A device and method for monitoring internal resistance and predicting aging of high-voltage fuses

Abstract

This application discloses a device and method for monitoring and predicting the internal resistance and aging of a high-voltage fuse, relating to the technical field of high-voltage fuse monitoring. The device includes a real-time monitoring box for the internal resistance of a high-voltage fuse and a local display and computing device. The real-time monitoring box is connected to the high-voltage fuse and uses the real-time monitoring box to collect operating data of the high-voltage fuse. The operating data includes real-time temperature, effective voltage value, and effective current value. The local display and computing device is connected to the real-time monitoring box for the internal resistance of a high-voltage fuse and uses the local display and computing device to determine the resistance value of the high-voltage fuse in real time based on the operating data of the high-voltage fuse collected by the real-time monitoring box, using a temperature compensation algorithm, and predicting the aging status of the high-voltage fuse using an artificial intelligence algorithm. This application can effectively monitor the operating status of a fuse and predict aging.

Description

Technical Field

[0001] The present application relates to the technical field of high-voltage fuse monitoring, and in particular to a device and method for monitoring the internal resistance and predicting aging of a high-voltage fuse. Background Art

[0002] High-voltage fuses are commonly used overcurrent protection devices in power systems, typically protecting transformers, distribution lines, switchgear, and more. When an overload or short circuit occurs in a circuit, the internal fuse element melts, interrupting the current and providing protection. However, long-term exposure to high temperature and high pressure causes the fuse element's resistance to gradually age and increase, ultimately leading to fuse failure. Therefore, effectively monitoring the operating status of high-voltage fuses and predicting their aging has become a critical research topic in the operation and maintenance of power equipment.

[0003] Traditional high-voltage fuse detection methods rely primarily on regular manual inspections or post-fault replacement. These methods fail to reflect the fuse's status in real time, nor can they provide early warning of the risk of aging failure, posing significant risks to high-voltage power systems. In recent years, the development of wireless sensing technology and artificial intelligence algorithms has made it possible to predict the status of power equipment based on real-time monitoring and big data analysis, providing a new solution for high-voltage fuse status monitoring. However, existing power equipment status prediction methods based on real-time monitoring and big data analysis do not establish a resistor aging trend prediction model by analyzing historical data.

[0004] Therefore, based on the shortcomings of existing technologies, there is an urgent need to provide a new method for monitoring and predicting the internal resistance of high-voltage fuses. Through artificial intelligence algorithms, the resistance aging of the fuse can be predicted, and early warning signals can be issued in advance to avoid accidents. Summary of the Invention

[0005] The purpose of this application is to provide a high-voltage fuse internal resistance monitoring and aging prediction device and method, which can effectively monitor the operating status of the fuse and predict the aging condition.

[0006] To achieve the above objectives, this application provides the following solutions:

[0007] In a first aspect, the present application provides a device for monitoring the internal resistance and predicting aging of a high-voltage fuse, the device comprising:

[0008] A high-voltage fuse internal resistance real-time monitoring box is connected to the high-voltage fuse and is used to collect operating data of the high-voltage fuse; the operating data includes: real-time temperature, voltage RMS value and current RMS value;

[0009] A local display and computing device is connected to the real-time monitoring box for the internal resistance of the high-voltage fuse, and is used to determine the resistance value of the high-voltage fuse in real time based on the operating data of the high-voltage fuse collected by the real-time monitoring box for the internal resistance of the high-voltage fuse, using a temperature compensation algorithm, and to predict the aging status of the high-voltage fuse using an artificial intelligence algorithm.

[0010] Optionally, the high-voltage fuse internal resistance real-time monitoring box includes: an insulating shell, a temperature detection unit, a voltage detection unit, a current detection unit, a Rogowski coil, a main control unit, a power supply unit, a battery and a wireless data transmission unit;

[0011] The temperature detection unit, voltage detection unit, current detection unit, Rogowski coil, main control unit, power supply unit, battery and wireless data transmission unit block are all placed in the insulating housing;

[0012] The temperature detection unit is in contact with the high-voltage fuse; the temperature detection unit is used to obtain the real-time temperature of the high-voltage fuse;

[0013] The voltage detection unit is connected in parallel with the high-voltage fuse; the voltage detection unit is used to obtain the effective value of the voltage of the high-voltage fuse;

[0014] The current detection unit is connected to the Rogowski coil via a wire; the high-voltage fuse passes through the Rogowski coil, and the effective value of the current of the high-voltage fuse is obtained through the current detection unit;

[0015] The main control unit is connected to the temperature detection unit, the voltage detection unit and the current detection unit; the main control unit is used to obtain the operating data of the high-voltage fuse;

[0016] The wireless data transmission unit is connected to the main control unit; the wireless data transmission unit is used to send the operating data of the high-voltage fuse obtained by the main control unit to the local display and computing device;

[0017] The battery is connected to the temperature detection unit, the voltage detection unit, the current detection unit, the main control unit and the wireless data transmission unit through the power supply unit; the battery is used to provide electrical energy to the power supply unit.

[0018] Optionally, the main control unit further comprises: a fault detection device;

[0019] The fault detection device is connected to the temperature detection unit, voltage detection unit, current detection unit and wireless data sending unit; when the fault detection module detects that the operating data of the high-voltage fuse exceeds the operating threshold, it generates early warning information based on the current operating data and sends it to the local display computing device through the wireless data sending unit.

[0020] Optionally, the temperature detection unit includes: a first input interface, a temperature sensor, a transmitter, a first filter circuit, a level conversion circuit and a first output interface;

[0021] The temperature sensor, transmitter, first filter circuit, level conversion circuit and first output interface are connected in series in sequence;

[0022] The first input interface is connected to the power supply unit, the transmitter, the first filter circuit, and the level conversion circuit; the first input interface is used to transmit the electrical energy in the power supply unit to the transmitter, the first filter circuit, and the level conversion circuit;

[0023] The first output interface is used to connect the level conversion circuit to the main control unit; and transmit the collected real-time temperature to the main control unit.

[0024] Optionally, the voltage detection unit includes: a second input interface, a measurement protection fuse, a surge protector, a signal amplification circuit, a second filtering circuit, a first effective value calculation circuit and a second output interface;

[0025] The measurement protection fuse, surge protector, signal amplification circuit, second filter circuit, first effective value calculation circuit and second output interface are connected in series in sequence;

[0026] The second input interface is electrically connected to the power supply unit, the signal amplifying circuit, the second filtering circuit, and the first effective value calculation circuit; the second input interface is used to transmit the electrical energy in the power supply unit to the signal amplifying circuit, the second filtering circuit, and the first effective value calculation circuit;

[0027] The second output interface is used to connect the first effective value calculation circuit to the main control unit; and transmit the determined voltage effective value to the main control unit.

[0028] Optionally, the current detection unit includes: a third input interface, an integrator, a third filtering circuit, a second effective value calculation circuit and a third output interface;

[0029] The Rogowski coil is connected in series with the integrator, the third filtering circuit, the second effective value calculation circuit and the third output interface in sequence;

[0030] The third input interface is connected to the power supply unit, the integrator, the third filtering circuit, and the second effective value calculation circuit; the third input interface is used to transmit the electric energy in the power supply unit to the integrator, the third filtering circuit, and the second effective value calculation circuit;

[0031] The third output interface is used to connect the second effective value calculation circuit to the main control unit; and transmit the determined current effective value to the main control unit.

[0032] Optionally, the local display computing device includes: a metal housing, a wireless data receiving unit and a human-computer interaction unit;

[0033] The wireless data receiving unit and the human interface interaction unit are both placed in the metal housing;

[0034] The wireless data receiving unit is connected to the wireless data sending unit; the wireless data receiving unit is used to receive the operating data sent by the wireless data sending unit;

[0035] The human-computer interaction unit is connected to the wireless data receiving unit; the human-computer interaction unit is used to determine the resistance value of the high-voltage fuse in real time based on the operating data of the high-voltage fuse using a temperature compensation algorithm, and to predict the aging status of the high-voltage fuse using an artificial intelligence algorithm.

[0036] Optionally, the human-computer interaction unit includes: a data storage module, a historical data analysis module and an artificial intelligence module;

[0037] The data storage module is connected to the wireless data receiving unit; the data storage module is used to store the operating data of the high-voltage fuse and the corresponding resistance value;

[0038] The historical data analysis module is connected to the data storage module; the historical data analysis module is used to perform historical data trend analysis based on the stored operating data and the corresponding resistance value; and determine the aging standard curve based on the historical data trend analysis results;

[0039] The artificial intelligence module is connected to the historical data analysis module; the artificial intelligence module is used to establish an aging prediction model for the high-voltage fuse based on the operating data of the high-voltage fuse and the corresponding resistance value using an artificial intelligence algorithm; and determine the resistance change rate and aging trend of the high-voltage fuse based on the aging prediction model, and then predict the remaining life of the high-voltage fuse based on the resistance change rate and aging trend using an aging standard curve.

[0040] In a second aspect, the present application provides a method for monitoring and aging prediction of a high-voltage fuse internal resistance, which is used to implement the high-voltage fuse internal resistance monitoring and aging prediction device. The method for monitoring and aging prediction of a high-voltage fuse internal resistance includes:

[0041] Obtaining operating data of the high-voltage fuse; the operating data includes: real-time temperature, voltage RMS value and current RMS value;

[0042] Based on the operating data of the high-voltage fuse collected by the real-time monitoring box of the high-voltage fuse internal resistance, a temperature compensation algorithm is used to determine the resistance value of the high-voltage fuse in real time, and the aging status of the high-voltage fuse is predicted based on the artificial intelligence algorithm.

[0043] Optionally, the operation data of the high-voltage fuse collected by the real-time monitoring box for the internal resistance of the high-voltage fuse is collected, a temperature compensation algorithm is used to determine the resistance value of the high-voltage fuse in real time, and an aging state of the high-voltage fuse is predicted according to an artificial intelligence algorithm, specifically including:

[0044] Smoothing the operating data of high-voltage fuses;

[0045] Based on the smoothed operating data, the jellyfish algorithm is used to calculate the resistance value of the high-voltage fuse in real time. The operating data and the corresponding resistance value are stored. Historical data trend analysis is performed based on the stored operating data and the corresponding resistance value. The aging standard curve is determined based on the results of the historical data trend analysis.

[0046] Extracting characteristic quantities of the operating data and the corresponding resistance value respectively; the characteristic quantities include: mean, variance, maximum value, minimum value and rate of change;

[0047] The Z-score normalization method is used to normalize the smoothed operating data, the corresponding resistance values, and the extracted feature quantities to generate a time series data set.

[0048] Split the time series dataset into training and validation sets;

[0049] The training set is used to train the bidirectional long short-term memory network model to obtain the aging prediction model of high-voltage fuses;

[0050] The aging prediction model of high-voltage fuses is verified using the validation set;

[0051] Determine the resistance change rate and aging trend of the high-voltage fuse based on the verified aging prediction model, and then use the aging standard curve to predict the remaining life of the high-voltage fuse based on the resistance change rate and aging trend;

[0052] When the remaining life is lower than the preset aging threshold, an early warning signal is triggered.

[0053] According to the specific embodiments provided in this application, this application has the following technical effects:

[0054] The present application provides a device and method for monitoring and predicting the internal resistance and aging of a high-voltage fuse. By connecting a high-voltage fuse internal resistance real-time monitoring box to the high-voltage fuse, the operating data of the high-voltage fuse is collected, and the operating status of the high-voltage fuse can be obtained in real time, realizing real-time monitoring of the fuse status, avoiding the lag of traditional periodic manual inspection, and being able to timely grasp the working status of the fuse; by connecting a local display computing device to the high-voltage fuse internal resistance real-time monitoring box, a temperature compensation algorithm is used to determine the resistance value of the high-voltage fuse in real time based on the operating data of the high-voltage fuse collected by the high-voltage fuse internal resistance real-time monitoring box, and an artificial intelligence algorithm is used to predict the aging status of the high-voltage fuse, thereby realizing early prediction of aging failure of the high-voltage fuse and avoiding accidents of emergency maintenance and power outages caused by equipment failure. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0056] Figure 1 This is a structural diagram of a high-voltage fuse internal resistance monitoring and aging prediction device in one embodiment of the present application;

[0057] Figure 2 This is a schematic diagram of the structure of the temperature detection unit in the real-time detection box of the internal resistance of the high-voltage fuse in one embodiment of the present application;

[0058] Figure 3 This is a schematic diagram of the structure of the voltage detection unit in the high-voltage fuse internal resistance real-time monitoring box in one embodiment of the present application;

[0059] Figure 4 This is a structural diagram of a current detection unit in a real-time monitoring box for internal resistance of a high-voltage fuse in one embodiment of the present application;

[0060] Figure 5 This is a schematic diagram of the structure of a human-computer interaction unit in a local display computing device in one embodiment of the present application. Description of the drawings:

[0062] 1- High-voltage fuse internal resistance real-time monitoring box, 11- Insulation housing, 12- Temperature detection unit, 121- Temperature sensor, 122- Transmitter, 123- First filter circuit, 124- Level conversion circuit, 125- First output interface, 126- First input interface, 13- Voltage detection unit, 131- Measurement protection fuse, 132- Surge protector, 133- Signal amplification circuit, 134- Second filter circuit, 135- First effective value calculation circuit, 136- Second output interface, 137- Second input interface , 14-current detection unit, 141-integrator, 142-third filtering circuit, 143-second effective value calculation circuit, 144-second output interface, 145-second input interface, 15-main control unit, 16-wireless data transmission unit, 17-power supply unit, 18-battery, 19-Rogowski coil, 2-local display computing device, 21-metal shell, 22-human-computer interaction unit, 221-data storage module, 222-historical data analysis module, 223-artificial intelligence module, 23-wireless data receiving unit. DETAILED DESCRIPTION

[0063] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0064] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0065] In an exemplary embodiment, Figure 1 As shown, the present application provides a high-voltage fuse internal resistance monitoring and aging prediction device, which includes: a high-voltage fuse internal resistance real-time monitoring box 1 and a local display and calculation device 2.

[0066] The high-voltage fuse internal resistance real-time monitoring box 1 is in contact with the high-voltage fuse and is used to collect the operating data of the high-voltage fuse; the operating data includes: real-time temperature, voltage effective value and current effective value.

[0067] The local display and computing device 2 is connected to the high-voltage fuse internal resistance real-time monitoring box 1. The local display and computing device 2 uses the operating data of the high-voltage fuse collected by the high-voltage fuse internal resistance real-time monitoring box 1 to determine the resistance value of the high-voltage fuse in real time using a temperature compensation algorithm, and uses an artificial intelligence algorithm to predict the aging status of the high-voltage fuse.

[0068] As a specific embodiment, the high-voltage fuse internal resistance real-time monitoring box 1 communicates with the local display and calculation unit 2 wirelessly; the grid current flows through the high-voltage fuse, and a voltage difference appears across the high-voltage fuse.

[0069] Specifically, such as Figure 1 As shown, the high-voltage fuse internal resistance real-time monitoring box 1 includes: an insulating housing 11, a temperature detection unit 12, a voltage detection unit 13, a current detection unit 14, a Rogowski coil 19, a main control unit 15, a power supply unit 17, a battery 18, and a wireless data transmission unit 16. The temperature detection unit 12, voltage detection unit 13, current detection unit 14, Rogowski coil 19, main control unit 15, power supply unit 17, battery 18, and wireless data transmission unit 16 are all placed in the insulating housing 11. The temperature detection unit 12 obtains the real-time temperature of the high-voltage fuse by contacting and connecting with the high-voltage fuse; the voltage detection unit 13 obtains the effective value of the voltage of the high-voltage fuse by being connected in parallel with the high-voltage fuse; and the current detection unit 14 is connected to the Rogowski coil 19 via a wire. The high-voltage fuse passes through the Rogowski coil 19, and the effective value of the current of the high-voltage fuse is obtained by the current detection unit 14.

[0070] The high-voltage fuse internal resistance real-time monitoring box 1 is electrically connected to the high-voltage fuse, ensuring that the temperature detection unit 12, the voltage detection unit 13 and the current detection unit 14 are in close contact with the high-voltage fuse, and calibrating the initial state of the device.

[0071] The main control unit 15 adopts a low-power processor and is connected to the temperature detection unit 12 , the voltage detection unit 13 and the current detection unit 14 . The operating data of the high-voltage fuse is obtained through the main control unit 15 .

[0072] The wireless data sending unit 16 is connected to the main control unit 15 , and the wireless data sending unit 16 sends the operating data of the high-voltage fuse obtained by the main control unit 15 to the local display and calculation device 2 .

[0073] The battery 18 is connected to the temperature detection unit 12, the voltage detection unit 13, the current detection unit 14, the main control unit 15 and the wireless data sending unit 16 through the power supply unit 17. The battery 18 provides electrical energy to the power supply unit 17, and the power supply unit 17 provides operating voltage to the temperature detection unit 12, the voltage detection unit 13, the current detection unit 14, the main control unit 15 and the wireless data sending unit 16.

[0074] Specifically, the main control unit 15 further includes: a fault detection device.

[0075] The fault detection device is connected to the temperature detection unit 12, the voltage detection unit 13, the current detection unit 14 and the wireless data sending unit 16, and when the fault detection module detects that the operating data of the high-voltage fuse exceeds the operating threshold, it generates an early warning message for the current operating data and sends it to the local display computing device 2 through the wireless data sending unit 16 to remind maintenance personnel to handle it in time.

[0076] Specifically, such as Figure 2 As shown, the temperature detection unit 12 includes: a first input interface 126, a temperature sensor 121, a transmitter 122, a first filter circuit 123, a level conversion circuit 124 and a first output interface 125, and the temperature sensor 121, the transmitter 122, the first filter circuit 123, the level conversion circuit 124 and the first output interface 125 are connected in series in sequence.

[0077] The first input interface 126 is connected to the power supply unit 17, the transmitter 122, the first filter circuit 123, and the level conversion circuit 124; the first input interface 126 transmits the electrical energy in the power supply unit 17 to the transmitter 122, the first filter circuit 123, and the level conversion circuit 124; the first output interface 125 connects the level conversion circuit 124 to the main control unit 15; and transmits the collected real-time temperature to the main control unit 15.

[0078] The temperature sensor 121 can be a surface-mount temperature sensor that detects the surface temperature of the high-voltage fuse. The temperature signal is converted into a voltage signal (adjustable voltage range, preferably -5V to +5V) after passing through the transmitter 122. This voltage signal contains a lot of electromagnetic interference signals and is converted into a clean voltage signal after passing through the filter circuit 123. Since the main control unit 15 can only receive positive voltage signals, the signal after passing through the filter circuit 123 needs to be level-converted to convert the temperature voltage signal into a positive voltage signal (adjustable voltage range, preferably 0 to +3.3V).

[0079] Specifically, such as Figure 3As shown, the voltage detection unit 13 includes: a second input interface 137, a measurement protection fuse 131, a surge protector 132, a signal amplifying circuit 133, a second filtering circuit 134, a first effective value calculation circuit 135 and a second output interface 136. The measurement protection fuse 131, the surge protector 132, the signal amplifying circuit 133, the second filtering circuit 134, the first effective value calculation circuit 135 and the second output interface 136 are connected in series in sequence. The measurement protection fuse 131 is a glass fiber-filled quartz sand fuse, which can ensure that after the high-voltage fuse to be tested is abnormally blown, the high-voltage fuse internal resistance real-time monitoring box 1 is also blown, that is, it can ensure that no leakage and high-voltage discharge channel are generated, and the safety of maintenance personnel can also be ensured.

[0080] Because the internal resistance of a high-voltage fuse is very small, the voltage across it after the grid current flows through it is only at the millivolt level. Therefore, the voltage signal across the high-voltage fuse detected by the voltage detection unit 13 must be amplified. Moreover, the voltage signal across the high-voltage fuse contains many electromagnetic interference signals and must be processed by the filtering circuit 134. Because the voltage signal across the high-voltage fuse is an AC signal, direct measurement is difficult. Therefore, the voltage signal across the high-voltage fuse must be converted into a positive RMS signal by the first RMS calculation circuit 135. This ensures that the processed voltage signal across the high-voltage fuse can be collected by the main control unit 15 and that the calculation accuracy is guaranteed.

[0081] The second input interface 137 is electrically connected to the power supply unit 17, the signal amplifying circuit 133, the second filtering circuit 134, and the first effective value calculation circuit 135. The second input interface 137 transmits the electrical energy in the power supply unit 17 to the signal amplifying circuit 133, the second filtering circuit 134 and the first effective value calculation circuit 135; the second output interface 136 connects the first effective value calculation circuit 135 to the main control unit 15; and transmits the determined voltage effective value to the main control unit 15.

[0082] like Figure 4 The current detection unit 14 shown includes: a third input interface 145, an integrator 141, a third filtering circuit 142, a second effective value calculation circuit 143 and a third output interface 144, and the Rogowski coil 19 is connected in series with the integrator 141, the third filtering circuit 142, the second effective value calculation circuit 143 and the third output interface 144.

[0083] The third input interface 145 is connected to the power supply unit 17, the integrator 141, the third filtering circuit 142, and the second effective value calculation circuit 143. The third input interface 145 transmits the electric energy in the power supply unit 17 to the integrator 141, the third filtering circuit 142, and the second effective value calculation circuit 143; the third output interface 144 connects the second effective value calculation circuit 143 to the main control unit 15, and transmits the determined current effective value to the main control unit 15.

[0084] The Rogowski coil 19 is used to obtain the current flowing through the high-voltage fuse to be tested. The current signal is converted into an adjustable voltage signal after passing through the integrator 141. Because the signal contains electromagnetic interference signals, it must be processed by the filter circuit 142. After processing, the voltage signal is converted into effective value data of the current after passing through the second effective value calculation circuit 143.

[0085] The present application utilizes the temperature detection unit 12, the voltage detection unit 13, and the current detection unit 14 to obtain the operating status of the high-voltage fuse in real time, automatically calculate its resistance value, and analyze its changes, thereby enabling real-time monitoring of the fuse status. This avoids the lag inherent in traditional periodic manual testing and allows for timely monitoring of the fuse's operating status.

[0086] like Figure 1 As shown, the local display computing device 2 includes: a metal shell 21 , a wireless data receiving unit 23 and a human-computer interaction unit 22 , and the wireless data receiving unit 23 and the human-computer interaction unit are placed in the metal shell 21 .

[0087] The wireless data receiving unit 23 is connected to the wireless data sending unit 16, and the wireless data receiving unit 23 receives the operating data sent by the wireless data sending unit 16; the human-computer interaction unit 22 is connected to the wireless data receiving unit 23; the human-computer interaction unit 22 uses a temperature compensation algorithm based on the operating data of the high-voltage fuse to determine the resistance value of the high-voltage fuse in real time, and uses an artificial intelligence algorithm to predict the aging state of the high-voltage fuse, that is, to estimate the time when the high-voltage fuse reaches the failure point, providing a basis for maintenance and replacement.

[0088] The wireless data transmission unit 16 and the wireless data reception unit 23 utilize a low-power wireless communication protocol, preferably LoRa, ZigBee, or Bluetooth, to ensure stable data transmission over long distances and reduce energy consumption, thereby extending the life of the device. Furthermore, the device can help optimize fuse replacement cycles and avoid unnecessary equipment replacement through long-term data recording and analysis.

[0089] The human-computer interaction unit 22 in the local display calculation unit 2 calculates the internal resistance of the high-voltage fuse based on the effective value of the voltage and the effective value of the current across the high-voltage fuse. Taking into account the effect of temperature on resistance, the calculated internal resistance of the high-voltage fuse is corrected by the temperature detection unit 12, and the corrected result is stored in the human-computer interaction unit 22.

[0090] like Figure 5 As shown, the human-computer interaction unit 22 includes: a data storage module 221 , a historical data analysis module 222 and an artificial intelligence module 223 .

[0091] The data storage module 221 is connected to the wireless data receiving unit 23 , and the data storage module 221 stores the operating data of the fuse and the corresponding resistance value.

[0092] The historical data analysis module 222 is connected to the data storage module 221 . The historical data analysis module 222 performs historical data trend analysis based on the stored operating data and the corresponding resistance values, and determines an aging standard curve based on the historical data trend analysis results.

[0093] The artificial intelligence module 223 is connected to the historical data analysis module 222. The artificial intelligence module 223 establishes an aging prediction model for the high-voltage fuse based on the operating data of the high-voltage fuse and the corresponding resistance value, and adopts an artificial intelligence algorithm. At the same time, the resistance change rate and aging trend of the high-voltage fuse are determined according to the aging prediction model, and then the remaining life of the high-voltage fuse is predicted using the aging standard curve based on the resistance change rate and the aging trend.

[0094] In an exemplary embodiment of the present application, the specific steps of monitoring the high-voltage fuse internal resistance monitoring and aging prediction device provided by the present application include:

[0095] 1) Initialization phase:

[0096] ①Electrically connect the high-voltage fuse internal resistance real-time monitoring box 1 to the high-voltage fuse to be tested, ensure that the temperature detection unit 12, the voltage detection unit 13 and the current detection unit 14 are in close contact with the high-voltage fuse, and calibrate the initial states of the high-voltage fuse internal resistance real-time monitoring box 1 and the local display calculation device 2;

[0097] ② Set the main control unit 15 to collect the operating status of the high-voltage fuse N times every day through the human-computer interaction unit 22;

[0098] ③ The power supply unit 17 is started, the device automatically starts, the main control unit 15 detects the power level of the battery 18, and confirms the connection with the local display computing device 2 through the wireless data transmission unit 16; the main control unit 15 reads the operating status of the high-voltage fuse N times;

[0099] 2) Data collection and transmission stage:

[0100] ① The temperature detection unit 12 is connected to the high-voltage fuse, and the real-time temperature of the high-voltage fuse is obtained N times every day, and transmitted to the main control unit 15 in real time;

[0101] ② The voltage detection unit 13 is connected in parallel with the high-voltage fuse to obtain the effective value of the voltage across the high-voltage fuse N times a day and transmit it to the main control unit 15;

[0102] ③ The current detection unit 14 cooperates with the Rogowski coil to obtain the effective value of the current of the high-voltage fuse N times a day and transmit it to the main control unit 15;

[0103] ④ The main control unit 15 transmits the acquired operating status of the high-voltage fuse to the local display and computing device 2 via wireless transmission;

[0104] 3) Artificial intelligence resistor aging prediction stage:

[0105] ① The artificial intelligence module 223 of the human-computer interaction unit 22 uses a sliding average or Kalman filter method to smooth the operating data of the high-voltage fuse, remove noise and outliers, and reduce measurement errors introduced by short-term fluctuations and environmental factors;

[0106] ② The artificial intelligence module 223 calculates the resistance value of the high-voltage fuse in real time based on the smoothed operating data using a compensation algorithm, and stores the operating data and the corresponding resistance value; performs a historical data trend analysis based on the stored operating data and the corresponding resistance value; and determines an aging standard curve based on the historical data trend analysis results;

[0107] ③ The artificial intelligence module 223 extracts characteristic quantities of the operating data and the corresponding resistance value, respectively, wherein the characteristic quantities include mean, variance, maximum value, minimum value and rate of change;

[0108] ④ The artificial intelligence module 223 uses the Z-score normalization method to normalize the smoothed operating data, the corresponding resistance values, and the extracted feature quantities to ensure that the numerical ranges of different data dimensions are consistent, thereby generating a time series data set;

[0109] ⑤ The artificial intelligence module adds a 5-layer bidirectional long short-term memory network (BiLSTM) unit, each layer contains 3 hidden units; the time series data set is divided into a training set and a validation set, the training set and validation set databases are input into the bidirectional long short-term memory network (BiLSTM), and the bidirectional long short-term memory network (BiLSTM) model is trained;

[0110] ⑥ During the training process, the MSE loss of the BiLSTM model on the validation set was defined as the objective function. A set of random hyperparameter combinations was initialized, the model was trained, and the MSE on the validation set was calculated. Based on the Gaussian process, Bayesian optimization (BO) was used to model the search space and select the optimal combination to improve performance. The hyperparameters were adjusted repeatedly with Bayesian optimization until the optimal hyperparameter combination was found. Finally, a trained BiLSTM prediction model was obtained. The validation set was used to verify the aging prediction model for high-voltage fuses.

[0111] ⑦ After the high-voltage fuse has been used for one year, the local display and computing device 2 inputs the high-voltage fuse operation data collected by the main control unit 15 into the trained bidirectional long short-term memory network (BiLSTM) prediction model. According to the resistance change rate and the aging trend of the model output, the aging standard curve is used to predict the remaining life of the high-voltage fuse and estimate the time to reach the failure point. When the predicted resistance value is close to or lower than the preset aging threshold, an early warning signal is triggered, and the local display and computing device 2 gives maintenance suggestions, suggesting replacing the fuse to prevent failures.

[0112] This application has a simple design and is applicable to various types of high-voltage fuses. In addition, due to the use of wireless communication technology, it is easy to install and deploy, and is particularly suitable for remote and difficult-to-reach power equipment monitoring scenarios.

[0113] The box body of the high-voltage fuse internal resistance real-time monitoring box 1 of the present application is an insulating shell 11, and the material is preferably epoxy resin. Epoxy resin has extremely high electrical insulation and can effectively avoid safety hazards caused by current leakage when the high-voltage fuse is working. This material can prevent electrical interference between the monitoring box body and the external environment, ensuring that the device operates safely and stably under high-voltage environments. Even when exposed to high voltage conditions for a long time, the insulating properties of epoxy resin can still remain stable, ensuring that the box body of the high-voltage fuse monitoring box 1 can operate safely in harsh electrical environments. The material properties of epoxy resin give the high-voltage fuse internal resistance real-time monitoring box good corrosion resistance and can resist the erosion of the device by external environments such as moisture, acid and alkali. At the same time, the excellent weather resistance of the high-voltage fuse internal resistance real-time monitoring box ensures that it is not easy to age or crack under long-term exposure to harsh environments such as high temperature and strong light, thereby extending the service life of the equipment. Epoxy resin also has high mechanical strength and can effectively protect the electronic components inside the high-voltage fuse monitoring box 1 from external shock or vibration. Furthermore, its robust structural design enhances the device's protection capabilities, reduces the possibility of external physical damage, and ensures safe operation in harsh operating conditions. Epoxy resin also exhibits excellent flame retardancy, preventing fire hazards in the event of a short circuit or equipment failure. Its high-temperature stability ensures the device will not burn in high-temperature environments or in the event of a sudden arc, effectively enhancing overall device safety.

[0114] In another exemplary embodiment, the present application provides a method for monitoring internal resistance and predicting aging of a high-voltage fuse, the method comprising:

[0115] S101: Acquire operating data of the high-voltage fuse; the operating data includes: real-time temperature, voltage RMS value, and current RMS value;

[0116] S102: Based on the operating data of the high-voltage fuse collected by the high-voltage fuse internal resistance real-time monitoring box 1, a temperature compensation algorithm is used to determine the resistance value of the high-voltage fuse in real time, and the aging state of the high-voltage fuse is predicted based on an artificial intelligence algorithm.

[0117] Before acquiring the high-voltage fuse's operating data, the initial state of the high-voltage fuse internal resistance real-time monitoring box 1 must be calibrated. The main control unit 15 reads the high-voltage fuse's temperature, voltage RMS value, and current RMS value N times daily. The device automatically starts by activating the power supply unit, checking the charge level of the battery 18, and confirming the connection with the local display and computing device 2 via the wireless data transmission unit 16.

[0118] Among them, S102 specifically includes:

[0119] S201: Smoothing the operating data of the high-voltage fuse.

[0120] S202: Based on the smoothed operating data, the jellyfish algorithm is used to calculate the resistance value of the high-voltage fuse in real time, and the operating data and the corresponding resistance value are stored. A historical data trend analysis is performed based on the stored operating data and the corresponding resistance value; and an aging standard curve is determined based on the results of the historical data trend analysis. The jellyfish algorithm is a type of temperature compensation algorithm.

[0121] Specifically, the jellyfish algorithm first sets an objective function: minimizing the error between the temperature-compensated resistance value and the actual measured value is used as the objective function; secondly, it selects optimization variables: setting the temperature coefficient or compensation parameters for different temperature ranges as optimization variables, and the jellyfish algorithm can optimize these variables within a specified range; then it calculates and adjusts: the jellyfish algorithm adjusts the temperature coefficient or other parameters in the compensation formula through an iterative and optimization process until the error is minimized; finally, it outputs the optimal parameters: after completing the optimization, the algorithm outputs the optimal temperature compensation parameters or model, thereby ensuring that resistance measurements under different temperature conditions can accurately compensate for temperature effects.

[0122] By monitoring the changing trends of fuse resistance over time, especially when the resistance approaches the fault threshold due to aging, this application can issue early warning signals. This real-time warning function effectively avoids the risk of power system interruptions and accidents caused by sudden fuse failure, significantly improving the safety of system operations.

[0123] This application stores operating data and corresponding resistance values, providing data storage and analysis capabilities. It can record long-term operating data for high-voltage fuses and further predict the fuse's health status through trend analysis of historical data. Combined with an intelligent analysis module, it can also provide early fault diagnosis. When abnormal current, voltage, or temperature are detected, an alarm mechanism is automatically triggered to help quickly locate the cause of the fault.

[0124] S203: extracting characteristic quantities of the operating data and the corresponding resistance value respectively; the characteristic quantities include: mean, variance, maximum value, minimum value and change rate;

[0125] S204: normalizing the smoothed operating data, the corresponding resistance values, and the extracted feature quantities using a Z-score normalization method to generate a time series data set;

[0126] S205: Divide the time series dataset into a training set and a validation set;

[0127] S206: Using the training set to train a bidirectional long short-term memory network (BiLSTM) model to obtain an aging prediction model for the high-voltage fuse;

[0128] Specifically, the artificial intelligence module adds a 5-layer bidirectional long short-term memory network (BiLSTM) unit, each layer contains 3 hidden units; the normalized time series historical data of the high-voltage fuse, such as the effective value of voltage, effective value of current, temperature, resistance value and characteristic quantities, are divided into a training set and a validation set, and the training set and validation set databases are input into the bidirectional long short-term memory network (BiLSTM) unit to train the bidirectional long short-term memory network (BiLSTM) model. In the specific training process, the MSE loss of the bidirectional long short-term memory network (BiLSTM) model on the validation set is defined as the objective function, a set of random hyperparameter combinations are initialized, the model is trained and the MSE on the validation set is calculated, and based on the Gaussian process, the Bayesian optimization (Bayesian optimization (BO)) algorithm models the search space and selects the optimal combination to improve performance. The iteration is repeated, and the Bayesian optimization continuously adjusts the hyperparameters until the optimal hyperparameter combination is found, and finally a trained bidirectional long short-term memory network (BiLSTM) prediction model is obtained.

[0129] Using a Bayesian optimization algorithm and a bidirectional long-short-term memory network, we can analyze historical data on high-voltage fuses and establish a resistance aging trend prediction model. This intelligent algorithm accurately predicts fuse aging trends, estimates the remaining fuse life, and provides maintenance personnel with accurate maintenance and replacement recommendations.

[0130] S207: Validate the aging prediction model of the high-voltage fuse using the validation set;

[0131] S208: Determine the resistance change rate and aging trend of the high-voltage fuse according to the verified aging prediction model, and then predict the remaining life of the high-voltage fuse using an aging standard curve based on the resistance change rate and aging trend;

[0132] S209: When the remaining life is lower than a preset aging threshold, a warning signal is triggered.

[0133] After the high-voltage fuse has been used for one year, the local display and computing device 2 will receive the real-time operating data of the high-voltage fuse read by the main control unit 15, and input the operating data into the trained bidirectional long short-term memory network (BiLSTM) prediction model. According to the resistance change rate and the aging trend of the model output, the aging standard curve is used to predict the remaining life of the high-voltage fuse and estimate the time to reach the failure point. When the predicted resistance value is close to or lower than the preset aging threshold, an early warning signal is triggered, and the local display and computing device 2 gives maintenance suggestions, suggesting replacing the fuse to prevent failures.

[0134] This application can predict the aging failure of high-voltage fuses in advance, thereby avoiding emergency maintenance and power outages caused by equipment failure. Through intelligent predictive maintenance strategies, unplanned downtime during equipment operation can be reduced, operation and maintenance costs can be lowered, and the operating efficiency of the power system can be improved.

[0135] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, 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.

[0136] This document uses specific examples to illustrate the principles and implementation methods of this application. The description of the above examples is only intended to help understand the method and core concept of this application. At the same time, for those skilled in the art, based on the concept of this application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A device for monitoring internal resistance and predicting aging of high-voltage fuses, characterized in that: The high-voltage fuse internal resistance monitoring and aging prediction device includes: A real-time monitoring box for internal resistance of a high-voltage fuse is connected to the high-voltage fuse and is used to collect operating data of the high-voltage fuse; the operating data includes: real-time temperature, voltage effective value and current effective value; A local display and computing device is connected to the high-voltage fuse internal resistance real-time monitoring box, and is used to determine the resistance value of the high-voltage fuse in real time using a temperature compensation algorithm based on the operating data of the high-voltage fuse collected by the high-voltage fuse internal resistance real-time monitoring box, and to predict the aging state of the high-voltage fuse using an artificial intelligence algorithm; The processing process of the local display computing device specifically includes: Smoothing the operating data of high-voltage fuses; Based on the smoothed operating data, the jellyfish algorithm is used to calculate the resistance value of the high-voltage fuse in real time. The operating data and the corresponding resistance value are stored. Historical data trend analysis is performed based on the stored operating data and the corresponding resistance value. The aging standard curve is determined based on the results of the historical data trend analysis. Extracting characteristic quantities of the operating data and the corresponding resistance value respectively; the characteristic quantities include: mean, variance, maximum value, minimum value and rate of change; The Z-score normalization method is used to normalize the smoothed operating data, the corresponding resistance values, and the extracted feature quantities to generate a time series data set. Split the time series dataset into training and validation sets; The training set is used to train the bidirectional long short-term memory network model to obtain the aging prediction model of high-voltage fuses; The aging prediction model of high-voltage fuses is verified using the validation set; Determine the resistance change rate and aging trend of the high-voltage fuse based on the verified aging prediction model, and then use the aging standard curve to predict the remaining life of the high-voltage fuse based on the resistance change rate and aging trend; When the remaining life is lower than the preset aging threshold, an early warning signal is triggered.

2. A high-voltage fuse internal resistance monitoring and aging prediction device according to claim 1, characterized in that: The high-voltage fuse internal resistance real-time monitoring box includes: an insulating shell, a temperature detection unit, a voltage detection unit, a current detection unit, a Rogowski coil, a main control unit, a power supply unit, a battery and a wireless data transmission unit; The temperature detection unit, voltage detection unit, current detection unit, Rogowski coil, main control unit, power supply unit, battery and wireless data transmission unit are all placed in the insulating housing; The temperature detection unit is in contact with the high-voltage fuse; the temperature detection unit is used to obtain the real-time temperature of the high-voltage fuse; The voltage detection unit is connected in parallel with the high-voltage fuse; the voltage detection unit is used to obtain the effective value of the voltage of the high-voltage fuse; The current detection unit is connected to the Rogowski coil via a wire; the high-voltage fuse passes through the Rogowski coil, and the effective value of the current of the high-voltage fuse is obtained through the current detection unit; The main control unit is connected to the temperature detection unit, the voltage detection unit and the current detection unit; the main control unit is used to obtain the operating data of the high-voltage fuse; The wireless data transmission unit is connected to the main control unit; the wireless data transmission unit is used to send the operating data of the high-voltage fuse obtained by the main control unit to the local display and computing device; The battery is connected to the temperature detection unit, the voltage detection unit, the current detection unit, the main control unit and the wireless data transmission unit through the power supply unit; the battery is used to provide electrical energy to the power supply unit.

3. A high-voltage fuse internal resistance monitoring and aging prediction device according to claim 2, characterized in that: The main control unit further comprises: a fault detection device; The fault detection device is connected to the temperature detection unit, voltage detection unit, current detection unit and wireless data sending unit; when the fault detection device detects that the operating data of the high-voltage fuse exceeds the operating threshold, it generates early warning information based on the current operating data and sends it to the local display and computing device through the wireless data sending unit.

4. A high-voltage fuse internal resistance monitoring and aging prediction device according to claim 2, characterized in that: The temperature detection unit includes: a first input interface, a temperature sensor, a transmitter, a first filter circuit, a level conversion circuit and a first output interface; The temperature sensor, transmitter, first filter circuit, level conversion circuit and first output interface are connected in series in sequence; The first input interface is connected to the power supply unit, the transmitter, the first filter circuit, and the level conversion circuit; the first input interface is used to transmit the electrical energy in the power supply unit to the transmitter, the first filter circuit, and the level conversion circuit; The first output interface is used to connect the level conversion circuit to the main control unit; and transmit the collected real-time temperature to the main control unit.

5. The device for monitoring internal resistance and predicting aging of a high-voltage fuse according to claim 2, characterized in that: The voltage detection unit includes: a second input interface, a measurement protection fuse, a surge protector, a signal amplification circuit, a second filtering circuit, a first effective value calculation circuit and a second output interface; The measurement protection fuse, surge protector, signal amplification circuit, second filter circuit, first effective value calculation circuit and second output interface are connected in series in sequence; The second input interface is electrically connected to the power supply unit, the signal amplifying circuit, the second filtering circuit, and the first effective value calculation circuit; the second input interface is used to transmit the electrical energy in the power supply unit to the signal amplifying circuit, the second filtering circuit, and the first effective value calculation circuit; The second output interface is used to connect the first effective value calculation circuit to the main control unit; and transmit the determined voltage effective value to the main control unit.

6. A high-voltage fuse internal resistance monitoring and aging prediction device according to claim 2, characterized in that: The current detection unit includes: a third input interface, an integrator, a third filter circuit, a second effective value calculation circuit and a third output interface; The Rogowski coil is connected in series with the integrator, the third filtering circuit, the second effective value calculation circuit and the third output interface in sequence; The third input interface is connected to the power supply unit, the integrator, the third filtering circuit, and the second effective value calculation circuit; the third input interface is used to transmit the electric energy in the power supply unit to the integrator, the third filtering circuit, and the second effective value calculation circuit; The third output interface is used to connect the second effective value calculation circuit to the main control unit; and transmit the determined current effective value to the main control unit.

7. A high-voltage fuse internal resistance monitoring and aging prediction device according to claim 2, characterized in that: The local display computing device includes: a metal housing, a wireless data receiving unit and a human-computer interaction unit; The wireless data receiving unit and the human-computer interaction unit are both placed in the metal housing; The wireless data receiving unit is connected to the wireless data sending unit; the wireless data receiving unit is used to receive the operating data sent by the wireless data sending unit; The human-computer interaction unit is connected to the wireless data receiving unit; the human-computer interaction unit is used to determine the resistance value of the high-voltage fuse in real time based on the operating data of the high-voltage fuse using a temperature compensation algorithm, and to predict the aging status of the high-voltage fuse using an artificial intelligence algorithm.

8. A high-voltage fuse internal resistance monitoring and aging prediction device according to claim 7, characterized in that: The human-computer interaction unit includes: a data storage module, a historical data analysis module and an artificial intelligence module; The data storage module is connected to the wireless data receiving unit; the data storage module is used to store the operating data of the high-voltage fuse and the corresponding resistance value; The historical data analysis module is connected to the data storage module; the historical data analysis module is used to perform historical data trend analysis based on the stored operating data and the corresponding resistance value; and determine the aging standard curve based on the historical data trend analysis results; The artificial intelligence module is connected to the historical data analysis module; the artificial intelligence module is used to establish an aging prediction model for the high-voltage fuse based on the operating data of the high-voltage fuse and the corresponding resistance value using an artificial intelligence algorithm; and determine the resistance change rate and aging trend of the high-voltage fuse based on the aging prediction model, and then predict the remaining life of the high-voltage fuse based on the resistance change rate and aging trend using an aging standard curve.

9. A method for monitoring and aging prediction of a high-voltage fuse internal resistance, based on the device for monitoring and aging prediction of a high-voltage fuse internal resistance according to any one of claims 1 to 8, characterized in that: The high-voltage fuse internal resistance monitoring and aging prediction method includes: Obtaining operating data of the high-voltage fuse; the operating data includes: real-time temperature, voltage effective value and current effective value; Based on the operating data of the high-voltage fuse collected by the real-time monitoring box of the high-voltage fuse internal resistance, a temperature compensation algorithm is used to determine the resistance value of the high-voltage fuse in real time, and the aging status of the high-voltage fuse is predicted based on the artificial intelligence algorithm; The method uses a temperature compensation algorithm to determine the resistance value of the high-voltage fuse in real time based on the operating data of the high-voltage fuse collected by the real-time monitoring box of the high-voltage fuse internal resistance, and predicts the aging state of the high-voltage fuse based on the artificial intelligence algorithm, specifically including: Smoothing the operating data of high-voltage fuses; Based on the smoothed operating data, the jellyfish algorithm is used to calculate the resistance value of the high-voltage fuse in real time. The operating data and the corresponding resistance value are stored. Historical data trend analysis is performed based on the stored operating data and the corresponding resistance value. The aging standard curve is determined based on the results of the historical data trend analysis. Extracting characteristic quantities of the operating data and the corresponding resistance value respectively; the characteristic quantities include: mean, variance, maximum value, minimum value and rate of change; The Z-score normalization method is used to normalize the smoothed operating data, the corresponding resistance values, and the extracted feature quantities to generate a time series data set. Split the time series dataset into training and validation sets; The training set is used to train the bidirectional long short-term memory network model to obtain the aging prediction model of high-voltage fuses; The aging prediction model of high-voltage fuses is verified using the validation set; Determine the resistance change rate and aging trend of the high-voltage fuse based on the verified aging prediction model, and then use the aging standard curve to predict the remaining life of the high-voltage fuse based on the resistance change rate and aging trend; When the remaining life is lower than the preset aging threshold, an early warning signal is triggered.

Images