Temperature-based cable fault handling method, apparatus, and non-transitory storage medium

Abstract

This invention discloses a temperature-based cable fault handling method, apparatus, and non-volatile storage medium. The method includes: acquiring initial temperature profile data and high-frequency characteristic data of a target cable using a distributed fiber optic temperature measurement system; if anomalies exist in the initial temperature profile data, generating and replacing the anomaly-containing data in the initial temperature profile data based on the high-frequency characteristic data to obtain the target temperature profile data; calculating the spatiotemporal gradient tensor and local anomaly factor based on the target temperature profile data; determining fault handling instructions for the target cable based on the spatiotemporal gradient tensor and local anomaly factor; and handling the faults existing in the target cable based on the fault handling instructions. This invention solves the technical problems of current cable temperature monitoring data loss due to single-point failures and the inability to accurately identify fault precursors based on high-dimensional spatiotemporal characteristics.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power cable fault detection and processing, in particular to a temperature-based cable fault processing method, device and nonvolatile storage medium. BACKGROUND

[0002] In the field of power cable state monitoring, temperature, as the core physical parameter reflecting the running health condition of the cable and the degradation degree of the insulation material, has long relied on the distributed optical fiber temperature measurement (DTS, Distributed Temperature Sensing) technology based on Raman scattering to realize global perception. However, the current mainstream system still follows the traditional architecture of “data acquisition-remote upload-cloud analysis-manual decision”, and its essence is still a passive, scalar and single-point dependent monitoring paradigm, which is difficult to meet the urgent needs of modern urban cable networks for high reliability, strong real-time performance and intelligent prediction. Although such a system can output a continuous temperature profile, it only relies on preset threshold values for out-of-limit alarms, ignoring the fault precursor characteristics contained in the spatial gradient evolution and time dynamic coupling of the temperature field, resulting in a large number of potential risks being hidden in “normal fluctuations”. At the same time, the sensing link is a single optical fiber in series structure, and the breakage of any node, the failure of the coupler or the failure of the acquisition unit will cause the interruption of the monitoring function of the entire cable. In addition, the closed-loop delay from data acquisition to control instruction issuance generally exists in seconds or even minutes, and for the sub-second temperature rise mutation caused by partial discharge or arc initial stage, the system cannot intervene before thermal runaway occurs. In addition, the complex environmental factors such as electromagnetic interference and mechanical vibration in the cable corridor have dynamic and variable frequency spectrum, and the traditional fixed parameter filtering algorithm lacks self-adaptive ability, often resulting in a large number of false alarm burrs due to misjudgment, or real abnormalities being hidden due to excessive suppression, causing a sharp decline in data reliability.

[0003] At present, there is no effective solution to the above problems. SUMMARY

[0004] The embodiments of the present application provide a temperature-based cable fault processing method, device and nonvolatile storage medium to at least solve the technical problems that the current cable temperature monitoring data loses integrity due to single-point failure, and cannot realize accurate identification of fault precursors based on high-dimensional spatiotemporal features.

[0005] According to one aspect of the present invention, a temperature-based cable fault handling method is provided, comprising: acquiring initial temperature profile data and high-frequency characteristic data of a target cable through a distributed optical fiber temperature measurement system, wherein the initial temperature profile data is the temperature of the target cable at multiple measurement points spatially distributed along the axial direction of the target cable, and the high-frequency characteristic data characterizes the high-frequency fluctuation characteristic data and optical signal distortion characteristic data in the distributed optical fiber temperature measurement system; in the event of anomalies in the initial temperature profile data, generating and replacing the anomaly data in the initial temperature profile data with the replacement data based on the high-frequency characteristic data to obtain the target temperature profile data; calculating a spatiotemporal gradient tensor and a local anomaly factor based on the target temperature profile data, wherein the spatiotemporal gradient tensor characterizes the temperature change along the axial direction of the target cable over time, and the local anomaly factor characterizes the degree of temperature deviation of each measurement point relative to its neighborhood; determining fault handling instructions for the target cable based on the spatiotemporal gradient tensor and the local anomaly factor; and handling the faults existing in the target cable based on the fault handling instructions.

[0006] Optionally, the high-frequency characteristic data includes the optical energy fluctuation rate of the preset frequency band, the instantaneous change rate of Raman scattered light intensity, the phase jitter variance, and the polarization state perturbation spectrum.

[0007] Optionally, if there are anomalies in the initial temperature profile data, replacement data corresponding to the abnormal data in the initial temperature profile data is generated based on high-frequency feature data and replaced to obtain target temperature profile data. This includes: inputting high-frequency feature data into a preset historical health model to obtain replacement data, wherein the historical health model is trained based on the normal temperature profile data and historical high-frequency feature data of the target cable within a preset historical period.

[0008] Optionally, the mathematical expression for the spatiotemporal gradient tensor is as follows:

[0009] ,

[0010] in, For measurement points ,time The temperature of the target cable The rate of change of temperature along the axial direction of the target cable. The rate of change of the spatial gradient of temperature along the axis of the target cable. The rate of change of temperature over time. This represents the rate of change of temperature over time.

[0011] Optionally, the mathematical expression for the local anomaly factor is as follows:

[0012] ,

[0013] in, For measurement points ,time The temperature of the target cable For measurement points A set of local spatial neighborhoods centered on the measurement point And a preset number of measurement points Adjacent measurement points, For at any time Neighborhood The median temperature at all measurement points within the area. For at any time Neighborhood The standard deviation of temperature at all measurement points within the range.

[0014] Optionally, based on the spatiotemporal gradient tensor and local anomaly factors, fault handling instructions for the target cable are determined, including: if the magnitude of the local anomaly factor exceeds a first preset threshold, the fault handling instruction is determined to be a first-level instruction, wherein the first-level instruction represents a handling instruction that directly triggers emergency physical isolation and protection actions; or if the magnitude of the local anomaly factor does not exceed the first preset threshold but exceeds a second preset threshold, the cause of the fault in the target cable is determined based on the spatiotemporal gradient tensor, and based on the cause of the fault, the fault handling instruction is determined to be a second-level instruction and the content of the second-level instruction, wherein the second-level instruction represents a handling instruction that initiates auxiliary cooling and monitoring enhancement measures; or if the magnitude of the local anomaly factor does not exceed the second preset threshold, the future temperature trend of the target cable is predicted based on the spatiotemporal gradient tensor, and based on the future temperature trend, the fault handling instruction is determined to be a third-level instruction and the content of the third-level instruction, wherein the third-level instruction represents a handling instruction that does not perform hardware operations and sends an alarm prompt to the user terminal.

[0015] According to another aspect of the present invention, a temperature-based cable fault handling device is also provided, comprising: an acquisition module, configured to acquire initial temperature profile data and high-frequency characteristic data of a target cable through a distributed optical fiber temperature measurement system, wherein the initial temperature profile data is the temperature of the target cable at multiple measurement points spatially distributed along the axial direction of the target cable, and the high-frequency characteristic data characterizes high-frequency fluctuation characteristic data and optical signal distortion characteristic data in the distributed optical fiber temperature measurement system; a generation module, configured to generate and replace the abnormal data in the initial temperature profile data with the abnormal data based on the high-frequency characteristic data, in the event of anomalies in the initial temperature profile data, thereby obtaining target temperature profile data; a calculation module, configured to calculate a spatiotemporal gradient tensor and a local anomaly factor based on the target temperature profile data, wherein the spatiotemporal gradient tensor characterizes the temperature change along the axial direction of the target cable over time, and the local anomaly factor characterizes the degree of temperature deviation of each measurement point relative to its neighborhood; a determination module, configured to determine a fault handling instruction for the target cable based on the spatiotemporal gradient tensor and the local anomaly factor; and a processing module, configured to process the fault existing in the target cable based on the fault handling instruction.

[0016] According to another aspect of the present invention, a non-volatile storage medium is also provided, the non-volatile storage medium including a stored program, wherein, when the program is running, the device where the non-volatile storage medium is located is controlled to execute any of the above-described temperature-based cable fault handling methods.

[0017] According to another aspect of the present invention, a computer device is also provided, the computer device including a processor for running a program, wherein the program executes any of the above-described temperature-based cable fault handling methods during execution.

[0018] According to another aspect of the present invention, a computer program product is also provided, including a computer program that, when executed by a processor, implements any of the above-described temperature-based cable fault handling methods.

[0019] In this embodiment of the invention, a temperature-based cable fault handling method is employed. A distributed optical fiber temperature measurement system is used to acquire initial temperature profile data and high-frequency characteristic data of the target cable. The initial temperature profile data represents the temperature of the target cable at multiple measurement points spatially distributed along the cable's axial direction. The high-frequency characteristic data characterizes the high-frequency fluctuation characteristics and optical signal distortion characteristics of the distributed optical fiber temperature measurement system. If anomalies exist in the initial temperature profile data, replacement data corresponding to the anomalies in the initial temperature profile data is generated based on the high-frequency characteristic data and used to replace them, thus obtaining the target temperature profile data. Based on the target temperature profile data, the spatiotemporal gradient tensor and local anomaly factor are calculated. The spatiotemporal gradient tensor characterizes the temperature variation along the target cable axis over time, while the local anomaly factor characterizes the degree of temperature deviation of each measurement point relative to its neighborhood. Based on the spatiotemporal gradient tensor and the local anomaly factor, fault handling instructions for the target cable are determined. Based on the fault handling instructions, the faults existing in the target cable are processed, achieving the goal of dynamically generating targeted fault handling instructions and implementing precise intervention in abnormal areas of the cable. This enables data self-repair, high-precision identification of fault precursors, and intelligent response without relying on redundant hardware. Consequently, it solves the current technical problems of cable temperature monitoring data loss due to single-point failure and the inability to accurately identify fault precursors based on high-dimensional spatiotemporal features. Attached Figure Description

[0020] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0021] Figure 1 A hardware block diagram of a computer terminal for implementing a temperature-based cable fault handling method is shown.

[0022] Figure 2 This is a schematic flowchart of a temperature-based cable fault handling method provided according to an embodiment of the present invention;

[0023] Figure 3 This is a structural block diagram of a temperature-based cable fault handling device provided according to an embodiment of the present invention. Detailed Implementation

[0024] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0025] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0026] According to an embodiment of the present invention, a temperature-based cable fault handling method is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0027] The method embodiment provided in Embodiment 1 of this application can be executed on a mobile terminal, computer terminal, or similar computing device. Figure 1 A hardware block diagram of a computer terminal for implementing a temperature-based cable fault handling method is shown. Figure 1 As shown, the computer terminal 10 may include one or more processors (shown as 102a, 102b, ..., 102n in the figure) (the processor may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of a BUS bus), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the sameFigure 1 The different configurations shown.

[0028] It should be noted that the aforementioned one or more processors and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer terminal 10. As involved in the embodiments of this application, the data processing circuits serve as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).

[0029] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the temperature-based cable fault handling method in this embodiment of the invention. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby implementing the temperature-based cable fault handling method of the aforementioned application. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor, and these remote memories can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0030] The display can be, for example, a touchscreen liquid crystal display (LCD) that allows the user to interact with the user interface of the computer terminal 10.

[0031] Figure 2 This is a schematic flowchart of a temperature-based cable fault handling method provided according to an embodiment of the present invention, as shown below. Figure 2 As shown, the method includes the following steps:

[0032] Step S201: The initial temperature profile data and high-frequency characteristic data of the target cable are obtained through the distributed optical fiber temperature measurement system. The initial temperature profile data is the temperature of the target cable at multiple measurement points spatially distributed along the axial direction of the target cable. The high-frequency characteristic data characterizes the high-frequency fluctuation characteristic data and optical signal distortion characteristic data in the distributed optical fiber temperature measurement system.

[0033] In this step, a dual-channel heterogeneous distributed fiber optic temperature measurement system is deployed to simultaneously acquire initial temperature profile data and high-frequency characteristic data of the target cable. These two data points are not acquired independently but originate from the multi-dimensional optical signal response of the same fiber optic sensing link. The initial temperature profile data is generated by the main channel based on a standard Raman scattering demodulation algorithm, accurately reconstructing the steady-state temperature distribution of thousands of sampling points along the cable axis, reflecting the overall macroscopic state of the thermal field. The high-frequency characteristic data is extracted by the auxiliary channel at a higher sampling rate, capturing transient perturbation information contained in the optical signal. This includes abrupt changes in Rayleigh scattering intensity caused by partial discharge, arc breakdown, or mechanical disturbances; nonlinear distortions in the backscattering spectrum; and sub-microsecond energy spikes in the optical time-domain reflectometry curve. These data do not directly correspond to temperature values ​​but characterize the high-frequency dynamic behavior of physical disturbances within the system. The auxiliary channel is not a simple backup but rather synchronously samples key state parameters of the main channel at a higher frequency. When a segment of the fiber optic signal in the main channel deteriorates, the auxiliary channel can immediately detect it and initiate a data repair algorithm based on spatiotemporal correlation. Using its own data and historical health data models, it generates an alternative temperature estimate for that segment, thereby maintaining data integrity.

[0034] Step S202: If there are anomalies in the initial temperature profile data, based on high-frequency feature data, generate alternative data corresponding to the data with anomalies in the initial temperature profile data and replace them to obtain the target temperature profile data.

[0035] In this step, when the initial temperature profile acquired by the main channel suffers from data loss or distortion due to physical damage such as fiber bending, connector oxidation, or local breakage, the information for that segment is not directly discarded. Instead, a "thermal shadow" self-healing mechanism is activated: the auxiliary channel continuously and synchronously samples key optical signal dynamic characteristics of the main channel at a higher frequency, such as the rate of change of scattering intensity, spectral distortion trends, and local phase drift. Although these high-frequency characteristic data do not directly characterize temperature, they can keenly capture early signs of main channel degradation and their spatial location. Based on the historical health database and spatiotemporal correlation model, a dynamic mapping relationship between the main and auxiliary channels is constructed. When an anomaly is detected in a segment of the main channel, the high-frequency characteristic sequence acquired by the auxiliary channel in the neighborhood of that location is immediately invoked. Combined with the temperature evolution pattern of neighboring healthy segments, a physically consistent alternative temperature value is generated in real time through spatiotemporal interpolation and feature inversion algorithms. This alternative data is not a simple interpolation but integrates the temperature gradient trend before the fault, the physical constraints of heat conduction, and the local environmental heat capacity characteristics, ensuring that the generated temperature profile is highly realistic in terms of spatial continuity and temporal evolution rationality. The replacement process is completed within milliseconds and is completely transparent to the upper-level decision-making module, thus maintaining complete awareness of the cable temperature field even in extreme conditions where the main channel fails.

[0036] Step S203: Based on the target temperature profile data, calculate the spatiotemporal gradient tensor and the local anomaly factor. The spatiotemporal gradient tensor characterizes the temperature change over time along the target cable axis, and the local anomaly factor characterizes the degree of temperature deviation of each measurement point relative to its neighborhood.

[0037] In this step, based on the target temperature profile data repaired by the "thermal shadow" mechanism, the spatiotemporal evolution characteristics of the temperature field are constructed in real time to surpass the limitations of traditional scalar threshold alarms. The spatiotemporal gradient tensor quantifies the spatial non-uniformity of temperature distribution and the acceleration characteristics of temperature rise by calculating the temperature gradient of each measurement point in the axial space of the cable and its second derivative with time, thereby capturing the asymmetric evolution patterns of typical faults such as "local sudden rise, stable adjacent sections" in the joint area. The local anomaly factor calculates the deviation of the temperature value of each measurement point from the median temperature in its neighboring spatial window (e.g., within 5 meters), effectively suppressing misjudgments caused by slow environmental drift or global temperature rise, and accurately identifying sudden anomalies in isolated hotspots. Together, the two constitute a high-dimensional feature tensor, which not only reflects "where the temperature is high" but also reveals "why the anomaly occurs"—the spatiotemporal gradient reveals the dynamic development trend of the fault, and the local anomaly factor locks the most vulnerable local nodes, forming a foundation for fault precursor identification that combines spatial sensitivity and temporal dynamics.

[0038] Step S204: Determine the fault handling instructions for the target cable based on the spatiotemporal gradient tensor and local anomaly factor.

[0039] In this step, a high-dimensional feature tensor constructed based on the spatiotemporal gradient tensor and local anomaly factors is used to initiate a three-layer millisecond-level funnel decision model at the edge. Instead of relying on a single temperature threshold, it determines the fault type and urgency level through the combination and evolution logic of feature patterns. When an abnormally steep increase in the temperature spatial gradient and a significant positive second-order time derivative (i.e., the temperature rise acceleration exceeds the physical limit) occurs in a certain segment of the spatiotemporal gradient tensor, accompanied by a sudden jump in local anomaly factors, it is determined to be a precursor to thermal runaway caused by an electric arc or partial discharge. The highest priority L1 command is immediately triggered—such as instantaneously cutting off the power supply or initiating emergency cooling—achieving a "reflex arc" response. If the feature tensor exhibits a slowly expanding cluster of local high anomaly factors and symmetrical gradient evolution, it matches a pre-stored "loose joint" or "insulation dampness" pattern library, triggering an L2-level alarm and pushing pre-set handling suggestions. For low-amplitude but continuously accumulating feature trends, a lightweight time series model is invoked to predict whether the safety boundary will be breached within the next few minutes, triggering an L3-level early warning in advance.

[0040] Step S205: Based on the fault handling instructions, handle the faults existing in the target cable.

[0041] In this step, after generating fault handling instructions at the edge decision layer, a resilient execution layer ensures reliable execution of these instructions in an atomic manner. Each instruction—such as "start wind turbine A," "trip circuit breaker B," or "close bypass switch C"—is encapsulated with the minimum necessary data (target device ID, action type, timestamp, checksum) into an indivisible atomic unit and stored in a local non-volatile memory instruction queue, ensuring no data loss during power outages or network interruptions. Instructions are delivered to the field execution device via a multi-protocol adaptive interface (e.g., Modbus TCP, GOOSE, MQTT, etc.), simultaneously initiating an acknowledgment-timeout retransmission mechanism: if no acknowledgment feedback is received from the execution unit within a set millisecond window, the instruction is automatically retransmitted; if consecutive retransmissions fail, rollback logic is triggered, such as automatically shutting down already started wind turbines or forcibly disconnecting already closed switches, preventing secondary risks caused by misoperation. This process is entirely completed locally, without relying on the cloud or network links, ensuring deterministic execution of instructions even in extreme environments such as power corridor communication interruptions or severe electromagnetic interference. Meanwhile, all operations are linked to the holographic sensing data of the temperature field, and are only triggered after the feature tensor clearly points to the real fault and interference and misjudgment are eliminated, thus preventing false actions caused by noise.

[0042] Through the above steps, the goal of dynamically generating targeted fault handling instructions and implementing precise intervention in abnormal areas of the cable is achieved. This enables data self-repair, high-precision identification of fault precursors, and intelligent response without relying on redundant hardware. It also solves the current technical problems of cable temperature monitoring data losing integrity due to single-point failure and being unable to accurately identify fault precursors based on high-dimensional spatiotemporal features.

[0043] As an optional embodiment, the high-frequency characteristic data includes the optical energy fluctuation rate of a preset frequency band, the instantaneous change rate of Raman scattered light intensity, the phase jitter variance, and the polarization state perturbation spectrum.

[0044] Optionally, high-frequency characteristic data originates from the high-precision capture of transient disturbances in weak optical signals in distributed optical fiber sensing by the auxiliary channel, which is a key sensing dimension for identifying early cable faults. The optical energy fluctuation rate of the preset frequency band reflects the rapid fluctuation of the scattered light intensity within a specific optical band (such as 1-10kHz), and can sensitively capture high-frequency electromagnetic pulse interference generated by partial discharge or arc; the instantaneous change rate of Raman scattered light intensity characterizes the drastic jump of temperature-sensitive Raman signals per unit time, which is directly related to the instantaneous energy release of sudden heat sources (such as joint arcing); the phase jitter variance reveals the structural micro-deformation caused by fiber micro-bending, connector loosening or mechanical vibration by analyzing the phase noise statistical characteristics of Rayleigh backscattered light, and its sudden increase in variance is often a precursor to physical degradation; the polarization state disturbance spectrum monitors the random drift and frequency domain distribution of the optical signal polarization direction, and is highly sensitive to optical field distortion caused by strong electromagnetic interference in the cable corridor or abnormal induction of the metal shielding layer.

[0045] As an optional embodiment, in the event of anomalies in the initial temperature profile data, alternative data corresponding to the abnormal data in the initial temperature profile data is generated based on high-frequency feature data and replaced to obtain target temperature profile data. This includes: inputting high-frequency feature data into a preset historical health model to obtain alternative data, wherein the historical health model is trained based on the normal temperature profile data and historical high-frequency feature data of the target cable within a preset historical period.

[0046] Optionally, when the initial temperature profile acquired by the main channel is partially missing or distorted due to fiber breakage, connector aging, or strong electromagnetic interference, the system does not simply interpolate or discard the data. Instead, it activates a "thermal shadow" self-healing mechanism, relying on high-frequency characteristic data continuously and synchronously acquired by the auxiliary channel—including the optical energy fluctuation rate of the preset frequency band, the instantaneous change rate of Raman scattered light intensity, phase jitter variance, and polarization state disturbance spectrum. Although these data do not directly characterize temperature, they accurately capture the micro-perturbation fingerprint of the local physical state of the cable. These real-time high-frequency features are input into a pre-trained historical health model. This model is constructed based on the "temperature profile-high-frequency feature" collaborative data pair accumulated during the long-term normal operation of the target cable, and has learned and solidified the implicit evolution law and spatial correlation of the temperature field under different disturbance modes. For example, when the auxiliary channel detects a sudden increase in phase jitter variance and an abnormal change rate of Raman light intensity in a certain section, the model infers that there is a slight bend in the optical fiber or a slight loosening of the connector. Combining this with the temperature distribution pattern corresponding to similar disturbances in history, the model automatically generates a reasonable estimate of the missing or abnormal temperature value in that area. The replacement data is not an isolated interpolation, but rather integrates a spatial neighborhood heat conduction model with temporal continuity constraints to ensure that the generated temperature profile is physically self-consistent and spatially coherent. After the replacement is completed, the target temperature profile regains its integrity and reliability, achieving seamless continuation of monitoring functions.

[0047] As an optional implementation, the mathematical expression for the spatiotemporal gradient tensor is as follows:

[0048] ,

[0049] in, For measurement points ,time The temperature of the target cable The rate of change of temperature along the axial direction of the target cable. The rate of change of the spatial gradient of temperature along the axis of the target cable. The rate of change of temperature over time. This represents the rate of change of temperature over time.

[0050] Optionally, the spatiotemporal gradient tensor is the core mathematical representation for achieving "holographic temperature field perception." It elevates the cable temperature from a single scalar value to a four-dimensional physical field with spatial structure and dynamic evolution. Specifically, it describes the local slope of temperature along the cable axis, identifying the starting point of abnormal temperature rise regions; reflects the spatial curvature of the temperature gradient, accurately locating nonlinear heat distributions such as "sharp rise-sudden drop" at joints, distinguishing it from uniform overheating; captures the instantaneous rate of temperature change over time, providing direct evidence of whether a thermal event is occurring; and serves as the acceleration of temperature rise, a key indicator for identifying millisecond-level drastic faults such as arcing and partial discharge—a sudden increase in its value often foreshadows the critical point of thermal runaway. These four elements are calculated synchronously at each measurement point, forming a dynamically updated four-element feature vector that fully characterizes the physical essence of the temperature field: "where it differs, how it differs, how quickly it changes, and how fast it changes."

[0051] As an optional implementation, the mathematical expression for the local anomaly factor is as follows:

[0052] ,

[0053] in, For measurement points ,time The temperature of the target cable For measurement points A set of local spatial neighborhoods centered on the measurement point And a preset number of measurement points Adjacent measurement points, For at any time Neighborhood The median temperature at all measurement points within the area. For at any time Neighborhood The standard deviation of temperature at all measurement points within the range.

[0054] Optionally, the Local Anomaly Factor (LAF) is a key robustness indicator for achieving "holographic temperature field perception." Its design aims to accurately identify local hotspots and avoid interference from slow changes in global temperature and the environment. This expression is based on the measured temperature of each measurement point at a given time, comparing it to the median, rather than the mean, temperature of all adjacent measurement points within its local neighborhood. This effectively suppresses the contamination of the baseline by outliers. Normalization is then achieved by dividing by the standard deviation of the temperatures within that neighborhood, ensuring scale invariance in the evaluation results. When the temperature at a point significantly deviates from the median of its "neighbors," and the deviation exceeds the normal fluctuation range within the neighborhood, the LAF value will rise sharply, accurately pinpointing "point anomalies" such as poor joint contact or localized insulation degradation, rather than "area drift" caused by an overall increase in ambient temperature. This mechanism has spatial adaptability, requiring no global threshold. Even if the temperature along the entire cable rises slowly, as long as there is no "abrupt deviation" in any local area, the LAF remains low, significantly reducing the false alarm rate. In the millisecond-level decision-making layer, the instantaneous rise of LAF, combined with the second derivative of temperature, becomes a combined feature for judging sudden faults such as arcing and discharge. It can detect potential risks through "relative anomalies" before the absolute temperature value exceeds the limit, thus achieving a fundamental leap from "passive alarm" to "active prediction".

[0055] As an optional embodiment, based on the spatiotemporal gradient tensor and local anomaly factors, the fault handling instructions for the target cable are determined, including: if the magnitude of the local anomaly factor exceeds a first preset threshold, the fault handling instruction is determined to be a first-level instruction, wherein the first-level instruction represents a handling instruction that directly triggers emergency physical isolation and protection actions; or if the magnitude of the local anomaly factor does not exceed the first preset threshold but exceeds a second preset threshold, the fault cause of the target cable is determined based on the spatiotemporal gradient tensor, and based on the fault cause, the fault handling instruction is determined to be a second-level instruction and the content of the second-level instruction, wherein the second-level instruction represents a handling instruction that initiates auxiliary cooling and monitoring enhancement measures; or if the magnitude of the local anomaly factor does not exceed the second preset threshold, the future temperature trend of the target cable is predicted based on the spatiotemporal gradient tensor, and based on the future temperature trend, the fault handling instruction is determined to be a third-level instruction and the content of the third-level instruction, wherein the third-level instruction represents a handling instruction that does not perform hardware operations but sends an alarm prompt to the user terminal.

[0056] Optionally, a three-level funnel decision-making mechanism based on the spatiotemporal gradient tensor and the local anomaly factor (LAF) enables a hierarchical response from instantaneous risk to trend warning. When the LAF or the second derivative of temperature with respect to time instantaneously exceeds the first preset threshold, it indicates an extreme anomaly where the local temperature deviates drastically from the surrounding background, such as millisecond-level thermal runaway caused by an electric arc or short circuit. This immediately triggers the first-level instruction—directly initiating physical isolation and protection actions, such as cutting off the power supply or closing the grounding switch, without the need for subsequent logical judgment, forming a "reflection arc" type emergency response to ensure that thermal runaway is physically blocked before it spreads. If the LAF does not reach the first threshold but is higher than the second threshold, it enters the pattern recognition layer, combining the joint features of the spatial second derivative (temperature curvature) and the temporal first derivative (temperature rise rate) in the spatiotemporal gradient tensor. The system rapidly matches the temperature evolution curve of the suspected area over the past few seconds, comparing it with pre-stored typical fault templates such as "loose joints" and "insulation dampness" to identify the fault type and trigger second-level instructions, such as activating nearby fans to enhance heat dissipation or increasing sampling frequency to strengthen monitoring, achieving precise intervention rather than blind shutdown. When the LAF (Loose Temperature Flow) remains below the second national value, it transitions to the trend prediction layer, using a lightweight state-space model to predict the temperature trend over the next few minutes. If the prediction is close to the warning line but has not yet posed an immediate risk, a third-level instruction is triggered, pushing trend alarms and suggested inspection prompts only to the maintenance terminal, without disturbing on-site equipment and avoiding misoperation. The three levels of instructions are progressively advanced, ensuring both millisecond-level response to extreme faults and intelligent early warning of slow degradation, achieving a balance between safety, accuracy, and reliability.

[0057] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the present invention is not limited to the described order of actions, because according to the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0058] Through the above description of the embodiments, those skilled in the art can clearly understand that the temperature-based cable fault handling method according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0059] According to embodiments of the present invention, an apparatus for implementing the above-described temperature-based cable fault handling method is also provided. Figure 3 This is a structural block diagram of a temperature-based cable fault handling device according to an embodiment of the present invention, such as... Figure 3 As shown, the device includes: an acquisition module 31, a generation module 32, a calculation module 33, a determination module 34, and a processing module 35. The device will be described below.

[0060] The acquisition module 31 is used to acquire the initial temperature profile data and high-frequency characteristic data of the target cable through the distributed optical fiber temperature measurement system. The initial temperature profile data is the temperature of the target cable at multiple measurement points spatially distributed along the axial direction of the target cable, and the high-frequency characteristic data characterizes the high-frequency fluctuation characteristic data and optical signal distortion characteristic data in the distributed optical fiber temperature measurement system.

[0061] The generation module 32, connected to the acquisition module 31, is used to generate and replace the abnormal data in the initial temperature profile data based on high-frequency feature data when there are anomalies in the initial temperature profile data, thereby obtaining the target temperature profile data.

[0062] The calculation module 33, connected to the generation module 32, is used to calculate the spatiotemporal gradient tensor and local anomaly factor based on the target temperature profile data. The spatiotemporal gradient tensor represents the temperature change over time along the target cable axis, and the local anomaly factor represents the degree of temperature deviation of each measurement point relative to its neighborhood.

[0063] The determination module 34, connected to the calculation module 33, is used to determine the fault handling instructions for the target cable based on the spatiotemporal gradient tensor and local anomaly factors.

[0064] The processing module 35, connected to the determination module 34, is used to process the faults existing in the target cable based on the fault processing instructions.

[0065] It should be noted that the acquisition module 31, generation module 32, calculation module 33, determination module 34, and processing module 35 mentioned above correspond to steps S201 to S205 in the embodiments. Multiple modules and their corresponding steps implement the same instances and application scenarios, but are not limited to the content disclosed in the above embodiments. It should also be noted that the above modules, as part of the device, can run on the computer terminal 10 provided in the embodiments.

[0066] Embodiments of the present invention may provide a computer device. Optionally, in this embodiment, the computer device may be located in at least one of a plurality of network devices in a computer network. The computer device includes a memory and a processor.

[0067] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the temperature-based cable fault handling method and apparatus in this embodiment of the invention. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby realizing the aforementioned temperature-based cable fault handling method. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to a computer terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0068] The processor can invoke information and application programs stored in memory via a transmission device to execute the following steps: Acquire initial temperature profile data and high-frequency characteristic data of the target cable through a distributed optical fiber temperature measurement system. The initial temperature profile data represents the temperature of the target cable at multiple measurement points spatially distributed along the cable's axis. The high-frequency characteristic data characterizes the high-frequency fluctuation characteristics and optical signal distortion characteristics of the distributed optical fiber temperature measurement system. If anomalies exist in the initial temperature profile data, generate and replace the anomaly-corresponding data based on the high-frequency characteristic data to obtain the target temperature profile data. Based on the target temperature profile data, calculate the spatiotemporal gradient tensor and local anomaly factor. The spatiotemporal gradient tensor characterizes the temperature variation along the target cable's axis over time, and the local anomaly factor characterizes the degree of temperature deviation of each measurement point relative to its neighborhood. Based on the spatiotemporal gradient tensor and local anomaly factor, determine fault handling instructions for the target cable. Based on the fault handling instructions, handle the faults existing in the target cable.

[0069] Optionally, the processor may also execute program code for the following steps: high-frequency characteristic data including preset frequency band light energy fluctuation rate, instantaneous change rate of Raman scattered light intensity, phase jitter variance, and polarization state perturbation spectrum.

[0070] Optionally, the processor may also execute program code for the following steps: in the case of anomalies in the initial temperature profile data, generate replacement data corresponding to the abnormal data in the initial temperature profile data based on high-frequency feature data and replace it to obtain target temperature profile data, including: inputting high-frequency feature data into a preset historical health model to obtain replacement data, wherein the historical health model is trained based on the normal temperature profile data and historical high-frequency feature data of the target cable within a preset historical period.

[0071] Optionally, the processor described above can also execute program code with the following steps: The mathematical expression for the spatiotemporal gradient tensor is as follows:

[0072] ,

[0073] in, For measurement points ,time The temperature of the target cable The rate of change of temperature along the axial direction of the target cable. The rate of change of the spatial gradient of temperature along the axis of the target cable. The rate of change of temperature over time. This represents the rate of change of temperature over time.

[0074] Optionally, the processor described above can also execute program code with the following steps: The mathematical expression for the local anomaly factor is as follows:

[0075] ,

[0076] in, For measurement points ,time The temperature of the target cable For measurement points A set of local spatial neighborhoods centered on the measurement point And a preset number of measurement points Adjacent measurement points, For at any time Neighborhood The median temperature at all measurement points within the area. For at any time Neighborhood The standard deviation of temperature at all measurement points within the range.

[0077] Optionally, the processor may also execute program code with the following steps: determining fault handling instructions for the target cable based on the spatiotemporal gradient tensor and local anomaly factors, including: determining the fault handling instruction as a first-level instruction when the magnitude of the local anomaly factor exceeds a first preset threshold, wherein the first-level instruction represents a handling instruction that directly triggers emergency physical isolation and protection actions; or determining the cause of the fault in the target cable based on the spatiotemporal gradient tensor when the magnitude of the local anomaly factor does not exceed the first preset threshold and the magnitude of the local anomaly factor exceeds a second preset threshold, and determining the fault handling instruction as a second-level instruction and the content of the second-level instruction based on the cause of the fault, wherein the second-level instruction represents a handling instruction that initiates auxiliary cooling and monitoring enhancement measures; or predicting the future temperature trend of the target cable based on the spatiotemporal gradient tensor when the magnitude of the local anomaly factor does not exceed the second preset threshold, and determining the fault handling instruction as a third-level instruction and the content of the third-level instruction based on the future temperature trend, wherein the third-level instruction represents a handling instruction that does not perform hardware operations and sends an alarm prompt to the user terminal.

[0078] This invention provides a temperature-based cable fault handling method. An initial temperature profile and high-frequency characteristic data of the target cable are acquired using a distributed optical fiber temperature measurement system. The initial temperature profile data represents the temperature of the target cable at multiple measurement points spatially distributed along the cable's axis. The high-frequency characteristic data characterizes the high-frequency fluctuation characteristics and optical signal distortion characteristics of the distributed optical fiber temperature measurement system. If anomalies exist in the initial temperature profile data, replacement data corresponding to the anomalies in the initial temperature profile data is generated based on the high-frequency characteristic data and used to replace them, thus obtaining the target temperature profile data. Based on the target temperature profile data, the spatiotemporal gradient tensor and local anomaly factor are calculated. The spatiotemporal gradient tensor characterizes the temperature along the target cable axis. The local anomaly factor characterizes the degree of temperature deviation of each measurement point relative to its neighborhood as the temperature changes over time. Based on the spatiotemporal gradient tensor and the local anomaly factor, fault handling instructions for the target cable are determined. Based on the fault handling instructions, the faults existing in the target cable are handled, achieving the goal of dynamically generating targeted fault handling instructions and implementing precise intervention in abnormal areas of the cable. This realizes the technical effects of data self-repair, high-precision identification of fault precursors, and intelligent response without relying on redundant hardware. It also solves the technical problems of current cable temperature monitoring data loss due to single-point failure and the inability to accurately identify fault precursors based on high-dimensional spatiotemporal features.

[0079] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a non-volatile storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0080] Embodiments of the present invention also provide a non-volatile storage medium. Optionally, in this embodiment, the aforementioned non-volatile storage medium can be used to store the program code executed by the temperature-based cable fault handling method provided in the above embodiments.

[0081] Optionally, in this embodiment, the non-volatile storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.

[0082] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: acquiring initial temperature profile data and high-frequency characteristic data of the target cable through a distributed optical fiber temperature measurement system, wherein the initial temperature profile data is the temperature of the target cable at multiple measurement points spatially distributed along the axial direction of the target cable, and the high-frequency characteristic data characterizes the high-frequency fluctuation characteristic data and optical signal distortion characteristic data in the distributed optical fiber temperature measurement system; in the case of anomalies in the initial temperature profile data, generating and replacing the anomaly data in the initial temperature profile data based on the high-frequency characteristic data to obtain the target temperature profile data; calculating the spatiotemporal gradient tensor and local anomaly factor based on the target temperature profile data, wherein the spatiotemporal gradient tensor characterizes the temperature change along the axial direction of the target cable over time, and the local anomaly factor characterizes the degree of temperature deviation of each measurement point relative to its neighborhood; determining fault handling instructions for the target cable based on the spatiotemporal gradient tensor and the local anomaly factor; and handling the faults existing in the target cable based on the fault handling instructions.

[0083] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: high-frequency characteristic data includes the optical energy fluctuation rate of a preset frequency band, the instantaneous change rate of Raman scattered light intensity, the phase jitter variance, and the polarization state perturbation spectrum.

[0084] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: when there are anomalies in the initial temperature profile data, generating replacement data corresponding to the data with anomalies in the initial temperature profile data based on high-frequency feature data and replacing it to obtain target temperature profile data, including: inputting high-frequency feature data into a preset historical health model to obtain replacement data, wherein the historical health model is trained based on the normal temperature profile data and historical high-frequency feature data of the target cable within a preset historical period.

[0085] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: The mathematical expression of the spatiotemporal gradient tensor is as follows:

[0086] ,

[0087] in, For measurement points ,time The temperature of the target cable The rate of change of temperature along the axial direction of the target cable. The rate of change of the spatial gradient of temperature along the axis of the target cable. The rate of change of temperature over time. This represents the rate of change of temperature over time.

[0088] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: the mathematical expression for the local anomaly factor is as follows:

[0089] ,

[0090] in, For measurement points ,time The temperature of the target cable For measurement points A set of local spatial neighborhoods centered on the measurement point And a preset number of measurement points Adjacent measurement points, For at any time Neighborhood The median temperature at all measurement points within the area. For at any time Neighborhood The standard deviation of temperature at all measurement points within the range.

[0091] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: determining fault handling instructions for the target cable based on the spatiotemporal gradient tensor and local anomaly factors, including: determining the fault handling instruction as a first-level instruction when the magnitude of the local anomaly factor exceeds a first preset threshold, wherein the first-level instruction represents a handling instruction that directly triggers emergency physical isolation and protection actions; or determining the fault cause of the target cable based on the spatiotemporal gradient tensor when the magnitude of the local anomaly factor does not exceed the first preset threshold and the magnitude of the local anomaly factor exceeds a second preset threshold, and determining the fault handling instruction as a second-level instruction and the content of the second-level instruction based on the fault cause, wherein the second-level instruction represents a handling instruction that initiates auxiliary cooling and monitoring enhancement measures; or predicting the future temperature trend of the target cable based on the spatiotemporal gradient tensor when the magnitude of the local anomaly factor does not exceed the second preset threshold, and determining the fault handling instruction as a third-level instruction and the content of the third-level instruction based on the future temperature trend, wherein the third-level instruction represents a handling instruction that does not perform hardware operations and sends an alarm prompt to the user terminal.

[0092] Embodiments of the present invention also provide a computer program product, including a computer program. Optionally, in this embodiment, when the computer program is executed by a processor, it can perform the following: acquiring initial temperature profile data and high-frequency characteristic data of a target cable through a distributed optical fiber temperature measurement system, wherein the initial temperature profile data is the temperature of the target cable at multiple measurement points spatially distributed along the axial direction of the target cable, and the high-frequency characteristic data characterizes the high-frequency fluctuation characteristic data and optical signal distortion characteristic data in the distributed optical fiber temperature measurement system; in the case of anomalies in the initial temperature profile data, generating and replacing the anomaly data in the initial temperature profile data based on the high-frequency characteristic data to obtain the target temperature profile data; calculating the spatiotemporal gradient tensor and local anomaly factor based on the target temperature profile data, wherein the spatiotemporal gradient tensor characterizes the temperature change along the axial direction of the target cable over time, and the local anomaly factor characterizes the degree of temperature deviation of each measurement point relative to its neighborhood; determining fault handling instructions for the target cable based on the spatiotemporal gradient tensor and the local anomaly factor; and handling the faults existing in the target cable based on the fault handling instructions.

[0093] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0094] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0095] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0096] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0097] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0098] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a non-volatile storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0099] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A temperature-based cable fault handling method, characterized in that, include: The initial temperature profile data and high-frequency characteristic data of the target cable are obtained through a distributed optical fiber temperature measurement system. The initial temperature profile data refers to the temperature of the target cable at multiple measurement points spatially distributed along the axial direction of the target cable. The high-frequency characteristic data characterizes the high-frequency fluctuation characteristic data and optical signal distortion characteristic data of the distributed optical fiber temperature measurement system. If there are anomalies in the initial temperature profile data, based on the high-frequency feature data, alternative data corresponding to the abnormal data in the initial temperature profile data is generated and replaced to obtain the target temperature profile data. Based on the target temperature profile data, the spatiotemporal gradient tensor and local anomaly factor are calculated, wherein the spatiotemporal gradient tensor characterizes the temperature change over time along the axial direction of the target cable, and the local anomaly factor characterizes the degree of temperature deviation of each measurement point relative to its neighborhood. Based on the spatiotemporal gradient tensor and the local anomaly factor, the fault handling instructions for the target cable are determined. Based on the fault handling instructions, the faults existing in the target cable are handled.

2. The method according to claim 1, characterized in that, The high-frequency characteristic data includes the optical energy fluctuation rate of the preset frequency band, the instantaneous change rate of Raman scattered light intensity, the phase jitter variance, and the polarization state perturbation spectrum.

3. The method according to claim 1, characterized in that, In the event of anomalies in the initial temperature profile data, based on the high-frequency feature data, alternative data corresponding to the anomaly data in the initial temperature profile data is generated and replaced to obtain target temperature profile data, including: The high-frequency feature data is input into a preset historical health model to obtain the alternative data, wherein the historical health model is trained based on the normal temperature profile data and historical high-frequency feature data of the target cable within a preset historical period.

4. The method according to claim 1, characterized in that, The mathematical expression for the spatiotemporal gradient tensor is as follows: ， in, For measurement points ,time The temperature of the target cable, The spatial rate of temperature change along the axial direction of the target cable. The rate of change of the spatial gradient of temperature along the axial direction of the target cable. The rate of change of temperature over time. This represents the rate of change of temperature over time.

5. The method according to claim 1, characterized in that, The mathematical expression for the local anomaly factor is as follows: ， in, For measurement points ,time The temperature of the target cable, For the measurement point The set of local spatial neighborhoods centered on the measurement point, containing the measurement point. and a preset number of measurement points Adjacent measurement points, For at any time Neighborhood The median temperature at all measurement points within the area. For at any time Neighborhood The standard deviation of temperature at all measurement points within the range.

6. The method according to any one of claims 1 to 5, characterized in that, The step of determining the fault handling instructions for the target cable based on the spatiotemporal gradient tensor and the local anomaly factor includes: When the magnitude of the local abnormal factor exceeds a first preset threshold, the fault handling instruction is determined to be a first-level instruction, wherein the first-level instruction represents a handling instruction that directly triggers emergency physical isolation and protection actions. Alternatively, if the magnitude of the local anomaly factor does not exceed the first preset threshold and the magnitude of the local anomaly factor exceeds the second preset threshold, the cause of the fault in the target cable is determined based on the spatiotemporal gradient tensor, and the fault handling instruction is determined to be a second-level instruction and the content of the second-level instruction based on the cause of the fault, wherein the second-level instruction represents the processing instruction to start auxiliary cooling and monitoring enhancement measures. Alternatively, if the magnitude of the local anomaly factor does not exceed the second preset threshold, the future temperature trend of the target cable is predicted based on the spatiotemporal gradient tensor, and based on the future temperature trend, the fault handling instruction is determined to be a third-level instruction and the content of the third-level instruction, wherein the third-level instruction represents a processing instruction that does not perform hardware operations and sends an alarm prompt to the user terminal.

7. A temperature-based cable fault handling device, characterized in that, include: The acquisition module is used to acquire initial temperature profile data and high-frequency characteristic data of a target cable through a distributed optical fiber temperature measurement system. The initial temperature profile data is the temperature of the target cable at multiple measurement points spatially distributed along the axial direction of the target cable. The high-frequency characteristic data characterizes the high-frequency fluctuation characteristic data and optical signal distortion characteristic data in the distributed optical fiber temperature measurement system. The generation module is used to generate replacement data corresponding to the abnormal data in the initial temperature profile data based on the high-frequency feature data when there are anomalies in the initial temperature profile data, and then replace the anomalies to obtain the target temperature profile data. The calculation module is used to calculate the spatiotemporal gradient tensor and local anomaly factor based on the target temperature profile data, wherein the spatiotemporal gradient tensor characterizes the temperature change over time along the axial direction of the target cable, and the local anomaly factor characterizes the degree of temperature deviation of each measurement point relative to its neighborhood. The determination module is used to determine the fault handling instructions for the target cable based on the spatiotemporal gradient tensor and the local anomaly factor. The processing module is used to process the faults existing in the target cable based on the fault processing instructions.

8. A non-volatile storage medium, characterized in that, The non-volatile storage medium includes a stored program, wherein, when the program is executed, it controls the device containing the non-volatile storage medium to perform the temperature-based cable fault handling method according to any one of claims 1 to 6.

9. A computer device, characterized in that, include: Memory and processor The memory stores computer programs; The processor is configured to execute a computer program stored in the memory, wherein when the computer program is executed, the processor performs the temperature-based cable fault handling method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the temperature-based cable fault handling method according to any one of claims 1 to 6.

Images