Power equipment fault positioning method and device based on distributed optical fiber sensing and computer equipment

Abstract

The invention relates to a power equipment fault positioning method and device based on distributed optical fiber sensing and computer equipment. Relates to the technical field of power equipment. The method comprises the following steps: respectively acquiring installation positions of a plurality of point type sensors, and mapping the plurality of installation positions to distance coordinates corresponding to a preset distributed optical fiber to obtain a mapping result; acquiring signals of each point sensor and a preset distributed optical fiber, and performing dynamic time offset correction and space verification to obtain a first time reference alignment result; based on a pre-established time synchronization architecture, unifying the time reference of each point sensor to obtain a second time reference alignment result; and generating a multi-dimensional data cube based on the multi-source sensor data, and carrying out fault positioning on the power equipment by combining the first time reference alignment result and the second time reference alignment result. By adopting the method, the fault positioning accuracy and efficiency of the power equipment based on distributed optical fiber sensing can be improved.

Description

Technical Field

[0001] This application relates to the field of power equipment technology, and in particular to a method, apparatus and computer equipment for fault location of power equipment based on distributed optical fiber sensing. Background Technology

[0002] As smart grids develop towards digitalization and intelligence, the safe and stable operation of key power equipment such as overhead transmission lines, power grid cables, and transformers is becoming increasingly important, and multi-source heterogeneous sensing technology has become the core support for equipment monitoring and fault diagnosis.

[0003] However, existing monitoring systems suffer from spatiotemporal inconsistencies in multi-source sensor data. For example, the local timestamps and manually calibrated spatial markers of discrete point sensors are susceptible to signal obstruction, severe weather, and human error, making it difficult to accurately align data from different sensors in both time and space. Furthermore, distributed fiber optic sensors are often used solely as physical quantity monitoring tools, and their potential function as a unified spatiotemporal reference has not been fully explored. The position mapping accuracy of point sensors is limited by calibration methods, making it difficult to meet the requirements for high-precision fault location. These factors result in large fault location errors in power equipment and an inability to quickly pinpoint fault locations. Therefore, current technologies based on distributed fiber optic sensing suffer from low accuracy and low efficiency in power equipment fault location. Summary of the Invention

[0004] Therefore, it is necessary to address the technical problems of low accuracy and low efficiency in fault location of power equipment based on distributed optical fiber sensing, and to provide a fault classification method, device, computer equipment, computer-readable storage medium and computer program product for train braking systems.

[0005] In a first aspect, this application provides a method for fault location of power equipment based on distributed optical fiber sensing, including:

[0006] The installation locations of multiple point sensors are obtained, and the multiple installation locations are mapped to the distance coordinates corresponding to the preset distributed optical fiber to obtain the mapping results;

[0007] Based on the mapping result, the signals of each of the point sensors and the preset distributed optical fiber are obtained, and the obtained signals are dynamically time offset corrected and spatially verified to obtain the first time reference alignment result.

[0008] Based on a pre-built time synchronization architecture, the time reference of each point sensor is unified to obtain a second time reference alignment result.

[0009] Based on the pre-acquired spatiotemporally aligned multi-source sensor data, a multi-dimensional data cube is generated, and the fault location of the power equipment is performed by combining the first time reference alignment result and the second time reference alignment result.

[0010] In one embodiment, the step of acquiring the installation positions of multiple point sensors and mapping the multiple installation positions to distance coordinates corresponding to a preset distributed optical fiber to obtain a mapping result includes: inputting a mechanical vibration signal of a preset frequency to the installation position of the point sensor; acquiring the mechanical vibration signal based on the preset distributed optical fiber, and determining the vibration frequency through the mechanical vibration signal, so as to map the installation position of the point sensor to the distance coordinates corresponding to the preset distributed optical fiber to obtain the mapping result.

[0011] In one embodiment, the step of acquiring the installation positions of multiple point sensors and mapping the multiple installation positions to distance coordinates corresponding to a preset distributed optical fiber to obtain a mapping result further includes: inputting a preset temperature step to the acquired installation positions of the multiple point sensors; acquiring the temperature change of the installation positions based on the preset distributed optical fiber to obtain the starting point of the temperature step, and using the starting point of the temperature step as the distance coordinate to obtain the mapping result.

[0012] In one embodiment, the step of acquiring the installation positions of multiple point sensors and mapping the multiple installation positions to distance coordinates corresponding to a preset distributed optical fiber to obtain a mapping result further includes: acquiring the micro-bend structure of the point sensors based on the installation positions of the multiple point sensors, and acquiring the reflection feature points of the micro-bend structure based on the preset distributed optical fiber; mapping the reflection feature points to the distance coordinates corresponding to the preset distributed optical fiber to obtain the mapping result.

[0013] In one embodiment, the step of acquiring signals from each of the point sensors and the preset distributed optical fiber based on the mapping result, and performing dynamic time offset correction and spatial verification on the acquired signals to obtain a first time reference alignment result includes: based on the mapping result, when the power equipment to be located experiences inrush current or lightning fault traveling wave, acquiring the signal of the preset distributed optical fiber and marking the local timestamp onto the point sensors and the preset distributed optical fiber; acquiring the time difference between the signals of the point sensors and the preset distributed optical fiber using a preset algorithm; and performing dynamic time offset correction and spatial verification on the acquired signals based on the time difference to obtain the first time reference alignment result.

[0014] In one embodiment, generating a multidimensional data cube based on pre-acquired spatiotemporally aligned multi-source sensor data includes: obtaining the spatial coordinates of the preset distributed optical fiber as a first-dimensional feature, obtaining the timestamps of the point sensors as a second-dimensional feature, and obtaining the multi-source sensor data as a multi-dimensional feature based on the pre-acquired spatiotemporally aligned multi-source sensor data; and generating the multidimensional data cube based on the first-dimensional feature, the second-dimensional feature, and the multi-dimensional feature.

[0015] Secondly, this application also provides a power equipment fault location device based on distributed optical fiber sensing, comprising:

[0016] The mapping result acquisition module is used to acquire the installation positions of multiple point sensors respectively, and map the multiple installation positions to the distance coordinates corresponding to the preset distributed optical fiber to obtain the mapping result;

[0017] The reference alignment result acquisition module is used to acquire the signals of each of the point sensors and the preset distributed optical fiber based on the mapping result, and to perform dynamic time offset correction and spatial verification on the acquired signals to obtain the first time reference alignment result.

[0018] The benchmark alignment result acquisition module is also used to unify the time benchmarks of each point sensor based on a pre-built time synchronization architecture to obtain a second time benchmark alignment result.

[0019] The fault location module is used to generate a multi-dimensional data cube based on pre-acquired spatiotemporally aligned multi-source sensor data, and combine the first time reference alignment result and the second time reference alignment result to locate the fault in the power equipment.

[0020] Thirdly, this application also provides a computer device, the computer device including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0021] The installation locations of multiple point sensors are obtained, and the multiple installation locations are mapped to the distance coordinates corresponding to the preset distributed optical fiber to obtain the mapping results;

[0022] Based on the mapping result, the signals of each of the point sensors and the preset distributed optical fiber are obtained, and the obtained signals are dynamically time offset corrected and spatially verified to obtain the first time reference alignment result.

[0023] Based on a pre-built time synchronization architecture, the time reference of each point sensor is unified to obtain a second time reference alignment result.

[0024] Based on the pre-acquired spatiotemporally aligned multi-source sensor data, a multi-dimensional data cube is generated, and the fault location of the power equipment is performed by combining the first time reference alignment result and the second time reference alignment result.

[0025] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0026] The installation locations of multiple point sensors are obtained, and the multiple installation locations are mapped to the distance coordinates corresponding to the preset distributed optical fiber to obtain the mapping results;

[0027] Based on the mapping result, the signals of each of the point sensors and the preset distributed optical fiber are obtained, and the obtained signals are dynamically time offset corrected and spatially verified to obtain the first time reference alignment result.

[0028] Based on a pre-built time synchronization architecture, the time reference of each point sensor is unified to obtain a second time reference alignment result.

[0029] Based on the pre-acquired spatiotemporally aligned multi-source sensor data, a multi-dimensional data cube is generated, and the fault location of the power equipment is performed by combining the first time reference alignment result and the second time reference alignment result.

[0030] Fifthly, this application also provides a computer program product, which includes a computer program that, when executed by a processor, performs the following steps:

[0031] The installation locations of multiple point sensors are obtained, and the multiple installation locations are mapped to the distance coordinates corresponding to the preset distributed optical fiber to obtain the mapping results;

[0032] Based on the mapping result, the signals of each of the point sensors and the preset distributed optical fiber are obtained, and the obtained signals are dynamically time offset corrected and spatially verified to obtain the first time reference alignment result.

[0033] Based on a pre-built time synchronization architecture, the time reference of each point sensor is unified to obtain a second time reference alignment result.

[0034] Based on the pre-acquired spatiotemporally aligned multi-source sensor data, a multi-dimensional data cube is generated, and the fault location of the power equipment is performed by combining the first time reference alignment result and the second time reference alignment result.

[0035] The aforementioned method, apparatus, computer equipment, storage medium, and computer program product for power equipment fault location based on distributed optical fiber sensing, in the process of power equipment fault location based on distributed optical fiber sensing, obtains the installation locations of multiple point sensors and maps these locations to the distance coordinates corresponding to a preset distributed optical fiber, thus obtaining a mapping result; it can locate point sensors and map fiber distance coordinates to establish a spatiotemporal correlation basis; it acquires signals from each point sensor and the preset distributed optical fiber based on the mapping result, and performs dynamic time offset correction and spatial verification on the acquired signals to obtain a first time reference alignment result; it can collect multi-source signals and perform spatiotemporal correction verification to achieve preliminary signal time alignment; it unifies the time reference of each point sensor based on a pre-built time synchronization architecture to obtain a second time reference alignment result; it can unify the time reference based on the synchronization architecture to achieve precise time synchronization of multiple sensors; it generates a multi-dimensional data cube based on the pre-acquired spatiotemporally aligned multi-source sensor data, and combines the first and second time reference alignment results to locate power equipment faults, thus constructing a data cube and combining the alignment results to ultimately achieve precise fault location of power equipment. Attached Figure Description

[0036] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0037] Figure 1 This is a flowchart illustrating a power equipment fault location method based on distributed optical fiber sensing in one embodiment.

[0038] Figure 2 This is a flowchart illustrating the steps of power equipment fault location based on distributed optical fiber sensing in one embodiment.

[0039] Figure 3 This is a flowchart illustrating a power equipment fault location method based on distributed optical fiber sensing in another embodiment.

[0040] Figure 4 This is a flowchart illustrating a power equipment fault location method based on distributed optical fiber sensing in yet another embodiment.

[0041] Figure 5 This is a structural block diagram of a power equipment fault location device based on distributed optical fiber sensing in one embodiment;

[0042] Figure 6This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0043] 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.

[0044] With the development of smart grids, multi-source heterogeneous sensors (such as distributed fiber optic sensors, point ultrasonic sensors, and current transformers) are widely used in equipment monitoring. However, while existing technologies can achieve multi-dimensional parameter acquisition and virtual scenario simulation, they neglect the most fundamental spatiotemporal inconsistency problem in multi-source data fusion. Specifically, traditional systems rely on the local timestamps and spatial markers of discrete sensors, which are susceptible to signal obstruction and weather conditions, leading to data misalignment in the spatiotemporal dimensions, large fault location errors, and difficulties in multi-source data fusion, thus affecting the reliability of upper-level diagnostic algorithms. For example, distributed fiber optic sensors (DOFS) are often only used as tools for temperature, strain, or vibration monitoring, failing to fully utilize their potential for continuous spatial coordinates and a unified time reference; the installation location mapping of point sensors relies on manual calibration or GIS systems, which are susceptible to error interference, resulting in inaccurate fault location and difficulties in multi-feature cross-validation, limiting the improvement of intelligent diagnostic effects. Therefore, there are currently technical problems with low accuracy and low efficiency in fault location of power equipment based on distributed fiber optic sensing.

[0045] To address the aforementioned technical problems of low accuracy and low efficiency in power equipment fault location based on distributed fiber optic sensing, in an exemplary embodiment, such as... Figure 1 As shown, a method for fault location of power equipment based on distributed optical fiber sensing is provided. Taking the application of this method to a terminal as an example, the method includes the following steps S102 to S106. Wherein:

[0046] Step S102: Obtain the installation locations of multiple point sensors and map the multiple installation locations to the distance coordinates corresponding to the preset distributed optical fiber to obtain the mapping results.

[0047] Among them, point-type detection sensors are sensors that can only detect physical quantities such as temperature, vibration, and stress at a specific single point location. The detection range is discrete single point. In power equipment monitoring, they are often deployed at critical fault-prone points of equipment, such as cable joints and transformer bushings, and have high detection accuracy. Distributed optical fiber uses optical fiber as the sensing medium and transmission carrier, and can perform distributed, unrestricted detection of physical quantities in continuous space along the optical fiber. Distance coordinate mapping is a spatial matching process that converts the physical installation position of a point sensor into the corresponding distance scale coordinates along the distributed optical fiber.

[0048] Step S104: Based on the mapping results, acquire the signals of each point sensor and the preset distributed optical fiber, and perform dynamic time offset correction and spatial verification on the acquired signals to obtain the first time reference alignment result.

[0049] Among them, dynamic time offset correction is a processing method for real-time or dynamic calibration of non-fixed time deviations generated during sensor signal transmission and acquisition; spatial verification is a verification process that combines sensor installation position and distance coordinate mapping results to verify the consistency of the spatial position corresponding to the signal; time reference alignment is a processing process that unifies the signal acquisition clocks of different sensors to the same time reference reference. The first time reference alignment can perform preliminary alignment correction at the signal level.

[0050] Step S106: Based on the pre-built time synchronization architecture, unify the time reference of each point sensor to obtain the second time reference alignment result.

[0051] Among them, the time synchronization architecture is a system built for multiple sensor nodes that can achieve clock unification and high-precision time synchronization; the second time reference alignment is a precise unified alignment based on the synchronization architecture.

[0052] Step S108: Based on the pre-acquired spatiotemporally aligned multi-source sensor data, a multi-dimensional data cube is generated, and the fault location of the power equipment is performed by combining the first time reference alignment result and the second time reference alignment result.

[0053] Among them, the multidimensional data cube is a structured data model constructed by aligning multi-source sensor data in time and space according to three core dimensions: time, space, and physical quantity. Multi-source sensor data can include various monitoring data collected by sensing devices of different types and deployment methods, such as point sensors and distributed optical fibers. Power equipment fault location based on distributed optical fiber sensing is a process of accurately determining the specific spatial location, time node, and fault type of power equipment fault by combining the fusion analysis results of multi-source sensor data.

[0054] In the aforementioned power equipment fault location method based on distributed optical fiber sensing, the installation locations of multiple point sensors are acquired and mapped to the distance coordinates corresponding to the preset distributed optical fibers to obtain mapping results. This allows for the location of point sensors and mapping of fiber distance coordinates, establishing a spatiotemporal correlation basis. Based on the mapping results, signals from each point sensor and the preset distributed optical fiber are acquired, and dynamic time offset correction and spatial verification are performed on the acquired signals to obtain a first time reference alignment result. Multi-source signals can be collected and spatiotemporally corrected for verification, achieving preliminary signal time alignment. A second time reference alignment result is obtained by unifying the time references of each point sensor based on a pre-built time synchronization architecture. A unified time reference based on the synchronization architecture enables precise time synchronization of multiple sensors. A multi-dimensional data cube is generated based on the pre-acquired spatiotemporally aligned multi-source sensor data, and the first and second time reference alignment results are combined to locate power equipment faults. This allows for the construction of a data cube and the combination of alignment results to ultimately achieve precise fault location of the power equipment.

[0055] In an exemplary embodiment, the installation locations of multiple point sensors are obtained, and these locations are mapped to distance coordinates corresponding to a preset distributed optical fiber to obtain the mapping result, including:

[0056] A mechanical vibration signal of a preset frequency is input to the installation location of the point sensor; the mechanical vibration signal is acquired based on a preset distributed optical fiber, and the vibration frequency is determined by the mechanical vibration signal, so as to map the installation location of the point sensor to the distance coordinates corresponding to the preset distributed optical fiber, and obtain the mapping result.

[0057] Among them, mechanical vibration signal is physical signal generated when an object undergoes mechanical vibration and can be captured by sensing device; preset frequency is fixed vibration frequency of mechanical vibration signal input to measuring point set in advance; installation position is the actual physical placement point of point sensor on power equipment; preset distributed optical fiber is optical fiber carrier with sensing function pre-deployed on power equipment; obtaining mechanical vibration signal based on preset distributed optical fiber means obtaining feedback signal of mechanical vibration signal based on preset distributed optical fiber, and mapping the installation position of point sensor to the distance coordinates corresponding to preset distributed optical fiber through feedback signal to obtain mapping result.

[0058] In this embodiment, by inputting a preset frequency mechanical vibration signal to the installation location of the point sensor, and capturing the signal and identifying the matching vibration frequency based on distributed optical fiber, a precise mapping from the physical installation location of the point sensor to the optical fiber distance coordinates is achieved. This allows for accurate identification of the target signal from mixed interference signals, effectively avoiding the influence of irrelevant signals such as background vibration of power equipment, and improving the accuracy of the location mapping. By completing the spatial coordinate transformation through vibration signal transmission and frequency matching, a precise correspondence between the physical location of the point sensor and the distance coordinates of the distributed optical fiber is established, achieving a unified spatial reference for the two sensing methods and providing a reliable coordinate basis for the precise spatial location of subsequent power equipment faults.

[0059] In one embodiment, the installation locations of multiple point sensors are obtained, and the multiple installation locations are mapped to distance coordinates corresponding to a preset distributed optical fiber to obtain the mapping result. The method further includes:

[0060] A preset temperature step is input to the installation locations of multiple point sensors; the temperature change at the installation locations is obtained based on a preset distributed optical fiber to obtain the starting point of the temperature step, and the starting point of the temperature step is used as the distance coordinate to obtain the mapping result.

[0061] Among them, temperature step is a sudden change in temperature that occurs in a very short time. It is a temperature change signal with a clear time starting point and can be accurately used as a feature identifier for spatial coordinate mapping. It is suitable for the scenario requirements of temperature sensing calibration of power equipment and can effectively distinguish it from the natural slow temperature change of the equipment. The temperature step starting point is the time and space corresponding node of the temperature step signal captured by the pre-set distributed optical fiber and manually input, which is the core basis for determining the initial position of the temperature change.

[0062] In this embodiment, by using a temperature step as the calibration signal, the natural temperature changes of power equipment and environmental interference can be effectively avoided, improving the accuracy of signal recognition and ensuring the reliability of the mapping results. Based on the preset sensing characteristics of the distributed optical fiber itself to capture the temperature step start point, the mapping operation process is simplified, the calibration efficiency is improved, and a reliable spatial reference is provided for subsequent spatiotemporal fusion of multi-source sensor data and fault location of power equipment based on distributed optical fiber sensing, thereby improving the efficiency of power equipment fault monitoring.

[0063] More specifically, in one embodiment, the installation locations of multiple point sensors are obtained, and the multiple installation locations are mapped to distance coordinates corresponding to a preset distributed optical fiber to obtain the mapping result. The method further includes:

[0064] Based on the installation locations of multiple point sensors, the micro-bending structure of the point sensors is obtained, and the reflection feature points of the micro-bending structure are obtained based on the preset distributed optical fiber. The reflection feature points are mapped to the distance coordinates corresponding to the preset distributed optical fiber to obtain the mapping result.

[0065] Among them, the micro-bend structure is a specific structure with a slight bending shape that is laid out for the optical fiber at the installation position of the point sensor. It is a man-made physical morphological feature structure of the optical fiber. When the optical fiber undergoes a micro-bend, it will change the light transmission characteristics and form a recognizable feature signal. Its structural shape is fixed and its features are unique, and it will not be confused with the signal of the natural bending of the optical fiber. The reflection feature point is a light reflection signal feature point with obvious recognizable characteristics generated by the change in light transmission characteristics when the distributed optical fiber detects the micro-bend structure. It is a unique signal identifier of the micro-bend structure and can be accurately extracted from the conventional transmission signal of the optical fiber. Its signal position on the optical fiber corresponds one-to-one with the physical position of the micro-bend structure.

[0066] In this embodiment, by using a micro-bent structure as a calibration marker, signal interference caused by the operation of power equipment and the environment can be avoided, ensuring the uniqueness and accuracy of feature point identification from the source, improving the accuracy of mapping results, and eliminating the need for repeated input of manual calibration signals. This achieves long-term accurate calibration of the sensor position, reduces the cost of subsequent maintenance and recalibration, and lays the foundation for subsequent spatiotemporal fusion of multi-source sensor data and accurate fault location of power equipment.

[0067] In one exemplary embodiment, such as Figure 2 As shown, signals from each point sensor and a preset distributed optical fiber are acquired based on the mapping results. Dynamic time offset correction and spatial verification are then performed on the acquired signals to obtain the first time reference alignment result, including:

[0068] Step S202: Based on the mapping result, when the power equipment to be located experiences inrush current or lightning fault traveling wave, the signal of the preset distributed optical fiber is acquired and the local timestamp is marked on the point sensor and the preset distributed optical fiber; Step S204: The time difference between the signals of the point sensor and the preset distributed optical fiber is acquired through a preset algorithm; Step S206: Based on the time difference, dynamic time offset correction and spatial verification are performed on the acquired signal to obtain the first time reference alignment result.

[0069] Among them, inrush current is a short-duration, high-amplitude surge current generated by the transient process of the circuit at the moment of power equipment closing and energizing. It is characterized by suddenness and obvious time-domain features, and is prone to causing equipment failure. Lightning fault traveling wave is an electromagnetic transient traveling wave signal generated at the fault point of power equipment after being struck by lightning, which propagates rapidly along the transmission line. It is the core characteristic signal of lightning fault. Local timestamp is the identifier collected by the clock of the sensor or fiber optic acquisition device itself. Time difference is the time difference between the local timestamps of the same fault characteristic signal after it is captured by a point sensor and a preset distributed fiber optic cable.

[0070] In this embodiment, by collecting feature signals and combining them with local timestamps, the acquisition time of the fault signal is accurately located, providing accurate raw data for subsequent time dimension analysis. The time difference between the point sensor and the distributed optical fiber signal is quantified by a preset algorithm, providing accurate quantitative basis for dynamic time offset correction. Based on the time difference, dynamic time offset correction and spatial verification are carried out to complete the initial alignment of the time reference of the multi-source fault signals, ensuring the accuracy of the alignment results and laying the foundation for accurate fault location in the future.

[0071] In one embodiment, a multidimensional data cube is generated based on pre-acquired spatiotemporally aligned multi-source sensor data, including:

[0072] Based on pre-acquired spatiotemporally aligned multi-source sensor data, the spatial coordinates of a pre-defined distributed optical fiber are obtained as the first dimension feature, the timestamps of point sensors are obtained as the second dimension feature, and the multi-source sensor data are obtained as the multi-dimensional feature; a multi-dimensional data cube is generated based on the first dimension feature, the second dimension feature, and the multi-dimensional feature.

[0073] Among them, the first dimension feature is the first core dimension of the multidimensional data cube construction, which refers to the spatial coordinate features corresponding to the preset distributed optical fiber; the second dimension feature is the second core dimension of the multidimensional data cube construction, which refers to the local timestamp feature marked when the point sensor collects signals; the multidimensional feature is the core data dimension of the multidimensional data cube, which refers to the various monitoring data features collected by multi-source sensors after spatiotemporal alignment.

[0074] In this embodiment, by clearly defining the three-dimensional core dimensions, the dispersed spatial coordinates, time information and multi-source sensor data are systematically integrated to improve the efficiency of data retrieval and retrieval. Furthermore, the multi-dimensional data cube can intuitively present the correlation characteristics of data in different dimensions, accurately identify the spatial location, time node and fault type of the fault, and further improve the accuracy and efficiency of power equipment fault location based on distributed optical fiber sensing.

[0075] This application provides a method for fault location of power equipment based on distributed optical fiber sensing. To better understand the process of the above-mentioned fault location method for power equipment based on distributed optical fiber sensing, combined with... Figure 3 As shown below, the specific process of a power equipment fault location method based on distributed optical fiber sensing according to this application is described in detail, including the following steps:

[0076] S302 is equipped with distributed optical fibers and point sensors to record raw data from the point sensors.

[0077] S304 synchronously collects the sensing data of distributed optical fiber and the data of point sensors during the operation of the power equipment fault location system based on distributed optical fiber sensing, and obtains continuous spatial coordinates, local timestamps and physical parameters of point sensors through the preset distributed optical fiber sensing system as multi-source raw data streams.

[0078] S306, spatial registration, maps the position of point sensors to fiber optic distance coordinates, achieving spatial benchmark unification.

[0079] Spatial registration also includes active excitation calibration and coordinate binding. Active excitation calibration includes, for example, mechanical vibration excitation, thermal pulse excitation, and fiber microbending feature method. Coordinate binding includes associating sensor ID with fiber coordinates, thereby outputting data after spatial registration, including precise coordinates.

[0080] More specifically, the spatial registration method based on active excitation calibration precisely maps the installation location of point sensors to the distance coordinates of distributed optical fibers, achieving a unified spatial reference. This method includes the mechanical vibration excitation method, applicable to distributed vibration sensing (DVS) or distributed acoustic sensing (DAS) systems based on φ-OTDR. A specific frequency mechanical vibration signal (e.g., 100Hz) is applied to the installation point of the point sensor. The distributed optical fiber monitors the vibration waveform in real time, identifies the characteristic frequency through a pattern recognition algorithm, and directly reads the precise distance coordinates of the vibration occurrence (e.g., 5000.2 meters from the fiber's starting end). By real-time monitoring and identification of characteristic vibration patterns through the distributed optical fiber, the precise distance of the vibration occurrence is determined. The distance coordinates are determined by several methods: 1) Coordinates are used, and the sensor ID is bound to these coordinates; 2) Thermal pulse excitation method, suitable for distributed temperature sensing (DTS) or distributed strain sensing (DSS) systems, applies a controllable temperature step at the sensor installation point (e.g., at a cable joint), monitors temperature changes through distributed optical fibers, and locates the starting point of the temperature step to obtain distance coordinates; 3) Fiber micro-bending feature method, applicable to all types of distributed optical fiber sensing systems (DVS, DAS, DTS, DSS), designs a micro-bending structure at the point sensor fixture, allowing the distributed optical fiber to record permanent reflection feature points, achieving one-time permanent calibration; 4) Spatial registration method, where the accuracy of distance coordinates is achieved through digital conversion of the physical length of the optical fiber, with errors controlled within 0.1 meters, overcoming the insufficient accuracy of GIS. For example, at the installation point of a tension sensor, the micro-bending structure serves as a permanent coordinate marker, recorded by the OTDR system, achieving one-time calibration without subsequent excitation.

[0081] Furthermore, the accuracy of spatial registration depends on the digital conversion of the physical length of the optical fiber, and its mathematical relationship satisfies: coordinate value = fiber length × refractive index / sampling resolution. By calibrating the light speed and sampling parameters, the linearity and uniqueness of the coordinates are ensured.

[0082] S308, Time Alignment: Corrects time offset by running events, performs event capture, cross-correlation analysis, and spatial verification, and outputs time synchronization data.

[0083] The operational events include inrush current during energization or lightning strikes. The output time synchronization data has an accuracy down to the microsecond level.

[0084] More often, online spatiotemporal alignment methods based on operational events utilize inherent events in the operation of cables or overhead transmission lines (such as inrush current and lightning fault traveling waves) to synchronously capture signals from point sensors and distributed optical fibers, achieving dynamic time offset correction and spatial verification. These online spatiotemporal alignment methods include: event capture: when inrush current or fault traveling waves occur, point sensors (such as current transformers and fault location devices) record electrical signals and add local timestamps, while distributed optical fibers synchronously detect vibration waves or strain changes; time alignment: cross-correlation analysis is used to calculate the time difference between the point sensor and distributed optical fiber signals, correcting clock offsets to achieve microsecond-level time synchronization accuracy; spatial verification: the correctness of the point sensor position mapping is verified using the vibration wave propagation trajectory; in time alignment, cross-correlation analysis is based on the signal peak timestamp, calculated using the formula ΔT = T_sensor - T_fiber, where T_sensor is the point sensor timestamp and T_fiber is the distributed optical fiber timestamp, with hardware clock compensation for optical transmission delay.

[0085] Furthermore, the cross-correlation function is Where x(t) is the point sensor signal, y(t) is the fiber optic signal, and τ is the time difference, the clock offset is corrected by peak detection to achieve time synchronization accuracy at the microsecond level. At the same time, the optical transmission delay is compensated (the delay is fixed and known). The correctness of the point sensor position mapping is verified by using the vibration wave propagation trajectory (starting from a known event source such as the switch position). For example, the relationship between the vibration wave propagation speed and distance is used to verify whether the coordinate binding is accurate. This method is suitable for long-distance overhead lines. The event propagation model can be optimized by combining wave speed (such as the speed of light or the speed of sound).

[0086] S310 generates a multi-dimensional data cube after hardware synchronous verification.

[0087] Hardware synchronization verification includes ensuring the time base of all sensors is unified through hardware architecture. Specific steps may include master-slave clock distribution, fiber optic time-frequency transmission, and timestamp marking, ultimately obtaining hardware-level synchronized data. The specific process of data fusion and multi-dimensional data cube generation may include integrating multi-source data into a spatiotemporally aligned multi-dimensional data cube, including dimension definition, cube construction, and fusion output. The crane dimension definition includes defining spatial coordinates as one-dimensional, timestamps as two-dimensional, and sensor parameters as multi-dimensional.

[0088] More specifically, the implementation of a hardware-level time synchronization architecture provides a unified high-precision time reference for all sensors, achieved through master-slave clock distribution or fiber optic time-frequency transmission. The hardware-level time synchronization architecture includes a master-slave clock network: a high-precision master clock (such as an OCXO temperature-controlled crystal oscillator) is set in the monitoring host, and synchronization signals are distributed to distributed fiber optic acquisition cards and point sensor intelligent units through physical cables or protocols (such as PTP / IEEE1588); fiber optic time-frequency transmission: wavelength division multiplexing technology is used to transmit time synchronization optical signals in the sensing fiber, providing a stable reference for long-distance environments (such as overhead power lines); the time synchronization architecture ensures that all sensor data are marked with a unified timestamp at the acquisition source, with an accuracy better than 1 microsecond, which is especially effective in environments where Global Navigation Satellite System (GNSS) denial is present.

[0089] In this method, each sensor is marked with a microsecond-precision timestamp based on the same master clock during data acquisition. Wavelength division multiplexing (WDM) technology is used to transmit time synchronization optical signals in the same optical fiber carrying the sensing signals. For example, the 1550nm band is used for sensing, and the 1310nm band is used for time synchronization. This method is suitable for GNSS-denied environments (such as underground utility tunnels or remote overhead power lines), with time transmission accuracy better than 1 microsecond. Error sources in the synchronization architecture (such as clock drift and transmission delay) are eliminated through closed-loop calibration, satisfying the relationship: Synchronization Error = Clock Deviation + Transmission Delay Compensation.

[0090] Multi-source data fusion based on data cubes generates multi-dimensional data cubes from spatiotemporally aligned multi-source data to support intelligent diagnostic algorithms. The construction of data cubes includes dimensional definition: spatial coordinates of distributed optical fibers are one dimension, timestamps are two dimensions, and sensor parameters (such as temperature, vibration, and images) are multi-dimensional, forming strictly aligned structured data. Fusion output: data cubes provide input for algorithms such as multi-feature cross-validation and holographic health profiling. For example, in the diagnosis of overhead power line galloping, a trajectory model is generated by combining image data and vibration frequency. Data cubes can achieve fast querying through spatiotemporal indexing and support real-time fault early warning.

[0091] More specifically, data fusion methods include dimensional definitions: the data cube uses the spatial coordinates of the distributed optical fiber as one dimension (continuous distance sequence), timestamps as two dimensions (unified time series), and sensor parameters as multiple dimensions (such as temperature, vibration, and image features). For example, in the diagnosis of galloping overhead transmission lines, the cube includes coordinate axes (0-100km), a time axis (0-24h), and parameter axes (galloping amplitude, frequency). Cube construction: data is aligned using spatiotemporal indexing algorithms (such as hash indexes) to ensure that each data point has a strict spatiotemporal label. The fusion output is a multidimensional array, supporting real-time querying and analysis. Intelligent diagnostic applications: based on the data cube, multi-feature cross-validation or holographic health profiling algorithms are performed. For example, combining image data and vibration frequency generates a galloping trajectory model, outputting fault warning information. Cube data can be integrated with upper-layer systems through API interfaces to achieve predictive maintenance.

[0092] S312 outputs intelligent diagnostic results.

[0093] The specific process of outputting intelligent diagnostic results may include executing fault diagnosis algorithms based on data cubes, such as multi-feature cross-validation, and specific steps may include anomaly detection and early warning generation.

[0094] In one embodiment, such as Figure 4 As shown, it also includes a power equipment fault location system based on distributed optical fiber sensing, which may specifically include a synchronization module, a processing module, a diagnostic module, and a sensing module.

[0095] The synchronization module includes a master clock source, the processing module includes a data alignment engine and a cube (multidimensional data) builder, the diagnostic module includes health status and fault warning, and the sensing module includes distributed fiber optic sensing units and point sensing units, with the point sensing units including current transformers and fault location devices.

[0096] Furthermore, the sensing module is used to collect data from distributed optical fibers and point sensors and convert it into raw features; the processing module is used to perform spatial registration, time alignment and data cube generation; the synchronization module is used to achieve hardware-level time synchronization; and the diagnostic module outputs fault warning information based on the data cube.

[0097] Through the above embodiments, this application solves the industry problem of spatiotemporal inconsistency of multi-source sensor data by systematically registering, aligning, and synchronizing spatial data, improving fault location accuracy and diagnostic reliability, and providing underlying support for predictive maintenance of smart grids. By unifying spatiotemporal references, the fusion error of multi-source sensor data is reduced to an acceptable range for engineering, improving fault location accuracy to the meter level. This can effectively cope with extreme environments (such as underground pipe corridors, strong electromagnetic interference, and severe weather), ensuring the continuity and reliability of data acquisition, improving the robustness of intelligent diagnostic algorithms, reducing false alarms and missed alarms, and supporting predictive maintenance of the power grid.

[0098] More specifically, the following are exemplary embodiments:

[0099] Example 1: Spatial registration method based on mechanical vibration excitation. Scenario: Deploying distributed fiber optic sensor (DVS system) and point-type ultra-high frequency (UHF) partial discharge sensor on a 10kV cable line.

[0100] Steps: 1) At the UHF sensor installation point (approximately 1500 meters from the cable start point), apply mechanical vibration at a specific frequency (e.g., 100Hz) using a calibrated vibratory hammer; 2) The DVS system monitors the vibration signal in real time, locks the characteristic frequency through pattern recognition, and reads its precise distance coordinates (e.g., 1500.5 meters); 3) In the system database, permanently bind the UHF sensor ID (e.g., “UHF_Node_01”) to this coordinate, complete spatial registration, and achieve precise mapping between the point sensor position and the fiber optic coordinates, with a spatial error of less than 0.1 meters.

[0101] Example 2: Online spatiotemporal alignment based on inrush current events. Scenario: When the cable is put into operation, the inrush current event is captured by both the point current transformer and the DVS system.

[0102] Steps: 1) The current transformer records the inrush current electrical signal and adds a local timestamp T_elec; 2) The DVS detects the vibration wave propagating from the switch position, with a starting timestamp of T_vib; 3) The central system calculates the time difference ΔT = T_elec - T_vib through cross-correlation analysis, correcting the clock offset between the point sensor and the DOFS system; 4) Simultaneously, the vibration wave propagation trajectory verifies the correctness of the sensor position mapping along the line, achieving time synchronization (accuracy down to the microsecond level) and dynamic spatial verification of multi-source data, improving the reliability of event correlation.

[0103] Example 3: Implementation of hardware-level time synchronization architecture. Architecture: A high-precision master clock (OCXO temperature-controlled crystal oscillator) is set in the monitoring host, and the synchronization signal is distributed to the DOFS acquisition card and intelligent point sensors (IED) through the fiber optic communication link.

[0104] Steps: 1) The master clock generates 1PPS (pulses per second) and ToD (time of day) signals, which are transmitted in the same sensing fiber using wavelength division multiplexing technology; 2) All sensors are marked with a unified timestamp at the data acquisition source; in GNSS-denied environments (such as underground utility tunnels), the time synchronization accuracy is ensured to be better than 1 microsecond.

[0105] Example 4: Spatiotemporal alignment based on traveling wave events of overhead transmission line faults. Scenario: On a 220kV overhead transmission line, distributed optical fibers are deployed along the ground wire, and point-type fault location monitoring devices are installed on the towers to capture transient traveling wave waveforms generated by lightning strikes.

[0106] Steps: 1) Spatial Registration: A portable vibration exciter is used to apply characteristic vibrations at the fault location device installation point (approximately 5 kilometers from the starting point). The DOFS (DVS system) locks the vibration signal and obtains precise coordinates (e.g., 5000.2 meters), completing the registration; 2) Time Alignment: When a lightning strike fault occurs, the fault location device records the traveling wave waveform (timestamp T_wave), and the DOFS synchronously detects the vibration wave (timestamp T_vib). The central system calculates the time difference through cross-correlation analysis and corrects the clock offset; 3) Data Fusion: After the traveling wave waveform and fiber optic vibration data are aligned in time and space, combined with the wave velocity model, the fault point is accurately located to the meter level (e.g., 5000.5 meters), overcoming the hundreds-meter error caused by time asynchrony in traditional traveling wave positioning and improving fault inspection efficiency.

[0107] Example 5: Galloping diagnosis based on image monitoring and fiber optic vibration. Scenario: An image monitoring device (high-definition camera) and distributed optical fibers (to monitor conductor vibration) are deployed on an overhead transmission line to monitor conductor galloping phenomena.

[0108] Steps: 1) Spatial registration: At the camera installation point, a temperature step is applied using the thermal pulse excitation method (DTS system), DOFS locates the temperature change point, and the camera coordinates are registered (e.g., 3000 meters from the starting end); 2) Event alignment: When strong winds cause conductor galloping, the image monitoring device captures the galloping video (timestamped T_image), and DOFS detects the vibration frequency change (timestamp T_vib); the system associates video frames with vibration data through time alignment; 3) Fusion analysis: Image data provides visual information on the galloping amplitude, and fiber optic vibration data provides frequency characteristics. After spatiotemporal alignment, a galloping trajectory cube is generated, supporting early warning models, realizing cross-modal diagnosis of galloping events, and reducing misjudgments.

[0109] Example 6: Icing early warning using tension sensors and fiber optic strain monitoring. Scenario: Tension sensors (monitoring conductor tension) and distributed optical fibers (monitoring strain) are deployed on overhead transmission lines for icing early warning.

[0110] Steps: 1) Spatial Registration: Using the fiber optic micro-bending feature method, a micro-bending structure is designed at the tension sensor fixture. DOFS records the coordinates of permanent feature points (e.g., 7000 meters from the starting point) to complete registration; 2) Data Fusion: During icing, the tension sensor detects an increase in tension (timestamp T_tension), and DOFS monitors strain changes (timestamp T_strain). The system ensures time consistency through a hardware synchronization architecture and analyzes the icing thickness distribution by combining spatial coordinates; 3) Early Warning Output: When the time-space aligned data indicates abnormal local strain and tension, an icing warning is triggered to improve the accuracy of icing warnings and avoid line breakage accidents.

[0111] 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.

[0112] Based on the same inventive concept, this application also provides a power equipment fault location device based on distributed optical fiber sensing for implementing the power equipment fault location method based on distributed optical fiber sensing described above. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more embodiments of the power equipment fault location device based on distributed optical fiber sensing provided below can be found in the limitations of the power equipment fault location method based on distributed optical fiber sensing described above, and will not be repeated here.

[0113] In one exemplary embodiment, such as Figure 5 As shown, a power equipment fault location device based on distributed optical fiber sensing is provided, comprising: a mapping result acquisition module 501, a reference alignment result acquisition module 502, and a fault location module 503, wherein:

[0114] The mapping result acquisition module 501 is used to acquire the installation positions of multiple point sensors respectively, and map the multiple installation positions to the distance coordinates corresponding to the preset distributed optical fiber to obtain the mapping result.

[0115] The reference alignment result acquisition module 502 is used to acquire the signals of each point sensor and the preset distributed optical fiber based on the mapping result, and to perform dynamic time offset correction and spatial verification on the acquired signals to obtain the first time reference alignment result.

[0116] The reference alignment result acquisition module 502 is also used to unify the time reference of each point sensor based on the pre-built time synchronization architecture to obtain the second time reference alignment result.

[0117] The fault location module 503 is used to unify the time reference of each point sensor based on a pre-built time synchronization architecture to obtain the second time reference alignment result.

[0118] Furthermore, in one embodiment, the mapping result acquisition module 501 is also used to input a mechanical vibration signal of a preset frequency to the installation position of the point sensor; acquire the mechanical vibration signal based on the preset distributed optical fiber, and determine the vibration frequency through the mechanical vibration signal, so as to map the installation position of the point sensor to the distance coordinates corresponding to the preset distributed optical fiber, and obtain the mapping result.

[0119] Furthermore, in one embodiment, the mapping result acquisition module 501 is also used to input a preset temperature step to the installation position of the acquired multiple point sensors; obtain the temperature change at the installation position based on the preset distributed optical fiber to obtain the starting point of the temperature step, and use the starting point of the temperature step as a distance coordinate to obtain the mapping result.

[0120] Furthermore, in one embodiment, the mapping result acquisition module 501 is also used to acquire the micro-bending structure of the point sensors based on the installation positions of the multiple point sensors, and acquire the reflection feature points of the micro-bending structure based on the preset distributed optical fiber; and map the reflection feature points to the distance coordinates corresponding to the preset distributed optical fiber to obtain the mapping result.

[0121] Furthermore, in one embodiment, the reference alignment result acquisition module 502 is also used to acquire the signal of the preset distributed optical fiber and mark the local timestamp to the point sensor and the preset distributed optical fiber when the power equipment to be located experiences a closing inrush current or a lightning strike fault traveling wave, based on the mapping result; acquire the time difference between the signals of the point sensor and the preset distributed optical fiber through a preset algorithm; and perform dynamic time offset correction and spatial verification on the acquired signal based on the time difference to obtain the first time reference alignment result.

[0122] Furthermore, in one embodiment, the fault location module 503 is also used to acquire, based on the pre-acquired spatiotemporally aligned multi-source sensor data, the spatial coordinates of a preset distributed optical fiber as a first-dimensional feature, the timestamps of point sensors as a second-dimensional feature, and the multi-source sensor data as a multi-dimensional feature; and to generate a multi-dimensional data cube based on the first-dimensional feature, the second-dimensional feature, and the multi-dimensional feature.

[0123] Each module in the aforementioned power equipment fault location device based on distributed optical fiber sensing can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the computer device's memory as software, so that the processor can call and execute the corresponding operations of each module.

[0124] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 6 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 fault location data for power equipment based on distributed fiber optic sensing. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a fault location method for power equipment based on distributed fiber optic sensing.

[0125] Those skilled in the art will understand that Figure 6 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.

[0126] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0127] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

[0128] 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.

[0129] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0130] Those skilled in the art will understand that all or part of the processes in 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. When executed, the computer program can include the processes of the embodiments described above. 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.

[0131] 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.

[0132] 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 fault location of power equipment based on distributed optical fiber sensing, characterized in that, The method includes: The installation locations of multiple point sensors are obtained, and the multiple installation locations are mapped to the distance coordinates corresponding to the preset distributed optical fiber to obtain the mapping results; Based on the mapping result, the signals of each of the point sensors and the preset distributed optical fiber are obtained, and the obtained signals are dynamically time offset corrected and spatially verified to obtain the first time reference alignment result. Based on a pre-built time synchronization architecture, the time reference of each point sensor is unified to obtain a second time reference alignment result. Based on the pre-acquired spatiotemporally aligned multi-source sensor data, a multi-dimensional data cube is generated, and the fault location of the power equipment is performed by combining the first time reference alignment result and the second time reference alignment result.

2. The method according to claim 1, characterized in that, The process of acquiring the installation locations of multiple point sensors and mapping these locations to distance coordinates corresponding to a preset distributed optical fiber to obtain the mapping result includes: A mechanical vibration signal of a preset frequency is input to the installation position of the point sensor; The mechanical vibration signal is acquired based on the preset distributed optical fiber, and the vibration frequency is determined through the mechanical vibration signal to map the installation position of the point sensor to the distance coordinates corresponding to the preset distributed optical fiber, thereby obtaining the mapping result.

3. The method according to claim 1, characterized in that, The step of acquiring the installation locations of multiple point sensors and mapping these installation locations to distance coordinates corresponding to a preset distributed optical fiber to obtain the mapping result further includes: A preset temperature step is input to the installation positions of the acquired multiple point sensors; Based on the preset distributed optical fiber, the temperature change at the installation location is obtained, the starting point of the temperature step is obtained, and the starting point of the temperature step is used as the distance coordinate to obtain the mapping result.

4. The method according to claim 1, characterized in that, The step of acquiring the installation locations of multiple point sensors and mapping these installation locations to distance coordinates corresponding to a preset distributed optical fiber to obtain the mapping result further includes: Based on the installation positions of the multiple point sensors, the micro-bending structure of the point sensors is obtained, and the reflection feature points of the micro-bending structure are obtained based on the preset distributed optical fiber. The reflection feature points are mapped to the distance coordinates corresponding to the preset distributed optical fiber to obtain the mapping result.

5. The method according to claim 1, characterized in that, The process of acquiring signals from each of the point sensors and the preset distributed optical fiber based on the mapping result, and performing dynamic time offset correction and spatial verification on the acquired signals to obtain a first time reference alignment result includes: Based on the mapping results, when the power equipment to be located experiences inrush current or lightning strike fault traveling wave, the signal of the preset distributed optical fiber is acquired and the local timestamp is marked on the point sensor and the preset distributed optical fiber. The time difference between the signals from the point sensor and the pre-defined distributed optical fiber is obtained by a preset algorithm. Based on the time difference, dynamic time offset correction and spatial verification are performed on the acquired signal to obtain the first time reference alignment result.

6. The method according to claim 1, characterized in that, The generation of a multidimensional data cube based on pre-acquired spatiotemporally aligned multi-source sensor data includes: Based on the pre-acquired spatiotemporally aligned multi-source sensor data, the spatial coordinates of the preset distributed optical fiber are obtained as the first dimension feature, the timestamp of the point sensor is obtained as the second dimension feature, and the multi-source sensor data is obtained as the multi-dimensional feature. The multidimensional data cube is generated based on the first dimension feature, the second dimension feature, and the multidimensional features.

7. A power equipment fault location device based on distributed optical fiber sensing, characterized in that, The device includes: The mapping result acquisition module is used to acquire the installation positions of multiple point sensors respectively, and map the multiple installation positions to the distance coordinates corresponding to the preset distributed optical fiber to obtain the mapping result; The reference alignment result acquisition module is used to acquire the signals of each of the point sensors and the preset distributed optical fiber based on the mapping result, and to perform dynamic time offset correction and spatial verification on the acquired signals to obtain the first time reference alignment result. The benchmark alignment result acquisition module is also used to unify the time benchmarks of each point sensor based on a pre-built time synchronization architecture to obtain a second time benchmark alignment result. The fault location module is used to generate a multi-dimensional data cube based on pre-acquired spatiotemporally aligned multi-source sensor data, and combine the first time reference alignment result and the second time reference alignment result to locate the fault in the power equipment.

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 6.

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 6.

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 6.

Images