency can be achieved by averaging the running data values ​​within each sampling period. Generating a running data sequence based on the timestamps of the unified frequency running data can be done by sorting the data in chronological order, thus generating a data sequence that reflects the trend of data changes over time.

[0069] In one embodiment, data cleaning of the running data is performed according to the cause of the blank data, including: if the cause is cable outage, the blank data is removed from the running data; if the cause is data transmission delay, the running data value at the next sampling time is used as the running data value at the previous sampling time, starting from the sampling time of the blank data; if the cause is transmission failure, the data value at the sampling time before or after the sampling time of the blank data is used as the data value at the sampling time of the blank data.

[0070] Cable outage refers to the temporary cessation of cable operation or use. If a cable is out of service, the data from that period cannot be used to assess its operational status and therefore needs to be discarded. Data transmission delay refers to the time interval between the sender sending data and the receiver actually receiving and using it. This interval is related to transmission distance, network status, or data volume. Data transmission delay affects the continuity of data over time, therefore, blank data caused by delay needs to be filled or supplemented. Transmission failure refers to problems occurring during data transmission, resulting in the inability to transmit some or all of the data normally. Transmission failure also affects data continuity, therefore, blank data also needs to be filled or supplemented.

[0071] For example, if the cause is data transmission delay, the data value of the next sampling moment can be sequentially filled in to the previous sampling moment starting from the sampling moment of the blank data, thus ensuring the continuity and reliability of the data. If the cause is transmission failure, the data value of the previous or next sampling moment can be used to fill in the blank data to ensure the continuity of the data. If the time interval between sampling moments is long or the data fluctuates greatly, an interpolation algorithm can be used to calculate the data value to fill in the blank data.

[0072] In one embodiment, before performing correlation analysis on each component parameter, the method further includes: determining a sample matrix based on the running data and the sampling period of the running data, and determining the covariance matrix of the sample matrix; calculating the eigenvalues ​​of the sample matrix and the eigenvectors corresponding to each eigenvalue based on the covariance matrix, wherein the eigenvalues ​​are used to calculate the component parameter contribution rate of each eigenvector, the eigenvectors are used to construct a feature matrix, and the feature matrix is ​​used to characterize the degree of correlation between each running data and the running state.

[0073] A sample matrix is ​​a matrix composed of rows or columns, arranged in chronological order of collected data samples. It can be used to store and process time-series data. Each row or column represents a data sample at a specific point in time or over a period of time, and each column or row represents a feature or attribute. A covariance matrix is ​​a symmetric matrix where the diagonal elements are the variances of each random variable, and the off-diagonal elements are the covariances between two random variables.

[0074] For example, determining the covariance matrix of the sample matrix can be achieved by calculating the sample mean for each operating parameter, then calculating the difference (i.e., deviation) between each sample value and the mean, and constructing a deviation matrix based on the operating parameters and the aforementioned differences. Each row represents a sample, and each column represents the deviation of a variable. The product of the transpose of the deviation matrix and the deviation matrix is ​​calculated, and divided by the number of samples; the resulting matrix is ​​the covariance matrix. Based on the covariance matrix, the eigenvalues ​​of the sample matrix and the eigenvectors corresponding to each eigenvalue can be calculated. Eigenvalue decomposition can be performed on the covariance matrix, and the eigenvalues ​​can be arranged in descending order. The eigenvectors corresponding to the larger eigenvalues ​​can be considered as the most important component parameters, thus achieving dimensionality reduction of the data.

[0075] In one embodiment, correlation analysis is performed on each component parameter to obtain a correlation feature matrix, including: calculating the ratio of each eigenvalue to the sum of all eigenvalues ​​to obtain the component parameter contribution rate corresponding to each eigenvector; calculating the ratio of the sum of multiple different component parameter contribution rates to the sum of the contribution rates of each component parameter to obtain the cumulative contribution rate of multiple component parameters; comparing the cumulative contribution rates of multiple component parameters with a second preset threshold, and determining the eigenvector corresponding to the cumulative contribution rate of the component parameter greater than the second preset threshold as the first eigenvector; multiplying each first eigenvector with its corresponding eigenvalue to obtain a correlation feature vector; using the correlation feature vector as the column vector of the feature matrix to construct the feature matrix; and evaluating the operating status of the cable through the feature matrix.

[0076] Among them, the component parameter contribution rate is an indicator that measures the degree to which each component parameter contributes to the total variance. The second preset threshold is used to determine the number of component parameters, which can be determined according to the actual dimensionality reduction requirements or proportions. The first eigenvector is determined based on the second preset threshold and is the eigenvector that has a significant impact on the cable's operating status.

[0077] For example, the ratio of the sum of the contribution rates of multiple different component parameters to the sum of the contribution rates of each component parameter is calculated to obtain the cumulative contribution rate of multiple component parameters. This can be achieved by selecting multiple component parameter contribution rates in order of magnitude of the eigenvalues ​​and adding them together, or by randomly selecting multiple component parameter contribution rates and adding them together. Multiplying each first eigenvector by its corresponding eigenvalue yields a correlation feature vector, which can reflect which parameters have a greater impact on the cable's operating status. Using the correlation feature vector as the column vector of the feature matrix, a feature matrix is ​​constructed. The cable's operating status is evaluated through the feature matrix. This can be done by analyzing data samples from the feature matrix to assess the cable's operating status. For example, the feature matrix can be visualized to intuitively determine the impact of each data point on the cable's operating status. Alternatively, the feature matrix can be used as input to a machine learning model, allowing the model to learn from the data samples in the feature matrix and their corresponding labels to achieve the assessment or prediction of the cable's operating status.

[0078] In one embodiment, such as Figure 3 As shown, a method for evaluating the operating status of a cable is provided, including the following steps:

[0079] Step 302: Collect temperature, current, and voltage data of the intelligent cable in operation according to the preset sampling frequency. Based on the distribution of sensors in the intelligent cable line, collect data on various related factors at different periods. The collection period and related factor quantities are shown in the table below:

[0080] Table 1

[0081]

[0082]

[0083] Specifically, for cable core temperature data, each sampling point was sampled at a frequency of 0.83Hz, meaning one temperature data point was collected every 12 seconds; for the three-phase current and voltage of the cable, the current and voltage data for the entire cable were sampled at a frequency of 1Hz; for the temperature of the cable sheath and optical fibers at various locations in the cable trench, each sampling point was sampled at a frequency of 0.083Hz, meaning one temperature data point was collected every 120 seconds (2 minutes). The real-time acquired data was collected by sensors, converted through photoelectric conversion and A / D conversion, and then transmitted to the computer system for processing and analysis.

[0084] Step 304: Perform data preprocessing on the collected data.

[0085] Preprocessing includes three steps: data cleaning, which involves deleting or completing blank data; frequency unification, which unifies the frequency of all collected data based on the collection frequency of 0.0083Hz for outer skin temperature and ambient temperature; and data sorting, which sorts and groups the cleaned data.

[0086] Data cleaning refers to identifying and handling blank data that may appear during data acquisition. Different processing methods are adopted according to the different causes of blank data. Possible causes of blank data include line outages, data transmission delays, and sampling transmission system failures. If it is a line outage, this process is skipped; if it is a data transmission delay, subsequent sampling information is pushed forward to the current sampling time; if it is a sampling transmission system failure, the missing blank data is directly filled in by adjacent sampled data. If sampling transmission system failures occur consecutively, an alert is sent to the control center.

[0087] Unified frequency refers to averaging the 120 current and voltage data collected in each sampling period, averaging the 10 data points of cable core temperature in one period, and taking the average value to unify the frequency of each factor, which is 0.0083Hz.

[0088]

[0089]

[0090]

[0091] Data cleaning refers to storing the cleaned and frequency-standardized data into computer folders, sorting it, and grouping the data according to time sequence as follows: {T A , I, U, T B T C1 T C2 T C3 T C4 There is a corresponding pair every 120 seconds.

[0092] Step 306: Perform a correlation analysis of cable core temperature based on the preprocessed data.

[0093] The processed data are used to construct an m×n original sample matrix y, where m is the time length of the sample data, and a new row of data is added every 2 minutes; n=8, representing 8 features, as shown below:

[0094]

[0095] For ease of explanation, matrix y can be rewritten as:

[0096]

[0097] Data digitization of the collected data (in T) A For example, m is the total number of data points:

[0098]

[0099]

[0100]

[0101] Where i = 1, 2, ..., m; For T A Average value, s TA For T A The variance.

[0102] Integrate all the data to form an m×n standard matrix Y:

[0103]

[0104] Calculate the covariance matrix:

[0105]

[0106] Among them, Y T Let Y be the transpose of matrix Y.

[0107] Calculate the eigenvalues ​​and eigenvectors of a matrix:

[0108] Calculate the eigenvalues ​​of the correlation coefficient matrix and arrange them in ascending order:

[0109] λ1≥λ2≥…≥λ n

[0110] Find the eigenvectors corresponding to the above eigenvalues:

[0111] u1, u2, ..., u n

[0112] Among them, u i =(u 1i u 2i ,…,u ni ) T (i = 1, 2, ..., n), which are the first principal component, the second principal component, ..., the nth principal component in sequence.

[0113] Calculate the principal component contribution rate η i :

[0114]

[0115] Select j (j≤n) principal components and calculate the cumulative contribution rate η. j :

[0116]

[0117] Write the principal component expression:

[0118] Calculate each η j Take η p =η j When η p When ≥80%, select the first p principal components, i.e., the 1st, 2nd, ..., pth principal components, where the i-th principal component F i This can be expressed as:

[0119] F i =u 1i Y1+u 2i Y2+…+u pi Y p

[0120] The closer the coefficients of the features in each principal component are, the higher the correlation between them. Principal components with different contribution rates represent different data features. The larger the coefficient of a feature in a principal component, the greater the influence of that feature on that principal component.

[0121] The above methods, based on the collection and processing of data on variables such as cable core temperature, operating current, voltage, sheath temperature, and cable trench temperature, produce a data matrix that can reflect more information about the original variables. This matrix can then be used to determine the strength of the correlation between cable core temperature and various factors. By using fewer variables to clearly describe the cable core temperature change state, it facilitates the monitoring and maintenance of the cable's operating status.

[0122] The above methods, based on the processing of collected data on variables such as cable core temperature, operating current, voltage, sheath temperature, and cable trench temperature, aim to reflect as much information as possible about the original variables while ensuring they are independent of each other, thereby determining the strength of the correlation between cable core temperature and various factors. This approach uses fewer variables to clearly describe the cable core temperature change state, facilitating monitoring and maintenance of the cable's operating status by staff.

[0123] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0124] Based on the same inventive concept, this application also provides a cable operating condition assessment device for implementing the cable operating condition assessment method described above. The solution provided by this device is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more cable operating condition assessment device embodiments provided below can be found in the limitations of the cable operating condition assessment method described above, and will not be repeated here.

[0125] In one embodiment, such as Figure 4 As shown, a cable operating status assessment device 400 is provided, including: an acquisition module 402, a preprocessing module 404, and an analysis module 406, wherein:

[0126] The acquisition module 402 is used to acquire the cable's operating data, which includes temperature data, current data, and voltage data.

[0127] The preprocessing module 404 is used to preprocess the operating data to obtain preprocessed operating data, and to determine the component parameters related to the cable core temperature based on the preprocessed operating data.

[0128] Analysis module 406 is used to perform correlation analysis on each component parameter to obtain a correlation feature matrix, which is used to evaluate the operating status of the cable.

[0129] In one embodiment, the temperature data includes the cable core temperature, cable sheath temperature, and ambient temperature. The acquisition module 402 is used to: acquire the cable core temperature according to a first preset sampling frequency and acquire the cable sheath temperature according to a second preset sampling frequency; acquire the ambient temperature at different locations according to the second preset sampling frequency using an optical fiber sensor; and acquire the three-phase current data and three-phase voltage data of the cable according to a third preset sampling frequency.

[0130] In one embodiment, the preprocessing module 404 is used to: determine blank data in the running data and obtain the cause of the blank data; clean the running data according to the cause; calculate the average value of multiple running data collected in each sampling period to obtain running data after unification of frequency; generate a running data sequence according to the time identifier of the running data after unification of frequency, the running data sequence is used to construct the original data matrix, and the original data matrix is ​​used to characterize the features of the running data.

[0131] In one embodiment, the preprocessing module 404 is configured to: remove blank data from the running data if the cause is cable outage; use the running data value at the next sampling time as the running data value at the previous sampling time if the cause is data transmission delay; and use the data value at the previous or next sampling time as the data value at the sampling time of the blank data if the cause is transmission failure.

[0132] In one embodiment, before performing correlation analysis on each component parameter, the preprocessing module 404 is used to: determine the sample matrix based on the running data and the sampling period of the running data, and determine the covariance matrix of the sample matrix; calculate the eigenvalues ​​of the sample matrix and the eigenvectors corresponding to each eigenvalue based on the covariance matrix, wherein the eigenvalues ​​are used to calculate the component parameter contribution rate of each eigenvector, the eigenvectors are used to construct the feature matrix, and the feature matrix is ​​used to characterize the degree of correlation between each running data and the running state.

[0133] In one embodiment, the analysis module 406 is used to: calculate the ratio of each eigenvalue to the sum of all eigenvalues ​​to obtain the contribution rate of the component parameters corresponding to each eigenvector; calculate the ratio of the sum of the contribution rates of multiple different component parameters to the sum of the contribution rates of each component parameter to obtain the cumulative contribution rate of multiple component parameters; compare the cumulative contribution rates of multiple component parameters with a second preset threshold, and determine the eigenvector corresponding to the cumulative contribution rate of the component parameters that is greater than the second preset threshold as the first eigenvector; multiply each first eigenvector with its corresponding eigenvalue to obtain the correlation feature vector; use the correlation feature vector as the column vector of the feature matrix to construct the feature matrix; and evaluate the operating status of the cable through the feature matrix.

[0134] Each module in the aforementioned cable operation status assessment device 400 can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0135] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 5 As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores raw cable operating data, pre-processed operating data, various process data, and correlation matrices, among other data. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When executed by the processor, the computer program implements a cable operating status evaluation method.

[0136] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0137] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0138] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

[0139] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0140] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data shall comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0141] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile 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. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0142] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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 specification.

[0143] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for evaluating the operating status of cables, characterized in that, The method includes: Acquire the cable's operating data, including temperature data, current data, and voltage data; The operating data is preprocessed to obtain preprocessed operating data, and the component parameters associated with the core temperature of the cable are determined based on the preprocessed operating data. A correlation analysis is performed on each of the component parameters to obtain a correlation feature matrix, which is used to evaluate the operating status of the cable. Before performing correlation analysis on each of the component parameters, the method further includes: The sample matrix is ​​determined based on the running data and the sampling period of the running data, and the covariance matrix of the sample matrix is ​​also determined. The eigenvalues ​​of the sample matrix and the eigenvectors corresponding to each eigenvalue are calculated based on the covariance matrix. The eigenvalues ​​are used to calculate the contribution rate of the component parameters of each eigenvector. The eigenvectors are used to construct a feature matrix. The feature matrix is ​​used to characterize the degree of correlation between each running data and the running state. The correlation analysis of each component parameter to obtain the correlation feature matrix includes: Calculate the ratio of each eigenvalue to the sum of all eigenvalues ​​to obtain the contribution rate of the component parameters corresponding to each eigenvector; The cumulative contribution rate of multiple component parameters is obtained by calculating the ratio of the sum of the contribution rates of multiple different component parameters to the sum of the contribution rates of each component parameter. The cumulative contribution rates of multiple component parameters are compared with the second preset threshold. The feature vector corresponding to the cumulative contribution rate of the component parameter that is greater than the second preset threshold is determined as the first feature vector. Each first feature vector is multiplied by its corresponding feature value to obtain the correlation feature vector. The correlation feature vector is used as the column vector of the feature matrix to construct the feature matrix. The operating status of the cable is evaluated through the feature matrix.

2. The method according to claim 1, characterized in that, The temperature data includes the cable core temperature, cable sheath temperature, and ambient temperature. The acquisition of the cable's operational data includes: The temperature of the cable core is collected according to a first preset sampling frequency, and the temperature of the cable sheath is collected according to a second preset sampling frequency. The ambient temperature at different locations is collected using an optical fiber sensor according to the second preset sampling frequency. The three-phase current data and three-phase voltage data of the cable are collected according to the third preset sampling frequency.

3. The method according to claim 1, characterized in that, The preprocessing of the running data to obtain preprocessed running data includes: Identify blank data in the running data, obtain the cause of the blank data, and perform data cleaning on the running data according to the cause; Calculate the average value of multiple operational data collected in each sampling period to obtain operational data with a unified frequency; An operational data sequence is generated based on the time identifier of the operational data after the unified frequency. The operational data sequence is used to construct an original data matrix, which is used to characterize the features of the operational data.

4. The method according to claim 3, characterized in that, The step of cleaning the running data according to the cause of the blank data includes: If the cause is that the cable is out of service, then the blank data will be removed from the operating data; If the cause is data transmission delay, then starting from the sampling time of the blank data, the running data value of the next sampling time will be used as the running data value of the previous sampling time. If the cause is a transmission failure, then the data value of the sampling time before or after the sampling time of the blank data is used as the data value of the sampling time of the blank data.

5. A cable operating status assessment device, characterized in that, The device includes: The acquisition module is used to acquire the cable's operating data, which includes temperature data, current data, and voltage data. A preprocessing module is used to preprocess the operating data to obtain preprocessed operating data, and to determine the component parameters associated with the core temperature of the cable based on the preprocessed operating data. The analysis module is used to perform correlation analysis on each of the component parameters to obtain a correlation feature matrix, which is used to evaluate the operating status of the cable. Before performing correlation analysis on each of the component parameters, the device includes: The sample matrix is ​​determined based on the running data and the sampling period of the running data, and the covariance matrix of the sample matrix is ​​also determined. The eigenvalues ​​of the sample matrix and the eigenvectors corresponding to each eigenvalue are calculated based on the covariance matrix. The eigenvalues ​​are used to calculate the contribution rate of the component parameters of each eigenvector. The eigenvectors are used to construct a feature matrix. The feature matrix is ​​used to characterize the degree of correlation between each running data and the running state. The correlation analysis of each component parameter to obtain the correlation feature matrix includes: Calculate the ratio of each eigenvalue to the sum of all eigenvalues ​​to obtain the contribution rate of the component parameters corresponding to each eigenvector; The cumulative contribution rate of multiple component parameters is obtained by calculating the ratio of the sum of the contribution rates of multiple different component parameters to the sum of the contribution rates of each component parameter. The cumulative contribution rates of multiple component parameters are compared with the second preset threshold. The feature vector corresponding to the cumulative contribution rate of the component parameter that is greater than the second preset threshold is determined as the first feature vector. Each first feature vector is multiplied by its corresponding feature value to obtain the correlation feature vector. The correlation feature vector is used as the column vector of the feature matrix to construct the feature matrix. The operating status of the cable is evaluated through the feature matrix.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

Images