High-voltage cable operation monitoring method, system, equipment, medium and product

Abstract

The invention relates to the technical field of power systems, and discloses a high-voltage cable operation monitoring method, system and device, a medium and a product, and the method comprises the steps: determining grounding impedance time sequence data of a target high-voltage cable, and determining a plurality of grounding induction ring currents of the target high-voltage cable according to the grounding impedance time sequence data and structure parameters; comparing each grounding induction ring current through a dynamic threshold value method, and generating a real-time cable state label corresponding to each grounding induction ring current, so as to take the grounding induction ring current as an evaluation index of the running state of the high-voltage cable; the training data set is constructed through the grounding induction circulation and the real-time cable state label, and the machine learning neural network is used for training, so that the high-voltage cable operation prediction model is obtained to adapt to the operation environments and conditions of different high-voltage cables, and the accuracy and timeliness of high-voltage cable operation monitoring are improved.

Description

Technical Field

[0001] This invention relates to the field of power system technology, and in particular to a method, system, equipment, medium and product for monitoring the operation of high-voltage cables. Background Technology

[0002] Cables are the sole medium for transmitting electrical energy in power systems, and their operational status profoundly impacts power supply quality. High-voltage cables, during power transmission, are susceptible to problems such as cable aging and insulation peeling due to heat generated by current flow and environmental factors, reducing their lifespan and leading to abnormal operating conditions. These abnormal operating conditions can alter the power system's supply level, potentially causing power outages and even disrupting regional production and daily life. Therefore, monitoring the operational status of high-voltage cables has become a major research focus in the power sector.

[0003] The operating status of cables directly affects the stability and safety of power systems. To ensure the normal operation of high-voltage cables, it is necessary to monitor their operating status in real time. Currently, the technical means for real-time monitoring of cable operating status are inefficient and have limited monitoring dimensions, resulting in poor accuracy in monitoring cable operating status and making it difficult to guarantee the reliability of stable power operation. Summary of the Invention

[0004] In view of this, the present invention provides a method, system, equipment, medium and product for monitoring the operation of high-voltage cables, which solves the technical problems of low working efficiency and limited monitoring dimensions of real-time monitoring of cable operation status, resulting in poor accuracy of monitoring cable operation status and difficulty in ensuring the reliability of stable power operation.

[0005] The first aspect of this invention provides a method for monitoring the operation of high-voltage cables, comprising:

[0006] Obtain the structural parameters of the target high-voltage cable, and determine the grounding impedance timing data of the target high-voltage cable based on the structural parameters;

[0007] Based on the grounding impedance timing data and the structural parameters, multiple grounding induced circulating currents of the target high-voltage cable are determined;

[0008] Each of the grounding induced circulating currents is compared using a dynamic threshold method to generate a real-time cable status label corresponding to each of the grounding induced circulating currents.

[0009] A training dataset is constructed based on the multiple grounding induction currents and the real-time cable status labels;

[0010] A high-voltage cable operation prediction model is obtained by training a machine learning neural network using the training dataset.

[0011] The real-time grounding induction current of the target high-voltage cable at that time period is input into the high-voltage cable operation prediction model, and the real-time cable status label of the target high-voltage cable at that time period is output.

[0012] Preferably, the structural parameters include the distributed capacitance of the shielding layer of the target high-voltage cable, the voltage difference between the cable conductor and the metal sheath, the frequency of the cable transmission current, the equivalent resistance of the metal sheath, and the voltage of the cable conductor.

[0013] The grounding impedance timing data of the target high-voltage cable is determined based on the structural parameters, including:

[0014] The grounding capacitance current of the target high-voltage cable is determined based on the distributed capacitance value of the shielding layer, the voltage difference between the cable conductor and the metal sheath, the frequency of the cable transmission current, and the equivalent resistance of the metal sheath.

[0015] Based on the grounding capacitor current and the cable conductor voltage, the grounding impedance of the target high-voltage cable at multiple sampling points is determined, and the grounding impedance time series data is generated.

[0016] Preferably, the method further includes:

[0017] The grounding impedance time series data is smoothed and denoised to obtain a smoothed impedance sequence.

[0018] Preferably, the structural parameters include the induced current of the three-phase metal shielding layer;

[0019] The step of determining multiple grounding induced circulating currents of the target high-voltage cable based on the grounding impedance timing data and the structural parameters includes:

[0020] Based on the induced current of the three-phase metal shield and the grounding impedances in the smooth impedance sequence, multiple grounding induced currents of the target high-voltage cable are determined.

[0021] Preferably, the step of comparing each of the grounding induced circulating currents using a dynamic threshold method to generate a real-time cable status tag corresponding to each of the grounding induced circulating currents includes:

[0022] Based on the multiple ground induced circulating currents, determine the average value and standard deviation of the ground induced circulating currents;

[0023] Based on the average value and standard deviation of the ground induced current, the upper and lower boundary values ​​of the ground induced current are determined, and based on the upper and lower boundary values, the boundary interval of the ground induced current is determined.

[0024] Determine whether each of the aforementioned grounding induction circulating currents is within the boundary interval;

[0025] If it is determined that the grounding induced current is within the boundary interval, then the real-time cable status label of the grounding induced current is determined to be in a normal state.

[0026] If it is determined that the grounding induced current is not within the boundary interval, then the real-time cable status label of the grounding induced current is determined to be in an abnormal state.

[0027] Preferably, the machine learning neural network is an LSTM neural network.

[0028] Secondly, the present invention also provides a high-voltage cable operation monitoring system, comprising:

[0029] An impedance determination module is used to acquire the structural parameters of the target high-voltage cable and determine the grounding impedance timing data of the target high-voltage cable based on the structural parameters.

[0030] The circulating current determination module is used to determine multiple grounding induced circulating currents of the target high-voltage cable based on the grounding impedance timing data and the structural parameters.

[0031] The circulating current comparison module is used to compare each of the grounding induced circulating currents using a dynamic threshold method, and generate a real-time cable status label corresponding to each of the grounding induced circulating currents.

[0032] The training set construction module is used to construct a training dataset based on the multiple grounding induction circulating currents and the real-time cable status labels;

[0033] The model training module is used to train the machine learning neural network using the training dataset to obtain a high-voltage cable operation prediction model.

[0034] The status prediction module is used to input the real-time grounding induction current of the target high-voltage cable at that time period into the high-voltage cable operation prediction model and output the real-time cable status label of the target high-voltage cable at that time period.

[0035] Thirdly, the present invention also provides an electronic device, the electronic device including a memory and a processor, the memory storing a computer program, the computer program being executed by the processor causing the processor to perform the steps of the high-voltage cable operation monitoring method as described in the first aspect.

[0036] Fourthly, the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed, implements the steps of the high-voltage cable operation monitoring method as described in the first aspect.

[0037] Fifthly, the present invention also provides a computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, wherein when the program instructions are executed by a computer, the computer performs the steps of the high-voltage cable operation monitoring method as described in the first aspect.

[0038] As can be seen from the above technical solution, this invention determines the grounding impedance time-series data of the target high-voltage cable, and based on the grounding impedance time-series data and structural parameters, determines multiple grounding induced circulating currents of the target high-voltage cable. Each grounding induced circulating current is compared using a dynamic threshold method to generate a real-time cable status label corresponding to each grounding induced circulating current. Thus, the grounding induced circulating current is used as an evaluation index for the operating status of the high-voltage cable, achieving real-time monitoring and early warning of the high-voltage cable's operating status. Compared to traditional monitoring methods, this invention not only improves the accuracy and reliability of monitoring but also enables earlier detection of potential faults. Furthermore, by constructing a training dataset using grounding induced circulating currents and real-time cable status labels and training it with a machine learning neural network, a high-voltage cable operation prediction model is obtained to adapt to different operating environments and conditions of high-voltage cables, improving the accuracy and timeliness of high-voltage cable operation monitoring. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0040] Figure 1 An application environment diagram of a high-voltage cable operation monitoring method provided in an embodiment of the present invention;

[0041] Figure 2 A flowchart illustrating a high-voltage cable operation monitoring method provided in an embodiment of the present invention;

[0042] Figure 3 This is a schematic diagram of the structure of a high-voltage cable operation monitoring system provided in an embodiment of the present invention;

[0043] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0044] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0045] The high-voltage cable operation monitoring method provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, terminal 101 communicates with server 102 via a network. A data storage system can store the data that server 102 needs to process. The data storage system can be integrated onto server 102 or placed on a cloud or other network server. Terminal 101 or server 102 acquires the structural parameters of the target high-voltage cable, determines the grounding impedance time-series data of the target high-voltage cable based on the structural parameters, determines multiple grounding induced circulating currents of the target high-voltage cable based on the grounding impedance time-series data and structural parameters, compares each grounding induced circulating current using a dynamic threshold method, and generates a real-time cable status label corresponding to each grounding induced circulating current, constructs a training dataset based on the multiple grounding induced circulating currents and the real-time cable status labels, trains a machine learning neural network using the training dataset to obtain a high-voltage cable operation prediction model, and inputs the real-time grounding induced circulating current of the target high-voltage cable into the high-voltage cable operation prediction model, outputting the real-time cable status label of the target high-voltage cable for that time period.

[0046] Terminal 101 can be, but is not limited to, various personal computers, laptops, smartphones, and tablets.

[0047] Server 102 can be a standalone physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides cloud computing services.

[0048] like Figure 2 As shown in the embodiment of this application, a method for monitoring the operation of a high-voltage cable is provided, which is applied to... Figure 1 Taking terminal 101 or server 102 as an example, the explanation includes the following steps S1 to S6. Wherein:

[0049] Step S1: Obtain the structural parameters of the target high-voltage cable and determine the grounding impedance timing data of the target high-voltage cable based on the structural parameters.

[0050] In the current power system, the core structure of high-voltage cables is classified according to the supply voltage of 35kV. High-voltage cables with a core voltage below 35kV contain three conductors and a shielding layer for each conductor, while high-voltage cables with a core voltage above 35kV contain only one conductor and a shielding layer.

[0051] The key data and structural parameters involved in the design, manufacturing and installation of the target high-voltage cable include, but are not limited to, cable length, conductor cross-sectional area, insulation material type, shielding layer structure and its material properties.

[0052] High-voltage cable shielding primarily employs grounding to reduce the induced voltage within the shielding layer, thereby minimizing power loss. The structural parameters of high-voltage cables can be categorized into the distributed capacitance of the cable conductor and shielding layer, the grounding capacitive current of the high-voltage cable, and the grounding induced current of the metallic shielding layer.

[0053] Grounding impedance time-series data is a sequence of grounding impedance values ​​for a high-voltage cable over a specific time period. Generally, when an anomaly occurs in a high-voltage cable, the line resistance at the abnormal location changes, thus affecting the cable's operational status data. Therefore, it reflects the grounding performance of the high-voltage cable at different points in time. By continuously monitoring and recording these grounding impedance values, the grounding impedance time-series data of the high-voltage cable can be obtained, allowing for analysis of the cable's operational status.

[0054] Step S2: Determine multiple grounding induced currents of the target high-voltage cable based on the grounding impedance timing data and structural parameters.

[0055] Among them, the grounding induced circulating current is the induced current on the cable shield. Because the shield of a high-voltage cable is grounded, when current flows through the conductor of the high-voltage cable, a current will be induced in the shield, and this current is the grounding induced circulating current. The magnitude of the grounding induced circulating current is related to factors such as the cable's structural parameters, current frequency, and grounding impedance. By analyzing the changes in the grounding induced circulating current, we can further understand the operating status of the high-voltage cable.

[0056] In the absence of insulation damage or multiple grounding points, the induced circulating current value of the metal sheath will change with the load current. If multiple groundings occur, the circulating current value will increase, thereby increasing the value of the grounding current, which in turn indicates damage to the cable insulation.

[0057] Step S3: Compare each grounding induced current using the dynamic threshold method to generate a real-time cable status label corresponding to each grounding induced current.

[0058] The dynamic threshold method is a technique for determining cable status by dynamically adjusting a threshold range based on real-time changes in grounding induced current. In practice, an initial threshold range is first set, determined based on historical data and empirical values. Then, changes in the grounding induced current are monitored in real time. When the grounding induced current exceeds or approaches the threshold range, the threshold range is dynamically adjusted according to the trend and rate of change. If the grounding induced current continues to exceed the adjusted threshold range, the cable status is determined to be abnormal, and a corresponding real-time cable status tag is generated. This method can more accurately reflect the actual operating status of the cable and improve monitoring accuracy.

[0059] Step S4: Construct a training dataset based on multiple grounding induction currents and real-time cable status labels.

[0060] Step S5: Train the machine learning neural network using the training dataset to obtain a high-voltage cable operation prediction model.

[0061] Machine learning neural networks include, but are not limited to, LSTM (Long Short-Term Memory) networks. LSTM neural networks are a special type of recurrent neural network capable of learning long-term dependencies. In high-voltage cable operation monitoring, LSTM neural networks can learn from historical grounding induced current data to capture the temporal dependencies within the data, thereby achieving accurate predictions of the high-voltage cable's operating status. The trained high-voltage cable operation prediction model can take real-time grounding induced current data as input and output corresponding cable status labels, thus enabling real-time monitoring and early warning of the high-voltage cable's operating status.

[0062] Step S6: Input the real-time grounding induction current of the target high-voltage cable at that time period into the high-voltage cable operation prediction model, and output the real-time cable status label of the target high-voltage cable at that time period.

[0063] The real-time cable status label can include normal and abnormal states to intuitively reflect the real-time operating status of the high-voltage cable. If the prediction result is a normal state, it indicates that the high-voltage cable is operating stably and no further measures are required; if the prediction result is an abnormal state, it indicates that the high-voltage cable has experienced a significant fault and requires immediate inspection and maintenance to prevent safety accidents.

[0064] It should be noted that, in this embodiment, the grounding impedance time-series data of the target high-voltage cable is determined, and based on the grounding impedance time-series data and structural parameters, multiple grounding induced circulating currents of the target high-voltage cable are determined. Each grounding induced circulating current is compared using a dynamic threshold method to generate a real-time cable status label corresponding to each grounding induced circulating current. Thus, the grounding induced circulating current is used as an evaluation index for the operating status of the high-voltage cable, achieving real-time monitoring and early warning of the high-voltage cable's operating status. Compared to traditional monitoring methods, this invention not only improves the accuracy and reliability of monitoring but also enables earlier detection of potential faults. Furthermore, by constructing a training dataset using grounding induced circulating currents and real-time cable status labels and training it with a machine learning neural network, a high-voltage cable operation prediction model is obtained to adapt to different operating environments and conditions of high-voltage cables, improving the accuracy and timeliness of high-voltage cable operation monitoring.

[0065] In some embodiments, the structural parameters include the distributed capacitance of the shielding layer of the target high-voltage cable, the voltage difference between the cable conductor and the metallic sheath, the frequency of the cable transmission current, the equivalent resistance of the metallic sheath, and the voltage of the cable conductor. In this case, determining the grounding impedance timing data of the target high-voltage cable based on the structural parameters includes:

[0066] Step S101: Determine the grounding capacitance current of the target high-voltage cable based on the distributed capacitance value of the shielding layer, the voltage difference between the cable conductor and the metal sheath, the frequency of the cable transmission current, and the equivalent resistance of the metal sheath.

[0067] When an induced voltage occurs in the cable shield, a distributed capacitance will form between the conductor and the shield. The capacitance value of the distributed capacitance is:

[0068]

[0069] In the formula, This represents the distributed capacitance value formed between the cable conductor and the shielding layer at time t; This represents the dielectric constant of the insulating material in the shielding layer; This indicates the outer diameter of the high-voltage cable without its shielding layer. This indicates the outer diameter of the cable including the shielding layer.

[0070] The equivalent capacitance between the conductor and the metal sheath of a high-voltage cable is related to the distributed capacitance and resistance of the insulation layer. The specific relationship is as follows:

[0071]

[0072] In the formula, Let be the grounding capacitance current of the high-voltage cable at time t; This indicates the voltage difference between the cable conductor and the metal sheath; Indicates the frequency of the current transmitted by the cable; This represents the equivalent resistance of the metal sheath.

[0073] Step S102: Determine the grounding impedance of the target high-voltage cable at multiple sampling points based on the grounding capacitance current and the cable conductor voltage, and generate grounding impedance time series data.

[0074] Grounding impedance is a crucial indicator of the grounding performance of high-voltage cables, reflecting the effectiveness of the cable's shielding layer grounding. Electromagnetic waves generated by current do not reflect during stable power transmission; however, reflection occurs when the cable malfunctions, and the reflection coefficient and projection coefficient are related to the cable impedance.

[0075] After calculating the grounding capacitance current of the high-voltage cable, the grounding impedance of the high-voltage cable at a certain sampling point can be obtained by the ratio of the grounding capacitance current to the cable conductor voltage. By continuously monitoring and recording the grounding impedance values ​​at multiple sampling points, the time-series data of the grounding impedance of the high-voltage cable can be formed. That is, if the voltage of the high-voltage cable at the measuring point is... And the grounding capacitor current is Then the grounding impedance at the measuring point is ,Right now:

[0076]

[0077] By combining the grounding impedances at multiple sampling points according to the time sequence, grounding impedance time sequence data is obtained.

[0078] Since the impedance is not a constant in the theoretical sense of a cable, its fluctuations are caused by electromagnetic interference, temperature drift, etc., and signal smoothing is needed to preserve the true trend of change. In some embodiments, it also includes:

[0079] The grounding impedance time series data is smoothed and denoised to obtain a smoothed impedance sequence.

[0080] Specifically, this application employs the Savitzky-Golay smoothing and denoising method to smooth and denoise the grounding impedance time series data, including:

[0081] Let the time index of the center point of the sliding window be m, and extract five consecutive time-series impedance data within the window to form a vector. ,middle Let m be the impedance value at time m. The Savitzky-Golay algorithm uses the least squares method to... Perform multiple binomial fittings, with the window sliding according to the time step, and output a smooth impedance sequence after traversing all data.

[0082] First, perform a binomial fit on the data within the window:

[0083]

[0084] In the formula, For impedance vector, , , This represents the coefficient vector.

[0085] Solve for the coefficient matrix using the least squares method:

[0086]

[0087] In the formula, This represents the Vandermonde matrix for multinomial regression.

[0088] The coefficient solution is:

[0089]

[0090] The fitted value when m=0 in the binomial fitting is taken as the smoothing result, and the center point is output smoothly. for:

[0091]

[0092] The grounding impedance time-series data is shifted by time sequence to generate a smooth impedance sequence. for:

[0093]

[0094] Among them, the Savitzky-Golay smoothing and denoising method is used to preprocess the impedance data to eliminate environmental interference during data acquisition and transmission, making the data smoother and the system monitoring more accurate.

[0095] In some embodiments, the structural parameters include the induced current of the three-phase metallic shield. In this case, multiple ground-induced circulating currents of the target high-voltage cable are determined based on ground impedance timing data and structural parameters, including:

[0096] Based on the induced current of the three-phase metal shield and the grounding impedances in the smooth impedance sequence, multiple grounding induced currents of the target high-voltage cable are determined.

[0097] The formula for calculating the grounding induced circulating current is as follows:

[0098]

[0099] In the formula, For grounding induced circulating current, For the grounding impedance within the smooth impedance sequence, Let be the total impedance of the sheathing circuit; where the total impedance of the sheathing circuit is:

[0100]

[0101] In the formula, , These are the sheath resistance and grounding resistance, respectively, and L is the sheath inductance; where the sheath inductance is:

[0102]

[0103] In the formula, This is a structural constant, typically taken as 0.2.

[0104] In some embodiments, each grounding induced circulating current is compared using a dynamic threshold method to generate a real-time cable status tag corresponding to each grounding induced circulating current, including:

[0105] Step S301: Determine the average value and standard deviation of the grounding induced current based on multiple grounding induced currents.

[0106] Let there be N grounding induced circulating currents, denoted as... Calculate the average and standard deviation of N grounding induced currents:

[0107]

[0108]

[0109] In the formula, This is the average value. The standard deviation is denoted as .

[0110] Step S302: Determine the upper and lower boundary values ​​of the grounding induced current based on the average value and standard deviation of the grounding induced current, and determine the boundary interval of the grounding induced current based on the upper and lower boundary values.

[0111] Specifically, the probability density factor k is determined by the confidence level of the safety requirements of the cable system. Then, using the probability density factor k, the average value and standard deviation of the grounding induced current, the upper and lower boundary values ​​of the grounding induced current are determined:

[0112]

[0113] in, , These are the lower and upper boundary values ​​of the ground induced circulating current, respectively, forming a boundary interval. , ).

[0114] Step S303: Determine whether each grounding induction current is within the boundary interval.

[0115] Step S304: If it is determined that the grounding induced current is within the boundary interval, then the real-time cable status label of the grounding induced current is determined to be in normal condition.

[0116] Step S305: If it is determined that the grounding induced current is not within the boundary interval, then the real-time cable status label of the grounding induced current is determined to be in an abnormal state.

[0117] The real-time cable status tag is generated by comparing the grounding induced circulating current with the boundary interval using the following formula.

[0118]

[0119] in, For real-time cable status tags, =0 is the normal state. =1 or 2 indicates an abnormal state.

[0120] In some embodiments, the machine learning neural network is an LSTM neural network.

[0121] The LSTM neural network consists of input, hidden, and output layers. The input layer takes into account the grounding induction current and real-time cable status labels. The hidden layer uses the LSTM structure as the initial structure and constructs a structure containing multiple LSTM cells to improve computation speed and replace traditional iterative computation. The output layer provides the system's prediction results. The model is trained based on the adaptive momentum estimation algorithm and the backpropagation algorithm.

[0122] Network training:

[0123] First, in the input layer, the dataset... Arranged chronologically, the training and test datasets are divided in a 9:1 ratio. , The data is then standardized using the following formula:

[0124]

[0125] In the formula, , These are the data before and after standardization. , These are the minimum and maximum values ​​in the dataset, respectively.

[0126] Generate standard datasets Set the step size to L, and input... The model output is the future safety state prediction result P, specifically the predicted ground induced current value. and status labels .

[0127] The mapping relationship between data input and output is as follows:

[0128]

[0129] In the formula, This is the set of parameters learned during model training (including the weights, biases, etc. of the LSTM cells). The input vector contains a normalized data sequence within a step size L, i.e. P represents the model output, which includes the predicted ground induced current value. θ represents the set of parameters (weights, biases, etc.) of the LSTM model.

[0130] Using the mean absolute error to calculate the error on the data, there will be a loss during training. Its function definition is as follows:

[0131]

[0132] In the formula, Let be the model's predicted value for the i-th sample; is the true value (label or circulation value) of the i-th sample; M is the total number of samples in the training set; B is the time step (length of the input sequence); M - B is the number of effective training samples (because the step size needs to be continuous).

[0133] The data is predicted using an improved LSTM network model. The data is sorted according to the shortest input time, thereby constructing... for:

[0134]

[0135] In the formula, is the sequence of input vectors for the test set; n is the total number of samples in the dataset.

[0136] After that Inputting into the improved LSTM network model, the output is:

[0137]

[0138] In the formula, This is the standardized prediction sequence output by the model.

[0139] Finally, the inverse standardization formula is used to operate on P to obtain the final predicted sequence:

[0140]

[0141] In the formula, This is the standardized r-th predicted value; The global maximum value of the original data; The original data has a global minimum value; r is the index of the predicted sequence, which satisfies 1≤r≤nMB.

[0142] Based on the same inventive concept, this application also provides a high-voltage cable operation monitoring system for implementing the high-voltage cable operation monitoring method described above.

[0143] The solution provided by this system is similar to the solution described in the above method. Therefore, the specific limitations of one or more high-voltage cable operation monitoring system embodiments provided below can be found in the limitations of the high-voltage cable operation monitoring method described above, and will not be repeated here.

[0144] like Figure 3 As shown in the figure, this application provides a high-voltage cable operation monitoring system, including:

[0145] Impedance determination module 100 is used to acquire the structural parameters of the target high-voltage cable and determine the grounding impedance timing data of the target high-voltage cable based on the structural parameters.

[0146] The circulating current determination module 200 is used to determine multiple grounding induced circulating currents of the target high-voltage cable based on grounding impedance timing data and structural parameters.

[0147] The circulating current comparison module 300 is used to compare each grounding induced circulating current using a dynamic threshold method and generate a real-time cable status label corresponding to each grounding induced circulating current.

[0148] Training set construction module 400 is used to construct a training dataset based on multiple grounding induction currents and real-time cable status labels;

[0149] The model training module 500 is used to train the machine learning neural network using the training dataset to obtain a high-voltage cable operation prediction model.

[0150] The status prediction module 600 is used to input the real-time grounding induction current of the target high-voltage cable into the high-voltage cable operation prediction model and output the real-time cable status label of the target high-voltage cable at that time.

[0151] In some embodiments, structural parameters include the distributed capacitance of the shielding layer of the target high-voltage cable, the voltage difference between the cable conductor and the metal sheath, the frequency of the cable transmission current, the equivalent resistance of the metal sheath, and the voltage of the cable conductor.

[0152] Impedance determination module 100 is used for:

[0153] The grounding capacitance current of the target high-voltage cable is determined based on the distributed capacitance value of the shielding layer, the voltage difference between the cable conductor and the metal sheath, the frequency of the cable transmission current, and the equivalent resistance of the metal sheath.

[0154] Based on the grounding capacitance current and the cable conductor voltage, the grounding impedance of the target high-voltage cable at multiple sampling points is determined, and grounding impedance time series data is generated.

[0155] In some embodiments, the system further includes: a noise reduction module, used for:

[0156] The grounding impedance time series data is smoothed and denoised to obtain a smoothed impedance sequence.

[0157] In some embodiments, structural parameters include the induced current of the three-phase metal shielding layer;

[0158] The circulating current determination module 200 is used for:

[0159] Based on the induced current of the three-phase metal shield and the grounding impedances in the smooth impedance sequence, multiple grounding induced currents of the target high-voltage cable are determined.

[0160] In some embodiments, the circulating current comparison module 300 is used for:

[0161] Based on multiple ground induced circulating currents, determine the average value and standard deviation of the ground induced circulating currents;

[0162] Based on the average value and standard deviation of the ground induced current, determine the upper and lower boundary values ​​of the ground induced current, and based on the upper and lower boundary values, determine the boundary interval of the ground induced current.

[0163] Determine whether each grounding induced current loop is within the boundary interval;

[0164] If it is determined that the grounding induced current is within the boundary interval, then the real-time cable status label of the grounding induced current is set to normal.

[0165] If it is determined that the grounding induced current is not within the boundary interval, then the real-time cable status label of the grounding induced current is determined to be in an abnormal state.

[0166] In some embodiments, the machine learning neural network is an LSTM neural network.

[0167] like Figure 4 As shown, this application provides an electronic device. The electronic device 10 includes a memory 20 and a processor 30. The memory 20 stores a computer program. When the computer program is executed by the processor 30, the processor 30 performs the steps of the high-voltage cable operation monitoring method as described in the above embodiment.

[0168] This application provides a computer-readable storage medium storing a computer program thereon, which, when executed, implements the steps of the high-voltage cable operation monitoring method as described in the above embodiments.

[0169] This application provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions, wherein when the program instructions are executed by a computer, the computer performs the steps of the high-voltage cable operation monitoring method as described in the above embodiments.

[0170] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, electronic devices, computer storage media, and computer program products described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0171] It should be noted that the terms "comprising" and "having" and any variations thereof in the specification, claims and accompanying drawings of this invention are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to such processes, methods, products or devices.

[0172] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0173] In the several embodiments provided by this invention, it should be understood that the disclosed systems, electronic devices, computer storage media, computer program products, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection between devices or units, and may be electrical, mechanical, or other forms.

[0174] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0175] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0176] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for executing all or part of the steps of the methods described in the various embodiments of the present invention through a computer device (which may be a personal computer, a server, or a network device, etc.). The aforementioned storage medium includes: USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, optical disks, and other media capable of storing program code.

[0177] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for monitoring the operation of high-voltage cables, characterized in that, include: Obtain the structural parameters of the target high-voltage cable, and determine the grounding impedance timing data of the target high-voltage cable based on the structural parameters; Based on the grounding impedance timing data and the structural parameters, multiple grounding induced circulating currents of the target high-voltage cable are determined; Each of the grounding induced circulating currents is compared using a dynamic threshold method to generate a real-time cable status label corresponding to each of the grounding induced circulating currents. A training dataset is constructed based on the multiple grounding induction currents and the real-time cable status labels; A high-voltage cable operation prediction model is obtained by training a machine learning neural network using the training dataset. The real-time grounding induction current of the target high-voltage cable at that time period is input into the high-voltage cable operation prediction model, and the real-time cable status label of the target high-voltage cable at that time period is output.

2. The high-voltage cable operation monitoring method according to claim 1, characterized in that, The structural parameters include the distributed capacitance of the shielding layer of the target high-voltage cable, the voltage difference between the cable conductor and the metal sheath, the frequency of the cable transmission current, the equivalent resistance of the metal sheath, and the voltage of the cable conductor. The grounding impedance timing data of the target high-voltage cable is determined based on the structural parameters, including: The grounding capacitance current of the target high-voltage cable is determined based on the distributed capacitance value of the shielding layer, the voltage difference between the cable conductor and the metal sheath, the frequency of the cable transmission current, and the equivalent resistance of the metal sheath. Based on the grounding capacitor current and the cable conductor voltage, the grounding impedance of the target high-voltage cable at multiple sampling points is determined, and the grounding impedance time series data is generated.

3. The high-voltage cable operation monitoring method according to claim 2, characterized in that, Also includes: The grounding impedance time series data is smoothed and denoised to obtain a smoothed impedance sequence.

4. The high-voltage cable operation monitoring method according to claim 3, characterized in that, The structural parameters include the induced current of the three-phase metal shielding layer; The step of determining multiple grounding induced circulating currents of the target high-voltage cable based on the grounding impedance timing data and the structural parameters includes: Based on the induced current of the three-phase metal shield and the grounding impedances in the smooth impedance sequence, multiple grounding induced currents of the target high-voltage cable are determined.

5. The high-voltage cable operation monitoring method according to claim 1 or 4, characterized in that, The step of comparing each of the grounding induced circulating currents using a dynamic threshold method to generate a real-time cable status tag corresponding to each of the grounding induced circulating currents includes: Based on the multiple ground induced circulating currents, determine the average value and standard deviation of the ground induced circulating currents; Based on the average value and standard deviation of the ground induced current, the upper and lower boundary values ​​of the ground induced current are determined, and based on the upper and lower boundary values, the boundary interval of the ground induced current is determined. Determine whether each of the aforementioned grounding induction circulating currents is within the boundary interval; If it is determined that the grounding induced current is within the boundary interval, then the real-time cable status label of the grounding induced current is determined to be in a normal state. If it is determined that the grounding induced current is not within the boundary interval, then the real-time cable status label of the grounding induced current is determined to be in an abnormal state.

6. The high-voltage cable operation monitoring method according to claim 5, characterized in that, The machine learning neural network is an LSTM neural network.

7. A high-voltage cable operation monitoring system, characterized in that, include: An impedance determination module is used to acquire the structural parameters of the target high-voltage cable and determine the grounding impedance timing data of the target high-voltage cable based on the structural parameters. The circulating current determination module is used to determine multiple grounding induced circulating currents of the target high-voltage cable based on the grounding impedance timing data and the structural parameters. The circulating current comparison module is used to compare each of the grounding induced circulating currents using a dynamic threshold method, and generate a real-time cable status label corresponding to each of the grounding induced circulating currents. The training set construction module is used to construct a training dataset based on the multiple grounding induction circulating currents and the real-time cable status labels; The model training module is used to train the machine learning neural network using the training dataset to obtain a high-voltage cable operation prediction model. The status prediction module is used to input the real-time grounding induction current of the target high-voltage cable at that time period into the high-voltage cable operation prediction model and output the real-time cable status label of the target high-voltage cable at that time period.

8. An electronic device, characterized in that, The electronic device includes a memory and a processor. The memory stores a computer program, and when the computer program is executed by the processor, the processor performs the steps of the high-voltage cable operation monitoring method as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed, it implements the steps of the high-voltage cable operation monitoring method as described in any one of claims 1-6.

10. A computer program product, characterized in that, The computer program product includes a computer program stored on a non-transitory computer-readable storage medium, the computer program including program instructions, wherein when the program instructions are executed by a computer, the computer performs the steps of the high-voltage cable operation monitoring method as described in any one of claims 1-6.

Images