Partial discharge prediction method and device for cable fireproof blanket, medium and equipment

Abstract

The invention relates to a partial discharge prediction method and device for a cable fireproof blanket, a medium and equipment. The method comprises the following steps: acquiring real-time partial discharge signals of a cable fireproof blanket under different voltages; wherein the real-time partial discharge signal comprises a real-time high-frequency current pulse signal, a real-time optical signal and a real-time sound signal; performing data processing on the real-time high-frequency current pulse signal, the real-time optical signal and the real-time sound signal to obtain the real-time high-frequency current pulse signal, the real-time optical signal and the real-time sound signal after data processing; inputting the real-time high-frequency current pulse signal, the real-time optical signal and the real-time sound signal after data processing into a target partial discharge prediction model to obtain the partial discharge condition of the cable fireproof blanket; wherein the target partial discharge prediction model is a model obtained by training the initial partial discharge prediction model. The partial discharge condition of the cable fireproof blanket can be accurately obtained, and safe and stable operation of a cable system is ensured.

Description

Technical Field

[0001] The present application relates to the technical field of partial discharge prediction, and in particular to a method, device, medium and equipment for predicting partial discharge of a cable fire blanket. Background Art

[0002] In power systems, cables are essential for power transmission, and their safety is of paramount importance. Cable fire blankets, as key protective equipment for ensuring safe cable operation, play an indispensable role in preventing the spread of fire and protecting cable insulation. However, over long-term operation, cable fire blankets are susceptible to partial discharge (PD) due to multiple influences, including electric fields, thermal fields, mechanical stress, and environmental factors. Partial discharge not only accelerates insulation aging and reduces protective performance, but in severe cases can also cause fires and major power accidents, posing a significant threat to the reliable operation of power systems.

[0003] Conventional technologies for detecting partial discharge in cable fire blankets often rely on monitoring a single signal, such as a high-frequency current pulse. This detection method has significant limitations. Because a single signal is susceptible to interference, detection accuracy is difficult to guarantee and cannot fully and accurately reflect the true partial discharge situation in cable fire blankets.

[0004] Therefore, it is necessary to provide a new technical solution to improve one or more problems existing in the above solutions.

[0005] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of this application, and therefore may include information that does not constitute prior art known to ordinary technicians in this field. Summary of the Invention

[0006] The purpose of this application is to provide a method, device, medium and equipment for predicting partial discharge of a cable fire blanket, thereby overcoming one or more problems caused by the limitations and defects of related technologies to at least a certain extent.

[0007] According to a first aspect of an embodiment of the present application, a method for predicting partial discharge of a cable fire blanket is provided, the method comprising:

[0008] Acquire real-time partial discharge signals of the cable fire blanket under different voltages; wherein the real-time partial discharge signals include real-time high-frequency current pulse signals, real-time light signals, and real-time sound signals;

[0009] performing data processing on the real-time high-frequency current pulse signal, the real-time light signal, and the real-time sound signal to obtain the real-time high-frequency current pulse signal, the real-time light signal, and the real-time sound signal after data processing;

[0010] The real-time high-frequency current pulse signal, real-time optical signal, and real-time sound signal after data processing are input into a target partial discharge prediction model to obtain partial discharge conditions of the cable fire blanket; wherein the target partial discharge prediction model is a model obtained by training the initial partial discharge prediction model.

[0011] In an embodiment of the present application, the step of obtaining the real-time partial discharge signal of the cable fire blanket under different voltages includes:

[0012] The cable fire blanket is gradually boosted at a preset boost value at intervals of a preset time period.

[0013] In an embodiment of the present application, the step of performing data processing on the real-time high-frequency current pulse signal, the real-time light signal, and the real-time sound signal includes:

[0014] Data cleaning and normalization processing are performed on the real-time high-frequency current pulse signal, the real-time light signal and the real-time sound signal.

[0015] In an embodiment of the present application, the initial partial discharge prediction model is obtained by modeling historical high-frequency current pulse signals, historical light signals, and historical sound signals through a neural network.

[0016] In an embodiment of the present application, the process of training the initial partial discharge prediction model includes:

[0017] The Adam optimization algorithm is used to optimize the network parameters of the initial partial discharge prediction model to obtain the target partial discharge prediction model.

[0018] In an embodiment of the present application, the step of optimizing the network parameters of the initial partial discharge prediction model using the Adam optimization algorithm to obtain the target partial discharge prediction model includes:

[0019]

[0020] m x =u×m x-1 +(1-u)×g x (2)

[0021]

[0022]

[0023] θ x+1 =θ x +Δθ x (7)

[0024] In the formula, x represents the x moment, g xRepresents the gradient of the loss function L(θ) at time x to the network parameter θ, represents the gradient, m x represents the first-order moment estimate of the gradient at time x, u represents the exponential decay rate of the first-order moment estimate, u x represents the exponential decay rate of the first-order moment estimate at time x, m x-1 Represents the first-order moment estimate of the gradient at time x-1, n x Represents the second-order moment estimate of the gradient at time x, n x-1 represents the second-order moment estimate of the gradient at time x-1, v represents the exponential decay rate of the second-order moment estimate, v x represents the exponential decay rate of the second-order moment estimate at time x, represents x at time m x The deviation correction, represents x at time n x Deviation correction, η represents the step size, ε represents the constant, θ x represents the network parameters at time x, Δθ x represents the updated value of the network parameters at time x, θ x+1 Represents the network parameters at time x+1.

[0025] In an embodiment of the present application, the step of inputting the processed real-time high-frequency current pulse signal, real-time optical signal, and real-time sound signal into a target partial discharge prediction model to obtain the partial discharge condition of the cable fire blanket includes:

[0026] When the output partial discharge probability is greater than a threshold, it is predicted that the cable fire blanket has partial discharge;

[0027] When the output partial discharge probability is less than the threshold, it is predicted that no partial discharge exists in the cable fire blanket.

[0028] According to a second aspect of an embodiment of the present application, a partial discharge prediction device for a cable fire blanket is provided, the device comprising:

[0029] An acquisition module is used to acquire real-time partial discharge signals of the cable fire blanket under different voltages; wherein the real-time partial discharge signals include real-time high-frequency current pulse signals, real-time light signals and real-time sound signals;

[0030] a data processing module, configured to perform data processing on the real-time high-frequency current pulse signal, the real-time light signal, and the real-time sound signal to obtain the real-time high-frequency current pulse signal, the real-time light signal, and the real-time sound signal after data processing;

[0031] A prediction module is configured to input the processed real-time high-frequency current pulse signal, real-time optical signal, and real-time sound signal into a target partial discharge prediction model to obtain partial discharge conditions of the cable fire blanket; wherein the target partial discharge prediction model is a model obtained by training an initial partial discharge prediction model.

[0032] According to a third aspect of the embodiments of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the steps of the partial discharge prediction method for a cable fire blanket described in any one of the above embodiments are implemented.

[0033] According to a fourth aspect of the embodiments of the present application, there is provided an electronic device, including:

[0034] processor; and

[0035] a memory for storing executable instructions of the processor;

[0036] The processor is configured to execute the steps of the method for predicting partial discharge of a cable fire blanket in any one of the above embodiments by executing the executable instructions.

[0037] The technical solutions provided by the embodiments of the present application may have the following beneficial effects:

[0038] In one embodiment of the present application, the above method is used to obtain multi-dimensional real-time partial discharge signals such as real-time high-frequency current pulse signals, real-time optical signals, and real-time sound signals of the cable fire blanket at different voltages, so that the partial discharge status of the cable fire blanket can be fully and accurately reflected subsequently. Data processing of the collected real-time high-frequency current pulse signals, real-time optical signals, and real-time sound signals can remove useless information such as noise and interference, making the data more accurate and reliable. Inputting the multiple signals after data processing into a trained target partial discharge prediction model can accurately obtain the partial discharge status of the cable fire blanket, thereby ensuring the safe and stable operation of the cable system.

[0039] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The accompanying drawings are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification, are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and those skilled in the art can derive other drawings based on these drawings without inventive effort.

[0041] Figure 1A flowchart schematically illustrates the steps of a method for predicting partial discharge of a cable fire blanket in an exemplary embodiment of the present application;

[0042] Figure 2 Schematically illustrates a flow chart in an exemplary embodiment of the present application;

[0043] Figure 3 A schematic diagram schematically illustrates a partial discharge detection experimental platform in an exemplary embodiment of the present application;

[0044] Figure 4 Schematically shows a 5KV voltage waveform image in an exemplary embodiment of the present application;

[0045] Figure 5 Schematically showing an image in which no partial discharge is generated at 5KV in an exemplary embodiment of the present application;

[0046] Figure 6 Schematically shows a 7.62KV voltage waveform image in an exemplary embodiment of the present application;

[0047] Figure 7 Schematically shows a partial discharge image generated at 7.62KV in an exemplary embodiment of the present application;

[0048] Figure 8 A block diagram schematically illustrates a partial discharge prediction device for a cable fire blanket in an exemplary embodiment of the present application;

[0049] Figure 9 Schematically illustrates a program product diagram in an exemplary embodiment of the present application;

[0050] Figure 10 The figure schematically shows a schematic diagram of an electronic device in an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0051] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete and will fully convey the concepts of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0052] In addition, the accompanying drawings are merely schematic illustrations of the present application and are not necessarily drawn to scale. Identical reference numerals in the figures denote identical or similar parts, and thus repetitive descriptions thereof will be omitted. Some of the blocks shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0053] This example embodiment first provides a method for predicting partial discharge of a cable fire blanket. Figure 1 As shown in , the method may include: steps S101 to S103.

[0054] Wherein, step S101: obtaining real-time partial discharge signals of the cable fire blanket under different voltages; wherein the real-time partial discharge signals include real-time high-frequency current pulse signals, real-time light signals and real-time sound signals.

[0055] Step S102: performing data processing on the real-time high-frequency current pulse signal, the real-time light signal and the real-time sound signal to obtain the real-time high-frequency current pulse signal, the real-time light signal and the real-time sound signal after data processing.

[0056] Step S103: Inputting the processed real-time high-frequency current pulse signal, real-time optical signal, and real-time sound signal into a target partial discharge prediction model to obtain partial discharge conditions of the cable fire blanket; wherein the target partial discharge prediction model is a model obtained by training the initial partial discharge prediction model.

[0057] In one embodiment of the present application, the above method is used to obtain multi-dimensional real-time partial discharge signals such as real-time high-frequency current pulse signals, real-time optical signals, and real-time sound signals of the cable fire blanket at different voltages, so that the partial discharge status of the cable fire blanket can be fully and accurately reflected subsequently. Data processing of the collected real-time high-frequency current pulse signals, real-time optical signals, and real-time sound signals can remove useless information such as noise and interference, making the data more accurate and reliable. Inputting the multiple signals after data processing into a trained target partial discharge prediction model can accurately obtain the partial discharge status of the cable fire blanket, thereby ensuring the safe and stable operation of the cable system.

[0058] Below, we will refer to Figures 2 to 3 Each step of the above method in this exemplary embodiment is described in more detail.

[0059] Before discussing this application, the partial discharge detection experimental platform is first explained:

[0060] like Figure 2 As shown in the figure, the partial discharge detection test platform consists of multiple core components, enabling accurate assessment of the operating status of electrical equipment through comprehensive testing methods. The main components of the partial discharge detection test platform include an AC power supply (220V), a voltage regulator (adjustment range: 0-300V, 1% accuracy, manual adjustment), a transformer (output voltage range: 0-100kV), a temperature control and monitoring system (control range: 20-90°C, accuracy: ±1°C), a high-frequency current transducer (HFCT, frequency range: 300kHz to 100MHz, accuracy: ±2%), an oscilloscope (sampling rate: 1GS / s, bandwidth: 50MHz to 1GHz), an ultrasonic sensor, a photodetector, and a partial discharge detection system. The voltage regulator and transformer are used to control the voltage, precisely adjusting the applied voltage to simulate the operating state of the equipment under different voltage conditions. The temperature control and monitoring system is generally used to regulate the temperature and ensure a stable experimental environment. The high-frequency current transducer (HFCT) is generally used to capture the high-frequency current pulse signals associated with partial discharge, and the oscilloscope is generally used to observe and record the partial discharge pulse waveform in real time. Ultrasonic sensors are generally used to collect sound signals, and photoelectric detectors are generally used to collect light signals.

[0061] It should be noted that Figure 2 The fire blanket sample tested is a cable fire blanket. The HFCT partial discharge detector is a high-frequency current sensor.

[0062] Generally, various sensors (such as high-frequency current sensors, ultrasonic sensors, and photoelectric detectors) are installed at key locations of electrical equipment (such as cables) to ensure that partial discharge signals can be accurately captured.

[0063] When partial discharge occurs, high-frequency current pulses, light signals, and sound signals are generated inside electrical equipment. With appropriate sensor layout, these signals can be effectively detected and subsequently analyzed.

[0064] When partial discharge (PD) occurs in a cable fire blanket, a high-frequency pulse signal is generated at the instant of the PD. This high-frequency pulse signal propagates along the cable fire blanket as a guided wave, ultimately converging into the ground wire and flowing into the earth. Unbalanced current in the ground wire generates a varying magnetic field. Installing a high-frequency current sensor (HFCT) on the cable fire blanket's ground wire can couple to the high-frequency current pulse signal generated at the instant of PD. The sensor converts the high-frequency current pulse signal into a voltage signal via an integrating resistor and transmits it to the PD detection system. The collected PD signal can be used to analyze the PD status of the cable fire blanket.

[0065] The HFCT used in the experiment is a high-frequency current sensor used in the Red Phase PDT-840 multifunctional partial discharge instrument. It has a bandwidth of 300 kHz to 100 MHz, an input impedance of 50 Ω, a transmission impedance of ≥5 mV / mA, a detection range of 0 to 300 mV, and an adjustable gain of 0 to 80 dB. It is connected to an oscilloscope via a BNC coaxial cable. The oscilloscope has a sampling rate of 5 GS / s and a bandwidth of 1 GHz, enabling real-time observation and recording of partial discharge pulse waveforms. The BNC stands for Bayonet Nut Connector.

[0066] Before testing partial discharge on a circuit fire blanket, ensure that all core components on the experimental platform, such as the AC power supply, voltage regulator, transformer, and oscilloscope, are in normal working order. The voltage regulator and transformer adjust the voltage according to the experimental requirements to simulate different voltage conditions. The temperature control system also needs to be set within a predetermined range to ensure a stable experimental environment. Various sensors (such as high-frequency current sensors and ultrasonic sensors) also need to be debugged to ensure that they can monitor partial discharge signals in the cable in real time.

[0067] In step S101, real-time partial discharge signals of a cable fire blanket under different voltages are acquired; wherein the real-time partial discharge signals include real-time high-frequency current pulse signals, real-time light signals, and real-time sound signals.

[0068] It is understandable that if Figure 3 As shown, a cable fire blanket is placed in a partial discharge test platform. Different voltages can be simulated using a voltage regulator and a transformer to obtain real-time partial discharge signals of the cable fire blanket at different voltages. This means that real-time high-frequency current pulse signals, real-time optical signals, and real-time sound signals can be obtained. High-frequency current pulse signals are generally collected using a high-frequency current sensor, optical signals are collected using a photodetector, and sound signals are collected using an ultrasonic sensor. Therefore, the present application is able to collect real-time high-frequency current pulse signals using a high-frequency current sensor, real-time optical signals are collected using a photodetector, and real-time sound signals are collected using an ultrasonic sensor. Therefore, by acquiring multi-dimensional, real-time partial discharge data, including real-time high-frequency current pulse signals, real-time optical signals, and real-time sound signals, from the cable fire blanket at different voltages, the present application is able to comprehensively and comprehensively reflect the partial discharge status of the cable fire blanket. Compared to single-type data collection, this multi-dimensional data collection method can more accurately capture the characteristic information of partial discharge, reduce information omissions, and improve the accuracy of partial discharge judgment.

[0069] In step S102 , data processing is performed on the real-time high-frequency current pulse signal, the real-time light signal, and the real-time sound signal to obtain the real-time high-frequency current pulse signal, the real-time light signal, and the real-time sound signal after data processing.

[0070] It is understandable that data processing of the collected real-time high-frequency current pulse signals, real-time light signals and real-time sound signals can remove useless information such as noise and interference, enhance effective signals, and make the data more accurate and reliable.

[0071] In step S103, the processed real-time high-frequency current pulse signal, real-time optical signal, and real-time sound signal are input into a target partial discharge prediction model to obtain partial discharge conditions of the cable fire blanket; wherein the target partial discharge prediction model is a model obtained by training the initial partial discharge prediction model.

[0072] It can be understood that the present application models historical high-frequency current pulse signals, historical light signals, and historical sound signals through a neural network to obtain an initial partial discharge prediction model.

[0073] The basic unit of a neural network is the neuron. Each neuron receives multiple inputs and, through an activation function, converts the weighted sum of these inputs into an output. Information is transmitted and processed between neurons. By adjusting the weights of the connections between neurons, patterns and regularities in the data are learned to achieve specific tasks, such as classification and regression. The structure of a neural network consists of an input layer, hidden layers, and an output layer. The input layer receives external data and passes it to the next layer. The hidden layers, which can be multiple, perform nonlinear transformations and feature extraction on the input data. They are the primary components of complex computations and learning in a neural network. The output layer generally generates the final output based on the processing results of the hidden layers.

[0074] It should be noted that before modeling the historical high-frequency current pulse signals, historical light signals and historical sound signals through neural networks, data processing of the historical high-frequency current pulse signals, historical light signals and historical sound signals is also required to remove useless information such as noise and interference, enhance effective signals, and make the data more accurate and reliable.

[0075] After establishing the initial partial discharge prediction model, it needs to be trained. This training typically involves a large amount of training data, including training high-frequency current pulse signals, training light signals, and training sound signals.

[0076] After training, the target partial discharge prediction model is obtained. Then, the real-time high-frequency current pulse signal, real-time light signal and real-time sound signal after data processing are input into the target partial discharge prediction model to obtain the partial discharge situation of the cable fire blanket.

[0077] It should be noted that the process of training the initial partial discharge prediction model in this application, as well as the partial discharge situation of the cable fire blanket, are described in the following embodiments and will not be repeated in this application.

[0078] In one embodiment, the step of obtaining real-time partial discharge signals of a cable fire blanket at different voltages includes:

[0079] The voltage of the cable fire blanket is gradually increased by a preset voltage value at every preset time period.

[0080] It is understandable that the present application uses a gradual voltage increase method to pressurize the cable fire blanket. The preset voltage increase value is 1KV, and the preset time period is 2 minutes. Boost 1kV each time and maintain each voltage stage for 2 minutes to observe whether a partial discharge signal is generated. If partial discharge occurs in the cable carpet, the high-frequency current pulse signal, light signal, and sound signal generated by the partial discharge will be captured in real time by the corresponding sensor. The high-frequency current sensor will monitor the high-frequency current changes in the cable carpet and display them in real time through an oscilloscope. The oscilloscope has a sampling rate of up to 5GS / s and a bandwidth of 1GHz, which can accurately record the waveform of partial discharge and provide data support for subsequent analysis.

[0081] In one embodiment, the step of processing the real-time high-frequency current pulse signal, the real-time light signal, and the real-time sound signal includes:

[0082] Perform data cleaning and normalization processing on real-time high-frequency current pulse signals, real-time optical signals and real-time sound signals.

[0083] As you can understand, data cleaning primarily involves addressing outliers and missing values in the data. Common methods for addressing outliers include statistical methods (such as the 3σ principle) or machine learning algorithms. Here, we use the simple 3σ principle as an example, assuming that the data approximately follows a normal distribution. For missing value handling, methods such as deleting rows (columns) containing missing values and filling in missing values (such as filling in the mean or median) can be used.

[0084] Normalization is to map data to a specific range. Common normalization methods include minimum-maximum normalization and normalization.

[0085] In one embodiment, the initial partial discharge prediction model is obtained by modeling historical high-frequency current pulse signals, historical light signals, and historical sound signals through a neural network.

[0086] It should be noted that the modeling process of the initial partial discharge prediction model has been described in the above embodiments, and will not be elaborated on in this application.

[0087] In one embodiment, the process of training the initial partial discharge prediction model includes:

[0088] The Adam optimization algorithm is used to optimize the network parameters of the initial partial discharge prediction model to obtain the target partial discharge prediction model.

[0089] It is understood that the Adam optimization algorithm is a first-order optimization algorithm that can replace the traditional stochastic gradient descent process. It can iteratively update neural network weights based on training data. The stochastic gradient descent algorithm maintains a single learning rate to update all weights, and the learning rate does not change during network training. The Adam optimization algorithm, on the other hand, designs independent adaptive learning rates for different parameters by calculating the first-order and second-order moment estimates of the gradient. The Adam optimization algorithm has high computational efficiency and low memory requirements, and is invariant to diagonal rescaling of the Adam optimization algorithm's gradient. Adam stands for Adaptive Moment Estimation.

[0090] Furthermore, the Adam optimization algorithm is used to optimize the network parameters of the initial partial discharge prediction model to obtain the target partial discharge prediction model, including:

[0091]

[0092] m x =u×m x-1 +(1-u)×g x (2)

[0093]

[0094] θ x+1 =θ x +Δθ x (7)

[0095] In the formula, x represents the x moment, g x Represents the gradient of the loss function L(θ) at time x to the network parameter θ, represents the gradient, m x represents the first-order moment estimate of the gradient at time x, u represents the exponential decay rate of the first-order moment estimate, u x represents the exponential decay rate of the first-order moment estimate at time x, m x-1 Represents the first-order moment estimate of the gradient at time x-1, n xRepresents the second-order moment estimate of the gradient at time x, n x-1 represents the second-order moment estimate of the gradient at time x-1, v represents the exponential decay rate of the second-order moment estimate, v x represents the exponential decay rate of the second-order moment estimate at time x, represents x at time m x The deviation correction, represents x at time n x Deviation correction, η represents the step size, ε represents the constant, θ x represents the network parameters at time x, Δθ x represents the updated value of the network parameters at time x, θ x+1 Represents the network parameters at time x+1.

[0096] It should be noted that the Adam optimization algorithm first initializes the parameter vector, first-order moment vector, and second-order moment vector, and then iteratively updates each part to converge the network parameter θ. That is, at time x, 1 is added, the first-order moment estimate and the second-order moment estimate of the deviation are updated, and then the deviation correction of the first-order moment estimate and the deviation correction of the second-order moment estimate are calculated. Then, the gradient of the network parameter θ at time x is updated, and finally the network parameter θ at time x calculated above is used. x The updated value Δθ x , updating the network parameters θ of the initial partial discharge prediction model. Updating the network parameters θ of the initial partial discharge prediction model is the process of optimizing them. Optimizing the network parameters θ of the initial partial discharge prediction model is actually the process of training the initial partial discharge prediction model. Once the optimized network parameters θ are obtained, the trained target partial discharge prediction model is obtained.

[0097] In one embodiment, the step of inputting the processed real-time high-frequency current pulse signal, the real-time optical signal, and the real-time sound signal into a target partial discharge prediction model to obtain the partial discharge condition of the cable fire blanket includes:

[0098] When the output partial discharge probability is greater than the threshold, it is predicted that the cable fire blanket has partial discharge;

[0099] When the output partial discharge probability is less than the threshold, it is predicted that there is no partial discharge in the cable fire blanket.

[0100] It is understood that this application inputs the processed real-time high-frequency current pulse signal, real-time optical signal, and real-time sound signal into the target partial discharge prediction model, which then outputs the partial discharge probability. The threshold is 0.5%. When the output partial discharge probability is greater than 0.5%, it is predicted that partial discharge exists in the cable fire blanket. When the output partial discharge probability is less than 0.5%, it is predicted that no partial discharge exists in the cable fire blanket.

[0101] It should be noted that the present application pressurizes the cable fire blanket by gradually increasing the voltage, so as to predict the partial discharge of the cable fire blanket at different voltages through the target partial discharge prediction model.

[0102] The present application will be further described below through examples.

[0103] The cable fire blanket was tested for partial discharge at a voltage level of 5kV. The test results are as follows: Figures 4 and 5 The noise reduction image clearly shows that the fire blanket sample exhibited no partial discharge at voltages of 5 kV and above. This demonstrates the excellent insulation performance of the cable fire blanket, confirming that its insulation meets high safety standards and is suitable for applications requiring high insulation performance.

[0104] When the voltage was further increased to 7.62kV, the cable fire blanket had obvious partial discharge phenomenon, such as Figures 6 and 7 shown.

[0105] At 7.62kV, the partial discharge image of the cable fire blanket shows significant partial discharge. While no partial discharge occurs at lower voltages (e.g., 5kV), indicating good insulation performance within this range, discharge increases significantly as the voltage increases to 7.62kV, indicating that the insulation performance of the cable fire blanket is approaching its critical point. This phenomenon provides strong data support for early fault detection and also provides a basis for safety during equipment operation, demonstrating that it can provide excellent insulation protection in practical applications, especially for the fire protection requirements of power cables.

[0106] It should be noted that although the steps of the method of this application are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in this specific order, or that all steps must be performed to achieve the desired results. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into a single step, and / or a single step may be decomposed into multiple steps. In addition, it is also easy to understand that these steps may be executed synchronously or asynchronously, for example, in multiple modules / processes / threads.

[0107] Furthermore, in this exemplary embodiment, a partial discharge prediction device for a cable fire blanket is also provided. Figure 8 As shown in , the apparatus 200 may include an acquisition module 210, a data processing module 220, and a prediction module 230. The acquisition module 210 is configured to acquire real-time partial discharge signals of the cable fire blanket at different voltages; the real-time partial discharge signals include real-time high-frequency current pulse signals, real-time optical signals, and real-time sound signals; the data processing module 220 is configured to process the real-time high-frequency current pulse signals, real-time optical signals, and real-time sound signals to obtain processed real-time high-frequency current pulse signals, real-time optical signals, and real-time sound signals; and the prediction module 230 is configured to input the processed real-time high-frequency current pulse signals, real-time optical signals, and real-time sound signals into a target partial discharge prediction model to obtain partial discharge conditions of the cable fire blanket; the target partial discharge prediction model is a model obtained by training the initial partial discharge prediction model.

[0108] In one embodiment, the apparatus further comprises:

[0109] The boost module is used to gradually boost the voltage of the cable fire blanket by a preset boost value at every preset time period.

[0110] In one embodiment, the apparatus further comprises:

[0111] The training module is used to optimize the network parameters of the initial partial discharge prediction model using the Adam optimization algorithm to obtain the target partial discharge prediction model.

[0112] In one embodiment, the apparatus further comprises:

[0113] A prediction submodule is used to predict the presence of partial discharge in the cable fire blanket when the output partial discharge probability is greater than a threshold;

[0114] and, for predicting that no partial discharge exists in the cable fire blanket when the output partial discharge probability is less than a threshold value.

[0115] Regarding the apparatus in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0116] It should be noted that although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the implementation mode of the present application, the features and functions of two or more modules or units described above can be concretized in one module or unit. Conversely, the features and functions of a module or unit described above can be further divided into multiple modules or units for concretization. The components displayed as modules or units may or may not be physical units, that is, they may be located in one place, or they may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the present application scheme. Those of ordinary skill in the art can understand and implement it without paying any creative work.

[0117] In an exemplary embodiment of the present application, a computer-readable storage medium is further provided, storing a computer program. When executed by a processor, the program can implement the steps of the method for predicting partial discharge of a cable fire blanket described in any of the aforementioned embodiments. In some possible implementations, various aspects of the present invention can also be implemented in the form of a program product, which includes program code. When the program product is executed on a terminal device, the program code is configured to cause the terminal device to execute the steps according to various exemplary embodiments of the present invention described in the aforementioned section of the method for predicting partial discharge of a cable fire blanket.

[0118] refer to Figure 9 As shown, a program product 300 for implementing the above method according to an embodiment of the present invention is described. The program product 300 may be a portable compact disc read-only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, a readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0119] The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0120] The computer-readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, wherein the readable program code is carried. The data signal propagated may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, device, or component. The program code contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination thereof.

[0121] The program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, and the like, as well as conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a stand-alone software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0122] In an exemplary embodiment of the present application, an electronic device is further provided, which may include a processor and a memory for storing executable instructions of the processor. The processor is configured to execute the executable instructions to perform the steps of the method for predicting partial discharge of a cable fire blanket described in any of the above embodiments.

[0123] Those skilled in the art will appreciate that various aspects of the present invention may be implemented as systems, methods, or program products. Therefore, various aspects of the present invention may be implemented in the following forms: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software implementations, which may be collectively referred to herein as "circuits," "modules," or "systems."

[0124] Refer to the following Figure 10 An electronic device 600 according to this embodiment of the present invention will be described. Figure 10 The electronic device 600 shown is merely an example and should not limit the functions and scope of use of the embodiments of the present invention.

[0125] like Figure 10As shown, electronic device 600 is implemented as a general-purpose computing device. Components of electronic device 600 may include, but are not limited to, at least one processing unit 610, at least one storage unit 620, a bus 630 connecting various system components (including storage unit 620 and processing unit 610), a display unit 640, and the like.

[0126] The storage unit stores program codes, which can be executed by the processing unit 610, so that the processing unit 610 performs the steps according to various exemplary embodiments of the present invention described in the above-mentioned cable fire blanket partial discharge prediction method section of this specification. For example, the processing unit 610 can perform the following steps: Figure 1 Follow the steps shown in .

[0127] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 6201 and / or a cache memory unit 6202 , and may further include a read-only memory unit (ROM) 6203 .

[0128] The storage unit 620 may also include a program / utility 6204 having a set (at least one) of program modules 6205, such program modules 6205 including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include an implementation of a network environment.

[0129] Bus 630 may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0130] The electronic device 600 can also communicate with one or more external devices 700 (e.g., a keyboard, a pointing device, a Bluetooth device, etc.), one or more devices that enable a user to interact with the electronic device 600, and / or any device that enables the electronic device 600 to communicate with one or more other computing devices (e.g., a router, a modem, etc.). Such communication can occur via an input / output (I / O) interface 650. Furthermore, the electronic device 600 can communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network such as the Internet) via a network adapter 660. The network adapter 660 can communicate with other modules of the electronic device 600 via the bus 630. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with the electronic device 600, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0131] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, USB flash drive, mobile hard disk, etc.) or on a network, and includes a number of instructions to enable a computing device (which can be a personal computer, server, or network device, etc.) to execute the above-mentioned cable fire blanket partial discharge prediction method according to the embodiments of the present application.

[0132] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present invention that follow the general principles of this application and include common knowledge or customary techniques in the art that are not disclosed herein.

Claims

1. A method for predicting partial discharge of a cable fire blanket, characterized in that: The method includes: Acquire real-time partial discharge signals of the cable fire blanket under different voltages; wherein the real-time partial discharge signals include real-time high-frequency current pulse signals, real-time light signals, and real-time sound signals; performing data processing on the real-time high-frequency current pulse signal, the real-time light signal, and the real-time sound signal to obtain the real-time high-frequency current pulse signal, the real-time light signal, and the real-time sound signal after data processing; The real-time high-frequency current pulse signal, real-time optical signal, and real-time sound signal after data processing are input into a target partial discharge prediction model to obtain partial discharge conditions of the cable fire blanket; wherein the target partial discharge prediction model is a model obtained by training the initial partial discharge prediction model.

2. The method for predicting partial discharge of a cable fire blanket according to claim 1, characterized in that: The step of obtaining the real-time partial discharge signal of the cable fire blanket under different voltages includes: The cable fire blanket is gradually boosted at a preset boost value at intervals of a preset time period.

3. The method for predicting partial discharge of a cable fire blanket according to claim 1, wherein: The step of performing data processing on the real-time high-frequency current pulse signal, the real-time light signal and the real-time sound signal includes: Data cleaning and normalization processing are performed on the real-time high-frequency current pulse signal, the real-time light signal and the real-time sound signal.

4. The method for predicting partial discharge of a cable fire blanket according to claim 1, wherein: The initial partial discharge prediction model is obtained by modeling historical high-frequency current pulse signals, historical light signals and historical sound signals through a neural network.

5. The method for predicting partial discharge of a cable fire blanket according to claim 1, characterized in that: The process of training the initial partial discharge prediction model includes: The Adam optimization algorithm is used to optimize the network parameters of the initial partial discharge prediction model to obtain the target partial discharge prediction model.

6. The method for predicting partial discharge of a cable fire blanket according to claim 5, characterized in that: The steps of optimizing the network parameters of the initial partial discharge prediction model using the Adam optimization algorithm to obtain the target partial discharge prediction model include: m x =u×m x-1 +(1-u)×g x (2) i x+1 =θ x +Δθ x (7) In the formula, x represents the x moment, g x Represents the gradient of the loss function L(θ) at time x to the network parameter θ, represents the gradient, m x represents the first-order moment estimate of the gradient at time x, u represents the exponential decay rate of the first-order moment estimate, u x represents the exponential decay rate of the first-order moment estimate at time x, m x-1 Represents the first-order moment estimate of the gradient at time x-1, n x Represents the second-order moment estimate of the gradient at time x, n x-1 represents the second-order moment estimate of the gradient at time x-1, v represents the exponential decay rate of the second-order moment estimate, v x represents the exponential decay rate of the second-order moment estimate at time x, represents x at time m x The deviation correction, represents x at time n x Deviation correction, η represents the step size, ε represents the constant, θ x represents the network parameters at time x, Δθ x represents the updated value of the network parameters at time x, θ x+1 Represents the network parameters at time x+1.

7. The method for predicting partial discharge of a cable fire blanket according to claim 1, characterized in that: The step of inputting the processed real-time high-frequency current pulse signal, real-time optical signal, and real-time sound signal into a target partial discharge prediction model to obtain the partial discharge condition of the cable fire blanket includes: When the output partial discharge probability is greater than a threshold, it is predicted that the cable fire blanket has partial discharge; When the output partial discharge probability is less than the threshold, it is predicted that no partial discharge exists in the cable fire blanket.

8. A partial discharge prediction device for a cable fire blanket, characterized in that: The device includes: An acquisition module is used to acquire real-time partial discharge signals of the cable fire blanket under different voltages; wherein the real-time partial discharge signals include real-time high-frequency current pulse signals, real-time light signals and real-time sound signals; a data processing module, configured to perform data processing on the real-time high-frequency current pulse signal, the real-time light signal, and the real-time sound signal to obtain the real-time high-frequency current pulse signal, the real-time light signal, and the real-time sound signal after data processing; A prediction module is configured to input the processed real-time high-frequency current pulse signal, real-time optical signal, and real-time sound signal into a target partial discharge prediction model to obtain partial discharge conditions of the cable fire blanket; wherein the target partial discharge prediction model is a model obtained by training an initial partial discharge prediction model.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method for predicting partial discharge of a cable fire blanket according to any one of claims 1 to 7 are implemented.

10. An electronic device, characterized in that: include: processor; as well as a memory for storing executable instructions of the processor; The processor is configured to execute the steps of the method for predicting partial discharge of a cable fire blanket according to any one of claims 1 to 7 by executing the executable instructions.

Images