Cable temperature data processing method and device, computer device and storage medium

Abstract

This application relates to a cable temperature data processing method, apparatus, computer equipment, storage medium, and computer program product. The method includes: clustering multiple sample cables based on two dimensions of temperature values ​​from their respective sample temperature data to obtain multiple cluster centers; the sample temperature data has two dimensions: instantaneous temperature and statistical temperature; correcting the preset cable state boundary instantaneous temperature value and preset cable state boundary statistical temperature value using the closest corresponding cluster centers to obtain corrected cable state boundary instantaneous temperature value and corrected cable state boundary statistical temperature value; and dividing the cable state into ranges based on the corrected cable state boundary instantaneous temperature value and corrected cable state boundary statistical temperature value to obtain multiple temperature ranges with two dimensions and their corresponding cable states. This method can accurately predict the cable state.

Description

Technical Field

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

[0002] With the continuous increase in social electricity demand and information transmission requirements, higher demands are placed on the safe operation of the power grid. Cables are transmission devices used to transmit electrical energy or signals in the power system, and are indispensable for power transmission. Once a cable fails, it will affect the safe and stable operation of the power grid. Therefore, cable fault detection is very important. Typically, cable fault detection is performed using a DC withstand voltage tester. During the testing process, the microphone of the DC withstand voltage tester is moved along the cable, and the location of the cable fault is determined based on the sound of cable discharge.

[0003] However, the method of using a DC withstand voltage tester to detect cable faults only detects the location of the faulty cable after a fault has occurred, so as to facilitate cable repair. It cannot predict the cable condition in advance to avoid cable faults, and thus still has an impact on the safe operation of the power grid. Summary of the Invention

[0004] Therefore, it is necessary to provide a cable temperature data processing method, apparatus, computer equipment, computer-readable storage medium, and computer program product that can predict the cable condition in order to address the above-mentioned technical problems.

[0005] Firstly, this application provides a method for processing cable temperature data. The method includes:

[0006] Based on the temperature values ​​of two dimensions in the sample temperature data of multiple sample cables, the multiple sample cables are clustered to obtain multiple cluster centers; the sample temperature data has two dimensions: instantaneous temperature dimension and statistical temperature dimension.

[0007] Determine the cluster centers that are closest to the instantaneous temperature value of the preset cable state boundary and the statistical temperature value of the preset cable state boundary, respectively;

[0008] For the preset instantaneous temperature value of the cable state boundary and the preset statistical temperature value of the cable state boundary, respectively, the nearest cluster center is used for correction to obtain the corrected instantaneous temperature value of the cable state boundary and the corrected statistical temperature value of the cable state boundary.

[0009] Based on the instantaneous temperature value of the corrected cable state boundary and the statistical temperature value of the corrected cable state boundary, the range is divided to obtain multiple temperature ranges with the two dimensions and their corresponding cable states; the multiple temperature ranges are used to determine the cable state of the target cable based on the temperature values ​​of the two dimensions in the target temperature data of the target cable.

[0010] Secondly, this application also provides a cable temperature data processing device. The device includes:

[0011] The clustering module is used to cluster the multiple sample cables based on the temperature values ​​of two dimensions in the sample temperature data of each sample cable, and obtain multiple cluster centers; the sample temperature data has two dimensions: instantaneous temperature dimension and statistical temperature dimension.

[0012] The correction module is used to determine the cluster center that is closest to the preset instantaneous temperature value of the cable state boundary and the preset statistical temperature value of the cable state boundary, respectively; and to correct the preset instantaneous temperature value of the cable state boundary and the preset statistical temperature value of the cable state boundary using the corresponding closest cluster center, respectively, to obtain the corrected instantaneous temperature value of the cable state boundary and the corrected statistical temperature value of the cable state boundary.

[0013] The range division module is used to divide the range based on the instantaneous temperature value of the corrected cable state boundary and the statistical temperature value of the corrected cable state boundary, to obtain multiple temperature ranges with the two dimensions and their corresponding cable states; the multiple temperature ranges are used to determine the cable state of the target cable based on the temperature values ​​of the two dimensions in the target temperature data of the target cable.

[0014] 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:

[0015] Based on the temperature values ​​of two dimensions in the sample temperature data of multiple sample cables, the multiple sample cables are clustered to obtain multiple cluster centers; the sample temperature data has two dimensions: instantaneous temperature dimension and statistical temperature dimension.

[0016] Determine the cluster centers that are closest to the instantaneous temperature value of the preset cable state boundary and the statistical temperature value of the preset cable state boundary, respectively;

[0017] For the preset instantaneous temperature value of the cable state boundary and the preset statistical temperature value of the cable state boundary, respectively, the nearest cluster center is used for correction to obtain the corrected instantaneous temperature value of the cable state boundary and the corrected statistical temperature value of the cable state boundary.

[0018] Based on the instantaneous temperature value of the corrected cable state boundary and the statistical temperature value of the corrected cable state boundary, the range is divided to obtain multiple temperature ranges with the two dimensions and their corresponding cable states; the multiple temperature ranges are used to determine the cable state of the target cable based on the temperature values ​​of the two dimensions in the target temperature data of the target cable.

[0019] 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:

[0020] Based on the temperature values ​​of two dimensions in the sample temperature data of multiple sample cables, the multiple sample cables are clustered to obtain multiple cluster centers; the sample temperature data has two dimensions: instantaneous temperature dimension and statistical temperature dimension.

[0021] Determine the cluster centers that are closest to the instantaneous temperature value of the preset cable state boundary and the statistical temperature value of the preset cable state boundary, respectively;

[0022] For the preset instantaneous temperature value of the cable state boundary and the preset statistical temperature value of the cable state boundary, respectively, the nearest cluster center is used for correction to obtain the corrected instantaneous temperature value of the cable state boundary and the corrected statistical temperature value of the cable state boundary.

[0023] Based on the instantaneous temperature value of the corrected cable state boundary and the statistical temperature value of the corrected cable state boundary, the range is divided to obtain multiple temperature ranges with the two dimensions and their corresponding cable states; the multiple temperature ranges are used to determine the cable state of the target cable based on the temperature values ​​of the two dimensions in the target temperature data of the target cable.

[0024] 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:

[0025] Based on the temperature values ​​of two dimensions in the sample temperature data of multiple sample cables, the multiple sample cables are clustered to obtain multiple cluster centers; the sample temperature data has two dimensions: instantaneous temperature dimension and statistical temperature dimension.

[0026] Determine the cluster centers that are closest to the instantaneous temperature value of the preset cable state boundary and the statistical temperature value of the preset cable state boundary, respectively;

[0027] For the preset instantaneous temperature value of the cable state boundary and the preset statistical temperature value of the cable state boundary, respectively, the nearest cluster center is used for correction to obtain the corrected instantaneous temperature value of the cable state boundary and the corrected statistical temperature value of the cable state boundary.

[0028] Based on the instantaneous temperature value of the corrected cable state boundary and the statistical temperature value of the corrected cable state boundary, the range is divided to obtain multiple temperature ranges with the two dimensions and their corresponding cable states; the multiple temperature ranges are used to determine the cable state of the target cable based on the temperature values ​​of the two dimensions in the target temperature data of the target cable.

[0029] The aforementioned cable temperature data processing method, apparatus, computer equipment, storage medium, and computer program products provide sample temperature data with two dimensions: instantaneous temperature and statistical temperature. These data dimensions are related to the cable condition, creating conditions for reliably determining the cable condition. Furthermore, by clustering multiple sample cables based on their respective sample temperature data, the obtained cluster centers can characterize the actual cable condition boundary temperatures during historical operation. This allows for the correction of preset instantaneous and statistical temperature values ​​for cable condition boundaries based on the obtained cluster centers, resulting in more accurate corrected instantaneous and statistical temperature values ​​for cable condition boundaries. Consequently, the defined temperature ranges and their corresponding cable conditions are more accurate. Furthermore, by using the defined temperature ranges and their corresponding cable conditions, the cable condition of the target cable can be predicted more accurately based on its target temperature data. Attached Figure Description

[0030] Figure 1 This is an application environment diagram of the cable temperature data processing method in one embodiment;

[0031] Figure 2 This is a flowchart illustrating a cable temperature data processing method in one embodiment;

[0032] Figure 3 This is a flowchart illustrating the clustering training steps in one embodiment;

[0033] Figure 4 This is a schematic diagram illustrating an example of cable condition boundary temperature value correction in one embodiment;

[0034] Figure 5 This is a schematic diagram illustrating the correspondence between temperature range and cable condition in one embodiment;

[0035] Figure 6 This is a structural block diagram of a cable temperature data processing device in one embodiment;

[0036] Figure 7 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0037] 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.

[0038] The cable temperature data processing method provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, computer device 102 can communicate with temperature measuring device 104 via a network, and temperature measuring device 104 can collect temperature data of cable 106. Based on the two-dimensional temperature values ​​from the sample temperature data of multiple sample cables acquired from temperature measuring device 104, computer device 102 clusters the multiple sample cables to obtain corrected instantaneous temperature values ​​and corrected statistical temperature values ​​for cable state boundaries, thereby obtaining multiple temperature ranges with two dimensions and their corresponding cable states. Computer device 102 can be a desktop computer, laptop computer, smartphone, tablet computer, or server. Temperature measuring device 104 is used to collect cable temperature data. Temperature measuring device 104 can be an infrared thermometer based on the principle of infrared thermometry to collect cable temperature data, or an optical fiber thermometer based on the fiber optic cable to collect the temperature of the cable core. Cable 106 can be a power cable specifically for transmitting electrical energy, or a communication cable used for information transmission.

[0039] In one embodiment, such as Figure 2 As shown, a cable temperature data processing method is provided. This embodiment applies this method to... Figure 1 Taking computer device 102 as an example, the method includes the following steps:

[0040] Step 202: Based on the temperature values ​​of two dimensions in the sample temperature data of each of the multiple sample cables, cluster the multiple sample cables to obtain multiple cluster centers; the sample temperature data has two dimensions: instantaneous temperature dimension and statistical temperature dimension.

[0041] The sample cable is the cable observed to predict the cable condition of the target cable. The sample temperature data is the temperature data of the sample cable observed to predict the cable condition of the target cable. Instantaneous temperature is the temperature of the cable measured in real time at any given moment. Statistical temperature is the temperature obtained by statistically analyzing instantaneous temperatures over a period of time. This period can be a day, a week, a month, or other times. The statistical temperature value can be the median of the instantaneous temperature values ​​over a period of time, or it can be the average value calculated from the instantaneous temperature values ​​over a period of time; this average value can be the arithmetic mean, weighted average, or other values.

[0042] Clustering is the process of grouping similar sample cables from multiple data points into several classes based on a specific data dimension. Clustering can be achieved using clustering algorithms such as K-means clustering, Mean shift clustering, DBSCAN (Density-Based Spatial Clustering of Applications with Noise), or others. Cluster centers are the individual centers of the resulting clusters. Cluster centers can be the sample temperature data of the cables or temperature data determined based on the individual sample temperature data of each cable within the corresponding class.

[0043] In one embodiment, a computer device can acquire the original temperature data of multiple sample cables, perform data normalization on the original temperature data of the multiple sample cables, and obtain sample temperature data of the multiple sample cables after data normalization. Based on the temperature values ​​of two dimensions in the sample temperature data of the multiple sample cables, the multiple sample cables can be clustered. Data normalization may include data normalization, such as mapping the original temperature data to a preset data range; it may also include data correction, such as correcting outliers and filling in missing values ​​in the original temperature data; and it may also include data cleaning, for example, removing the sample cable and its original temperature data when the original temperature data of the sample cable is missing or displayed incorrectly.

[0044] In one embodiment, a computer device can cluster multiple sample cables based on the temperature values ​​in two dimensions of their respective sample temperature data. During the clustering process, multiple initial cluster centers are obtained. Based on the multiple initial cluster centers and a preset clustering algorithm, the sample temperature data of the multiple sample cables are iteratively trained to obtain multiple cluster centers output by the iterative training.

[0045] Step 204: Determine the cluster center that is closest to the preset instantaneous temperature value of the cable state boundary and the preset statistical temperature value of the cable state boundary.

[0046] Cable condition refers to the health status of a cable. Cable condition can include non-faulty condition and faulty condition. Non-faulty condition can include normal condition and faulty condition, while faulty condition can include general fault condition and severe fault condition.

[0047] The preset instantaneous temperature value for cable condition boundary is the temperature value that divides different cable conditions under a pre-set instantaneous temperature dimension. The preset statistical temperature value for cable condition boundary is the temperature value that divides different cable conditions under a pre-set statistical temperature dimension.

[0048] In one embodiment, the computer device can preset the instantaneous temperature value of the cable state boundary as the temperature value of each of the two dimensions, construct instantaneous temperature data of the two dimensions, and select the cluster center with the smallest distance between the instantaneous temperature data of the two dimensions and multiple cluster centers as the cluster center closest to the preset instantaneous temperature value of the cable state boundary; and construct two-dimensional statistical temperature data of the cable state boundary as the temperature value of each of the two dimensions, and select the cluster center with the smallest distance between the statistical temperature data of the two dimensions and multiple cluster centers as the cluster center closest to the preset statistical temperature value of the cable state boundary.

[0049] Step 206: For the preset instantaneous temperature value of the cable state boundary and the preset statistical temperature value of the cable state boundary, respectively, the corresponding closest cluster center is used for correction to obtain the corrected instantaneous temperature value of the cable state boundary and the corrected statistical temperature value of the cable state boundary.

[0050] The correction process involves adjusting the temperature values ​​used to classify cable states in a specific way to make the classification of cable states more accurate. The corrected instantaneous temperature value for cable state boundaries is the temperature value obtained after correcting the preset instantaneous temperature value for cable state boundaries. The corrected statistical temperature value for cable state boundaries is the temperature value obtained after correcting the preset statistical temperature value for cable state boundaries.

[0051] In one embodiment, a computer device can periodically cluster multiple sample cables, obtaining multiple cluster centers and recording the classification labels corresponding to each cluster center. In this embodiment, the computer device can determine the classification label of the closest cluster center for each preset instantaneous temperature value and preset statistical temperature value of cable state boundaries, obtain multiple historical cluster centers corresponding to the classification labels, and use the closest cluster center and the obtained historical cluster centers for correction to obtain corrected instantaneous temperature values ​​and corrected statistical temperature values ​​of cable state boundaries. Here, the classification label is the label corresponding to the category of the cluster center.

[0052] In one embodiment, for a preset instantaneous temperature value of cable state boundary, the computer device can use the temperature value of the instantaneous temperature dimension in the corresponding nearest cluster center to correct it, thereby obtaining a corrected instantaneous temperature value of cable state boundary; for a preset statistical temperature value of cable state boundary, the computer device can use the temperature value of the statistical temperature dimension in the corresponding nearest cluster center to correct it, thereby obtaining a corrected statistical temperature value of cable state boundary.

[0053] Step 208: Based on the instantaneous temperature value of the corrected cable state boundary and the statistical temperature value of the corrected cable state boundary, the range is divided to obtain multiple temperature ranges with two dimensions and their corresponding cable states; the multiple temperature ranges are used to determine the cable state of the target cable based on the temperature values ​​of the two dimensions in the target temperature data of the target cable.

[0054] The two-dimensional temperature range consists of the temperature value range under the instantaneous temperature dimension and the temperature value range under the statistical temperature dimension. The target cable is the cable whose state is to be predicted. The target temperature data refers to the two-dimensional temperature data measured on the target cable.

[0055] In one embodiment, the computer device can divide a preset temperature range for the instantaneous temperature dimension based on the corrected cable state boundary instantaneous temperature value, thereby obtaining a temperature range for the instantaneous temperature dimension; and divide a preset temperature range for the statistical temperature dimension based on the corrected cable state boundary statistical temperature value, thereby obtaining a temperature range for the statistical temperature dimension; based on the temperature ranges for the instantaneous and statistical temperature dimensions, multiple temperature ranges with two dimensions and their corresponding cable states are obtained. The preset temperature range is a range formed by a pre-set upper and lower temperature limit value. The upper and lower temperature limit values ​​can be infinity, infinitesimal, or specific values.

[0056] In one embodiment, a computer device can determine the cable state corresponding to multiple temperature ranges in two dimensions based on a pre-configured state delineation strategy. The pre-configured state delineation strategy is a pre-configured strategy that maps different cable states to temperature ranges.

[0057] In the aforementioned cable temperature data processing method, the sample temperature data has two dimensions: instantaneous temperature and statistical temperature. These data dimensions are related to the cable condition, creating conditions for reliably determining the cable condition. Furthermore, based on the sample temperature data of multiple sample cables, clustering is performed on the multiple sample cables. The obtained cluster centers can characterize the actual situation of the cable condition boundary temperature during historical operation. This allows for the correction of the preset instantaneous temperature value and the preset statistical temperature value of the cable condition boundary based on the obtained cluster centers, resulting in more accurate corrected instantaneous temperature value and corrected statistical temperature value of the cable condition boundary. Consequently, the multiple temperature ranges and their corresponding cable conditions are more accurate. Furthermore, by using the multiple temperature ranges and their corresponding cable conditions, the cable condition of the target cable can be predicted more accurately based on the target temperature data of the target cable.

[0058] In one embodiment, step 204 includes: acquiring temperature values ​​for two dimensions in multiple cluster centers respectively; determining the cluster center with the closest instantaneous temperature value of the preset cable state boundary among multiple cluster centers based on the instantaneous temperature value of the instantaneous temperature dimension in multiple cluster centers; and determining the cluster center with the closest statistical temperature value of the preset cable state boundary among multiple cluster centers based on the statistical temperature value of the statistical temperature dimension in multiple cluster centers.

[0059] In this embodiment, for the preset instantaneous temperature value of the cable state boundary and the preset statistical temperature value of the cable state boundary, the closest cluster center is determined by the temperature value of each of the multiple cluster centers under the corresponding dimension. This makes the closest cluster center more reasonable, which can improve the correction accuracy and further improve the accuracy of cable state prediction.

[0060] In one embodiment, for a preset instantaneous temperature value at the cable state boundary, the computer device can calculate the difference between the temperature value of each of the multiple cluster centers in the instantaneous temperature dimension and the preset instantaneous temperature value at the cable state boundary, and the cluster center corresponding to the smallest absolute value of the difference is the cluster center closest to the preset instantaneous temperature value at the cable state boundary.

[0061] In one embodiment, for a preset cable state boundary statistical temperature value, the computer device can calculate the difference between the temperature value of each of the multiple cluster centers in the statistical temperature dimension and the preset cable state boundary statistical temperature value, and the cluster center corresponding to the smallest absolute value of the difference is the cluster center closest to the preset cable state boundary statistical temperature value.

[0062] In one embodiment, step 206 includes: calculating the average of the instantaneous temperature value of the preset cable state boundary and the temperature value of the instantaneous temperature dimension in the corresponding nearest cluster center to obtain the corrected instantaneous temperature value of the cable state boundary; and calculating the average of the statistical temperature value of the preset cable state boundary and the temperature value of the statistical temperature dimension in the corresponding nearest cluster center to obtain the corrected statistical temperature value of the cable state boundary.

[0063] In this embodiment, by calculating the average of the instantaneous temperature value of the preset cable state boundary and the temperature value of the instantaneous temperature dimension in the corresponding nearest cluster center, and by calculating the average of the statistical temperature value of the preset cable state boundary and the temperature value of the statistical temperature dimension in the corresponding nearest cluster center, a reasonable correction can be made to improve the accuracy of cable state prediction.

[0064] In one embodiment, the computer device can calculate the arithmetic mean of the instantaneous temperature value of the preset cable state boundary and the temperature value of the instantaneous temperature dimension in the corresponding nearest cluster center to obtain the corrected instantaneous temperature value of the cable state boundary; and calculate the arithmetic mean of the statistical temperature value of the preset cable state boundary and the temperature value of the statistical temperature dimension in the corresponding nearest cluster center to obtain the corrected statistical temperature value of the cable state boundary.

[0065] In one embodiment, the computer device can obtain a pre-configured weight allocation strategy, determine the weight ratio of the instantaneous temperature value of the preset cable state boundary and the temperature value of the instantaneous temperature dimension in the corresponding nearest cluster center according to the weight allocation strategy, calculate a weighted average of the instantaneous temperature value of the preset cable state boundary and the temperature value of the instantaneous temperature dimension in the corresponding nearest cluster center based on the respective weight ratios, and obtain a corrected instantaneous temperature value of the cable state boundary; determine the weight ratio of the statistical temperature value of the preset cable state boundary and the temperature value of the statistical temperature dimension in the corresponding nearest cluster center according to the weight allocation strategy, and calculate a weighted average of the statistical temperature value of the preset cable state boundary and the temperature value of the statistical temperature dimension in the corresponding nearest cluster center based on the respective weight ratios, and obtain a corrected statistical temperature value of the cable state boundary.

[0066] The pre-configured weight allocation strategy is a strategy for pre-configuring the weight ratios. This strategy can involve assigning different pre-defined weight ratios to the instantaneous temperature values ​​at preset cable state boundaries and the temperature values ​​in the corresponding nearest cluster centers, as well as assigning different pre-defined weight ratios to the statistical temperature values ​​at preset cable state boundaries and the temperature values ​​in the corresponding nearest cluster centers. Furthermore, the pre-configured weight allocation strategy can also assign a larger weight ratio to the temperature values ​​of cluster centers when the number of sample cables in the cluster reaches a preset number, and a smaller weight ratio when the number of sample cables in the cluster does not reach the preset number.

[0067] In one embodiment, step 202 includes: clustering the multiple sample cables based on the temperature values ​​in two dimensions of their respective sample temperature data, dividing the multiple sample cables into two categories; for each sample cable, calculating the intra-class average distance between the targeted sample cable and other sample cables in the same category within the two categories, and calculating the out-of-class average distance between the targeted sample cable and sample cables in different categories within the two categories, based on the intra-class dissimilarity determined by the intra-class average distance of the multiple sample cables and the out-of-class dissimilarity determined by the out-of-class average distance of the multiple sample cables; and obtaining two cluster centers corresponding to the two categories when the cluster evaluation coefficient is greater than a preset evaluation coefficient.

[0068] The two categories can correspond to different cable conditions, or they can be faulty and normal. The intra-class average distance is the arithmetic mean of the distances between the sample cable and other sample cables in the same category. The out-of-class average distance is the arithmetic mean of the distances between the sample cable and sample cables in different categories.

[0069] Intra-class dissimilarity refers to the degree of dissimilarity within the same category; the smaller the intra-class dissimilarity, the better the clustering effect. Intra-class dissimilarity is the arithmetic mean of the average intra-class distances to the respective sample cables. Out-of-class dissimilarity refers to the degree of dissimilarity between different categories; the larger the out-of-class dissimilarity, the better the clustering effect. Out-of-class dissimilarity is the arithmetic mean of the average out-of-class distances to the respective sample cables.

[0070] Clustering evaluation coefficients are used to evaluate the clustering effect of multiple sample cables. The value of the clustering evaluation coefficient can range from -1 to 1. The closer the value of the clustering evaluation coefficient is to 1, the better the clustering effect and the higher the reliability of the clustering results; the closer the value of the clustering evaluation coefficient is to -1, the worse the clustering effect and the lower the reliability of the clustering results. More preset evaluation coefficients are pre-set evaluation coefficients.

[0071] In this embodiment, clustering evaluation coefficients for the two categories are determined to evaluate the clustering effect of dividing multiple sample cables into two categories. When the clustering evaluation coefficient is greater than the preset evaluation coefficient, it indicates that the clustering effect is good and the two categories are more accurate. This further improves the accuracy of subsequent correction when correcting the preset instantaneous temperature value of the cable state boundary and the preset statistical temperature value of the cable state boundary based on the two obtained cluster centers, and can further improve the accuracy of cable state prediction.

[0072] In one embodiment, the computer device can acquire two initial cluster centers. Based on the acquired two initial cluster centers, iterative training is performed on the temperature values ​​of two dimensions in the sample temperature data of multiple sample cables. During the iterative training process, the two initial cluster centers are used as two current cluster centers. The multiple sample cables are iteratively classified into the current categories indicated by the corresponding current cluster centers according to the distance between the sample temperature data of the multiple sample cables and the two current cluster centers. The arithmetic mean of the sample temperature data of the sample cables in each current category is calculated to redetermine the current cluster centers. Multiple redetermined current cluster centers are obtained until the maximum number of iterations is reached, at which point the iterative training stops, and the two cluster centers and two categories at the time of stopping the iterative training are obtained.

[0073] In one embodiment, the computer device can calculate the arithmetic mean of the intra-class average distances corresponding to each of the multiple sample cables to obtain the intra-class dissimilarity; and calculate the arithmetic mean of the out-of-class average distances corresponding to each of the multiple sample cables to obtain the out-of-class dissimilarity.

[0074] In one embodiment, the computer device may determine the larger of the intra-class dissimilarity and the inter-class dissimilarity, calculate the difference between the inter-class dissimilarity and the intra-class dissimilarity, and use the ratio of the difference to the larger one as the clustering evaluation coefficient for the two categories.

[0075] In one embodiment, step 202 further includes: when the clustering evaluation coefficient is less than the preset evaluation coefficient, clustering the multiple sample cables based on the temperature values ​​of two dimensions in the sample temperature data of each sample cable, dividing the multiple sample cables into three categories, and obtaining three cluster centers corresponding to the three categories respectively.

[0076] The three categories can be normal, prone to failure, and faulty.

[0077] In this embodiment, when the clustering evaluation coefficient is less than the preset evaluation coefficient, it indicates that the clustering effect is not good enough when multiple sample cables are clustered into two categories. Therefore, the multiple sample cables are divided into three categories for more detailed classification, so as to obtain more reasonable cluster centers and improve the accuracy of correction.

[0078] In one embodiment, the above-mentioned cable temperature data processing method further includes: generating a cable state determination model based on multiple temperature ranges with two dimensions and their corresponding cable states; the cable state determination model takes the cable temperature data as input and the cable state of the cable as output; inputting the target temperature data of the target cable into the cable state determination model, determining the temperature range to which the target temperature data belongs, and outputting the cable state corresponding to the determined temperature range as the cable state of the target cable.

[0079] The cable condition determination model is a model used to determine the cable condition by inputting the cable's temperature data.

[0080] In this embodiment, by generating a cable condition determination model, the cable condition can be quickly determined by inputting the target temperature data of the target cable, thereby improving the prediction efficiency of the cable condition.

[0081] In one embodiment, in a specific application scenario, the cable can be a smart cable with built-in optical fiber. The temperature of the cable core is collected through the built-in optical fiber to obtain the cable temperature data. The above-mentioned cable temperature data processing method specifically includes the following steps.

[0082] The computer equipment can acquire the raw temperature data of multiple sample cables. When the raw temperature data of a sample cable is missing or displays an ERROR, the sample cable and its raw temperature data are removed, and normalized to obtain the sample temperature data of each of the multiple sample cables. The sample temperature data has two dimensions: instantaneous temperature and statistical temperature.

[0083] like Figure 3As shown in the flowchart of the clustering training steps, the computer device can randomly select k (or more) initial cluster centers from the sample temperature data of multiple sample cables. Based on the k initial cluster centers, iterative training is performed on the sample temperature data of multiple sample cables. During the iterative training process, the k initial cluster centers are used as k current cluster centers. The multiple sample cables are iteratively classified into the current categories indicated by the corresponding current cluster centers according to the distance between the sample temperature data of multiple sample cables and the k current cluster centers. The arithmetic mean of the sample temperature data of the sample cables in each of the k current categories is calculated to redetermine the current cluster centers. The k redetermined current cluster centers are obtained until the standard measure function converges, and the iterative training stops. The k cluster centers and k categories at the time of stopping the iterative training are obtained.

[0084] When k is 2, meaning the clustering results in two categories, the computer can calculate the average intra-cluster distance between the target cable and other target cables in the same category within both categories, based on the sample temperature data of each of the multiple sample cables. It can also calculate the average out-of-cluster distance between the target cable and target cables in different categories. Based on the intra-cluster dissimilarity determined by the average intra-cluster distances and the out-of-cluster dissimilarity determined by the average out-of-cluster distances, clustering evaluation coefficients (profile coefficients) for the two categories are determined. When the clustering evaluation coefficients are greater than the preset evaluation coefficients, two cluster centers corresponding to the two categories are obtained.

[0085] When the clustering evaluation coefficient is less than the preset evaluation coefficient, the computer equipment can cluster multiple sample cables based on the temperature values ​​of two dimensions in the sample temperature data of each sample cable, divide the multiple sample cables into three categories, and obtain three cluster centers corresponding to the three categories respectively.

[0086] The computer equipment can determine the cluster center with the closest instantaneous temperature value of the preset cable state boundary among multiple cluster centers (two or three cluster centers) based on the instantaneous temperature value of the statistical temperature dimension; determine the cluster center with the closest statistical temperature value of the preset cable state boundary among multiple cluster centers based on the temperature values ​​of the statistical temperature dimension; calculate the arithmetic mean of the instantaneous temperature value of the preset cable state boundary and the temperature value of the instantaneous temperature dimension in the corresponding closest cluster center to obtain the corrected instantaneous temperature value of the cable state boundary; and calculate the arithmetic mean of the statistical temperature value of the preset cable state boundary and the temperature value of the statistical temperature dimension in the corresponding closest cluster center to obtain the corrected statistical temperature value of the cable state boundary.

[0087] For example, see... Figure 4 The diagram shows an example of cable condition boundary temperature value correction. The preset instantaneous temperature values ​​for cable condition boundaries include a preset instantaneous temperature value for easy failure (40℃) and a preset instantaneous temperature value for failure (60℃). The preset statistical temperature values ​​for cable condition boundaries include a preset statistical temperature value for easy failure (30℃) and a preset statistical temperature value for failure (50℃). Multiple cluster centers are two clusters.

[0088] Furthermore, a Cartesian coordinate system is constructed with instantaneous temperature as the x-axis and statistical temperature as the y-axis. Straight lines perpendicular to the corresponding coordinate axes are drawn using preset fault-prone instantaneous temperature values, preset fault instantaneous temperature values, preset fault-prone statistical temperature values, and preset fault statistical temperature values, respectively. This yields fault-prone instantaneous temperature lines, fault instantaneous temperature lines, fault-prone statistical temperature lines, and fault statistical temperature lines. The positions of the two cluster centers within the constructed Cartesian coordinate system are then determined. The two cluster centers are as follows: Figure 4 Based on the two coordinate points (34,46) and (68,48), the instantaneous temperature line prone to failure, the instantaneous temperature line of failure, the statistical temperature line of prone to failure, and the statistical temperature line of failure are corrected to obtain the corrected instantaneous temperature line prone to failure, the corrected instantaneous temperature line of failure, the corrected statistical temperature line of prone to failure, and the corrected statistical temperature line of failure, so as to obtain the corrected instantaneous temperature value of prone to failure (36℃), the corrected instantaneous temperature value of failure (64℃), the corrected statistical temperature value of prone to failure (38℃), and the corrected statistical temperature value of failure (49℃).

[0089] Computer equipment can be based on, for example Figure 4 The instantaneous temperature lines corresponding to the corrected cable condition boundary temperature values, the corrected fault-prone instantaneous temperature lines, and the corrected fault-prone statistical temperature lines corresponding to the corrected cable condition boundary statistical temperature values ​​are shown below. These are used to divide the range into nine temperature ranges in two dimensions. The correspondence between each temperature range and the cable condition can be seen as follows: Figure 5 As shown.

[0090] The computer device can generate a cable condition determination model based on nine temperature ranges with two dimensions and their corresponding cable conditions. The target temperature data of the target cable is input into the cable condition determination model to determine the temperature range to which the target temperature data belongs, and the cable condition corresponding to the determined temperature range is output as the cable condition of the target cable.

[0091] 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.

[0092] Based on the same inventive concept, this application also provides a cable temperature data processing apparatus for implementing the cable temperature data processing method described above. The solution provided by this apparatus is similar to the implementation described in the above method; therefore, the specific limitations in one or more cable temperature data processing apparatus embodiments provided below can be found in the limitations of the cable temperature data processing method described above, and will not be repeated here.

[0093] In one embodiment, such as Figure 6 As shown, a cable temperature data processing device 600 is provided, including: a clustering module 610, a correction module 620, and a range division module 630, wherein:

[0094] Clustering module 610 is used to cluster multiple sample cables based on the temperature values ​​of two dimensions in the sample temperature data of each sample cable, and obtain multiple cluster centers; the sample temperature data has two dimensions: instantaneous temperature dimension and statistical temperature dimension.

[0095] The correction module 620 is used to determine the cluster center that is closest to the preset instantaneous temperature value of the cable state boundary and the preset statistical temperature value of the cable state boundary respectively; and to correct the preset instantaneous temperature value of the cable state boundary and the preset statistical temperature value of the cable state boundary respectively by using the corresponding closest cluster center to obtain the corrected instantaneous temperature value of the cable state boundary and the corrected statistical temperature value of the cable state boundary.

[0096] The range division module 630 is used to divide the range based on the instantaneous temperature value of the corrected cable state boundary and the statistical temperature value of the corrected cable state boundary, to obtain multiple temperature ranges with two dimensions and their corresponding cable states; the multiple temperature ranges are used to determine the cable state of the target cable based on the temperature values ​​of the two dimensions in the target temperature data of the target cable.

[0097] In one embodiment, the correction module 620 is further configured to acquire temperature values ​​in two dimensions of the plurality of cluster centers respectively; determine the cluster center with the closest preset cable state boundary instantaneous temperature value among the plurality of cluster centers based on the temperature values ​​of the instantaneous temperature dimension among the plurality of cluster centers; and determine the cluster center with the closest preset cable state boundary statistical temperature value among the plurality of cluster centers based on the temperature values ​​of the statistical temperature dimension among the plurality of cluster centers.

[0098] In one embodiment, the correction module 620 is further configured to calculate the average value of the instantaneous temperature value of the preset cable state boundary and the temperature value of the instantaneous temperature dimension in the corresponding nearest cluster center to obtain the corrected instantaneous temperature value of the cable state boundary; and to calculate the average value of the statistical temperature value of the preset cable state boundary and the temperature value of the statistical temperature dimension in the corresponding nearest cluster center to obtain the corrected statistical temperature value of the cable state boundary.

[0099] In one embodiment, the clustering module 610 is further configured to cluster the multiple sample cables based on the temperature values ​​in two dimensions of their respective sample temperature data, dividing the multiple sample cables into two categories; for each of the multiple sample cables, according to their respective sample temperature data, calculate the intra-class average distance between the targeted sample cable and other sample cables in the same category within the two categories, and calculate the out-of-class average distance between the targeted sample cable and sample cables in different categories within the two categories; determine the clustering evaluation coefficient for the two categories based on the intra-class dissimilarity determined by the intra-class average distance corresponding to each of the multiple sample cables, and the out-of-class dissimilarity determined by the out-of-class average distance corresponding to each of the multiple sample cables; when the clustering evaluation coefficient is greater than a preset evaluation coefficient, obtain two cluster centers corresponding to the two categories respectively.

[0100] In one embodiment, the clustering module 610 is further configured to, when the clustering evaluation coefficient is less than a preset evaluation coefficient, cluster the multiple sample cables based on the temperature values ​​of two dimensions in the sample temperature data of each sample cable, divide the multiple sample cables into three categories, and obtain three cluster centers corresponding to the three categories respectively.

[0101] In one embodiment, the cable temperature data processing device 600 further includes a cable state determination model. The cable state determination model is generated based on multiple temperature ranges with two dimensions and their corresponding cable states. The cable state determination model takes the cable temperature data as input and outputs the cable state in which the cable is located. The cable state determination model is used to input the target temperature data of the target cable into the cable state determination model, determine the temperature range to which the target temperature data belongs, and output the cable state corresponding to the determined temperature range as the cable state in which the target cable is located.

[0102] Each module in the aforementioned cable temperature data processing device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0103] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 7 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 operation of the operating system and computer programs stored in the non-volatile storage media. The database stores data required for executing the cable temperature data processing method. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a cable temperature data processing method.

[0104] Those skilled in the art will understand that Figure 7 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.

[0105] In one embodiment, a computer device is also 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 method embodiments.

[0106] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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 processing cable temperature data, characterized in that, The method includes: Based on the temperature values ​​of two dimensions in the sample temperature data of multiple sample cables, clustering is performed on the multiple sample cables to obtain multiple cluster centers. This clustering includes: dividing the multiple sample cables into two categories based on the temperature values ​​of two dimensions in the sample temperature data of each sample cable; the sample temperature data has two dimensions: instantaneous temperature and statistical temperature. The instantaneous temperature is the temperature measured in real time at any given moment, and the statistical temperature is the temperature statistically obtained based on the instantaneous temperature over a period of time. For each of the plurality of sample cables, based on the sample temperature data of each of the plurality of sample cables, the intra-class average distance between the sample cable and other sample cables in the same category in the two categories is calculated, and the out-of-class average distance between the sample cable and sample cables in different categories in the two categories is also calculated. Based on the intra-class dissimilarity determined by the intra-class average distances corresponding to each of the plurality of sample cables, and the out-of-class dissimilarity determined by the out-of-class average distances corresponding to each of the plurality of sample cables, a clustering evaluation coefficient for the two categories is determined. When the clustering evaluation coefficient is greater than a preset evaluation coefficient, two cluster centers corresponding to the two categories are obtained respectively. The process involves determining the cluster centers that are closest to both the instantaneous temperature value and the statistical temperature value of the preset cable state boundary. This determination includes: acquiring temperature values ​​in two dimensions from the plurality of cluster centers; determining the cluster center with the closest instantaneous temperature value of the preset cable state boundary from among the plurality of cluster centers based on the instantaneous temperature dimension value; and determining the cluster center with the closest statistical temperature value of the preset cable state boundary from among the plurality of cluster centers based on the statistical temperature dimension value. For the preset instantaneous temperature value of the cable state boundary and the preset statistical temperature value of the cable state boundary, respectively, the nearest cluster center is used for correction to obtain the corrected instantaneous temperature value of the cable state boundary and the corrected statistical temperature value of the cable state boundary. Based on the instantaneous temperature value of the corrected cable state boundary and the statistical temperature value of the corrected cable state boundary, the range is divided to obtain multiple temperature ranges with the two dimensions and their corresponding cable states; the multiple temperature ranges are used to determine the cable state of the target cable based on the temperature values ​​of the two dimensions in the target temperature data of the target cable.

2. The method according to claim 1, wherein the step of correcting the preset cable state boundary instantaneous temperature value and the preset cable state boundary statistical temperature value using the corresponding nearest cluster center to obtain the corrected cable state boundary instantaneous temperature value and the corrected cable state boundary statistical temperature value includes: The average value of the instantaneous temperature at the preset cable state boundary and the temperature value of the instantaneous temperature dimension in the nearest cluster center is calculated to obtain the corrected instantaneous temperature at the cable state boundary. The average value of the preset cable state boundary statistical temperature value and the temperature value of the statistical temperature dimension in the nearest cluster center is calculated to obtain the corrected cable state boundary statistical temperature value.

3. The method according to claim 1, characterized in that, The method involves clustering the multiple sample cables based on two dimensions of temperature values ​​from their respective sample temperature data to obtain multiple cluster centers, including: When the clustering evaluation coefficient is less than the preset evaluation coefficient, the multiple sample cables are clustered based on the temperature values ​​of two dimensions in the sample temperature data of each sample cable, and the multiple sample cables are divided into three categories to obtain three cluster centers corresponding to the three categories respectively.

4. The method according to claim 1, characterized in that, The method further includes: Based on multiple temperature ranges with the two dimensions and their corresponding cable states, a cable state determination model is generated; the cable state determination model takes the cable temperature data as input and the cable state as output. Input the target temperature data of the target cable into the cable state determination model, determine the temperature range to which the target temperature data belongs, and output the cable state corresponding to the determined temperature range as the cable state of the target cable.

5. A cable temperature data processing device, characterized in that, The device includes: The clustering module is used to cluster the multiple sample cables based on two dimensions of temperature values ​​from their respective sample temperature data, obtaining multiple cluster centers. This clustering process includes: dividing the multiple sample cables into two categories based on the two dimensions of temperature values ​​from their respective sample temperature data; the sample temperature data has two dimensions: instantaneous temperature and statistical temperature. The instantaneous temperature is the temperature measured in real time at any given moment, and the statistical temperature is calculated based on the instantaneous temperature over a period of time. The temperature is measured; for each of the plurality of sample cables, based on the sample temperature data of each of the plurality of sample cables, the intra-class average distance between the sample cable and other sample cables in the same category in the two categories is calculated, and the out-of-class average distance between the sample cable and sample cables in different categories in the two categories is calculated; based on the intra-class dissimilarity determined by the intra-class average distance corresponding to each of the plurality of sample cables, and the out-of-class dissimilarity determined by the out-of-class average distance corresponding to each of the plurality of sample cables, the clustering evaluation coefficient for the two categories is determined; when the clustering evaluation coefficient is greater than the preset evaluation coefficient, two cluster centers corresponding to the two categories are obtained respectively; The correction module is used to determine the cluster centers that are closest to the preset cable state boundary instantaneous temperature value and the preset cable state boundary statistical temperature value, respectively. The determination of the cluster centers that are closest to the preset cable state boundary instantaneous temperature value and the preset cable state boundary statistical temperature value includes: acquiring temperature values ​​in two dimensions from the plurality of cluster centers; determining the cluster center that is closest to the preset cable state boundary instantaneous temperature value from the plurality of cluster centers based on the instantaneous temperature dimension temperature value; and determining the cluster center that is closest to the preset cable state boundary statistical temperature value from the plurality of cluster centers based on the statistical temperature dimension temperature value. The correction module is further configured to correct the instantaneous temperature value of the preset cable state boundary and the statistical temperature value of the preset cable state boundary by using the corresponding closest cluster center to obtain the corrected instantaneous temperature value of the cable state boundary and the corrected statistical temperature value of the cable state boundary. The range division module is used to divide the range based on the instantaneous temperature value of the corrected cable state boundary and the statistical temperature value of the corrected cable state boundary, to obtain multiple temperature ranges with the two dimensions and their corresponding cable states; the multiple temperature ranges are used to determine the cable state of the target cable based on the temperature values ​​of the two dimensions in the target temperature data of the target cable.

6. The apparatus according to claim 5, characterized in that, The clustering module is also used to cluster the multiple sample cables based on the temperature values ​​of two dimensions in the sample temperature data of each sample cable when the clustering evaluation coefficient is less than the preset evaluation coefficient, divide the multiple sample cables into three categories, and obtain three cluster centers corresponding to the three categories respectively.

7. The apparatus according to claim 5, characterized in that, The device also includes a cable condition determination model; the cable condition determination model is generated based on multiple temperature ranges with the two dimensions and their corresponding cable conditions. The cable condition determination model takes the cable temperature data as input and the cable condition as output. The cable condition determination model is used to input the target temperature data of the target cable into the cable condition determination model, determine the temperature range to which the target temperature data belongs, and output the cable condition corresponding to the determined temperature range as the cable condition of the target cable.

8. 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.

9. 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.

10. 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