Novel high-voltage fuse

Abstract

The invention relates to the technical field of fuses, and discloses a novel high-voltage fuse, which comprises a fuse mechanism and a control module, and is characterized in that the control module is electrically connected with the fuse mechanism; the fuse mechanism comprises a contact part, an exhaust contact seat part, an insulator, a fuse carrying part and a fiber grating sensor, the lower part of the insulator and the lower part of the fuse carrying part are connected through the exhaust contact seat part, the fiber grating sensor is located in the fuse carrying part, and the upper part of the insulator and the upper part of the fuse carrying part are connected through the contact part. According to the invention, the sensing precision of the operation state of the fuse is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of fuses, and in particular to a novel high-voltage fuse. Background Art

[0002] A high-voltage fuse is a protection device used in a power system. Its main function is to cut off the current by melting its key component (the fuse element) when an overload or short circuit occurs in the circuit, thereby protecting electrical equipment from damage. The fuse element remains conducting under normal current; when the current is abnormal, the fuse element heats up and melts, triggering the arc extinguishing medium to absorb energy and cool the arc to achieve circuit interruption. The drop-out high-voltage fuse is a type of high-voltage fuse and is an overcurrent protection device commonly used in a distribution network. Its typical feature is that the fuse tube automatically drops after fusing to form a visible disconnection point, combining both circuit protection and physical isolation functions. It is mainly applied to the protection of distribution transformers, overhead lines, and branch lines, and is widely used especially in outdoor environments due to its simple structure, low cost, and intuitive maintenance.

[0003] However, the design concept of the existing drop-out high-voltage fuse is centered around "passive protection". Its functions focus on rapid fusing and arc extinguishing when a fault occurs, but whether the fuse tube drops and whether the fuse element melts need to be judged through manual visual inspection or regular patrol, which is inefficient and poses safety hazards. Summary of the Invention

[0004] The purpose of the present invention is to provide a novel high-voltage fuse to solve the problems existing in the above-mentioned prior art.

[0005] To achieve the above purpose, the present invention provides the following solution: The present invention provides a novel high-voltage fuse, including:

[0006] A fuse mechanism and a control module, the control module is electrically connected to the fuse mechanism, and the control module is used to control the fuse mechanism; the fuse mechanism includes:

[0007] A contact head, an exhaust contact seat part, an insulator, a fuse carrier part, and a fiber Bragg grating sensor. The lower part of the insulator and the lower part of the fuse carrier part are connected through the exhaust contact seat part. The fiber Bragg grating sensor is located in the fuse carrier part, and the fiber Bragg grating sensor is fixedly connected to the fuse carrier part through a ceramic sleeve. The upper part of the insulator and the upper part of the fuse carrier part are connected through the contact head;

[0008] The control module includes:

[0009] An acquisition unit, configured to obtain multi-dimensional data of the fiber Bragg grating sensor, and synchronously acquire multiple pieces of the multi-dimensional data based on wavelength division multiplexing. The acquisition unit is also configured to obtain voltage data;

[0010] A processing unit, configured to obtain temperature data and strain data of the melting carrier part based on the multi-dimensional data, and further configured to preprocess and aggregate the temperature data, the strain data and the voltage data to obtain a data set;

[0011] A judgment unit, configured to train a state monitoring model based on historical data, and further configured to input the data set into the state monitoring model for comparison;

[0012] An early warning unit, configured to determine an abnormal event based on the comparison result and send corresponding early warning information based on each abnormal event.

[0013] Furthermore, the control module includes:

[0014] An acquisition unit, configured to acquire sensor data, store the sensor data at a fixed time interval, and perform denoising. The acquisition unit is further configured to align the timestamps of the sensor data and use KNN interpolation to process missing values;

[0015] A judgment unit, configured to extract the sensor data, input the sensor data into a pre-trained state model for comparison, and further configured to determine the current operating state of the oil level gauge assembly based on the comparison result of the state model;

[0016] An early warning unit, configured to, when the current operating state of the oil level gauge assembly is abnormal, determine an abnormal area based on the abnormal state and send corresponding early warning information based on each abnormal area.

[0017] Furthermore, the exhaust contact part includes a rotary connecting frame and a lower contact, the rotary connecting frame is fixedly connected to the lower contact, and the lower contact is locked and connected to the melting carrier part.

[0018] Furthermore, the melting carrier part includes a pull ring casting, an arc shortening rod, a lining metal tube and a melting tube. The melting tube is locked and connected to the lower contact. A lining metal tube is fixedly connected inside the melting tube, the arc shortening rod is fixedly connected inside the lining metal tube, and the pull ring casting is fixedly connected to the upper part of the melting tube.

[0019] Furthermore, the contact head part includes a conductive cap and a connecting buckle. The conductive cap is fixedly connected to the upper end of the melting tube. One end of the connecting buckle is fixedly connected to the insulator, and the other end of the connecting buckle is clamped to the conductive cap, and the conductive cap is in the shape of a plum blossom.

[0020] Furthermore, when obtaining the multi-dimensional data of the fiber Bragg grating sensor and synchronously collecting a plurality of the multi-dimensional data based on wavelength division multiplexing, it includes:

[0021] Connect several of the fiber Bragg grating sensors in series to the same optical fiber, and based on an optical fiber demodulator, split the composite reflection spectrum into independent channels;

[0022] Convert each of the independent channels into an electrical signal, determine the center wavelength of the reflection peak of the fiber Bragg grating sensor through a sliding window Gaussian fitting algorithm, and obtain the wavelength offset of the fiber Bragg grating sensor.

[0023] Further, when obtaining the temperature data and strain data of the carrier melting part based on the multi-dimensional data, it includes:

[0024] Obtain the temperature sensitivity coefficient and strain sensitivity coefficient of the fiber Bragg grating sensor, construct a linear equation system, and determine the temperature data and the strain data based on the linear equation system.

[0025] Further, when preprocessing and aggregating the temperature data, the strain data, and the voltage data to obtain a data set, it includes:

[0026] Repair missing data based on linear interpolation, and interpolate the voltage data into the same time series based on the time stamp of the fiber Bragg grating sensor;

[0027] Use a moving average filter to suppress the instantaneous temperature rise of the temperature data, and remove high-frequency noise based on wavelet transform;

[0028] Extract derivative features of the temperature data, strain data, and voltage data based on a sliding window. The derivative features include time domain features based on the temperature data, the strain data, and the voltage data, and frequency domain features extracted based on Fourier transform;

[0029] Aggregate the temperature data, the strain data, the voltage data, and the derivative features to form the data set, and perform normalization processing on the temperature data, the strain data, the voltage data, and the derivative features to obtain the data set.

[0030] Further, when training a state monitoring model based on historical data, it includes:

[0031] Divide the historical data into normal working condition data and fault working condition data, and obtain the joule heat and thermal expansion data of the material of the carrier melting part;

[0032] Perform feature decomposition on the data set of the historical data and conduct model training, perform 5-fold cross-validation on the time series of the training data, and select the model parameters with the highest F1-Score as the parameters of the state monitoring model.

[0033] Further, when inputting the data set into the state monitoring model for comparison, it includes:

[0034] Based on the state monitoring model, obtain all abnormal state probabilities, and determine an abnormal state threshold. When the comparison result is greater than the abnormal state threshold, enter the abnormal judgment, traverse all abnormal state probabilities, and select the abnormal state with the highest probability as the comparison result;

[0035] All abnormal states are divided into overload, short circuit, and poor contact;

[0036] When the temperature rises slowly, the residual Joule heat is small, and the strain increases uniformly, it is determined as overload;

[0037] When the temperature increases suddenly, the residual Joule heat is large, and the strain mutates, it is determined as a short circuit;

[0038] When the local temperature is abnormal, the residual value of Joule heat is large, and the strain fluctuates, it is determined as poor contact.

[0039] Further, when determining an abnormal event based on the comparison result and sending corresponding warning information based on each abnormal event, it includes:

[0040] When the comparison result is overload, generate a first-level warning;

[0041] When the comparison result is poor contact, generate a second-level warning;

[0042] When the comparison result is a short circuit, generate a third-level warning.

[0043] The present invention discloses the following technical effects: By embedding the fiber Bragg grating sensor inside the fuse part, it is possible to collect multi-dimensional physical parameters such as temperature and strain in real time. Compared with traditional single-parameter monitoring, the synchronous acquisition of multi-dimensional data improves the perception accuracy of the fuse operation state. By using wavelength division multiplexing technology to synchronously collect multi-channel fiber Bragg grating data and combining with the real-time acquisition of voltage data, the system can comprehensively capture the correlation between electrical and mechanical states, providing a more complete basis for fault diagnosis. The processing unit preprocesses the original data to eliminate the influence of environmental interference, and at the same time generates a high signal-to-noise ratio data set through aggregation, improving the usability of the data and laying a reliable foundation for subsequent analysis. The state monitoring model trained based on historical data can autonomously learn the normal behavior pattern and abnormal characteristics of the fuse. By comparing the real-time data set with the model threshold, the system can identify abnormal signals, such as local overheating or mechanical deformation, avoiding the lag of the traditional threshold determination method. The warning unit can locate the type of abnormal event through the model comparison result and send warning information in levels. Through multi-dimensional perception, intelligent analysis, and active warning, the real-time monitoring ability, fault response speed, and long-term operation reliability of the fuse are improved, and the equipment maintenance efficiency is increased. Description of the Drawings

[0044] The accompanying drawings, which form a part of this application, are used to provide a further understanding of this application. The schematic embodiments of this application and their descriptions are used to explain this application and do not constitute an improper limitation to this application. In the drawings:

[0045] Figure 1 is the overall schematic diagram of the novel high-voltage fuse provided by the embodiment of the present invention;

[0046] Figure 2 is the sectional view of the fuse-carrying part in the novel high-voltage fuse provided by the embodiment of the present invention;

[0047] Figure 3 is the functional block diagram of the novel high-voltage fuse provided by the embodiment of the present invention.

[0048] In the figure: 1, insulator; 2, fiber Bragg grating sensor; 210, ceramic bushing; 220, silica gel sleeve; 3, contact head part; 310, conductive cap; 320, connecting buckle; 4, exhaust contact seat part; 410, rotary connecting frame; 420, lower contact; 5, fuse-carrying part; 510, pull-ring casting; 520, arc shortening rod; 530, inner lining metal tube; 540, fuse tube; 6, circulator; 7, fiber optic demodulator; 8, optical fiber. Detailed Embodiments

[0049] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0050] To make the above objects, features, and advantages of the present invention more obvious and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0051] Next, the exemplary embodiments of the present disclosure will be described in more detail with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art. It should be noted that, without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

[0052] In some embodiments of this application, referring to Figures 1 - 3 as shown, a novel high-voltage fuse includes:

[0053] A fuse mechanism and a control module, the control module is electrically connected to the fuse mechanism, and the control module is used to control the fuse mechanism. The fuse mechanism includes:

[0054] A contact head 3, an exhaust contact seat 4, an insulator 1, a fuse carrier 5, and a fiber Bragg grating sensor 2. The lower part of the insulator 1 and the lower part of the fuse carrier 5 are connected through the exhaust contact seat 4. The fiber Bragg grating sensor 2 is located in the fuse carrier 5, and the fiber Bragg grating sensor 2 is fixedly connected to the fuse carrier 5 through a ceramic sleeve 210. The upper part of the insulator 1 and the upper part of the fuse carrier 5 are connected through the contact head 3.

[0055] The control module includes:

[0056] An acquisition unit, configured to obtain multi-dimensional data of the fiber Bragg grating sensor 2, and synchronously acquire multiple multi-dimensional data based on wavelength division multiplexing. The acquisition unit is also configured to obtain voltage data.

[0057] A processing unit, configured to obtain temperature data and strain data of the fuse carrier 5 based on the multi-dimensional data. The processing unit is also configured to preprocess the temperature data, strain data, and voltage data, and perform aggregation to obtain a data set.

[0058] A judgment unit, configured to train a state monitoring model based on historical data. The judgment unit is also configured to input the data set into the state monitoring model for comparison.

[0059] An early warning unit, configured to determine abnormal events based on the comparison result and send corresponding early warning information based on each abnormal event.

[0060] Specifically, the fuse mechanism is composed of a contact head 3, an exhaust contact seat 4, an insulator 1, a fuse carrier 5, and a fiber Bragg grating sensor 2. The lower ends of the insulator 1 and the fuse carrier 5 are connected through the exhaust contact seat 4. Among them, the insulator 1 is fixedly connected to the exhaust contact seat 4, and the fuse carrier 5 is rotatably connected to the exhaust contact seat 4. The contact head 3 is used to contact the circuit. There are two fiber Bragg grating sensors 2, which are arranged inside the fuse carrier 5. One fiber Bragg grating sensor 2 is arranged inside the fuse carrier 5 through a ceramic sleeve 210, and the other fiber Bragg grating sensor 2 is also arranged inside the fuse carrier 5 through a ceramic sleeve 210. However, a silica gel sleeve 220 is also arranged on the outer surface of the ceramic sleeve 210. The fiber Bragg grating sensor 2 without the silica gel sleeve 220 is used to sense the temperature and strain of the fuse carrier 5, while the fiber Bragg grating sensor 2 with the silica gel sleeve 220 is used to sense only the temperature. Since the silica gel sleeve 220 isolates the strain but does not isolate the heat, it will not affect the acquisition of its heat data. A fiber Bragg grating (FBG) is an optical device that forms a periodic refractive index modulation in the fiber core through an ultraviolet laser. During the manufacturing process of the fuse carrier 5, the ceramic sleeve 210 is embedded to embed the fiber Bragg grating sensor 2 therein, ensuring its direct contact with the fuse carrier 5 to sense temperature and strain, while avoiding damage to the optical fiber during high-temperature fusing. At the same time, multiple fiber Bragg grating sensors 2 are arranged along the length direction of the melt to form a distributed monitoring network to capture heat data and strain data. The two fiber Bragg grating sensors are connected in series through a single optical fiber, and the optical fiber is led out from the upper side of the fuse carrier (in the direction coaxial with the rotating shaft). Without affecting the normal operation of the fuse, the optical fiber is led out from the side wall, and the position where the optical fiber is led out from the side wall is sealed. It is necessary to solve both moisture and dust prevention and rotation without affecting the optical fiber at the same time. Therefore, the optical fiber needs to have a redundant length, so that when the fuse drops, it will not fail due to insufficient optical fiber length. The sealing can be achieved by filling high-temperature-resistant silica gel and curing it to form an elastic sealing body, or other sealing means that can achieve the same sealing effect are also acceptable. And, the optical fiber demodulator 7 is electrically connected to the circulator 6. After the optical fiber is led out of the fuse, it is connected to the circulator 6, and the circulator 6 is electrically connected to the optical fiber demodulator 7. Usually, a bracket is equipped when the fuse is set. The circulator 6 and the optical fiber demodulator 7 can be fixedly connected to the bracket, or fixed at a position that does not directly contact the fuse relatively. An armored layer can be sleeved on the optical fiber for protection. The fiber Bragg grating sensor 2 detects the reflection wavelength shift of each sensor through the optical fiber demodulator 7, and at the same time realizes the synchronous acquisition of signals of multiple sensors on a single optical fiber through wavelength division multiplexing technology. Then, the temperature and strain data are inversely solved through the processing unit, and the inversely solved data are aggregated to obtain a data set. Subsequently, the judgment unit inputs the data set into the state monitoring model for comparison. Through the comparison result, it can be known whether the current operating state of the fuse is abnormal, and different warning information is given according to the abnormal points.

[0061] It is understandable that through the differential design of the dual fiber Bragg grating sensors 2 (with or without the silicone sleeve 220 to isolate strain), the measurement of temperature and strain is achieved, avoiding signal crosstalk caused by physical coupling of a single sensor. The purity of the temperature data combined with the dynamic changes of the strain improves the resolution of abnormal state recognition, especially the distinction of different fault modes such as overload and short circuit. Multiple fiber Bragg grating sensors 2 are arranged along the fuse melting part 5 to form a distributed sensing network, which can capture the heat data and mechanical deformation data of the melt. Overcoming the limitations of traditional single-point monitoring, it can detect potential risks of local overheating or stress concentration earlier and improve the ability to predict potential risks. The ceramic sleeve 210 packaging technology not only ensures the direct contact between the fiber optic sensor and the fuse melt to improve the heat conduction efficiency, but also isolates the physical damage to the sensor caused by the extreme environment at the moment of melting through high-temperature resistant materials. The silicone sleeve 220 further isolates the interference of mechanical vibration on strain measurement, ensuring the long-term stability of data acquisition. Based on the wavelength division multiplexing technology, a single optical fiber can realize the parallel transmission of multi-sensor signals, simplifying the complexity of traditional multi-cable layout. Reducing the space occupancy rate of the internal structure of the device, while reducing the attenuation and noise interference during signal transmission. Through the preprocessing module, the temperature, strain and voltage data are aggregated and standardized to construct a multi-modal data set, providing high-quality input for subsequent analysis. Combining the state monitoring model trained with historical data, it can adaptively learn the characteristic laws of the fuse under different working conditions and gradually improve the generalization recognition ability of complex abnormal modes. The warning unit triggers a differential response strategy according to the severity of the comparison result, such as distinguishing overload prompts, poor contact warnings and short circuit emergency handling. This hierarchical mechanism optimizes the allocation efficiency of operation and maintenance resources, avoiding response delays or resource waste caused by "one-size-fits-all" alarms. By real-time monitoring the temperature and mechanical state of the fuse melting part 5, abnormal trends can be identified before the melt reaches the critical melting point, such as the gradual temperature rise caused by overload or the deformation accumulation caused by mechanical aging. This forward-looking warning provides a time window for manual or automatic intervention, reducing the probability of unplanned melting. The natural electromagnetic interference resistance of fiber optic sensing technology enables it to still work stably in harsh electromagnetic environments such as high-strength electric fields and lightning surges. At the same time, the corrosion-resistant and moisture-proof design of ceramic and silicone materials ensures the long-term reliability of the sensor in extreme climate conditions such as high humidity and salt spray outdoors. The non-invasive fiber optic sensing solution can achieve state monitoring without damaging the original structure of the fuse, reducing the human operation risk during installation and maintenance. In addition, by locating the abnormal type, it can specifically guide component replacement or local repair, avoiding the high cost of replacing the whole device.

[0062] In some embodiments of the present application, the exhaust contact part 4 includes a rotary connecting frame 410 and a lower contact 420. The rotary connecting frame 410 is fixedly connected to the lower contact 420, and the lower contact 420 is locked and connected to the fuse melting part 5.

[0063] In some embodiments of the present application, the fuse-holding part 5 includes a pull-ring casting 510, an arc-shortening rod 520, a lining metal tube 530, and a fuse tube 540. The fuse tube 540 is tightly connected to the lower contact 420. A lining metal tube 530 is fixedly connected inside the fuse tube 540. An arc-shortening rod 520 is fixedly connected inside the lining metal tube 530. A pull-ring casting 510 is fixedly connected to the upper part of the fuse tube 540.

[0064] In some embodiments of the present application, the contact part 3 includes a conductive cap 310 and a connecting buckle 320. The conductive cap 310 is fixedly connected to the upper end of the fuse tube 540. One end of the connecting buckle 320 is fixedly connected to the insulator 1, and the other end of the connecting buckle 320 is snap-connected to the conductive cap 310, and the conductive cap 310 is in the shape of a plum blossom.

[0065] Specifically, the insulator 1 is fixed by insert casting. The fuse-holding part 5 is connected to the insulator 1 through a rotating connecting frame 410, allowing it to rotate around an axis to achieve a dropping action. After the fuse-holding part is installed, it forms an angle of 15° to 30° with the plumb line to ensure that it falls naturally by gravity after fusing. The insulator 1 provides vertical support, and the rotating shaft is located at the bottom of the fuse-holding part, enabling it to rotate freely around this point. The lower contact 420 provides contact pressure through a stainless steel spring to ensure close contact between the fuse-holding part and the lower contact 420. The lower contact 420 is located below the dropping direction of the fuse-holding part. Before fusing, the fuse-holding part is locked by the spring. During fusing, the fuse element fuses, causing the fuse-holding part to lose support. After the spring is released, the fuse-holding part rotates around the rotating shaft and separates from the lower contact 420. During operation, the fuse-holding part 5 is fixed in the closed position by the spring pressure of the lower contact 420, and its upper end is snap-connected to the connecting buckle 320. The current passes through the conductive cap 310 to the fuse tube 540, and the arc is shortened through the arc-shortening rod 520, and then is conducted through the lower contact 420. The fuse-holding part 5 rotates downward around the rotating shaft under the action of gravity and is completely separated from the lower contact 420, forming a visible break. The opening at the bottom of the fuse tube 540 is exposed as the fuse-holding part 5 drops, and the fault gas is discharged through a single-end downward exhaust method.

[0066] It is understandable that through the locking connection of the rotating connecting frame 410 and the lower contact 420, and the dropping mechanism of the melting-carrying part 5 rotating around the axis, the triggering and separation of the fusing action are ensured. The introduction of the rotating structure enhances the stability of the melting-carrying part 5 in the normal closed state. At the same time, during fusing, rapid tripping is achieved through the synergistic effect of gravity and spring force, reducing the risk of jamming or malfunction. The lower contact 420 uses a stainless steel spring to provide a constant contact pressure, offsetting the loosening of the contact surface caused by thermal expansion or mechanical vibration. This not only ensures the electrical conduction stability during operation but also enables the rapid detachment of the melting-carrying part 5 through spring release at the moment of fusing, improving the breaking efficiency. The preset angle (15° - 30°) formed by the melting-carrying part 5 and the plumb line naturally guides the falling direction of the fuse tube 540 through the action of gravity, ensuring a clearly visible physical fracture after fusing. The combination of the inner lining metal tube 530 and the arc shortening rod 520 accelerates the contraction and cooling of the arc through physical constraints and electromagnetic field optimization, shortening the arcing time, reducing the ablation of the fuse tube 540 and surrounding components by arc energy, and improving the equipment life and breaking safety. The geometric structure of the plum blossom-shaped conductive cap 310 increases the contact area, equalizes the current distribution, reduces the contact resistance and local temperature rise. Combined with the metal inner lining structure of the fuse tube 540, the heat dissipation path is further improved, avoiding material aging or fusing delay caused by hot spot accumulation. The single-end downward exhaust channel at the bottom of the fuse tube 540, combined with the opening exposure mechanism after the melting-carrying part 5 falls, realizes the directional and rapid discharge of fault gases, preventing the risk of pressure shock or secondary discharge caused by gas accumulation in a closed space and improving the operating environment safety.

[0067] In some embodiments of the present application, when acquiring multi-dimensional data of the fiber Bragg grating sensor 2 and synchronously collecting multiple multi-dimensional data based on wavelength division multiplexing, it includes:

[0068] Connect several fiber Bragg grating sensors 2 in series to the same optical fiber, and divide the composite reflection spectrum into independent channels based on the optical fiber demodulator 7.

[0069] Convert each independent channel into an electrical signal, determine the center wavelength of the reflection peak of the fiber Bragg grating sensor 2 through the sliding window Gaussian fitting algorithm, and obtain the wavelength offset of the fiber Bragg grating sensor 2.

[0070] In some embodiments of the present application, when acquiring the temperature data and strain data of the melting-carrying part 5 based on multi-dimensional data, it includes:

[0071] Obtain the temperature sensitivity coefficient and strain sensitivity coefficient of the fiber Bragg grating sensor 2, construct a linear equation system, and determine the temperature data and strain data based on the linear equation system.

[0072] Specifically, two fiber Bragg grating sensors 2 are connected in series to the same optical fiber. Each sensor is preset with a different Bragg wavelength, and the wavelength interval between adjacent sensors needs to be greater than the maximum expected offset to avoid signal overlap. The optical signal emitted by the broadband light source enters the sensing network through the optical fiber. Then, each sensor reflects the light of its specific wavelength, and the remaining wavelengths are projected. Subsequently, the reflected light returns to the optical fiber demodulator 7 through the circulator 6. The demodulator divides the composite reflection spectrum into independent channels through an arrayed waveguide grating or a tunable filter. The independent channel represents the reflection wavelength range of the i-th fiber Bragg grating sensor 2 corresponding to the i-th channel. At the same time, the optical signal of each channel is converted into an electrical signal, and the output is a voltage-wavelength sequence. The electrical signal of each channel is intercepted locally according to the window width to obtain spectral data: , where is the electrical signal sequence of the i-th channel, is the wavelength value of the k-th sampling point, N is the total number of sampling points, and W is the window width. Then, the spectral data within each window is fitted: , where A is the amplitude of the reflection peak, is the fitted center wavelength, is the full width at half maximum of the reflection peak, B is the background noise baseline, represents the reflection spectral intensity of the fiber Bragg grating sensor 2. Then, the wavelength offset is calculated according to the fitting result: , where is the initial Bragg wavelength of the i-th fiber Bragg grating sensor 2, is the real-time Bragg wavelength of the i-th fiber Bragg grating sensor 2, is the wavelength offset of the i-th fiber Bragg grating sensor 2. In this embodiment, two fiber Bragg grating sensors 2 are provided. The two fiber Bragg grating sensors 2 are FBG1 (without the silica gel sleeve 220) and FBG2 (with the silica gel sleeve 220) respectively. Among them, FBG1 senses both temperature and strain simultaneously, and the wavelength offset is: , where is the wavelength offset of FBG1, is the temperature sensitivity coefficient of the FBG sensor, is the strain sensitivity coefficient of the FBG sensor, is the temperature change, is the strain change, representing the difference between the current mechanical strain and the reference strain. And FBG2 only senses temperature, and the wavelength offset is: , where is the wavelength offset of FBG2. Then, by solving the simultaneous equations for the strain, the temperature influence is eliminated, and the pure strain change is obtained: .

[0073] It is understandable that the physical separation measurement of temperature and strain is achieved through the differentiated design of the dual fiber grating sensor 2 (with or without the silicone sleeve 220 to isolate the strain). The sensor without the silicone sleeve 220 directly senses the combined effect of temperature and strain, while the sensor with the silicone sleeve 220 only senses the temperature, and eliminates the interference of temperature on the mechanical strain measurement through simultaneous equations. It fundamentally solves the measurement error caused by cross-sensitivity of traditional sensors and improves the recognition accuracy of abnormal conditions (such as overload and mechanical fatigue). By connecting multiple sensors in series on the same optical fiber and independently collecting data based on wavelength division multiplexing technology, the temperature and strain distribution at different positions of the fuse can be obtained synchronously, and early abnormal signals of local hot spots or stress concentration areas can be captured, avoiding the risk of missed detection due to single-point monitoring blind spots, and improving the comprehensiveness and reliability of state perception. A sliding window Gaussian fitting algorithm is used to extract the central wavelength of the reflection peak, and mathematical modeling is used to separate the effective signal from the background noise, thereby suppressing the interference introduced by ambient light fluctuations, circuit noise and optical fiber transmission loss, ensuring high-precision detection of weak wavelength offsets, and providing a technical basis for early warning of subtle anomalies (such as local temperature rise caused by poor contact).

[0074] In some embodiments of the present application, the temperature data, the strain data and the voltage data are preprocessed and aggregated, and when the data set is obtained, the following steps are included:

[0075] The missing data are repaired based on linear interpolation, and the voltage data are interpolated to the same time series based on the timestamp of the fiber Bragg grating sensor 2.

[0076] The sliding average filter is used to suppress the instantaneous temperature rise of the temperature data, and the high-frequency noise is removed based on the wavelet transform.

[0077] Derivative features of temperature data, strain data and voltage data are extracted based on a sliding window. The derived features include time domain features based on temperature data, strain data and voltage data and frequency domain features extracted based on Fourier transform.

[0078] The temperature data, strain data, voltage data, and derived features are aggregated to form a data set, and the temperature data, strain data, voltage data, and derived features are normalized to obtain a data set.

[0079] Specifically, the acquired temperature data, strain data, and voltage data are time-stamp aligned. At the same time, the missing values in the temperature data and strain data are supplemented by linear interpolation of adjacent points. In order to suppress the instantaneous temperature rise noise caused by direct sunlight, the average value is taken within the window width: ,in, Expressed as the mean of the window width, is the time window width, Indicates the value of the repaired temperature data at the missing timestamp Then, the high-frequency noise is removed through wavelet transform. Since wavelet transform is a mature existing technology, it will not be elaborated here. After that, the time-domain and frequency-domain features of the temperature data, strain data, and voltage data are extracted within the window width. The time-domain features specifically include, but are not limited to, the temperature change rate, strain accumulation, and voltage fluctuation standard deviation. The frequency-domain features are obtained by performing Fourier transform on the temperature data, strain data, and voltage data respectively to extract their main frequency components. Then, the original data and its derived features are normalized and feature aggregation is performed to obtain the aggregated dataset.

[0080] It can be understood that the missing values in the temperature and strain data are repaired by linear interpolation to ensure the integrity and coherence of the time series. This processing avoids model misjudgment caused by data interruption and provides a continuous and reliable data basis for subsequent analysis. Based on the timestamps of the fiber optic sensors, cubic spline interpolation is performed on the voltage data for alignment to eliminate the time asynchrony problem caused by the sampling frequency differences of different sensors, ensuring the spatio-temporal consistency of the temperature, strain, and voltage data and enhancing the correlation analysis ability of multi-modal data. Moving average filtering can smooth the instantaneous temperature fluctuations caused by external factors such as direct sunlight and retain the true temperature rise trend. Combining with wavelet transform to remove high-frequency noise further improves the signal-to-noise ratio of the signal, making the data more conform to the actual physical process. The frequency-domain features are extracted by Fourier transform to obtain the main frequency components, analyzing the periodic law of the signal from the perspective of energy distribution and reducing the interference of random noise on feature representation. The complementarity of the time-domain and frequency-domain features enhances the robustness of anomaly detection. The sliding window mechanism extracts features such as the temperature change rate, strain accumulation, and voltage fluctuation standard deviation in the time domain, dynamically reflecting the instantaneous changes and cumulative effects of the equipment state. The main frequency components in the frequency domain reveal the periodic law behind the data, providing a deep basis for fault mode recognition. The time-domain features (such as the temperature change rate) are directly related to the physical state changes of the equipment, and the frequency-domain features (such as the high-frequency energy ratio) map the frequency band characteristics of mechanical vibration or arc discharge. The combination of the two makes the feature set have both intuitive physical meaning and the ability to represent hidden patterns. Normalization processing unifies the temperature, strain, voltage, and their derived features to the same scale, avoiding model weight deviation caused by dimensional differences. This step significantly improves the convergence speed and stability of machine learning algorithms. The aggregated dataset contains the original data and derived features, providing a unified input for various analysis tasks such as classification, regression, and clustering, and can be adapted to different scenarios such as overload warning, life prediction, and fault diagnosis.

[0081] In some embodiments of the present application, when training the state monitoring model based on historical data, it includes:

[0082] The historical data is divided into normal working condition data and fault working condition data, and the joule heat and thermal expansion data of the material of the melting part 5 are obtained.

[0083] Perform feature decomposition on the dataset of historical data and conduct model training. Perform 5-fold cross-validation on the time series of the training data, and select the model parameters with the highest F1-Score as the parameters of the condition monitoring model.

[0084] Specifically, by obtaining the joule heat data and thermal expansion data of the material in the melting section 5, and at the same time obtaining the dataset in the historical data, perform feature decomposition and construct a feature matrix. The feature matrix: , where F is the feature matrix, is the joule heat power of the melting section 5, is the cumulative amount of joule heat, is the temperature change rate, is the mechanical strain separation amount, is the proportion of the main frequency energy. Its probability output layer passes through the Softmax activation function: , where x is the input feature vector (i.e., the feature matrix, all features of the sample), is the conditional probability, k is the target class index, K is the total number of classes, is the Logit value of class k, that is, the original prediction score of the model for class k, is for to perform exponential operation, j is the summation index. Specifically, the Softmax activation function is a non-linear function that converts any real number vector into a probability distribution, and is used to output the abnormal type. Furthermore, the loss function of the model is: , where L is the value of the loss function, is the class weight, which is used to balance the problem of uneven sample distribution, is the one-hot encoding of the true label. That is, when the true class is k, is 1, otherwise it is 0. For example, the short circuit label: , is the probability predicted by the model, that is . Furthermore, divide the feature matrix into 5 subsets according to time for cross-validation training. Successively use 4 subsets as the training set and 1 subset as the validation set, and then train the model. Finally, calculate the F1-Score of the validation set: , where F1 is the result of the F1-Score, is the precision, is the recall rate. The higher the F1-Score, the better the balance the model achieves between reducing false positives and false negatives. Therefore, select the parameters with the highest F1-Score as the parameters of the condition monitoring model.

[0085] It is understandable that by introducing the joule heat and thermal expansion data of the fusible part 5 material, the physical essence of the equipment operation is embedded in the feature engineering. The joule heat power reflects the energy accumulation effect of current overload, and the thermal expansion strain is related to the coupling relationship between material deformation and temperature change. The deep combination of these physical quantities enhances the model's understanding ability of the fuse working mechanism, making the state judgment closer to the actual physical process. The clear physical quantity definitions (such as temperature change rate, mechanical strain separation) and frequency-domain energy distribution characteristics (main frequency energy ratio) in the feature matrix provide a clear physical interpretation path for model decision-making. The time-domain features (such as joule heat accumulation) capture the gradual change trend of the equipment state, and the frequency-domain features (such as main frequency energy ratio) reveal the frequency band characteristics of periodic or sudden faults. The multi-dimensional complementarity of the two enhances the model's adaptability to complex working conditions, enabling it to identify hidden overload hazards that develop slowly and detect instantaneous short circuits or arc discharges. Time series 5-fold cross-validation is adopted, strictly following the time order of the data to divide the training set and the validation set, avoiding false high precision caused by future information leakage. Ensure that the model still maintains reliable performance on data in unknown time intervals, reducing the risk of misjudgment caused by data distribution deviation. Taking F1-Score as the core evaluation index, balancing precision (reducing false alarms) and recall (reducing missed alarms), avoiding the model being biased towards the majority class (normal data), and enhancing the sensitivity to the minority class (faults).

[0086] In some embodiments of the present application, when inputting the data set into the state monitoring model for comparison, it includes:

[0087] Based on the state monitoring model, obtain all abnormal state probabilities, and determine the abnormal state threshold. When the comparison result is greater than the abnormal state threshold, enter the abnormal judgment, and traverse all abnormal state probabilities, and select the abnormal state with the highest probability as the comparison result.

[0088] All abnormal states are divided into overload, short circuit, and poor contact.

[0089] When the temperature rises slowly, the joule heat residual is small, and the strain increases uniformly, it is determined as overload.

[0090] When the temperature increases suddenly, the joule heat residual is large, and the strain changes suddenly, it is determined as a short circuit.

[0091] When the local temperature is abnormally high, the joule heat residual value is large, and the strain fluctuates, it is determined as poor contact.

[0092] In some embodiments of the present application, when determining an abnormal event based on the comparison result and sending corresponding warning information based on each abnormal event, it includes:

[0093] When the comparison result is overload, generate a first-level warning.

[0094] When the comparison result is poor contact, generate a second-level warning.

[0095] When the comparison result is a short circuit, a third-level early warning is generated.

[0096] It can be understood that through the multi-dimensional analysis of the comprehensive temperature change trend, Joule heat residual, and strain characteristics, the limitation of misjudgment by a single parameter is avoided. For example, overload requires simultaneous satisfaction of slow temperature rise, small Joule heat residual, and uniform growth of strain. The abnormal mode is verified from multiple perspectives such as energy accumulation and material deformation, improving the physical rationality of the determination. Based on the threshold determination mechanism of the abnormal state probability, normal fluctuations and real faults are distinguished. An early warning is triggered only when the probability exceeds the preset threshold, reducing the false alarm rate caused by short-term interference (such as instantaneous voltage surges), while ensuring sensitive capture of potential risks. The abnormal events are clearly classified into overload, short circuit, and poor contact, and different determination conditions are defined (such as sudden temperature increase corresponding to a short circuit, local temperature anomaly corresponding to poor contact), enabling the model to accurately locate the root cause of the fault and providing a basis for targeted disposal. According to the severity of the anomaly, first-level (overload), second-level (poor contact), and third-level (short circuit) early warnings are divided to achieve dynamic calibration of the risk level. The first-level early warning indicates potential risks, the second-level early warning requires planned maintenance, and the third-level early warning triggers an emergency response, optimizing the priority allocation of operation and maintenance resources. All abnormal state probabilities are traversed and the type with the highest probability is selected as the result, reducing the dependence on manual review. The system automatically associates the early warning level, shortening the time delay from fault identification to action initiation and improving the emergency response efficiency. The early warnings of overload and poor contact provide forward-looking hints for equipment deterioration, supporting load adjustment or component replacement before a fault occurs, avoiding power outages caused by unplanned outages, and reducing derivative risks.

[0097] In summary, the beneficial effects of the present invention are as follows: By embedding the fiber Bragg grating sensor 2 inside the fuse melting part 5, multi-dimensional physical parameters such as temperature and strain can be collected in real time. Compared with traditional single-parameter monitoring, the synchronous acquisition of multi-dimensional data improves the perception accuracy of the fuse operation state. Through wavelength division multiplexing technology, multiple fiber Bragg grating data are synchronously collected, combined with the real-time acquisition of voltage data, the system can comprehensively capture the correlation between electrical and mechanical states, providing a more complete basis for fault diagnosis. The processing unit preprocesses the original data to eliminate the influence of environmental interference, and at the same time generates a high signal-to-noise ratio data set through aggregation, improving the usability of the data and laying a reliable foundation for subsequent analysis. The state monitoring model trained based on historical data can autonomously learn the normal behavior mode and abnormal characteristics of the fuse. By comparing the real-time data set with the model threshold, the system can identify abnormal signals, such as local overheating or mechanical deformation, avoiding the lag of the traditional threshold determination method. The early warning unit can locate the type of abnormal event and send early warning information in levels through the model comparison result. Through multi-dimensional perception, intelligent analysis, and active early warning, the real-time monitoring ability, fault response speed, and long-term operation reliability of the fuse are improved, and the equipment maintenance efficiency is increased.

[0098] Those skilled in the art should understand that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0099] The present application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the flows and / or blocks in the flowchart and / or block diagram can also be implemented. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0100] These computer program instructions can also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable storage medium generate a manufactured article including instruction means, and the instruction means implements the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0101] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0102] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: still can modify the specific implementation manners of the present invention or make equivalent replacements, and any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the protection scope of the claims of the present invention.

Claims

1. A novel high-voltage fuse, characterized in that, Comprising: A fuse mechanism and a control module, the control module being electrically connected to the fuse mechanism, and the control module being used to control the fuse mechanism; the fuse mechanism includes: A contact head (3), an exhaust contact seat part (4), an insulator (1), a fuse-carrying part (5), and a fiber Bragg grating sensor (2). The lower part of the insulator (1) and the lower part of the fuse-carrying part (5) are connected through the exhaust contact seat part (4). The fiber Bragg grating sensor (2) is located inside the fuse-carrying part (5), and the fiber Bragg grating sensor (2) is fixedly connected to the fuse-carrying part (5) through a ceramic sleeve (210). The upper part of the insulator (1) and the upper part of the fuse-carrying part (5) are connected through the contact head (3); The control module includes: An acquisition unit configured to obtain multi-dimensional data of the fiber Bragg grating sensor (2), and synchronously acquire a plurality of the multi-dimensional data based on wavelength division multiplexing. The acquisition unit is further configured to obtain voltage data; A processing unit configured to obtain temperature data and strain data of the fuse-carrying part (5) based on the multi-dimensional data. The processing unit is further configured to preprocess and aggregate the temperature data, the strain data, and the voltage data to obtain a data set; A judgment unit configured to train a state monitoring model based on historical data. The judgment unit is further configured to input the data set into the state monitoring model for comparison; An early warning unit configured to determine abnormal events based on the comparison result and send corresponding early warning information based on each abnormal event.

2. The novel high-voltage fuse according to claim 1, wherein, The exhaust contact seat part (4) includes a rotary connecting frame (410) and a lower contact (420). The rotary connecting frame (410) is fixedly connected to the lower contact (420), and the lower contact (420) is tightly connected to the fuse-carrying part (5).

3. The novel high-voltage fuse according to claim 2, characterized in that, The fuse-carrying part (5) includes a pull-ring casting (510), an arc shortening rod (520), an inner lining metal tube (530), and a fuse tube (540). The fuse tube (540) is tightly connected to the lower contact (420). An inner lining metal tube (530) is fixedly connected inside the fuse tube (540). The arc shortening rod (520) is fixedly connected inside the inner lining metal tube (530). The upper part of the fuse tube (540) is fixedly connected to the pull-ring casting (510).

4. The novel high-voltage fuse according to claim 3, characterized in that, The contact head (3) includes a conductive cap (310) and a connecting buckle (320). The conductive cap (310) is fixedly connected to the upper end of the fuse tube (540). One end of the connecting buckle (320) is fixedly connected to the insulator (1), and the other end of the connecting buckle (320) is snap-connected to the conductive cap (310), and the conductive cap (310) is in the shape of a plum blossom.

5. The novel high-voltage fuse according to claim 4, characterized in that, When obtaining the multi-dimensional data of the fiber Bragg grating sensor (2) and synchronously acquiring a plurality of the multi-dimensional data based on wavelength division multiplexing, it includes: Connecting a plurality of the fiber Bragg grating sensors (2) in series to the same optical fiber, and splitting the composite reflection spectrum into independent channels based on an optical fiber demodulator (7); Convert each of the independent channels into an electrical signal, determine the center wavelength of the reflection peak of the fiber Bragg grating sensor (2) through a sliding window Gaussian fitting algorithm, and obtain the wavelength offset of the fiber Bragg grating sensor (2).

6. The novel high-voltage fuse according to claim 5, characterized in that, When obtaining the temperature data and strain data of the carrier melting part (5) based on the multi-dimensional data, it includes: Obtain the temperature sensitivity coefficient and strain sensitivity coefficient of the fiber Bragg grating sensor (2), construct a linear equation system, and determine the temperature data and the strain data based on the linear equation system.

7. The novel high-voltage fuse according to claim 6, characterized in that, When preprocessing and aggregating the temperature data, the strain data, and the voltage data to obtain a data set, it includes: Repair missing data based on linear interpolation, and interpolate the voltage data into the same time series based on the time stamp of the fiber Bragg grating sensor (2); Use a moving average filter to suppress the instantaneous temperature rise of the temperature data, and remove high-frequency noise based on wavelet transform; Extract derivative features of the temperature data, strain data, and voltage data based on a sliding window. The derivative features include time domain features based on the temperature data, the strain data, and the voltage data, and frequency domain features extracted based on Fourier transform; Aggregate the temperature data, the strain data, the voltage data, and the derivative features to form the data set, and perform normalization processing on the temperature data, the strain data, the voltage data, and the derivative features to obtain the data set.

8. The novel high-voltage fuse according to claim 7, wherein, When training a state monitoring model based on historical data, it includes: Divide the historical data into normal condition data and fault condition data, and obtain the Joule heat and thermal expansion data of the material of the carrier melting part (5); Perform feature decomposition on the data set of the historical data and conduct model training, perform 5-fold cross-validation on the time series of the training data, and select the model parameters with the highest F1-Score as the parameters of the state monitoring model.

9. The novel high-voltage fuse according to claim 8, characterized in that, When inputting the data set into the state monitoring model for comparison, it includes: Obtain the probabilities of all abnormal states based on the state monitoring model, determine an abnormal state threshold. When the comparison result is greater than the abnormal state threshold, enter the abnormal judgment, traverse all the abnormal state probabilities, and select the abnormal state with the highest probability as the comparison result; All abnormal states are divided into overload, short circuit, and poor contact; When the temperature rises slowly, the Joule heat residual is small, and the strain increases uniformly, it is determined as overload; When the temperature increases suddenly, the Joule heat residual is large, and the strain changes abruptly, it is determined as a short circuit; When the local temperature is abnormally high, the Joule heat residual value is large, and the strain fluctuates, it is determined as poor contact.

10. The novel high-voltage fuse according to claim 9, characterized in that, When determining an abnormal event based on the comparison result and sending corresponding warning information based on each abnormal event, it includes: When the comparison result is overload, generate a first-level warning; When the comparison result is poor contact, generate a second-level warning; When the comparison result is a short circuit, generate a third-level warning.

Images