Cable current-carrying capacity data processing method and device, readable storage medium and electronic equipment

Abstract

The invention provides a cable current-carrying capacity data processing method and device, a readable storage medium and electronic equipment, by implementing the embodiment of the invention, cable performance parameters and a first data set of a first time period from a data sensor are acquired, and the cable performance parameters are electric heating performance data of a target cable; the first data set is a data set of environmental state data and historical current-carrying capacity of the target cable, determining a predicted current-carrying data set of a second time period based on the first data set, a pre-trained current-carrying capacity prediction model and cable performance parameters, and performing current-carrying capacity safety supervision evaluation based on the predicted current-carrying data set to obtain a current-carrying capacity safety supervision evaluation result, according to the scheme, the current-carrying capacity is predicted in real time based on the environmental data and the historical current-carrying capacity data by using the pre-constructed and trained current-carrying capacity model, so that the current-carrying capacity prediction is more efficient and accurate, the accuracy of the current-carrying capacity prediction result is improved, and the safety of the cable is further improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power data processing, and in particular to a method, device, readable storage medium and electronic device for processing cable current carrying capacity data. Background Art

[0002] With the acceleration of urban modernization, the power industry is developing rapidly in the direction of intelligence, convenience, reliability and cleanliness. Under this trend, traditional urban overhead power transmission lines are gradually being replaced by underground cables that occupy a small area, are safer and more aesthetically pleasing. The precise setting of the cable current carrying capacity is crucial: if it is set too low, it will lead to the idle waste of expensive power assets; if it is set too high, it may cause the problem of excessive temperature of the cable insulation layer, which will not only significantly shorten the service life of the power cable, but is also more likely to cause serious safety accidents, such as fire. Therefore, the precise determination of real-time dynamic current carrying capacity is of great significance to the power sector.

[0003] However, the current current carrying capacity calculation mostly relies on physical models and adopts traditional current carrying capacity calculation methods, which are difficult to respond to real-time changing parameters of the outside world in a timely manner. It has the problems of poor real-time performance, limited accuracy, slow environmental response speed and low authenticity. Summary of the invention

[0004] The embodiments of the present application provide a method, device, readable storage medium and electronic device for processing cable current carrying capacity data, which can calculate the cable current carrying capacity more accurately and quickly, and is conducive to improving the accuracy and efficiency of current carrying capacity prediction.

[0005] In a first aspect, an embodiment of the present application provides a method for processing cable current carrying capacity data, which is applied to a server of a power monitoring system, wherein the power monitoring system further includes a data sensor and a mobile terminal communicating with the server, and the method includes:

[0006] Acquire cable performance parameters and a first data group of a first time period from a data sensor, wherein the cable performance parameters are electric and thermal performance data of a target cable, the first data group is a data set of environmental status data and historical current carrying capacity of the target cable, and the first time period is a preset variable time period length;

[0007] Determine a predicted current-carrying data group for a second period based on the first data group, a pre-trained current-carrying capacity prediction model, and cable performance parameters, the second period being a subsequent period to the first period;

[0008] Based on the predicted current-carrying data group, a current-carrying capacity safety and supervision assessment is performed to obtain a current-carrying capacity safety and supervision assessment result, and the current-carrying capacity safety and supervision assessment result is displayed on a mobile terminal.

[0009] In a second aspect, an embodiment of the present application provides a device for processing cable current carrying capacity data, which is applied to a server of a power monitoring system, wherein the power monitoring system further includes a data sensor and a mobile terminal communicating with the server, and the device includes:

[0010] An acquisition module, used to acquire cable performance parameters and a first data group of a first time period from a data sensor, wherein the cable performance parameters are electric and thermal performance data of a target cable, the first data group is a data set of environmental status data and historical current carrying capacity of the target cable, and the first time period is a preset variable time period length;

[0011] A prediction module, used to determine a predicted current-carrying data group for a second period based on the first data group, a pre-trained current-carrying capacity prediction model and cable performance parameters, the second period being a subsequent period to the first period;

[0012] The evaluation module is used to perform a current carrying capacity safety and supervision evaluation based on the predicted current carrying data group to obtain a current carrying capacity safety and supervision evaluation result, and display the current carrying capacity safety and supervision evaluation result on a mobile terminal.

[0013] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the program includes instructions for executing some or all of the steps described in the first aspect of the embodiment of the present application.

[0014] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium on which a computer program is stored. The computer program includes program instructions, and when the program instructions are executed by a processor, the processor executes some or all of the steps described in the first aspect.

[0015] In a fifth aspect, an embodiment of the present application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps described in the first aspect of the embodiment of the present application. The computer program product may be a software installation package.

[0016] By implementing the embodiments of the present application, cable performance parameters and a first data group of a first time period from a data sensor are obtained, wherein the cable performance parameters are the electrothermal performance data of the target cable, the first data group is a data set of environmental status data and historical current carrying capacity of the target cable, the first time period is a preset variable time period length, and a predicted current carrying capacity data group of a second time period is determined based on the first data group, a pre-trained current carrying capacity prediction model and cable performance parameters, the second time period is the next subsequent time period of the first time period, and a current carrying capacity safety and supervision assessment is performed based on the predicted current carrying capacity data group to obtain a current carrying capacity safety and supervision assessment result, and the current carrying capacity safety and supervision assessment result is displayed on a mobile terminal. This solution uses a pre-built and trained current carrying capacity model to predict the current carrying capacity in real time based on environmental data and historical current carrying capacity data, which can make the current carrying capacity prediction more efficient and accurate, improve the accuracy of the current carrying capacity prediction result, and thereby improve the safety of the cable. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the background technology, the drawings required for use in the embodiments of the present invention or the background technology will be described below.

[0018] Figure 1 is a system architecture diagram of a power monitoring system provided by an embodiment of the present application;

[0019] Figure 2 It is a flowchart of a method for processing cable current carrying capacity data provided by an embodiment of the present application;

[0020] Figure 3a It is a schematic diagram of the architecture of a current carrying capacity prediction model provided in an embodiment of the present application;

[0021] Figure 3b It is a schematic diagram of the architecture of another current carrying capacity prediction model provided in an embodiment of the present application;

[0022] Figure 4 It is a flowchart of a method for processing cable current carrying capacity data provided by an embodiment of the present application;

[0023] Figure 5 It is a structural schematic diagram of a cable current carrying capacity data processing device proposed in an embodiment of the present application;

[0024] Figure 6 It is a structural schematic diagram of an electronic device proposed in an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0026] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or electronic device that includes a series of steps or units is not limited to the listed steps or units, but in an optional example also includes steps or units that are not listed, or in an optional example also includes other steps or units inherent to these processes, methods, products, or electronic devices.

[0027] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0028] The cable current carrying capacity data processing method, device, readable storage medium and electronic device provided in the embodiments of the present application can be applied to Figure 1 In the power monitoring system shown, see Figure 1 , Figure 1 is a system architecture diagram of a power monitoring system provided in an embodiment of the present application, such as Figure 1 As shown, the power monitoring system 100 includes: a server 110 , a data sensor 120 , and a mobile terminal 130 .

[0029] The mobile terminal 130 can communicate with the server 110 through a network. The mobile terminal 130 refers to a device used by a user, such as a smart phone, a computer, or other electronic devices that can display information.

[0030] In the present solution, the mobile terminal 130 is provided with a display interface, which is mainly responsible for interacting with the server 110, so that the user can easily view the current carrying capacity safety and supervision assessment results. The server 110 refers to a remote computer used to process a large number of computing tasks and store data. In the present solution, a current carrying capacity prediction model and a program or model for performing current carrying capacity safety and supervision assessment are deployed on the server 110. The server 110 can also be used to obtain data during use, such as environmental status data, etc. These data are obtained by the data sensor 120 and sent to the server 110, so that the server 110 can optimize the current carrying capacity prediction model each time it is used. The server 110 can send the current carrying capacity safety and supervision assessment results to the mobile terminal 130.

[0031] Based on this, the present application provides a method, device, readable storage medium and electronic device for processing cable current carrying capacity data. The present application is described in detail below in conjunction with the accompanying drawings.

[0032] See also Figure 2 , Figure 2 is a flow chart of a method for processing cable current carrying capacity data provided by an embodiment of the present application, the method is applied to a server of a power monitoring system, the power monitoring system also includes a data sensor and a mobile terminal communicating with the server, such as Figure 2 As shown, the method comprises the following steps:

[0033] S210, obtaining cable performance parameters and a first data group of a first time period from a data sensor, wherein the cable performance parameters are the electrical and thermal performance data of the target cable, the first data group is a data set of environmental status data and historical current carrying capacity of the target cable, and the first time period is a preset variable time period length.

[0034] Among them, the cable performance data is the electrothermal performance parameters of the target cable, the target cable is the cable to be supervised, and the electrothermal performance parameters are thermal performance parameters and electrical performance parameters. Specifically, the electrothermal performance parameters may include one or more of the maximum temperature rise value, the thermal resistance from the conductor to the insulation layer in the cable, the thermal resistance from the insulation layer to the sheath, the thermal resistance from the sheath to the external environment, dielectric loss, conductor AC resistance, and cable metal sheath loss ratio, which are not limited here; when the structure of the target cable is different, for example, the target cable also has armor, then the electrothermal performance parameters may include one or more of the maximum temperature rise value, the thermal resistance from the conductor to the insulation layer in the cable, the thermal resistance from the insulation layer to the sheath, the thermal resistance from the sheath to the armor, the thermal resistance from the armor to the external environment, dielectric loss, conductor AC resistance, and cable metal sheath loss ratio, which are not limited here.

[0035] The sensor adopts a single-point or distributed sensor to obtain environmental data around the cable, including temperature, humidity, wind speed, solar radiation, etc.; infrared imaging technology is used to obtain cable temperature data; current transformers are used to obtain cable load current data. The data sensor may include multiple types of data sensors, for example, sensors for obtaining temperature, sensors for obtaining humidity, sensors for obtaining wind speed, sensors for obtaining solar radiation, sensors for obtaining target cable current carrying capacity, etc., and other sensors may also be included, and the specific sensors are not limited here.

[0036] The length of the first time period may be a preset fixed length, or may be changed according to a time length specified by a user, and the length of the first time period has a time association relationship with the predictable time length, and the time association relationship may be the same time length, or other, which is not limited here. The first time length may include at least one moment, and the time step may be preset, specified, or automatically matched according to the length of the first time period, which is not limited here.

[0037] Among them, the above-mentioned first data groups are all sorted in time series and have time correspondence, that is, one moment can correspond to a set of corresponding environmental data and historical current carrying capacity, and are arranged in time sequence.

[0038] For example, if the first time period is specified as 1 day, 24 hours, the cable current carrying capacity can be predicted based on the first data set and cable performance parameters of each hour in 24 hours according to the time step matching the first time period of 1 hour. If the first time period is specified as 1 hour, 60 minutes, the cable current carrying capacity can be predicted based on the first data set and cable performance parameters of each minute in 60 minutes according to the time step matching the first time period of 1 minute. If the first time period is specified as 1 day, 24 hours, but if the time step is half an hour, that is, 30 minutes, the cable current carrying capacity can be predicted based on the first data set and cable performance parameters of every 30th minute in 24 hours.

[0039] For example, if the data sensors include a temperature sensor, a humidity sensor, a wind speed sensor, a solar radiation sensor, and a current carrying capacity sensor, and the first time period is 5 hours and the time step is 1 hour, the first data group may include: temperature: T = [35, 36, 37, 38, 39], humidity: H = [60, 62, 63, 64, 65], wind speed: W = [1.5, 1.7, 2.0, 2.5, 2.8], solar radiation: S = [500, 550, 600, 650, 700], current carrying capacity: L = [450, 460, 470, 480, 490].

[0040] S220, determining a predicted current-carrying data group for a second time period based on the first data group, a pre-trained current-carrying capacity prediction model and cable performance parameters, the second time period being the next subsequent time period of the first time period.

[0041] The second time period is a time period to be predicted, which is a time period following the first time period. The second time period has a time association relationship with the first time period, and the time association relationship may be equal in time length. For example, if the first time period is 5 hours, the second time period may also be 5 hours. In practical applications, the second time period may also be smaller than the first time period, for example, the second time period only includes the next moment or only includes the next hour, which is not specifically limited here.

[0042] Among them, the current carrying capacity prediction model is a model built and trained based on the memory neural network model. Specifically, the memory neural network model can be an xLSTM model, which is an improvement and reconstruction of the LSTM (long short-term memory network, LSTM) model. The trained xLSTM model is deployed in the power monitoring system and prediction is performed through real-time data input.

[0043] In a possible embodiment, determining a predicted current-carrying data group for a second time period based on a first data group, a pre-trained current-carrying capacity prediction model and cable performance parameters includes: performing a standardization operation on the first data group to obtain a second data group; inputting the second data group into a first model input layer; and obtaining a predicted current-carrying data group determined by a first model output layer based on a pre-trained current-carrying capacity prediction model.

[0044] Among them, after obtaining the first data group, the original data in the first data group can be preprocessed. For example, Kalman filtering and K-means clustering technology can be used to remove noise and outliers, and then the data is normalized to meet the input requirements of the current carrying capacity prediction model. The input of the model is the first data group after the time series is standardized.

[0045] It can be seen that in this embodiment, the input data is standardized so that the input data has a unified standard, which improves the processing speed of the model and makes the model processing more efficient.

[0046] In a possible embodiment, before the step of acquiring the cable performance parameter and the first data set of the first time period from the data sensor, the method further includes:

[0047] 221. Construct a current carrying capacity prediction model to be trained, wherein the current carrying capacity prediction model to be trained includes a first model input layer, a first model hidden layer, and a first model output layer;

[0048] 222. Training the current carrying capacity prediction model to be trained based on the training data set to obtain the current carrying capacity prediction model, the training data set includes the training actual value and the historical environment data group, the current carrying capacity prediction model includes a first model input layer, a first model hidden layer and a first model output layer; training the current carrying capacity prediction model to be trained based on the training data set to obtain the current carrying capacity prediction model includes:

[0049] 2221. Obtain training prediction values ​​according to the training actual values, the historical environmental data group and the current carrying capacity prediction model to be trained;

[0050] 2222. Perform error analysis based on the actual training value, the predicted training value, and the error analysis method to obtain a training error value;

[0051] 2223. Perform model optimization based on the training error value and the model optimization algorithm to obtain the current carrying capacity prediction model to be trained, and the model optimization algorithm includes at least one of a back propagation algorithm and a cross-validation method.

[0052] Among them, see Figure 3a , Figure 3a : is a schematic diagram of the architecture of a current carrying capacity prediction model provided in an embodiment of the present application. The current carrying capacity prediction model to be trained is a model that has been constructed but not yet trained. The current carrying capacity prediction model to be trained and the current carrying capacity prediction model have the same model architecture, except that the current carrying capacity prediction model is a trained model obtained after training the current carrying capacity prediction model to be trained. Figure 3a As shown, the current carrying capacity prediction model includes a first model input layer, a first model hidden layer and a first model output layer, and the trained current carrying capacity prediction model also has a first model input layer, a first model hidden layer and a first model output layer. The training data set includes training actual values ​​and a historical environment data group, and the above-mentioned training actual values ​​and historical environment data group can be the historical actual data of the cable obtained from the database, that is, the current carrying capacity actually generated by the cable under the condition of historical environment data, and the above-mentioned database can be other modules with storage function, which is not limited here.

[0053] Specifically, the process of training the current carrying capacity prediction model to be trained based on the training data set to obtain the current carrying capacity prediction model may include: inputting the training actual value and the historical environment data group into the current carrying capacity prediction model to be trained to obtain the training prediction value, performing error analysis according to the training prediction value and the training actual value and the error analysis method to obtain the training error value, and the above-mentioned error analysis method may be to use the loss function to perform error analysis, and specifically, the loss function may select the mean square error function, the mean absolute error, the cross entropy loss, the root mean square error, the average error, etc., which are not limited here. Then, according to the calculated training error value and the model optimization algorithm, multiple parameters in the current carrying capacity prediction model to be trained are adjusted and optimized to achieve the update of weight parameters and bias parameters in the current carrying capacity prediction model to be trained. The above-mentioned model optimization algorithm may include at least one of the back propagation algorithm and the cross validation method.

[0054] Specifically, if the current carrying capacity prediction model to be trained is the model constructed and trained based on the memory neural network model, that is, an xLSTM model, then, after obtaining the training error value through the loss function, the gradient of the training error value for each parameter is propagated from the output layer to the input layer to update the weight of the current carrying capacity prediction model to be trained. Specifically, for each time step of the current carrying capacity prediction model to be trained, it is necessary to calculate the gradient of the loss function with respect to the output gate, the gradient of the loss function with respect to the new input unit state, the gradient of the loss function with respect to the old unit state, and the gradient of the loss function with respect to the new unit state. Then, according to the calculated gradient, an optimization algorithm, such as an Adam optimizer, is used to update the weight of the current carrying capacity prediction model to be trained. The Adam optimizer is a method based on the first-order moment estimation and the second-order moment estimation of the gradient, which uses the first-order moment estimation and the second-order moment estimation of the gradient to dynamically adjust the learning rate of each parameter. The above weights refer to the parameters used to calculate the hidden state and the unit state in the xLSTM. These weights play a vital role in the forward propagation process of the xLSTM. Specifically, it includes one or more of the input gate weight, forget gate weight, output gate weight, and hidden layer weight. The input gate determines which new information will be stored in the unit state, the forget gate determines which information will be discarded from the unit state, and the output gate determines the next hidden state (that is, the output of the next time step). The state of the hidden layer is determined by the hidden state of the previous time step and the input of the current time step. The above-mentioned bias term means that each gate has a corresponding bias term, which is also part of the xLSTM weight. They are trained together with the weights to optimize the performance of the model. During the training process, the hyperparameters of the model are adjusted through cross-validation, such as the number of units in xLSTM, the learning rate, the batch size, etc., to ensure that the model achieves the best performance. Specifically, first, an initial set of hyperparameters needs to be selected for the model, which can be the above-mentioned actual training values ​​and training prediction values, and then the cross-validation method is used to evaluate the performance of the model under different hyperparameter settings. This usually involves dividing the data into k subsets, using one of the subsets as the validation set in turn, and the remaining k-1 subsets as the training set, and then adjusting the hyperparameters to optimize the model performance. For example, if you find that increasing the number of xLSTM units can improve the accuracy of the model, you can try increasing the number of units. Similarly, if you find that reducing the learning rate can reduce overfitting, you can try reducing the learning rate and repeat the above steps until you find an optimal set of hyperparameters. This process may require multiple iterations, and each iteration will adjust the hyperparameters based on the results of the previous one. Until the preset stopping condition is reached, such as reaching a certain number of training rounds or the loss function converges.

[0055] Specifically, the loss function can be the mean square error, and the calculation method can be: Among them, y i is the actual training value, is the training prediction value, m is the number of samples, that is, y i and Dimension.

[0056] It can be seen that in this embodiment, the xLSTM neural network can dynamically adjust the key parameters in the cable model and provide more accurate current carrying capacity prediction by learning the historical data and real-time monitoring data of the cable operation.

[0057] In a possible embodiment, the first model hidden layer includes a first memory neural network model and a second memory neural network model, the first memory neural network model includes a second model input layer, a second model hidden layer, and a second model output layer, and the second memory neural network model includes a third model input layer, a third model hidden layer, and a third model output layer.

[0058] Among them, see Figure 3b , Figure 3b It is a schematic diagram of the architecture of another current carrying capacity prediction model provided in an embodiment of the present application. The hidden layer of the first model includes multiple memory neural network models, specifically, multiple LSTMs. The number of memory neural network models in the hidden layer is not limited here and may include N. The hidden layer also includes hidden states and memory units. Each memory neural network model includes a second model input layer, a second model hidden layer, and a second model output layer. For example, the hidden layer of the first model includes a first memory neural network model and a second memory neural network model, and the first memory neural network model and the second memory neural network model are two or more of the multiple memory neural network models, which are used to explain the data flow within the model in detail. Each layer of the memory neural network model LSTM has multiple units, and the units are used to process and store information in sequence data.

[0059] Specifically, each memory neural network model includes the following memory neural network calculation formula: Forget gate: f t =σ(W f ·[h t-1 ,x t ]+b f ), where f t represents the output of the forget gate, W f is the weight matrix, b f is the bias term, [h t-1 ,x t ] is the hidden state h of the previous moment t-1 and the current input x t σ is the activation function that limits the output between 0 and 1. Input gate: i t =σ(W i ·[h t-1 ,x t ]+bi ), where i t represents the output of the input gate, W i and b i is the weight matrix and bias term of the input gate. Candidate memory unit: in represents the value of the candidate memory cell, W c and b c is the weight matrix and bias term of the input gate. Update the memory unit Among them C t is the current state of the memory unit, C t-1 is the state of the memory cell at the previous moment. Output gate o t =σ(W o ·[h t-1 ,x t ]+b o ), where o t represents the output of the output gate. The hidden state is updated h t =o t tanh(C t ), h t is the hidden state at the current moment, that is, the hidden state parameter mentioned above.

[0060] It can be seen that in this embodiment, nesting multiple memory neural network models in the hidden layer of the current-carrying prediction model can increase the complexity of the model, enhance the memory capacity and expression ability of the model, make the current-carrying capacity prediction more efficient and accurate, and improve the accuracy of the current-carrying capacity prediction results, thereby improving the safety of the cable.

[0061] In a possible embodiment, the first model output layer includes a preset current-carrying calculation model, which is used to obtain a predicted current-carrying data group based on hidden state parameters, thermal performance parameters, and electrical performance parameters. The hidden state parameters are the results obtained by the first model output layer from the first model hidden layer, and are used to update correction parameters. The correction parameters are parameters obtained by the first model output layer through forward propagation processing based on the hidden state parameters for correcting the determination process of the current-carrying capacity.

[0062] Among them, the current-carrying calculation model is a model set in the first model output layer for calculating and predicting current-carrying data. The current-carrying calculation model is based on updated correction parameters and thermal performance parameters and electrical performance parameters. The current-carrying calculation model can be a calculation model, and the calculation model can include calculation formulas, etc., which are not specifically limited here.

[0063] Among them, the hidden state parameters are output by the memory neural network model in the hidden layer of the first model, and the process of obtaining the hidden state parameters includes: after the second data group is input into the second model input layer of the first memory neural network model, the second model output layer passes the first memory output result obtained to the third model input layer of the second memory neural network model; obtains the second memory output result obtained by the third model input layer, and uses the second memory output result as the hidden state parameter.

[0064] The correction parameter is based on the data obtained from the hidden state parameter, and each hidden state parameter can obtain a correction parameter. Specifically, the correction parameter can be calculated based on the hidden state parameter, the weight matrix of the first model output layer, and the bias term of the first model output layer. The calculation process may include: t+1 =W0h t +b0, where h t is the hidden state, W0 and b0 are the weight matrix and bias term respectively, y t+1 is the correction parameter for the next predicted moment.

[0065] It can be seen that in this embodiment, by setting a model for current carrying capacity calculation in the output layer of the first model, correction parameters are obtained based on the hidden state parameters transmitted from the hidden layer of the first model, and a predicted current carrying capacity data group is obtained according to the correction parameters and thermal performance parameters as well as electrical performance parameters. The correction parameters can be updated once each time a prediction is made, which can make the current carrying capacity prediction more efficient and accurate, improve the accuracy of the current carrying capacity prediction results, and thereby improve the safety of the cable.

[0066] In a possible embodiment, the thermal performance parameters include at least one of the maximum temperature rise value, the first thermal resistance, the second thermal resistance, and the third thermal resistance of the target cable, and the electrical performance parameters include at least one of the conductor AC resistance, dielectric loss, and cable metal sheath loss ratio of the target cable; the cable performance parameters include at least one of the thermal performance parameters and the electrical performance parameters; the current calculation model includes a parameter correction module and a calculation module, the parameter correction module is used to update the correction parameters based on the hidden state parameters, and the calculation module is used to determine the predicted current data group based on the correction parameters, thermal performance parameters, electrical performance parameters, and the prediction formula; the prediction formula includes: Among them, I t+1 To predict the current carrying capacity, ΔT max is the maximum temperature rise value, R T1 is the first thermal resistance, R T2 is the second thermal resistance, R T3 is the third thermal resistance, W d is the dielectric loss, R c is the AC resistance of the conductor, y t+1 is the correction parameter, λ1 is the cable metal sheath loss ratio, and n is the number of cores of the target cable.

[0067] Among them, the cable performance data is the electric and thermal performance parameters of the target cable, and the electric and thermal performance parameters are thermal performance parameters and electrical performance parameters. Specifically, when the target cable does not have armor, the electric and thermal performance parameters may include the maximum temperature rise value, the first thermal resistance, the second thermal resistance, and the third thermal resistance. The first thermal resistance is the thermal resistance from the conductor to the insulation layer in the cable, the second thermal resistance is the thermal resistance from the insulation layer to the sheath, and the third thermal resistance is the thermal resistance from the sheath to the external environment. The electrical performance parameters include one or more of the dielectric loss, the conductor AC resistance, and the cable metal sheath loss ratio, which are not limited here. The prediction formula includes: Among them, I t+1 To predict the current carrying capacity, ΔT max is the maximum temperature rise value, R T1 is the first thermal resistance, R T2 is the second thermal resistance, R T3 is the third thermal resistance, W d is the dielectric loss, R c is the AC resistance of the conductor, y t+1 is a correction parameter, λ1 is the cable metal sheath loss ratio, and n is the number of cores of the target cable. Specifically, λ1 is the ratio of the cable metal sheath to the total loss of all conductors of the cable.

[0068] Among them, when the structure of the target cable is different, for example, the target cable also has armor, the electrothermal performance parameters may include the maximum temperature rise value, the first thermal resistance, the second thermal resistance, the fourth thermal resistance, and the fifth thermal resistance. The first thermal resistance is the thermal resistance from the conductor to the insulation layer in the cable, the second thermal resistance is the thermal resistance from the insulation layer to the sheath, the fourth thermal resistance is the thermal resistance from the sheath to the armor, and the fifth thermal resistance is the thermal resistance from the armor to the external environment. The prediction formulas include:

[0069] Among them, I t+1 To predict the current carrying capacity, ΔT max is the maximum temperature rise value, R T1 is the first thermal resistance, R T2 is the second thermal resistance, R T3 is the third thermal resistance, W d is the dielectric loss, R c is the AC resistance of the conductor, y t+1 is the correction parameter, λ1 is the cable metal sheath loss ratio, λ2 is the armor loss ratio, specifically, λ2 is the ratio of the cable armor layer to the total loss of all conductors of the cable, and n is the number of cores of the target cable.

[0070] It can be seen that in this embodiment, a prediction model is constructed based on the electrothermal performance coefficient, the electrical performance coefficient and the correction parameters. The prediction model uses updated correction parameters for each prediction, which can make the current carrying capacity prediction more efficient and accurate, improve the accuracy of the current carrying capacity prediction results, and thus improve the safety of the cable.

[0071] For example, it is assumed that the environmental parameters have been collected (past 1 to 24 hours), and the noise and outliers have been removed. For the sake of convenience, the data at 5 time points are used for example calculations. The actual implementation requires the use of the collected time series data (past 1 to 24 hours). Temperature (T), humidity (H), wind speed (W), solar radiation (S), current current carrying capacity (L). The data of these features are as follows: temperature: T = [35, 36, 37, 38, 39], humidity: H = [60, 62, 63, 64, 65], wind speed: W = [1.5, 1.7, 2.0, 2.5, 2.8], solar radiation: S = [500, 550, 600, 650, 700], current carrying capacity: L = [450, 460, 470, 480, 490]. Then perform data preprocessing. First, normalize the data of each feature so that the data range is between [0, 1]. Assuming the temperature range is 0℃ to 50℃, normalize the temperature to: T t =(T-0) / (50-0)=[0.7,0.72,0.74,0.76,0.78]; Assuming the humidity range is from 0% to 100%, the humidity is normalized to: H t =(H-0) / (100-0)=[0.6,0.62,0.63,0.64,0.65]; Assuming the wind speed range is 0m / s to 10m / s, normalize the wind speed: W t =(W-0) / (10-0)=[0.15,0.17,0.2,0.25,0.28]; Assuming that the solar radiation ranges from 0W / m2 to 1000W / m2, the solar radiation is normalized to: S t =(S-0) / (1000-0)=[0.5,0.55,0.6,0.65,0.7], assuming the current carrying capacity ranges from 0A to 1000A, normalize the current carrying capacity: L t =(L-0) / (1000-0)=[0.45,0.46,0.47,0.48,0.49]. The normalized input data is:

[0072]

[0073] Then use the current carrying capacity prediction model xLSTM to calculate: For the sake of convenience, a simplified model is used, and its architecture is as follows: the input dimension of the input layer is 5 (temperature, humidity, wind speed, solar radiation, current carrying capacity); the hidden layer uses a two-layer memory neural network model LSTM, with 50 hidden neural units in each layer. The output dimension of the output layer is 5, that is, the model correction coefficient for the next 5 moments. The LSTM layer of xLSTM contains 50 hidden nodes, and each layer passes through the forget gate, input gate, candidate memory unit, memory unit update, output gate and hidden state update in turn, that is, the above memory neural network calculation formula, to obtain a hidden state h with a dimension of 1×5 t Finally, the model correction parameter y is obtained through the first model output layer t+1 =[0.9,0.95,1.0,1.05,1.1]. Then calculate the current carrying capacity, assuming that the maximum allowable temperature rise ΔT of the cable is known. max =50K; known parameters in the thermal circuit model: W d =5W / m, R T1 =0.1K·m / W, R T2 =0.2K·m / W, R T3 =0.3K·m / W, R T4 =0.4K·m / W, n=1, R C =0.0001Ω / m, λ1=0.2, λ2=0.1. Then, based on the current calculation model, the current carrying capacity at the next five moments is calculated to be I t+1 =[634.28,617.29,601.66,587.35,574.36].

[0074] S230, performing a current carrying capacity safety and supervision assessment based on the predicted current carrying data group to obtain a current carrying capacity safety and supervision assessment result, and displaying the current carrying capacity safety and supervision assessment result on a mobile terminal.

[0075] Among them, the current carrying capacity safety and supervision assessment can be based on the predicted current carrying data group to determine the maximum current carrying value, to determine whether it exceeds the threshold, or it can be based on the predicted current carrying data group to predict the trend, which is not limited here. The content displayed on the mobile terminal can be a pop-up window information or a visual page, which is not limited here.

[0076] In a possible embodiment, the first data group includes a historical current carrying capacity data group of the target cable, the historical current carrying capacity data group includes at least one historical current carrying capacity parameter, the predicted current carrying capacity data group includes at least one predicted current carrying capacity parameter, and the current carrying capacity safety and supervision evaluation is performed based on the predicted current carrying capacity data group to obtain the current carrying capacity safety and supervision evaluation result, and the current carrying capacity safety and supervision evaluation result is displayed on the mobile terminal, including:

[0077] 231. Obtain a first ampacity trend based on at least one historical ampacity parameter, and obtain a second ampacity trend based on at least one predicted ampacity parameter;

[0078] 232. Obtain a predicted trend according to the first current carrying capacity trend and the second current carrying capacity trend, the predicted trend including the first trend and the second trend, the first trend indicating that the second current carrying capacity trend is increasing compared to the first current carrying capacity trend, and the second trend indicating that the second current carrying capacity trend is decreasing compared to the first current carrying capacity trend;

[0079] 233. If the predicted trend is detected to be the second trend, a current carrying capacity safety situation is obtained based on the second current carrying capacity trend and the current carrying capacity threshold, where the current carrying capacity safety situation includes safe and unsafe;

[0080] 234. Use the predicted trend and / or the safety of the current carrying capacity as the result of the safety supervision assessment;

[0081] 235. Display the safety and supervision assessment results and the predicted current carrying data group on the mobile terminal.

[0082] Among them, the first current carrying capacity trend and the second current carrying capacity trend can be obtained based on the lowest current carrying capacity and the highest current carrying capacity in the historical current carrying capacity data group and the predicted current carrying capacity data group. For example, it can be represented by the lowest current carrying capacity to the highest current carrying capacity. Then, based on the obtained first current carrying capacity trend and the second current carrying capacity trend, the predicted trend is obtained for the predicted current carrying capacity data group. The predicted trend characterizes that the second current carrying capacity trend rises or falls relative to the first current carrying capacity trend. Specifically, the predicted trend includes the first trend and the second trend. The first trend characterizes that the second current carrying capacity trend rises compared to the first current carrying capacity trend, and the second trend characterizes that the second current carrying capacity trend falls compared to the first current carrying capacity trend. If the predicted trend is detected to be the second trend, the second current carrying capacity trend is compared with the current carrying capacity threshold to obtain the current carrying capacity safety situation. If the second current carrying capacity trend is not within the current carrying capacity threshold range, the current carrying capacity safety situation is unsafe. If the second current carrying capacity trend is within the current carrying capacity threshold range, the current carrying capacity safety situation is safe. The current carrying capacity safety situation is sent to the mobile terminal as the case evaluation result and displayed on the mobile terminal. In addition, the predicted current carrying capacity data group can also be sent to the mobile terminal and displayed to facilitate manual inspection by the staff.

[0083] Among them, when it is detected that the current carrying capacity safety situation is unsafe, an alarm operation is performed, which can be through warning labels, patterns, information, pop-up windows, alarms and other methods, which are not limited here.

[0084] For example, the model predicts that the current carrying capacity of the cable in the next five moments will be (570A~630A). Compared with the previous trend (450A~490A), the current carrying capacity continues to increase slightly, but it is still within the safe range (assuming the upper limit of safety is 700A). If it exceeds the safe range, the system will issue an alarm and take measures.

[0085] It can be seen that in this embodiment, by analyzing the trend of the current carrying capacity and obtaining early warning warnings, the safety of the target cable can be improved.

[0086] It can be seen that by implementing the embodiments of the present application, the cable performance parameters and the first data group of the first time period from the data sensor are obtained, the cable performance parameters are the electrothermal performance data of the target cable, the first data group is the environmental status data of the target cable and the data set of the historical current carrying capacity, the first time period is a preset variable time period length, and the predicted current carrying capacity data group of the second time period is determined based on the first data group, the pre-trained current carrying capacity prediction model and the cable performance parameters, the second time period is the next subsequent time period of the first time period, and a current carrying capacity safety and supervision assessment is performed based on the predicted current carrying capacity data group to obtain the current carrying capacity safety and supervision assessment result, and the current carrying capacity safety and supervision assessment result is displayed on the mobile terminal. This scheme uses a pre-built and trained current carrying capacity model to predict the current carrying capacity in real time based on environmental data and historical current carrying capacity data, which can make the current carrying capacity prediction more efficient and accurate, improve the accuracy of the current carrying capacity prediction result, and thereby improve the safety of the cable.

[0087] See also Figure 4 , Figure 4 is a flow chart of a method for processing cable current carrying capacity data provided by an embodiment of the present application, the method is applied to a server of a power monitoring system, the power monitoring system also includes a data sensor and a mobile terminal communicating with the server, such as Figure 4 As shown, the method also includes the following steps:

[0088] S410, obtaining cable performance parameters and a first data group of a first time period from a data sensor, wherein the cable performance parameters are electric and thermal performance data of a target cable, the first data group is a data set of environmental status data and historical current carrying capacity of the target cable, and the first time period is a preset variable time period length;

[0089] S420, performing a real-time model training process, so that the model is continuously trained, and an updated current carrying capacity prediction model is obtained, where the updated current carrying capacity prediction model is a model obtained by real-time training and updating the pre-trained current carrying capacity model;

[0090] S430, determining a predicted current-carrying data group for a second period based on the first data group, an updated current-carrying capacity prediction model and cable performance parameters, the second period being the next period following the first period;

[0091] S440, performing a current carrying capacity safety and supervision assessment based on the predicted current carrying data group to obtain a current carrying capacity safety and supervision assessment result, and displaying the current carrying capacity safety and supervision assessment result on a mobile terminal.

[0092] Among them, the implementation training process of updating the current carrying capacity prediction model is Figure 2 The training process of the current carrying capacity prediction model in the embodiment updates the training data set used, adds the historical data obtained when it was last used, and adds the historical environment data group when it was last used and the current carrying capacity value when it was last used.

[0093] It should be noted that other processes Figure 2 The details of the embodiments are the same and will not be repeated here.

[0094] It can be seen that in this embodiment, real-time training is continuously performed based on historical data during use, so that the model is continuously updated in different environments, making the model's prediction more accurate, and the current carrying capacity prediction can be made more efficient and accurate, thereby improving the accuracy of the current carrying capacity prediction results and thus improving the safety of the cable.

[0095] See also Figure 5 , Figure 5 The present invention provides a schematic diagram of a cable current carrying capacity data processing device, which is applied to a server of a power monitoring system. The power monitoring system also includes a data sensor and a mobile terminal that communicate with the server. The cable current carrying capacity data processing device 500 includes: an acquisition module 510, a prediction module 520, and an evaluation module 530, wherein:

[0096] An acquisition module 510 is used to acquire a cable performance parameter and a first data group of a first time period from a data sensor, wherein the cable performance parameter is the electric and thermal performance data of the target cable, the first data group is a data set of the environmental state data and the historical current carrying capacity of the target cable, and the first time period is a preset variable time period length;

[0097] A prediction module 520, configured to determine a predicted current-carrying data group for a second period based on the first data group, a pre-trained current-carrying capacity prediction model and cable performance parameters, the second period being a subsequent period to the first period;

[0098] The evaluation module 530 is used to perform a current carrying capacity safety and supervision evaluation based on the predicted current carrying data group to obtain a current carrying capacity safety and supervision evaluation result, and display the current carrying capacity safety and supervision evaluation result on the mobile terminal.

[0099] In a possible implementation, the prediction module 520 is specifically used to determine the predicted current-carrying data set for the second time period based on the first data set, the pre-trained current-carrying capacity prediction model and the cable performance parameters:

[0100] Performing a standardization operation on the first data set to obtain a second data set;

[0101] Inputting the second data set into the first model input layer;

[0102] Obtain a predicted current-carrying capacity data set determined by the first model output layer based on a pre-trained current-carrying capacity prediction model.

[0103] In a possible implementation, the evaluation module 530 performs a current carrying capacity safety and monitoring evaluation based on the predicted current carrying data group to obtain a current carrying capacity safety and monitoring evaluation result, and displays the current carrying capacity safety and monitoring evaluation result on the mobile terminal, specifically for:

[0104] deriving a first ampacity trend based on at least one historical ampacity parameter, and deriving a second ampacity trend based on at least one predicted ampacity parameter;

[0105] A predicted trend is obtained according to the first current carrying capacity trend and the second current carrying capacity trend, the predicted trend including the first trend and the second trend, the first trend indicating that the second current carrying capacity trend is rising compared with the first current carrying capacity trend, and the second trend indicating that the second current carrying capacity trend is falling compared with the first current carrying capacity trend;

[0106] If the predicted trend is detected to be the second trend, the current carrying capacity safety situation is obtained based on the second current carrying capacity trend and the current carrying capacity threshold, and the current carrying capacity safety situation includes safe and unsafe;

[0107] Use the predicted trend and / or the safety of the current carrying capacity as the result of the safety supervision assessment;

[0108] The safety and supervision assessment results and predicted current carrying data groups are displayed on the mobile terminal.

[0109] In a possible embodiment, before the step of obtaining the cable performance parameter and the first data group of the first time period from the data sensor, the cable current carrying capacity data processing device 500 is further used to: construct a current carrying capacity prediction model to be trained, the current carrying capacity prediction model to be trained includes a first model input layer, a first model hidden layer and a first model output layer;

[0110] Based on the training data set, the current carrying capacity prediction model to be trained is trained to obtain a current carrying capacity prediction model, wherein the training data set includes a training actual value and a historical environment data group, and the current carrying capacity prediction model includes a first model input layer, a first model hidden layer, and a first model output layer;

[0111] The current carrying capacity prediction model to be trained based on the training data set is obtained by:

[0112] Obtaining a training prediction value according to the training actual value, the historical environmental data group and the current carrying capacity prediction model to be trained;

[0113] Perform error analysis based on actual training values, predicted training values, and error analysis methods to obtain training error values;

[0114] Model optimization is performed based on the training error value and the model optimization algorithm to obtain the current carrying capacity prediction model to be trained, and the model optimization algorithm includes at least one of a back propagation algorithm and a cross validation method.

[0115] In a possible embodiment, before the step of obtaining the cable performance parameter and the first data group of the first time period from the data sensor, the cable current carrying capacity data processing device 500 is further used to: construct a current carrying capacity prediction model to be trained, the current carrying capacity prediction model to be trained includes a first model input layer, a first model hidden layer and a first model output layer;

[0116] Among them, the first model hidden layer includes a first memory neural network model and a second memory neural network model, the first memory neural network model includes a second model input layer, a second model hidden layer, and a second model output layer, and the second memory neural network model includes a third model input layer, a third model hidden layer, and a third model output layer.

[0117] Among them, the first model output layer includes a preset current-carrying calculation model, which is used to obtain a predicted current-carrying data group based on hidden state parameters, thermal performance parameters and electrical performance parameters. The hidden state parameters are the results obtained by the first model output layer from the first model hidden layer, which are used to update the correction parameters. The correction parameters are the parameters obtained by the first model output layer based on the hidden state parameters for forward propagation processing to correct the determination process of the current-carrying capacity.

[0118] The thermal performance parameters include at least one of the maximum temperature rise value, the first thermal resistance, the second thermal resistance, and the third thermal resistance of the target cable; the electrical performance parameters include at least one of the conductor AC resistance, the dielectric loss, and the cable metal sheath loss ratio of the target cable; the cable performance parameters include at least one of the thermal performance parameters and the electrical performance parameters;

[0119] The current calculation model includes a parameter correction module and a calculation module, the parameter correction module is used to update the correction parameters based on the hidden state parameters, and the calculation module is used to determine the predicted current data group based on the correction parameters, thermal performance parameters, electrical performance parameters, and prediction formulas;

[0120] The prediction formula includes:

[0121]

[0122] Among them, I t+1 To predict the current carrying capacity, ΔT max is the maximum temperature rise value, R T1 is the first thermal resistance, R T2is the second thermal resistance, R T3 is the third thermal resistance, W d is the dielectric loss, R c is the AC resistance of the conductor, y t+1 is the correction parameter, λ1 is the cable metal sheath loss ratio, and n is the number of cores of the target cable.

[0123] It is worth noting that the specific functional implementation of the cable current carrying capacity data processing device 500 is shown in the above Figure 2 and Figure 3a and Figure 3b The description of the method for processing the cable current carrying capacity data shown in the figure, for example, the acquisition module 510 is used to implement the relevant content of executing S210 or S410. The various units or modules in the cable current carrying capacity data processing device 500 can be respectively or completely combined into one or several other units or modules to constitute, or one (some) of the units or modules can be further divided into multiple functionally smaller units or modules to constitute, which can achieve the same operation without affecting the realization of the technical effects of the embodiments of the present invention. The above-mentioned units or modules are divided based on logical functions. In actual applications, the functions of one unit (or module) are implemented by multiple units (or modules), or the functions of multiple units (or modules) are implemented by one unit (or module).

[0124] It can be seen that the cable current carrying capacity data processing device described in the embodiment of the present application obtains the cable performance parameters and the first data group of the first time period from the data sensor, the cable performance parameters are the electric and thermal performance data of the target cable, the first data group is the environmental status data of the target cable and the data set of the historical current carrying capacity, the first time period is a preset variable time period length, and the predicted current carrying capacity data group of the second time period is determined based on the first data group, the pre-trained current carrying capacity prediction model and the cable performance parameters, the second time period is the next subsequent time period of the first time period, and the current carrying capacity safety and supervision assessment is performed based on the predicted current carrying capacity data group to obtain the current carrying capacity safety and supervision assessment result, and the current carrying capacity safety and supervision assessment result is displayed on the mobile terminal. This scheme uses a pre-built and trained current carrying capacity model to predict the current carrying capacity in real time based on environmental data and historical current carrying capacity data, which can make the current carrying capacity prediction more efficient and accurate, improve the accuracy of the current carrying capacity prediction result, and thereby improve the safety of the cable.

[0125] See also Figure 6 , Figure 6 It is a structural diagram of an electronic device proposed in an embodiment of the present application. As shown in the figure, the electronic device 600 includes a processor 610, a memory 620, a communication interface 630 and one or more programs 621. The one or more programs 621 are stored in the memory 620 and are configured to be executed by the processor 610.

[0126] The processor 610, the memory 620, and the communication interface 630 are connected to each other and perform communication work with each other;

[0127] The memory 620 may be a volatile memory such as a dynamic random access memory DRAM, or a non-volatile memory such as a mechanical hard disk. The memory 620 is used to store a set of executable program codes, and the processor 610 is used to call one or more programs 621 stored in the memory 620, and may execute any part or all of the steps recorded in the embodiment of the method for obtaining the current carrying capacity of the cable.

[0128] Among them, the electronic device 600 may include smart phones (such as Android phones, iOS phones, Windows Phone phones, etc.), tablet computers, PDAs, driving recorders, vehicle-mounted electronic devices, servers, laptops, mobile Internet electronic devices (MID, Mobile Internet Devices) or wearable electronic devices (such as smart watches, Bluetooth headsets), etc. The above are only examples and not exhaustive, including but not limited to the above electronic devices.

[0129] It can be seen that the electronic device described in the embodiment of the present application obtains cable performance parameters and a first data group of a first time period from a data sensor, the cable performance parameters are the electrothermal performance data of the target cable, the first data group is a data set of environmental status data and historical current carrying capacity of the target cable, the first time period is a preset variable time period length, and a predicted current carrying data group of the second time period is determined based on the first data group, a pre-trained current carrying capacity prediction model and the cable performance parameters, the second time period is the next subsequent time period of the first time period, and a current carrying capacity safety and supervision assessment is performed based on the predicted current carrying capacity data group to obtain a current carrying capacity safety and supervision assessment result, and the current carrying capacity safety and supervision assessment result is displayed on a mobile terminal. This scheme uses a pre-built and trained current carrying capacity model to predict the current carrying capacity in real time based on environmental data and historical current carrying capacity data, which can make the current carrying capacity prediction more efficient and accurate, improve the accuracy of the current carrying capacity prediction result, and thereby improve the safety of the cable.

[0130] An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program for exchanging data with a brain, wherein the computer program enables a computer to execute part or all of the steps of any method recorded in the above method embodiment, and the above computer includes an electronic device.

[0131] The embodiment of the present application also provides a computer program product, the computer program product includes a non-transitory computer-readable storage medium storing a computer program, the computer program is operable to cause a computer to execute some or all of the steps of any method described in the method embodiment. The computer program product may be a software installation package, and the computer includes an electronic device.

[0132] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0133] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0134] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the above-mentioned units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0135] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0136] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0137] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially 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, and the computer software product is stored in a memory, including a number of instructions to enable a computer electronic device (which can be a personal computer, electronic device or network electronic device, etc.) to perform all or part of the steps of the above-mentioned methods of each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0138] A person skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, and the memory can include: a flash drive, a read-only memory (English: Read-Only Memory, abbreviated as: ROM), a random access memory (English: Random Access Memory, abbreviated as: RAM), a magnetic disk or an optical disk, etc.

[0139] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for processing cable current carrying capacity data, characterized in that: A server applied to a power monitoring system, wherein the power monitoring system further comprises a data sensor and a mobile terminal communicating with the server, and the method comprises: Acquire a cable performance parameter and a first data group of a first time period from the data sensor, wherein the cable performance parameter is the electric and thermal performance data of the target cable, the first data group is a data set of the environmental state data and the historical current carrying capacity of the target cable, and the first time period is a preset variable time period length; Determine a predicted current-carrying data group for a second period based on the first data group, a pre-trained current-carrying capacity prediction model and the cable performance parameters, the second period being a subsequent period to the first period; A current carrying capacity safety and supervision assessment is performed based on the predicted current carrying data group to obtain a current carrying capacity safety and supervision assessment result, and the current carrying capacity safety and supervision assessment result is displayed on the mobile terminal.

2. The method according to claim 1, characterized in that Before the step of acquiring the cable performance parameter and the first data set of the first time period from the data sensor, the method further comprises: Constructing a current carrying capacity prediction model to be trained, wherein the current carrying capacity prediction model to be trained includes a first model input layer, a first model hidden layer, and a first model output layer; The current carrying capacity prediction model to be trained is trained based on a training data set to obtain the current carrying capacity prediction model, wherein the training data set includes a training actual value and a historical environment data group, and the current carrying capacity prediction model includes the first model input layer, the first model hidden layer, and the first model output layer; The step of training the current carrying capacity prediction model to be trained based on the training data set to obtain the current carrying capacity prediction model comprises: Obtaining a training prediction value according to the training actual value, the historical environmental data group and the current carrying capacity prediction model to be trained; Perform error analysis based on the actual training value, the predicted training value, and an error analysis method to obtain a training error value; Model optimization is performed based on the training error value and a model optimization algorithm to obtain the current carrying capacity prediction model to be trained, and the model optimization algorithm includes at least one of a back propagation algorithm and a cross-validation method.

3. The method according to claim 2, characterized in that The first model hidden layer includes a first memory neural network model and a second memory neural network model, the first memory neural network model includes a second model input layer, a second model hidden layer, and a second model output layer, and the second memory neural network model includes a third model input layer, a third model hidden layer, and a third model output layer.

4. The method according to any one of claims 2 to 3, characterized in that: The first model output layer includes a preset current-carrying calculation model, which is used to obtain the predicted current-carrying data group based on hidden state parameters, the thermal performance parameters and the electrical performance parameters. The hidden state parameters are the results obtained by the first model output layer from the first model hidden layer, which are used to update correction parameters. The correction parameters are the parameters obtained by the first model output layer through forward propagation processing based on the hidden state parameters for correcting the determination process of the current-carrying capacity.

5. The method according to claim 4, characterized in that The thermal performance parameters include at least one of the maximum temperature rise value, the first thermal resistance, the second thermal resistance, and the third thermal resistance of the target cable; the electrical performance parameters include at least one of the conductor AC resistance, the dielectric loss, and the cable metal sheath loss ratio of the target cable; the cable performance parameters include at least one of the thermal performance parameters and the electrical performance parameters; The current carrying calculation model includes a parameter correction module and a calculation module, wherein the parameter correction module is used to update the correction parameter based on the hidden state parameter, and the calculation module is used to determine the predicted current carrying data group based on the correction parameter, the thermal performance parameter, the electrical performance parameter, and a prediction formula; The prediction formula includes: Among them, I t+1 To predict the current carrying capacity, ΔT max is the maximum temperature rise value, R T1 is the first thermal resistance, R T2 The second thermal resistance, R T3 is the third thermal resistance, W d is the dielectric loss, R c is the AC resistance of the conductor, y t+1 is the correction parameter, λ1 is the cable metal sheath loss ratio, and n is the number of cores of the target cable.

6. The method according to claim 1, characterized in that The method of determining the predicted current carrying data set for the second time period based on the first data set, the pre-trained current carrying capacity prediction model and the cable performance parameters comprises: Performing a standardization operation on the first data set to obtain a second data set; Inputting the second data set into the first model input layer; Obtain a predicted current-carrying capacity data set determined by the first model output layer based on a pre-trained current-carrying capacity prediction model.

7. The method according to claim 1, characterized in that The first data group includes a historical current carrying capacity data group of the target cable, the historical current carrying capacity data group includes at least one historical current carrying capacity parameter, the predicted current carrying capacity data group includes at least one predicted current carrying capacity parameter, and the current carrying capacity safety and supervision evaluation is performed based on the predicted current carrying capacity data group to obtain a current carrying capacity safety and supervision evaluation result, and the current carrying capacity safety and supervision evaluation result is displayed on the mobile terminal, including: Obtain a first ampacity trend based on the at least one historical ampacity parameter, and obtain a second ampacity trend based on the at least one predicted ampacity parameter; Obtaining a predicted trend according to the first current carrying capacity trend and the second current carrying capacity trend, the predicted trend including a first trend and a second trend, the first trend indicating that the second current carrying capacity trend is increasing compared to the first current carrying capacity trend, and the second trend indicating that the second current carrying capacity trend is decreasing compared to the first current carrying capacity trend; If it is detected that the predicted trend is the second trend, obtaining a current carrying capacity safety situation based on the second current carrying capacity trend and the current carrying capacity threshold, wherein the current carrying capacity safety situation includes safe and unsafe; Taking the predicted trend and / or the current carrying capacity safety situation as the safety supervision assessment result; The safety and supervision assessment result and the predicted current carrying data group are displayed on the mobile terminal.

8. A device for processing cable current carrying capacity data, characterized in that: A server applied to a power monitoring system, the power monitoring system further comprising a data sensor and a mobile terminal communicating with the server, the device comprising: An acquisition module, used for acquiring cable performance parameters and a first data group of a first time period from the data sensor, wherein the cable performance parameters are electric and thermal performance data of a target cable, the first data group is a data set of environmental status data and historical current carrying capacity of the target cable, and the first time period is a preset variable time period length; A prediction module, configured to determine a predicted current-carrying data group for a second time period based on the first data group, a pre-trained current-carrying capacity prediction model and the cable performance parameters, wherein the second time period is a next time period following the first time period; The evaluation module is used to perform a current carrying capacity safety and supervision evaluation based on the predicted current carrying data group to obtain a current carrying capacity safety and supervision evaluation result, and display the current carrying capacity safety and supervision evaluation result on the mobile terminal.

9. A computer-readable storage medium, characterized in that: The processing program storing the cable current carrying capacity data comprises an execution instruction. When the processor of the electronic device executes the execution instruction, the processor executes the method as claimed in any one of claims 1 to 7.

10. An electronic device, characterized in that: It comprises a processor and a memory storing execution instructions, wherein the memory stores one or more programs; when the processor executes the execution instructions stored in the memory, the processor executes the method according to any one of claims 1 to 7.

Images