Fuse self-diagnosis device and life prediction method

Abstract

The invention discloses a fuse self-diagnosis device and a life prediction method. The fuse self-diagnosis device comprises a shell, a safety fuse module, a power supply module, a temperature measurement module, a voltage measurement module, a current measurement module, a control unit, a wireless data sending module, a wireless data receiving module and a master control module. And the safety fuse module is used for protecting other modules from being damaged after the fuse is fused. And the power supply module realizes self power supply by using an electromagnetic environment where the fuse is located. Current, voltage and temperature data acquired by the sensors are processed by the control unit and then transmitted to the master control module through the wireless data transmitting module. An intelligent prediction algorithm based on a neural network is integrated in the master control module, and the algorithm can accurately predict the resistance change trend of the fuse and judge the residual life of the fuse by carrying out deep learning and analysis on data collected by a sensor, so that an abnormal state or a potential fault can be pre-judged in advance, and the risks of accidental shutdown and equipment damage are reduced.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of power protection devices, and in particular to a fuse self-diagnosis device and life prediction method for a high-voltage switch cabinet. Background Art

[0002] Fuses are common protective devices in power systems. Their main function is to cut off current when the circuit is overloaded or short-circuited, protecting the safe operation of equipment and lines. With the increasing complexity of power systems, fuse status monitoring and fault warning have become particularly important. However, traditional fuse monitoring methods mostly rely on manual inspections or simple electrical inspections, which makes it difficult to monitor the status of fuses in real time. Especially in complex environments such as high-voltage switchgear, the working status of fuses is easily affected by multiple factors such as temperature, load current, and voltage fluctuations, increasing the risk of fuse failure or malfunction.

[0003] The core working principle of the fuse self-diagnosis device and life prediction method is to accurately evaluate the operating status of the fuse and provide an early warning function by real-time acquisition and analysis of parameters such as current, voltage, and temperature in the working environment of the fuse. The device includes a current measurement module, a pressure measurement module, a temperature measurement module, and a data processing unit. Through these sensor modules, key parameters such as the load current, operating voltage, and surface temperature of the fuse can be monitored in real time. The wireless communication module transmits the data to the remote monitoring system, and combined with the algorithm, remote monitoring and intelligent analysis of the fuse life can be achieved, avoiding possible failures or equipment downtime accidents, greatly improving the operational reliability and safety of the power system.

[0004] Although there are some technologies for fuse condition monitoring, most of them

[0005] The system can only measure current or voltage, and cannot comprehensively consider multiple parameters in the operation of the fuse, resulting in low monitoring accuracy, unable to provide real-time feedback on the fuse status, and unable to provide early warning functions in combination with the fuse life. In addition, the existing monitoring equipment is bulky and complex to install, making it difficult to adapt to the application requirements of narrow spaces such as high-voltage switchgear. Therefore, it is urgent to develop a fuse monitoring device with high integration, strong real-time performance, and compact structure, which can operate stably in complex electrical environments to ensure the safety and reliability of the system.

[0006] Therefore, developing a fuse monitoring device with a high degree of integration, easy installation and intelligent monitoring function has broad market application prospects and important commercial value. Summary of the invention

[0007] The embodiments of the present invention provide a fuse self-diagnosis device and a life prediction method to solve the problems of low monitoring accuracy, bulky monitoring equipment, and how to predict the life of a fuse in the prior art.

[0008] In order to solve the above technical problems, the embodiments of the present application disclose the following technical solutions:

[0009] A fuse self-diagnosis device, characterized in that it comprises: a housing, a safety fuse module, a power module, a temperature measurement module, a voltage measurement module, a current measurement module, a control unit, a wireless data transmission module, a wireless data receiving module, and a master control module;

[0010] The safety fuse module, the power module, the temperature measurement module, the voltage measurement module, the current measurement module, the control unit, and the wireless data transmission module are placed inside the housing;

[0011] The wireless data receiving module and the master control module are placed outside the housing;

[0012] The power supply module is electrically connected to the temperature measurement module, the voltage measurement module, the current measurement module, and the control unit;

[0013] The temperature measurement module, the voltage measurement module, and the current measurement module are electrically connected to the control unit;

[0014] The control unit is electrically connected to the wireless data sending module;

[0015] The wireless data receiving module is electrically connected to the master control module.

[0016] The safety fuse module is composed of multiple quartz sand-filled fuses connected in series, with a single fuse with a withstand voltage of not less than 1kV, and the number is not less than 8. The first safety fuse is connected to the positive end of the fuse to be tested, and the last safety fuse is electrically connected to the measuring voltage module.

[0017] The power module includes: an electromagnetic induction coil, an energy collection chip, a first voltage conversion chip, a second voltage conversion chip and a first output terminal;

[0018] The first output terminal is electrically connected to the control unit, the temperature measurement module, the voltage measurement module, and the current measurement module;

[0019] The electromagnetic induction coil converts the electromagnetic field changes around the fuse to be tested into electrical energy; the energy collection chip rectifies and boosts the voltage output by the electromagnetic induction coil, and the preferred model is LTC3108; the power supply module does not need to be electrically connected to the fuse to be tested, thereby avoiding the damage of components caused by electric arcs, resulting in power supply interruption, greatly reducing power supply failures, and improving the safety and reliability of the system;

[0020] The electromagnetic induction coil surrounds the fuse to be tested, and generates an induced electromotive force from the change of the magnetic field around the fuse to be tested through the principle of electromagnetic induction; the electromagnetic induction coil is electrically connected to the energy collection chip; the energy collection chip is electrically connected to the first voltage conversion chip and the second voltage conversion chip; the energy collection chip, the first voltage conversion chip, and the second voltage conversion chip are all electrically connected to the first output terminal;

[0021] The energy collection chip converts the first voltage induced by the electromagnetic induction coil into a second voltage; the first voltage conversion chip converts the second voltage output by the energy collection chip into a third voltage; the second voltage conversion chip converts the second voltage output by the energy collection chip into a fourth voltage.

[0022] The control unit receives the temperature, voltage, and current information of the temperature measuring module, the voltage measuring module, and the current measuring module; after receiving the current, voltage, temperature and other data, the control unit sends the processed data to the wireless data sending module through the digital communication interface, converts it into a wireless signal, and sends it to the master control module; the control unit is connected to the second voltage.

[0023] The temperature measurement module includes: a second input terminal, a temperature sensor, and a second output terminal; the temperature sensor and the fuse to be tested are fixedly connected using thermal conductive silicone to ensure good thermal conductivity between the temperature sensor and the fuse to be tested; the second input terminal is electrically connected to the temperature sensor to power the temperature sensor; the temperature sensor is electrically connected to the second output terminal; the second input terminal is connected to the fourth voltage; the second output terminal is electrically connected to the control unit; wherein the temperature sensor is preferably DS18B20, and the output digital signal avoids interference problems in analog signal transmission, improves measurement stability and anti-interference, and has low power consumption and can remain stable during long-term operation.

[0024] The voltage measurement module includes: a third input terminal, a signal amplifying circuit, a filtering circuit, an effective value chip, and a third output terminal; the signal amplifying circuit, the filtering circuit, the effective value chip, and the third output terminal are electrically connected in series in sequence; the third input terminal is electrically connected to the signal amplifying circuit, the filtering circuit, and the effective value chip to supply power to the signal amplifying circuit, the filtering circuit, and the effective value chip; the third input terminal is connected to the third voltage; and the third output terminal is electrically connected to the control unit.

[0025] The current measurement module includes: a Rogowski coil, an integrator, a fourth input terminal, a filter circuit, an effective value chip, and a fourth output terminal; the Rogowski coil surrounds the fuse to be tested and performs current detection through electromagnetic induction coupling; the Rogowski coil, the integrator, the filter circuit, the effective value chip and the fourth output terminal are electrically connected in series in sequence; the fourth input terminal is electrically connected to the integrator, the filter circuit, and the effective value chip to supply power to the integrator, the filter circuit, and the effective value chip; the fourth input terminal is connected to the third voltage; and the fourth output terminal is electrically connected to the control unit.

[0026] The wireless data sending module and the wireless data receiving module are both based on the Star Flash wireless communication chip, which has the characteristics of low power consumption and long-distance transmission, and can meet the needs of efficient wireless data communication; among which, the preferred models of the Star Flash chip are: XK7101, XK9000, and ZL70550.

[0027] The inner layer of the shell is silicone and the outer layer is epoxy resin. This insulation structure can avoid arc discharge that may occur in a high-voltage environment and prevent electrical interference between modules.

[0028] The life prediction method adopts a neural network prediction algorithm, specifically a long short-term memory network algorithm (LSTM). The algorithm predicts the resistance change trend of the fuse to be tested. If the resistance of the fuse to be tested exceeds 20% of its factory rated value, that is, the fuse to be tested has reached its life, an alarm mechanism is triggered to prompt the staff to handle it in time; the specific use steps and life prediction method include the following steps:

[0029] 1) Initialization phase

[0030] ① Install the fuse self-diagnosis device in the high-voltage switch cabinet, ensure that the safety fuse module is electrically connected to the fuse to be tested, and ensure that the safety fuse module, the power module, the temperature measurement module, the voltage measurement module, the current measurement module, the control unit and the wireless data transmission module are correctly installed inside the housing;

[0031] ② Use the electromagnetic induction coil to surround the fuse to be tested, convert the electromagnetic field changes around it into electrical energy, and provide it to the energy collection chip;

[0032] ③ The energy collection chip rectifies and boosts the unstable electric energy output by the electromagnetic induction coil, outputs a stable power supply, and provides operating power for the control unit, the current measurement module, the voltage measurement module, and the temperature measurement module; this design utilizes the electromagnetic environment in the switch cabinet to achieve self-power supply, avoids dependence on an external power supply, and improves the autonomy and safety of the system;

[0033] ④ Through the energy collection chip and the first voltage conversion chip and the second voltage conversion chip, ensure that each module obtains an adapted power supply to support the stable operation of the fuse self-diagnosis device;

[0034] 2) Data collection and transmission stage

[0035] ① The control unit activates the current measurement module, the voltage measurement module and the temperature measurement module in sequence by sending a control signal, and starts to collect the current, voltage and temperature data of the fuse to be tested in real time;

[0036] ② Each sensor module transmits the collected data to the control unit;

[0037] ③ The control unit converts the received analog signals into digital signals through ADC (analog-to-digital converter), and processes and corrects these signals to ensure the accuracy and consistency of the data;

[0038] ④ The processed current, voltage and temperature data will be transmitted to the wireless data transmission module through the digital communication interface, and then the data will be converted into wireless signals through the Star Flash protocol and transmitted to the master control module outside the shell; the master control module will calculate the resistance value of the fuse to be tested in real time according to the received data as the basic data for subsequent prediction;

[0039] 3) Neural network prediction stage

[0040] ① The master control module arranges the resistance data received in real time in chronological order to form time series data, and merges it with the previous historical data to provide a more comprehensive input data set;

[0041] ② Before the neural network prediction, the data needs to be fully preprocessed. First, the noise and outliers in the data are removed, and the input data such as temperature, voltage and current are normalized to ensure the consistency and reliability of the input data of the LSTM neural network, so as to avoid the degradation of model performance due to data differences;

[0042] ③ Extract characteristic values ​​related to the resistance change of the fuse to be tested from the input data, including the historical change of resistance, temperature, voltage, current and their corresponding change rate, etc.; use sliding window technology to construct data sequences at multiple times as input features to enhance the LSTM model's ability to capture time series features and improve prediction accuracy;

[0043] ④ Divide the sorted time series data into training sets and test sets. Usually 80% of the data is used to train the model and 20% of the data is used to test the accuracy of the model. Configure the input layer, multiple hidden layers and output layer of the LSTM model, and set key parameters such as the number of hidden layer neurons, time step, and learning rate to ensure that the model has sufficient learning ability when processing time series data.

[0044] ⑤ Training phase: input the preprocessed resistance time series into the LSTM model, train the model using historical resistance data, and adjust the model parameters through feedback; after training, use the test set to verify the prediction performance and accuracy of the model to ensure its robustness in different scenarios;

[0045] ⑥ Prediction stage: Use the trained LSTM model to make real-time predictions on the newly received resistance data, and speculate the resistance change trend within a certain period of time in the future; if the predicted resistance exceeds the rated value of the fuse to be tested by 20%, the alarm mechanism is triggered, prompting the maintenance personnel to replace the fuse to be tested in time to avoid possible failures or equipment downtime accidents;

[0046] ⑦ Dynamic optimization: The LSTM model has the ability to learn online and update in real time. As new data is continuously input, the model can automatically adjust parameters to ensure the accuracy and timeliness of the prediction results, further improving the accuracy of the system's prediction of fuse life;

[0047] This process achieves full automation of fuse self-diagnosis and life prediction through three stages: initialization, data collection and transmission, and neural network prediction. It greatly improves the stability of the system and the accuracy of prediction, ensuring the safety of the fuse during long-term operation.

[0048] The technical solution provided by the embodiment of the present invention may have the following beneficial effects:

[0049] In the embodiment of the present invention, a safety fuse module is used to protect other modules from damage after the fuse is blown, which is safe and reliable. In addition, the device does not need to lead out an additional power supply port to power the sensor module and the control unit, but uses an electromagnetic induction coil combined with an energy collection chip to achieve self-power supply through an electromagnetic environment, avoiding the arc that may cause damage to the cable insulation layer, resulting in a short circuit or power supply interruption, thereby greatly reducing power supply failures and improving the safety and reliability of the system. The communication module of the device uses a Star Flash chip. The chip is based on the Star Flash protocol and has the characteristics of low power consumption and long-distance transmission. It can meet the needs of efficient data communication and reduce wiring costs. The Star Flash chip has strong anti-interference ability, which can ensure that data can still be transmitted stably in a complex electromagnetic environment to avoid communication interruption or data loss. An LSTM neural network algorithm is added to the master control module of the device. The algorithm establishes a prediction model for the resistance change trend by deep learning and analysis of the historical data of the fuse resistance value. The LSTM model can detect abnormal trends in advance by processing the time series data of the fuse resistance, and then predict the remaining life of the fuse. When the predicted result of the resistance value shows that it exceeds the rated resistance value by 20%, the system will trigger the early warning mechanism to remind the maintenance personnel to check and replace the fuse. This early warning function can effectively reduce the probability of failure, reduce the maintenance cost of the power system, and ensure the safety and reliability of equipment operation; the inner layer of the outer shell of this device is silicone, and the outer layer is epoxy resin. This insulation structure can avoid arc discharge that may occur under high voltage environment and prevent electrical interference between modules. Therefore, the embodiment of the present invention enhances the independence and reliability of the system. By predicting the resistance value of the fuse in real time and then predicting the remaining life of the fuse, abnormal conditions or potential faults can be predicted in advance, improving the reliability and safety of the system, reducing the risk of unexpected shutdown and equipment damage, and improving the operating efficiency of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0051] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0052] Figure 1 It is a structural schematic diagram of a fuse self-diagnosis device provided by an embodiment of the present invention;

[0053] Figure 2It is a schematic diagram of the structure of a power module of a fuse self-diagnosis device provided by an embodiment of the present invention;

[0054] Figure 3 It is a schematic diagram of the structure of a temperature measurement module of a fuse self-diagnosis device provided by an embodiment of the present invention;

[0055] Figure 4 It is a schematic diagram of the structure of a voltage measurement module of a fuse self-diagnosis device provided by an embodiment of the present invention;

[0056] Figure 5 It is a structural schematic diagram of a current measuring module of a fuse self-diagnosis device provided in an embodiment of the present invention;

[0057] Figure 6 It is a flow chart of the operation of an LSTM model in a master control module of a fuse self-diagnosis device provided by an embodiment of the present invention; DETAILED DESCRIPTION

[0058] In order to enable those skilled in the art to better understand the technical solutions in the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work should fall within the scope of protection of the present application.

[0059] In order to better understand the present application, the implementation methods of the present application are explained in detail below with reference to the accompanying drawings.

[0060] The embodiment of the present invention provides a fuse self-diagnosis device and a life prediction method. Figure 1 , Figure 1 Schematic diagram of the structure of a fuse self-diagnosis device provided by an embodiment of the present invention. Figure 1 It can be seen that the fuse self-diagnosis device and life prediction method provided by the embodiment of the present invention mainly include: a housing 10, a safety fuse module 142, a power module 11, a temperature measurement module 12, a voltage measurement module 13, a current measurement module 14, a control unit 15, a wireless data transmission module 16, a master control module 17, and a wireless data receiving module 18;

[0061] The safety fuse module 142, the power module 11, the temperature measurement module 12, the voltage measurement module 13, the current measurement module 14, the control unit 15, and the wireless data transmission module 16 are placed inside the housing 10;

[0062] The wireless data receiving module 18 and the master control module 17 are placed outside the housing 10;

[0063] The power supply module 11 is electrically connected to the temperature measurement module 12, the voltage measurement module 13, the current measurement module 14, and the control unit 15;

[0064] The temperature measuring module 12, the voltage measuring module 13, and the current measuring module 14 are electrically connected to the control unit 15;

[0065] The control unit 15 is electrically connected to the wireless data sending module 16;

[0066] The wireless data receiving module 18 is electrically connected to the master control module 17 .

[0067] Further, see Figure 1 The embodiment of the present invention explains the structure of the safety fuse module 142. The safety fuse module is composed of multiple quartz sand-filled fuses connected in series, with a single fuse with a withstand voltage of not less than 1kV, and the number is not less than 8. The first safety fuse is connected to the positive end of the fuse to be tested, and the last safety fuse is electrically connected to the measuring voltage module.

[0068] Further, the embodiment of the present invention explains the structure of the power module 11, see Figure 2 , Figure 2 Schematic diagram of the power module structure provided by the embodiment of the present invention. Figure 2 As shown, the power module 11 includes: an electromagnetic induction coil 20, an energy collection chip 111, a first voltage conversion chip 112, a second voltage conversion chip 113 and a first output terminal 114;

[0069] The first output terminal 114 is electrically connected to the control unit 15, the temperature measuring module 12, the voltage measuring module 13, and the current measuring module 14;

[0070] The electromagnetic induction coil 20 surrounds the fuse to be tested, and generates an induced electromotive force from the change of the magnetic field around the fuse to be tested through the principle of electromagnetic induction; the electromagnetic induction coil 20 is electrically connected to the energy collection chip 111; the energy collection chip 111 is electrically connected to the first voltage conversion chip 112 and the second voltage conversion chip 113; the energy collection chip 111, the first voltage conversion chip 112, and the second voltage conversion chip 113 are all electrically connected to the first output terminal 114;

[0071] The energy collection chip 111 converts the first voltage VDD1 induced by the electromagnetic induction coil 20 into a second voltage VDD2; the first voltage conversion chip 112 converts the second voltage VDD2 output by the energy collection chip 111 into a third voltage VDD3; the second voltage conversion chip 113 converts the second voltage VDD2 output by the energy collection chip 111 into a fourth voltage VDD4.

[0072] The electromagnetic induction coil 20 converts the electromagnetic field changes around the fuse to be tested into electrical energy; the energy collection chip 111 rectifies and boosts the voltage output by the electromagnetic induction coil 20, and the preferred model is LTC3108; the power module 11 does not need to be electrically connected to the fuse to be tested, thereby avoiding the damage of components caused by electric arcs, resulting in power supply interruption, greatly reducing power supply failures, and improving the safety and reliability of the system;

[0073] Among them, the energy collection chip 111 converts the AC voltage induced by the electromagnetic induction coil 20 into a 3.3V DC voltage, the first voltage conversion chip 112 converts the 3.3V DC voltage output by the energy collection chip 111 into a ±5V dual power supply output, the second voltage conversion chip 113 converts the 3.3V DC voltage output by the energy collection chip 111 into a 5V DC voltage output, and the first output terminal 114 has three voltage outputs, namely 3.3V DC voltage VDD2, ±5V dual power supply output VDD3, and 5V DC voltage VDD4.

[0074] Further, see Figure 1 The control unit 15 receives the temperature, voltage, and current information of the temperature measuring module 12, the voltage measuring module 13, and the current measuring module 14; after receiving the current, voltage, temperature and other data, the control unit 15 sends the processed data to the wireless data sending module 16 through the digital communication interface, converts it into a wireless signal, and sends it to the master control module 17; the control unit 15 is connected to the second voltage VDD2; wherein, the control unit 15 can be a DSP or other single-chip microcomputer.

[0075] Further, the present invention explains the structural diagram of the temperature measurement module, see Figure 3 , Figure 3 Schematic diagram of the temperature measurement module provided by the embodiment of the present invention. Figure 3As shown, the temperature measuring module 12 includes: a second input terminal 123, a temperature sensor 121, and a second output terminal 122; the temperature sensor 121 and the fuse to be tested are fixedly connected using thermally conductive silicone to ensure good thermal conductivity between the temperature sensor 121 and the fuse to be tested, and to ensure accurate measurement of the temperature of the fuse to be tested; the temperature sensor 121 and the second output terminal 122 are electrically connected in series; the second input terminal 123 is electrically connected to the temperature sensor 121 to power the temperature sensor 121; the second input terminal 123 is connected to a fourth voltage VDD4; the second output terminal 122 is electrically connected to the control unit 15; wherein the temperature sensor 121 is preferably DS18B20, and the output digital signal avoids the interference problem in the transmission of analog signals, improves the stability and anti-interference of the measurement, and has low power consumption and can remain stable during long-term operation;

[0076] Further, the embodiment of the present invention explains the structural diagram of the voltage measurement module, see Figure 4 , Figure 4 Schematic diagram of the voltage measurement module provided by the embodiment of the present invention. Figure 4 As shown, the voltage measurement module 13 includes: a third input terminal 135, a signal amplifying circuit 131, a filtering circuit 132, an effective value chip 133, and a third output terminal 134; the signal amplifying circuit 131, the filtering circuit 132, the effective value chip 133, and the third output terminal 134 are electrically connected in series; the third input terminal 135 is electrically connected to the signal amplifying circuit 131, the filtering circuit 132, and the effective value chip 133 to supply power to the signal amplifying circuit 131, the filtering circuit 132, and the effective value chip 133; the third input terminal 135 is connected to the third voltage VDD3 of the third output terminal The sub-circuit 134 is electrically connected to the control unit 15; wherein, since the resistance of the fuse to be tested is relatively low, the voltage across the fuse is only at the millivolt level after the grid current flows through it. Therefore, when measuring the voltage signal across the fuse to be tested, the signal amplification circuit 131 is used to amplify the tiny voltage signal across the fuse to be tested to ensure the accuracy of subsequent processing and acquisition; the filtering circuit 132 is used to filter out electromagnetic interference in the voltage signal to ensure the purity of the signal; the effective value chip 133 is responsible for converting the AC voltage signal across the fuse to be tested into a positive effective value signal to ensure that the main control unit 15 can accurately collect and process the voltage signal.

[0077] Further, the present invention provides an explanation of the structural diagram of the current measurement module, see Figure 5 , Figure 5 Schematic diagram of the structure of the current measurement module provided by the embodiment of the present invention. Figure 5 As shown, the current measuring module 14 includes: a Rogowski coil 19, an integrator 151, a fourth input terminal 155, a filter circuit 152, an effective value chip 153, and a fourth output terminal 154; the Rogowski coil 19 surrounds the fuse to be tested and performs current detection with the fuse to be tested through electromagnetic induction coupling; the Rogowski coil 19, the integrator 151, the filter circuit 152, the effective value chip 153 and the fourth output terminal 154 are electrically connected in series; the fourth input terminal 155 and the integrator 151 , the filter circuit 152 and the effective value chip 153 are electrically connected to supply power to the integrator 151, the filter circuit 152 and the effective value chip 153; the fourth input terminal 155 is connected to the third voltage VDD3; the fourth output terminal 154 is electrically connected to the control unit 15; wherein, the Rogowski coil 19 generates a voltage signal proportional to the current by inducing the alternating current in the conductor, and the signal can be converted into a DC output after being processed by the integrator 151, reflecting the average value or effective value of the current. At the same time, the filter circuit 152 is used to remove high-frequency noise and electromagnetic interference in the voltage signal to ensure the purity of the signal. Finally, the effective value chip 153 converts the AC voltage signal into an accurate effective value signal, so that the control unit 15 can accurately collect and process the signal.

[0078] Further, see Figure 1 The wireless data sending module 16 and the wireless data receiving module 18 are both based on the Star Flash wireless communication chip, which has the characteristics of low power consumption and long-distance transmission, and can meet the needs of efficient wireless data communication; wherein, the preferred models of the Star Flash chip are: XK7101, XK9000, and ZL70550.

[0079] Furthermore, the inner layer of the housing 10 is made of silicone and the outer layer is made of epoxy resin. This insulating structure can avoid arc discharge that may occur in a high-voltage environment and prevent electrical interference between modules.

[0080] Furthermore, the life prediction method in the master control module 17 adopts a neural network prediction algorithm, specifically a long short-term memory network algorithm (LSTM), which predicts the resistance change trend of the fuse to be tested. If the resistance of the fuse to be tested exceeds 20% of its factory rated value, that is, the fuse to be tested reaches its life, an alarm mechanism is triggered to prompt the staff to handle it in time;

[0081] The embodiment of the present invention explains the neural network prediction algorithm added in the master control module 17, see Figure 6 , Figure 6 : is a flowchart of the neural network algorithm in the master control module provided by the embodiment of the present invention. Figure 6As shown, the neural network algorithm flow chart in the master control module 17 includes: data transmission, data preprocessing, building LSTM model, model training and optimization, model evaluation and assessment, resistance value prediction and alarm, model optimization and update. The data transmission is performed by transmitting the measured current, voltage, temperature and other parameters to the master control module 17 through the wireless data transmission chip 16, calculating the corresponding resistance value, and arranging the resistance value data in chronological order to form time series data; the data preprocessing is performed by processing the missing values ​​and abnormal values ​​in the data and normalizing or standardizing the resistance value so that the LSTM model can effectively learn the characteristics of the data. The resistance data is divided into a training set and a test set in chronological order, usually 80% of the data is used for training and 20% for testing; the construction of the LSTM model is performed by setting the input layer, the LSTM hidden layer and the output layer, and setting the key parameters of the model, such as the number of hidden layers, the number of neurons, the time step, the learning rate, etc.; the model training and optimization is performed by inputting the preprocessed resistance time series into the LSTM model for training, and using the historical resistance to predict the future resistance; the model evaluation and assessment is performed by using the test set to evaluate the model and verify the accuracy of the model; the resistance prediction and alarm is performed by using the trained LSTM model to make real-time predictions on the newly transmitted resistance data, predicting the resistance at a certain moment in the future. If the resistance exceeds 20% of the rated value, it means that the fuse to be tested has reached its service life and the alarm mechanism is triggered; the model optimization and update is performed by adjusting the model's hyperparameters and data processing methods according to the prediction results to optimize the model's performance.

[0082] Specifically, an operator uses the fuse self-diagnosis device and life prediction method to observe the life of a certain fuse, including the following steps:

[0083] 1) Initialization phase

[0084] ① Install the fuse self-diagnosis device in the high-voltage switch cabinet, ensure that the safety fuse module is electrically connected to the fuse to be tested, and ensure that the safety fuse module, the power module, the temperature measurement module, the voltage measurement module, the current measurement module, the control unit and the wireless data transmission module are correctly installed inside the housing;

[0085] ② Use the electromagnetic induction coil to surround the fuse to be tested, convert the electromagnetic field changes around it into electrical energy, and provide it to the energy collection chip;

[0086] ③ The energy collection chip rectifies and boosts the unstable electric energy output by the electromagnetic induction coil, outputs a stable power supply, and provides operating power for the control unit, the current measurement module, the voltage measurement module, and the temperature measurement module; this design utilizes the electromagnetic environment in the switch cabinet to achieve self-power supply, avoids dependence on an external power supply, and improves the autonomy and safety of the system;

[0087] ④ Through the energy collection chip and the first voltage conversion chip and the second voltage conversion chip, ensure that each module obtains an adapted power supply to support the stable operation of the fuse self-diagnosis device;

[0088] 2) Data collection and transmission stage

[0089] ① The control unit activates the current measurement module, the voltage measurement module and the temperature measurement module in sequence by sending a control signal, and starts to collect the current, voltage and temperature data of the fuse to be tested in real time;

[0090] ② Each sensor module transmits the collected data to the control unit;

[0091] ③ The control unit converts the received analog signals into digital signals through ADC (analog-to-digital converter), and processes and corrects these signals to ensure the accuracy and consistency of the data;

[0092] ④ The processed current, voltage and temperature data will be transmitted to the wireless data transmission module through the digital communication interface, and then the data will be converted into wireless signals through the Star Flash protocol and transmitted to the master control module outside the shell; the master control module will calculate the resistance value of the fuse to be tested in real time according to the received data as the basic data for subsequent prediction;

[0093] 2) Data collection and transmission stage

[0094] ① The control unit activates the current measurement module, the voltage measurement module and the temperature measurement module in sequence by sending a control signal, and starts to collect the current, voltage and temperature data of the fuse to be tested in real time;

[0095] ② The data collected by each sensor module is transmitted to the control unit through internal connections;

[0096] ③ The control unit converts the received analog signals into digital signals through ADC (analog-to-digital converter), and processes and corrects these signals to ensure the accuracy and consistency of the data;

[0097] ④ The processed current, voltage and temperature data will be transmitted to the wireless data sending module through the digital communication interface, and then the data will be converted into wireless signals through the Star Flash protocol and transmitted to the master control module outside the shell; the master control module will calculate the resistance value of the fuse to be tested in real time based on the received data as the basic data for subsequent predictions.

[0098] 3) Neural network prediction stage

[0099] ① The master control module arranges the resistance data received in real time in chronological order to form time series data, and merges it with the previous historical data to provide a more comprehensive input data set;

[0100] ② Before the neural network prediction, the data needs to be fully preprocessed. First, the noise and outliers in the data are removed, and the input data such as temperature, voltage and current are normalized to ensure the consistency and reliability of the input data of the LSTM neural network, so as to avoid the degradation of model performance due to data differences;

[0101] ③ Extract characteristic values ​​related to the resistance change of the fuse to be tested from the input data, including the historical change of resistance, temperature, voltage, current and their corresponding change rate, etc.; use sliding window technology to construct data sequences at multiple times as input features to enhance the LSTM model's ability to capture time series features and improve prediction accuracy;

[0102] ④ Divide the sorted time series data into training sets and test sets. Usually 80% of the data is used to train the model and 20% of the data is used to test the accuracy of the model. Configure the input layer, multiple hidden layers and output layer of the LSTM model, and set key parameters such as the number of hidden layer neurons, time step, and learning rate to ensure that the model has sufficient learning ability when processing time series data.

[0103] ⑤ Training phase: Input the preprocessed resistance time series into the LSTM model, use the historical resistance data to train the model, and adjust the model parameters through feedback. After the training is completed, use the test set to verify the prediction performance and accuracy of the model to ensure its robustness in different scenarios;

[0104] ⑥ Prediction stage: Use the trained LSTM model to make real-time predictions on the newly received resistance data, and speculate the resistance change trend in a certain period of time in the future. If the predicted resistance exceeds the rated value of the fuse to be tested by 20%, the alarm mechanism will be triggered, prompting the maintenance personnel to replace the fuse to be tested in time to avoid possible failures or equipment downtime accidents;

[0105] ⑦ Dynamic optimization: The LSTM model has the ability of online learning and real-time updating. As new data is continuously input, the model can automatically adjust parameters to ensure the accuracy and timeliness of the prediction results, further improving the system's prediction accuracy of the fuse life.

[0106] This process achieves full automation of fuse self-diagnosis and life prediction through three stages: initialization, data collection and transmission, and neural network prediction. It greatly improves the stability of the system and the accuracy of prediction, ensuring the safety of the fuse during long-term operation.

[0107] For the parts not described in detail in this embodiment, please refer to Figure 1-Figure 6 The embodiments shown in this embodiment and the above embodiments can be referenced to each other and will not be described in detail here.

[0108] The above description is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest range consistent with the principles and novel features disclosed herein.

Claims

1. A fuse self-diagnosis device, characterized in that: include: Housing, safety fuse module, power module, temperature measurement module, voltage measurement module, current measurement module, control unit, wireless data transmission module, wireless data receiving module, master control module; The safety fuse module, the power module, the temperature measurement module, the voltage measurement module, the current measurement module, the control unit, and the wireless data transmission module are placed inside the housing; The wireless data receiving module and the master control module are placed outside the housing; The power supply module is electrically connected to the temperature measurement module, the voltage measurement module, the current measurement module, and the control unit; The temperature measurement module, the voltage measurement module, and the current measurement module are electrically connected to the control unit; The control unit is electrically connected to the wireless data sending module; The wireless data receiving module is electrically connected to the master control module.

2. The fuse self-diagnosis device according to claim 1, characterized in that: The safety fuse module is composed of multiple quartz sand-filled fuses connected in series, with a single fuse with a withstand voltage of not less than 1kV, and the number is not less than 8. The first safety fuse is connected to the positive end of the fuse to be tested, and the last safety fuse is electrically connected to the measuring voltage module.

3. The fuse self-diagnosis device according to claim 1, characterized in that: The power module includes: an electromagnetic induction coil, an energy collection chip, a first voltage conversion chip, a second voltage conversion chip and a first output terminal; The first output terminal is electrically connected to the control unit, the temperature measurement module, the voltage measurement module, and the current measurement module; The electromagnetic induction coil converts the electromagnetic field changes around the fuse to be tested into electrical energy; the energy collection chip rectifies and boosts the voltage output by the electromagnetic induction coil, and the preferred model is LTC3108; the power supply module does not need to be electrically connected to the fuse to be tested, thereby avoiding the damage of components caused by electric arcs, resulting in power supply interruption, greatly reducing power supply failures, and improving the safety and reliability of the system; The electromagnetic induction coil surrounds the fuse to be tested, and generates an induced electromotive force from the change of the magnetic field around the fuse to be tested through the principle of electromagnetic induction; the electromagnetic induction coil is electrically connected to the energy collection chip; the energy collection chip is electrically connected to the first voltage conversion chip and the second voltage conversion chip; the energy collection chip, the first voltage conversion chip, and the second voltage conversion chip are all electrically connected to the first output terminal; The energy collection chip converts the first voltage induced by the electromagnetic induction coil into a second voltage; the first voltage conversion chip converts the second voltage output by the energy collection chip into a third voltage; the second voltage conversion chip converts the second voltage output by the energy collection chip into a fourth voltage.

4. The fuse self-diagnosis device according to claim 1, characterized in that: The control unit receives the temperature, voltage, and current information of the temperature measuring module, the voltage measuring module, and the current measuring module; after receiving the current, voltage, temperature and other data, the control unit sends the processed data to the wireless data sending module through the digital communication interface, converts it into a wireless signal, and sends it to the master control module; the control unit is connected to the second voltage.

5. The fuse self-diagnosis device according to claim 1, characterized in that: The temperature measurement module includes: a second input terminal, a temperature sensor, and a second output terminal; the temperature sensor and the fuse to be tested are fixedly connected using thermal conductive silicone to ensure good thermal conductivity between the temperature sensor and the fuse to be tested; the second input terminal is electrically connected to the temperature sensor to power the temperature sensor; the temperature sensor is electrically connected to the second output terminal; the second input terminal is connected to the fourth voltage; the second output terminal is electrically connected to the control unit; wherein the temperature sensor is preferably DS18B20, and the output digital signal avoids interference problems in analog signal transmission, improves measurement stability and anti-interference, and has low power consumption and can remain stable during long-term operation.

6. The fuse self-diagnosis device according to claim 1, characterized in that: The voltage measurement module includes: a third input terminal, a signal amplifying circuit, a filtering circuit, an effective value chip, and a third output terminal; the signal amplifying circuit, the filtering circuit, the effective value chip, and the third output terminal are electrically connected in series in sequence; the third input terminal is electrically connected to the signal amplifying circuit, the filtering circuit, and the effective value chip to supply power to the signal amplifying circuit, the filtering circuit, and the effective value chip; the third input terminal is connected to the third voltage; and the third output terminal is electrically connected to the control unit.

7. The fuse self-diagnosis device according to claim 1, characterized in that: The current measurement module includes: a Rogowski coil, an integrator, a fourth input terminal, a filter circuit, an effective value chip, and a fourth output terminal; the Rogowski coil surrounds the fuse to be tested and performs current detection through electromagnetic induction coupling; the Rogowski coil, the integrator, the filter circuit, the effective value chip and the fourth output terminal are electrically connected in series in sequence; the fourth input terminal is electrically connected to the integrator, the filter circuit, and the effective value chip to supply power to the integrator, the filter circuit, and the effective value chip; the fourth input terminal is connected to the third voltage; and the fourth output terminal is electrically connected to the control unit.

8. The fuse self-diagnosis device according to claim 1, characterized in that: The wireless data sending module and the wireless data receiving module are both based on the Star Flash wireless communication chip, which has the characteristics of low power consumption and long-distance transmission, and can meet the needs of efficient wireless data communication; among which, the preferred models of the Star Flash chip are: XK7101, XK9000, and ZL70550.

9. The fuse self-diagnosis device according to claim 1, characterized in that: The inner layer of the shell is silicone and the outer layer is epoxy resin. This insulation structure can avoid arc discharge that may occur in a high-voltage environment and prevent electrical interference between modules.

10. The fuse self-diagnosis device according to claim 1, characterized in that: The life prediction method adopts a neural network prediction algorithm, specifically a long short-term memory network algorithm (LSTM). The algorithm predicts the resistance change trend of the fuse to be tested. If the resistance of the fuse to be tested exceeds 20% of its factory rated value, that is, the fuse to be tested has reached its life, an alarm mechanism is triggered to prompt the staff to handle it in time; the specific use steps and life prediction method include the following steps: 1) Initialization phase ① Install the fuse self-diagnosis device in the high-voltage switch cabinet, ensure that the safety fuse module is electrically connected to the fuse to be tested, and ensure that the safety fuse module, the power module, the temperature measurement module, the voltage measurement module, the current measurement module, the control unit and the wireless data transmission module are correctly installed inside the housing; ② Use the electromagnetic induction coil to surround the fuse to be tested, convert the electromagnetic field changes around it into electrical energy, and provide it to the energy collection chip; ③ The energy collection chip rectifies and boosts the unstable electric energy output by the electromagnetic induction coil, outputs a stable power supply, and provides operating power for the control unit, the current measurement module, the voltage measurement module, and the temperature measurement module; this design utilizes the electromagnetic environment in the switch cabinet to achieve self-power supply, avoids dependence on an external power supply, and improves the autonomy and safety of the system; ④ Through the energy collection chip and the first voltage conversion chip and the second voltage conversion chip, ensure that each module obtains an adapted power supply to support the stable operation of the fuse self-diagnosis device; 2) Data collection and transmission stage ① The control unit activates the current measurement module, the voltage measurement module and the temperature measurement module in sequence by sending a control signal, and starts to collect the current, voltage and temperature data of the fuse to be tested in real time; ② Each sensor module transmits the collected data to the control unit; ③ The control unit converts the received analog signals into digital signals through ADC (analog-to-digital converter), and processes and corrects these signals to ensure the accuracy and consistency of the data; ④ The processed current, voltage and temperature data will be transmitted to the wireless data transmission module through the digital communication interface, and then the data will be converted into wireless signals through the Star Flash protocol and transmitted to the master control module outside the shell; the master control module will calculate the resistance value of the fuse to be tested in real time according to the received data as the basic data for subsequent prediction; 3) Neural network prediction stage ① The master control module arranges the resistance data received in real time in chronological order to form time series data, and merges it with the previous historical data to provide a more comprehensive input data set; ② Before the neural network prediction, the data needs to be fully preprocessed. First, the noise and outliers in the data are removed, and the input data such as temperature, voltage and current are normalized to ensure the consistency and reliability of the input data of the LSTM neural network, so as to avoid the degradation of model performance due to data differences; ③ Extract characteristic values ​​related to the resistance change of the fuse to be tested from the input data, including the historical change of resistance, temperature, voltage, current and their corresponding change rate, etc.; use sliding window technology to construct data sequences at multiple times as input features to enhance the LSTM model's ability to capture time series features and improve prediction accuracy; ④ Divide the sorted time series data into training sets and test sets. Usually 80% of the data is used to train the model and 20% of the data is used to test the accuracy of the model. Configure the input layer, multiple hidden layers and output layer of the LSTM model, and set key parameters such as the number of hidden layer neurons, time step, and learning rate to ensure that the model has sufficient learning ability when processing time series data. ⑤ Training phase: input the preprocessed resistance time series into the LSTM model, train the model using historical resistance data, and adjust the model parameters through feedback; after training, use the test set to verify the prediction performance and accuracy of the model to ensure its robustness in different scenarios; ⑥ Prediction stage: Use the trained LSTM model to make real-time predictions on the newly received resistance data, and speculate the resistance change trend within a certain period of time in the future; if the predicted resistance exceeds the rated value of the fuse to be tested by 20%, the alarm mechanism is triggered, prompting the maintenance personnel to replace the fuse to be tested in time to avoid possible failures or equipment downtime accidents; ⑦ Dynamic optimization: The LSTM model has the ability to learn online and update in real time. As new data is continuously input, the model can automatically adjust parameters to ensure the accuracy and timeliness of the prediction results, further improving the accuracy of the system's prediction of fuse life; This process achieves full automation of fuse self-diagnosis and life prediction through three stages: initialization, data collection and transmission, and neural network prediction. It greatly improves the stability of the system and the accuracy of prediction, ensuring the safety of the fuse during long-term operation.

Images