A method and device for predicting the temperature of a cable

Abstract

The present invention discloses a method and device for predicting the temperature of a cable. The method includes: obtaining the thermal path parameters of the cable to be measured and the cable temperature training samples in the cable database, calculating the core temperature sequence data of the cable to be measured according to the thermal path parameters, using the empirical mode decomposition method and the complete ensemble empirical mode decomposition method to perform a stationary processing on the core temperature sequence data to obtain the stationary temperature sequence data, establishing a time series combined prediction model based on the cable temperature training samples, inputting the thermal path parameters and the stationary sequence data into the time series combined prediction model, and calculating the real-time temperature prediction result data of the cable to be measured. It is beneficial to solve the technical problem that the existing cable temperature prediction method does not consider the transient process of the cable surface temperature and the cable temperature rise, resulting in inaccurate predicted temperature, and improves the prediction accuracy of the cable temperature.

Description

Technical Field

[0001] The present invention relates to the technical field of predicting cable temperature, and particularly to a method and device for predicting cable temperature. Background Art

[0002] Due to advantages such as less occupied area, low line consumption, and high operation reliability, power cables are widely used in power transmission and distribution systems. As a key state parameter for the normal operation of cables, cable temperature directly affects the insulation and current-carrying capacity of cables. Excessive temperature accelerates the aging of cable insulation, reduces its insulation performance, and triggers local discharge accidents of cables; too low temperature reduces the utilization rate of cable resources. Therefore, the temperature of the cable conductor directly determines the power transmission capacity of the cable, and it is necessary to monitor the operating temperature of the cable in real time. And the temperature prediction system can predict the temperature trend in the next time period according to the current operating state of the cable, and improve the overall power transmission efficiency of the cable by dynamically adjusting the load current size in real time.

[0003] Currently, in the calculation of cable conductor temperature, the influence of the cable surface temperature on the cable conductor temperature is closely related. Without considering the influence of the surface temperature, a complete boundary condition cannot be provided for the temperature field calculation, resulting in an obvious deviation between the calculated temperature value and the actual measured value of the cable operation. In the calculation and prediction of cable conductor temperature, most current studies are based on the steady-state heat balance equation. In fact, the cable operating environment, load, etc. are constantly changing. Especially in the case of emergency dispatching, not considering the transient process of the cable body temperature rise will lead to inaccurate predicted temperature.

[0004] Therefore, in order to improve the prediction accuracy of cable temperature and solve the technical problem that the existing cable temperature prediction method does not consider the transient process of cable surface temperature and cable temperature rise, resulting in inaccurate predicted temperature, it is urgent to construct a method for predicting cable temperature. Summary of the Invention

[0005] The present invention provides a method and device for predicting cable temperature, which solves the technical problem that the existing cable temperature prediction method does not consider the transient process of cable surface temperature and cable temperature rise, resulting in inaccurate predicted temperature.

[0006] In the first aspect, the present invention provides a method for predicting cable temperature, including:

[0007] Obtaining the thermal circuit parameters of the cable to be measured and the cable temperature training samples in the cable database; the cable temperature training samples include historical cable temperature data and corresponding sample category labels;

[0008] Calculating the core temperature sequence data of the cable to be measured according to the thermal circuit parameters;

[0009] The empirical mode decomposition method and the complete ensemble empirical mode decomposition method are used to perform stationary processing on the core temperature sequence data to obtain stationary temperature sequence data;

[0010] Based on the historical cable temperature data and the corresponding sample class labels, a time series combined prediction model is established;

[0011] The thermal path parameters and the stationary sequence data are input into the time series combined prediction model, and the real-time temperature prediction result data of the cable to be measured is calculated.

[0012] Optionally, according to the thermal path parameters, calculating the core temperature sequence data of the cable to be measured includes:

[0013] Construct a transient thermal path model of the cable body of the cable to be measured corresponding to the thermal path parameters;

[0014] According to the transient thermal path model of the cable body, calculate the core temperature sequence data of the cable to be measured.

[0015] Optionally, using the empirical mode decomposition method and the complete ensemble empirical mode decomposition method to perform stationary processing on the core temperature sequence data to obtain stationary temperature sequence data includes:

[0016] Using the empirical mode decomposition method to perform stationary processing on the core temperature sequence data to obtain preliminary stationary temperature sequence data;

[0017] Using the complete ensemble empirical mode decomposition method to decompose the preliminary stationary temperature sequence data to obtain the stationary temperature sequence data.

[0018] Optionally, based on the historical cable temperature data and the corresponding sample class labels, establishing a time series combined prediction model includes:

[0019] Establish a preliminary time series combined prediction model corresponding to the historical cable temperature data and the corresponding sample class labels;

[0020] According to the historical cable temperature data and the corresponding sample class labels, train the preliminary time series combined prediction model to obtain the trained preliminary time series combined prediction model;

[0021] Based on the historical cable temperature data and the corresponding sample class labels, verify the trained preliminary time series combined prediction model to obtain the time series combined prediction model.

[0022] Optionally, according to the historical cable temperature data and the corresponding sample class labels, training the preliminary time series combined prediction model to obtain the trained preliminary time series combined prediction model includes:

[0023] Input the cable thermal path parameters and the cable stabilized temperature sequence data in the historical cable temperature data into the preliminary time series combined prediction model to generate corresponding sample categories;

[0024] Determine the training error according to the cable thermal path parameters and the cable stabilized temperature sequence data in the historical cable temperature data, the corresponding sample category labels, and the sample categories;

[0025] Based on the training error, adjust the preliminary time series combined prediction model to obtain optimal parameters, and use the optimal parameters to optimize the preliminary time series combined prediction model to obtain the trained preliminary time series combined prediction model.

[0026] In a second aspect, the present invention provides a device for predicting cable temperature, including:

[0027] An acquisition module for acquiring the thermal path parameters of the cable to be measured and the cable temperature training samples in the cable database; the cable temperature training samples include historical cable temperature data and corresponding sample category labels;

[0028] A sequence module for calculating the core temperature sequence data of the cable to be measured according to the thermal path parameters;

[0029] A stabilization module for performing a stabilization process on the core temperature sequence data by using an empirical mode decomposition method and an ensemble empirical mode decomposition method to obtain stabilized temperature sequence data;

[0030] A building module for building a time series combined prediction model based on the historical cable temperature data and the corresponding sample category labels;

[0031] A calculation module for inputting the thermal path parameters and the stabilized sequence data into the time series combined prediction model to calculate the real-time temperature prediction result data of the cable to be measured.

[0032] Optionally, the sequence module includes:

[0033] A construction sub-module for constructing a transient thermal path model of the cable body of the cable to be measured corresponding to the thermal path parameters;

[0034] A sequence sub-module for calculating the core temperature sequence data of the cable to be measured according to the transient thermal path model of the cable body.

[0035] Optionally, the stabilization module includes:

[0036] A stabilization sub-module for performing a stabilization process on the core temperature sequence data by using the empirical mode decomposition method to obtain preliminary stabilized temperature sequence data;

[0037] A decomposition sub-module, configured to decompose the preliminarily stabilized temperature sequence data by using the complete ensemble empirical mode decomposition method to obtain the stabilized temperature sequence data.

[0038] Optionally, the establishing module includes:

[0039] An establishing sub-module, configured to establish a preliminary time series combined prediction model corresponding to the historical cable temperature data and the corresponding sample class labels;

[0040] A training sub-module, configured to train the preliminary time series combined prediction model according to the historical cable temperature data and the corresponding sample class labels to obtain a trained preliminary time series combined prediction model;

[0041] A verification sub-module, configured to verify the trained preliminary time series combined prediction model based on the historical cable temperature data and the corresponding sample class labels to obtain the time series combined prediction model.

[0042] Optionally, the training sub-module includes:

[0043] A generating unit, configured to input the cable thermal path parameters and the cable stabilized temperature sequence data in the historical cable temperature data into the preliminary time series combined prediction model to generate corresponding sample classes;

[0044] An error unit, configured to determine a training error according to the cable thermal path parameters and the cable stabilized temperature sequence data in the historical cable temperature data, the corresponding sample class labels, and the sample classes;

[0045] An optimization unit, configured to adjust the preliminary time series combined prediction model based on the training error to obtain optimal parameters, and use the optimal parameters to optimize the preliminary time series combined prediction model to obtain the trained preliminary time series combined prediction model.

[0046] As can be seen from the above technical solutions, the present invention has the following advantages: The present invention provides a method for predicting the temperature of a cable. By obtaining the thermal path parameters of the cable to be measured and the cable temperature training samples in the cable database, the cable temperature training samples include historical cable temperature data and corresponding sample category labels. According to the thermal path parameters, the core temperature sequence data of the cable to be measured is calculated. The empirical mode decomposition method and the complete ensemble empirical mode decomposition method are used to smooth the core temperature sequence data to obtain the smoothed temperature sequence data. Based on the historical cable temperature data and the corresponding sample category labels, a time series combined prediction model is established. The thermal path parameters and the smoothed sequence data are input into the time series combined prediction model, and the real-time temperature prediction result data of the cable to be measured is calculated. Through a method for predicting the temperature of a cable, the technical problem that the existing cable temperature prediction method does not consider the transient process of the cable surface temperature and the cable temperature rise, resulting in inaccurate predicted temperature, is solved, and the prediction accuracy of the cable temperature is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0048] Figure 1 It is a flowchart of the first embodiment of a method for predicting the temperature of a cable according to the present invention;

[0049] Figure 2 It is a flowchart of the second embodiment of a method for predicting the temperature of a cable according to the present invention;

[0050] Figure 3 It is a schematic structural diagram of the transient thermal path model of the cable body in a method for predicting the temperature of a cable according to the present invention;

[0051] Figure 4 It is a simplified schematic structural diagram of the transient thermal path model of the cable body in a method for predicting the temperature of a cable according to the present invention;

[0052] Figure 5 It is a structural block diagram of the time series combined prediction model in a method for predicting the temperature of a cable according to the present invention;

[0053] Figure 6 It is a structural block diagram of an embodiment of a device for predicting the temperature of a cable according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0054] An embodiment of the present invention provides a method and device for predicting the temperature of a cable, which are used to solve the technical problem that the existing cable temperature prediction methods do not consider the transient process of the cable surface temperature and the cable temperature rise, resulting in inaccurate predicted temperature.

[0055] In order to make the invention objectives, features, and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the embodiments described below are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0056] Embodiment 1, please refer to Figure 1 , Figure 1 which is a flowchart of the steps of Embodiment 1 of a method for predicting the temperature of a cable according to the present invention, and includes:

[0057] Step S101, obtain the thermal circuit parameters of the cable to be measured and the cable temperature training samples in the cable database; the cable temperature training samples include historical cable temperature data and corresponding sample category labels;

[0058] Step S102, calculate the core temperature sequence data of the cable to be measured according to the thermal circuit parameters;

[0059] In the embodiment of the present invention, a transient thermal circuit model of the cable body of the cable to be measured corresponding to the thermal circuit parameters is constructed, and according to the transient thermal circuit model of the cable body, the core temperature sequence data of the cable to be measured is calculated.

[0060] Step S103, use the empirical mode decomposition method and the complete ensemble empirical mode decomposition method to perform a stationary processing on the core temperature sequence data to obtain stationary temperature sequence data;

[0061] In the embodiment of the present invention, the empirical mode decomposition method is used to perform a stationary processing on the core temperature sequence data to obtain preliminary stationary temperature sequence data, and the complete ensemble empirical mode decomposition method is used to decompose the preliminary stationary temperature sequence data to obtain the stationary temperature sequence data.

[0062] Step S104, establish a time series combined prediction model based on the historical cable temperature data and the corresponding sample category labels;

[0063] In an embodiment of the present invention, a preliminary time-series combined prediction model corresponding to the historical cable temperature data and the corresponding sample category labels is established. According to the historical cable temperature data and the corresponding sample category labels, the preliminary time-series combined prediction model is trained to obtain a trained preliminary time-series combined prediction model. Based on the historical cable temperature data and the corresponding sample category labels, the trained preliminary time-series combined prediction model is verified to obtain the time-series combined prediction model.

[0064] Step S105: Input the thermal path parameters and the stationary sequence data into the time-series combined prediction model, and calculate the real-time temperature prediction result data of the cable to be measured.

[0065] In a method for predicting cable temperature provided by an embodiment of the present invention, by obtaining the thermal path parameters of the cable to be measured and the cable temperature training samples in the cable database, the cable temperature training samples include historical cable temperature data and corresponding sample category labels. According to the thermal path parameters, the core temperature sequence data of the cable to be measured is calculated. The empirical mode decomposition method and the complete ensemble empirical mode decomposition method are used to perform stationary processing on the core temperature sequence data to obtain stationary temperature sequence data. Based on the historical cable temperature data and the corresponding sample category labels, a time-series combined prediction model is established. The thermal path parameters and the stationary sequence data are input into the time-series combined prediction model, and the real-time temperature prediction result data of the cable to be measured is calculated. Through a method for predicting cable temperature, the technical problem that the existing cable temperature prediction method does not consider the transient process of the cable surface temperature and the cable temperature rise, resulting in inaccurate predicted temperature, is solved, and the prediction accuracy of the cable temperature is improved.

[0066] Embodiment 2: Please refer to Figure 2 , Figure 2 which is a flow chart of the steps of a method for predicting cable temperature of the present invention, including:

[0067] Step S201: Obtain the thermal path parameters of the cable to be measured and the cable temperature training samples in the cable database; the cable temperature training samples include historical cable temperature data and corresponding sample category labels;

[0068] Step S202: Construct a transient thermal path model of the cable body of the cable to be measured corresponding to the thermal path parameters;

[0069] In an embodiment of the present invention, a transient thermal path model of the cable body of the cable to be measured is constructed from the thermal path parameters.

[0070] In specific implementation, please refer to Figure 3 , Figure 3It is a structural schematic diagram of the transient thermal circuit model of the cable body in a cable temperature prediction method of the present invention, wherein T1, T2, and T3 are the thermal resistances of the insulating layer, the inner sheath, and the outer sheath, respectively, Q, W, and θ represent the heat capacity, loss, and temperature, respectively, and the following table c, n, w, i, and a represent the cable conductor, inner sheath, outer sheath, insulating layer, and armor layer, respectively.

[0071] The thermal circuit model is simplified according to the dual relationship between the thermal circuit and the electrical circuit. The equivalent heat capacity and the core conductor loss are proportionally distributed to adjacent temperature nodes according to the IEC60853 standard. Due to the proportional relationship between the armor layer loss and the core conductor loss, the armor layer loss is equivalent to the corresponding thermal resistance and heat capacity parameters, and the heat capacity of the insulation layer and the inner sheath is simplified to an equivalent heat capacity.

[0072] Step S203, calculating the cable core temperature sequence data of the cable to be tested according to the transient thermal circuit model of the cable body;

[0073] In the embodiment of the present invention, the transient thermal circuit model of the cable body is simplified to facilitate the calculation of the cable core temperature sequence data of the cable to be tested.

[0074] In the specific implementation, see Figure 4 , Figure 4 FIG. 1 is a simplified structural schematic diagram of a transient thermal circuit model of a cable body in a cable temperature prediction method of the present invention, wherein T k is the cable thermal resistance, Q k is the cable heat capacity, W c is the cable conductor loss, θ c is the temperature of the cable conductor, θ w is the temperature of the cable outer sheath.

[0075] Figure 4 Medium T k With Q k The definition is as follows:

[0076] T k =1 / 3T1+T2+qT3;

[0077]

[0078] According to the transient response formula, the temperature rise caused by the current in the cable is

[0079]

[0080] In addition, the cable core temperature change caused solely by the cable surface temperature can be calculated based on the simplified structural schematic diagram of the equivalent thermal circuit model. The temperature calculation formula is as follows:

[0081]

[0082] The change in the core temperature caused by both the cable current and the cable surface temperature can be expressed as:

[0083] Δθ(t) = Δθ c (t) + Δθ w (t);

[0084] When calculating the core temperature at time t, according to the principle of calculus, the overall temperature change in the t time period can be obtained. The t time period is divided into β segments. When β approaches infinity, the temperature difference of the cable core can be known as:

[0085]

[0086] Step S204, using the empirical mode decomposition method, perform a stationary processing on the core temperature sequence data to obtain preliminary stationary temperature sequence data;

[0087] In the embodiment of the present invention, the empirical mode decomposition method is used to stationary the core temperature sequence data to obtain preliminary stationary temperature sequence data;

[0088] In a specific implementation, in the field of signal processing, the empirical mode decomposition (EMD) method is usually used to decompose a non - linear or non - stationary time series to achieve the stationary processing of the series. Assuming a non - stationary time series is x(t), the calculation formula after EMD decomposition is specifically:

[0089]

[0090] Among them, IMF j is the j - th intrinsic mode function (IMF) of the decomposition, and T(t) represents the residual amount of the sequence. The EMD decomposition steps are roughly as follows:

[0091] 1) Through the maximum and minimum points of the non - stationary time series x(t), combined with the cubic spline function interpolation method, fit the upper and lower envelope lines e + (t), e - (t), and finally calculate the average envelope line

[0092] 2) Calculate the high - frequency signal IMF must satisfy the condition, ε ∈ [0.2 - 0.3];

[0093] 3) When meets the HSD condition, It is the first IMF decomposed from the sequence and represents the high-frequency part in the sequence. After removing the high-frequency part from the original sequence signal, a new sequence signal is obtained; then steps 1) and 2) are cycled until the remaining IMFs can no longer be decomposed, and the trend term T(t) is obtained.

[0094] Step S205: Use the complete ensemble empirical mode decomposition method to decompose the preliminarily stabilized temperature sequence data to obtain the stabilized temperature sequence data.

[0095] In the embodiment of the present invention, the complete ensemble empirical mode decomposition method is used to decompose the preliminarily stabilized temperature sequence data to obtain the stabilized temperature sequence data.

[0096] In a specific implementation, when the EMD (empirical mode decomposition method) performs stationary processing on a non-stationary sequence, there will be a problem of component aliasing at different time scales. To address this problem, the complete ensemble empirical mode decomposition method with adaptive noise (CEEMDAN) adds Gaussian white noise that satisfies the X~N(0,1) distribution on the basis of EMD decomposition, effectively solving the problem of mode aliasing in the EMD decomposition process.

[0097] Step S206: Establish a preliminary time series combined prediction model corresponding to the historical cable temperature data and the corresponding sample category labels.

[0098] In the embodiment of the present invention, to improve the accuracy of the prediction model, an LSTM-BP model (long short-term memory network and BP neural network model) is established for combined prediction according to the historical cable temperature data and the corresponding sample category labels, and the corresponding preliminary time series combined prediction model is obtained.

[0099] Step S207: Train the preliminary time series combined prediction model according to the historical cable temperature data and the corresponding sample category labels to obtain the trained preliminary time series combined prediction model.

[0100] In an alternative embodiment, training the preliminary time series combined prediction model according to the historical cable temperature data and the corresponding sample category labels to obtain the trained preliminary time series combined prediction model includes:

[0101] Input the cable thermal path parameters and the cable stabilized temperature sequence data in the historical cable temperature data into the preliminary time series combined prediction model to generate the corresponding sample category.

[0102] Determine the training error according to the cable thermal path parameters and the cable stabilized temperature sequence data in the historical cable temperature data, the corresponding sample category labels, and the sample category.

[0103] Based on the training error, adjust the preliminary time series combined prediction model to obtain optimal parameters, and use the optimal parameters to optimize the preliminary time series combined prediction model to obtain the trained preliminary time series combined prediction model.

[0104] In an embodiment of the present invention, input the cable thermal path parameters and the cable stabilized temperature sequence data in the historical cable temperature data into the preliminary time series combined prediction model to generate corresponding sample categories. Determine the training error based on the cable thermal path parameters, the cable stabilized temperature sequence data, the corresponding sample category labels, and the sample categories in the historical cable temperature data. Based on the training error, adjust the preliminary time series combined prediction model to obtain optimal parameters, and use the optimal parameters to optimize the preliminary time series combined prediction model to obtain the trained preliminary time series combined prediction model.

[0105] In a specific implementation, please refer to Figure 5 , Figure 5 is a structural block diagram of a time series combined prediction model in a method for predicting cable temperature according to the present invention. Among them, 501 is the input sequence, 502 is denoising filtering, 503 is CEEMDAN (Complete Ensemble Empirical Mode Decomposition) decomposition, 504 is the training process, 505 is a long short-term memory network model (LSTM model), 506 is a BP neural network model, 507 is a time series combined prediction model, INF is the intrinsic mode function (i.e., sequence data and thermal path parameters), T(t) is the residual quantity, and the LSTM-BP combined prediction model uses LSTM to predict n IMF components after denoising filtering and CEEMDAN decomposition, and at the same time uses a BP neural network to predict the T(t) residual quantity. Finally, integrating the prediction results of the two prediction models is the combined prediction result.

[0106] Step S208: Verify the trained preliminary time series combined prediction model based on the historical cable temperature data and the corresponding sample category labels to obtain a time series combined prediction model;

[0107] Step S209: Input the thermal path parameters and the stabilized sequence data into the time series combined prediction model to calculate and obtain the real-time temperature prediction result data of the cable to be measured;

[0108] In an embodiment of the present invention, input the thermal path parameters and the stabilized sequence data into the time series combined prediction model to obtain the real-time temperature prediction result data of the cable to be measured.

[0109] In a specific implementation, establish input sequence data by using model parameters related to cable temperature, including {α1, α2,..., α at each time p}p characteristic quantities are used to learn the relationship between them and temperature through a combined prediction model, so as to realize real-time prediction of cable temperature. The performance of the model is described by three evaluation indexes: mean square error (MSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). The evaluation results are shown in the following table:

[0110]

[0111] It can be seen from the above table that the overall error of the time series combined prediction model of the present invention is small and the accuracy is high, which proves the correctness of the prediction method of the cable temperature of the present invention.

[0112] In a method for predicting cable temperature provided by an embodiment of the present invention, by obtaining the thermal path parameters of the cable to be measured and the cable temperature training samples in the cable database, the cable temperature training samples include historical cable temperature data and corresponding sample category labels. According to the thermal path parameters, the core temperature sequence data of the cable to be measured is calculated. The empirical mode decomposition method and the complete ensemble empirical mode decomposition method are used to smooth the core temperature sequence data to obtain smoothed temperature sequence data. Based on the historical cable temperature data and the corresponding sample category labels, a time series combined prediction model is established. The thermal path parameters and the smoothed sequence data are input into the time series combined prediction model, and the real-time temperature prediction result data of the cable to be measured is calculated. Through a method for predicting cable temperature, the technical problem that the existing cable temperature prediction method does not consider the transient process of the cable surface temperature and the cable temperature rise, resulting in inaccurate predicted temperature, is solved, and the prediction accuracy of the cable temperature is improved.

[0113] Please refer to Figure 6 , Figure 6 which is a structural block diagram of an embodiment of a device for predicting cable temperature according to the present invention, including:

[0114] An acquisition module 601, configured to acquire the thermal path parameters of the cable to be measured and the cable temperature training samples in the cable database; the cable temperature training samples include historical cable temperature data and corresponding sample category labels;

[0115] A sequence module 602, configured to calculate the core temperature sequence data of the cable to be measured according to the thermal path parameters;

[0116] A smoothing module 603, configured to smooth the core temperature sequence data by using the empirical mode decomposition method and the complete ensemble empirical mode decomposition method to obtain smoothed temperature sequence data;

[0117] A building module 604, configured to build a time series combined prediction model based on the historical cable temperature data and the corresponding sample category labels;

[0118] A calculation module 605, configured to input the thermal path parameters and the smoothed sequence data into the time series combined prediction model, and calculate the real-time temperature prediction result data of the cable to be measured.

[0119] In an alternative embodiment, the sequence module 602 includes:

[0120] A construction sub-module, configured to construct a transient thermal path model of the cable body of the cable to be measured corresponding to the thermal path parameters;

[0121] A sequence sub-module, configured to calculate the core temperature sequence data of the cable to be measured according to the transient thermal path model of the cable body.

[0122] In an alternative embodiment, the smoothing module 603 includes:

[0123] A smoothing sub-module, configured to perform smoothing processing on the core temperature sequence data by using the empirical mode decomposition method to obtain preliminary smoothed temperature sequence data;

[0124] A decomposition sub-module, configured to decompose the preliminary smoothed temperature sequence data by using the complete ensemble empirical mode decomposition method to obtain the smoothed temperature sequence data.

[0125] In an alternative embodiment, the establishment module 604 includes:

[0126] An establishment sub-module, configured to establish a preliminary time series combined prediction model corresponding to the historical cable temperature data and the corresponding sample class labels;

[0127] A training sub-module, configured to train the preliminary time series combined prediction model according to the historical cable temperature data and the corresponding sample class labels to obtain a trained preliminary time series combined prediction model;

[0128] A verification sub-module, configured to verify the trained preliminary time series combined prediction model based on the historical cable temperature data and the corresponding sample class labels to obtain the time series combined prediction model.

[0129] In an alternative embodiment, the training sub-module includes:

[0130] A generation unit, configured to input the cable thermal path parameters and the cable smoothed temperature sequence data in the historical cable temperature data into the preliminary time series combined prediction model to generate corresponding sample classes;

[0131] An error unit, configured to determine a training error according to the cable thermal path parameters and the cable smoothed temperature sequence data in the historical cable temperature data, the corresponding sample class labels, and the sample classes;

[0132] An optimization unit, configured to adjust the preliminary time series combination prediction model based on the training error to obtain optimal parameters, and use the optimal parameters to optimize the preliminary time series combination prediction model to obtain the trained preliminary time series combination prediction model.

[0133] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the foregoing method embodiments and will not be described herein again.

[0134] In several embodiments provided in the present application, it should be understood that the methods and devices disclosed by the present invention can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For example, 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 displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be in an electrical, mechanical, or other form.

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

[0136] In addition, the functional units in each embodiment of the present invention can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0137] If the 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 storage medium. Based on such an 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. The computer software product is stored in a readable storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned readable storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0138] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of various embodiments of the present invention.

Claims

1. A method for predicting the temperature of a cable, characterized in that, Including: Obtain the thermal path parameters of the cable to be measured and the cable temperature training samples in the cable database; The cable temperature training samples include historical cable temperature data and corresponding sample class labels; According to the thermal path parameters, calculate the core temperature sequence data of the cable to be measured; Adopt the empirical mode decomposition method and the complete ensemble empirical mode decomposition method to perform stationary processing on the core temperature sequence data to obtain stationary temperature sequence data; Based on the historical cable temperature data and the corresponding sample class labels, establish a time series combined prediction model; Input the thermal path parameters and the stationary sequence data into the time series combined prediction model, and calculate the real-time temperature prediction result data of the cable to be measured; According to the thermal path parameters, calculate the core temperature sequence data of the cable to be measured, including: Construct a transient thermal path model of the cable body of the cable to be measured corresponding to the thermal path parameters; According to the transient thermal path model of the cable body, calculate the core temperature sequence data of the cable to be measured; Adopt the empirical mode decomposition method and the complete ensemble empirical mode decomposition method to perform stationary processing on the core temperature sequence data to obtain stationary temperature sequence data, including: Adopt the empirical mode decomposition method to perform stationary processing on the core temperature sequence data to obtain preliminary stationary temperature sequence data; Use the complete ensemble empirical mode decomposition method to decompose the preliminary stationary temperature sequence data to obtain the stationary temperature sequence data.

2. The prediction method of cable temperature according to claim 1, wherein Based on the historical cable temperature data and the corresponding sample class labels, establish a time series combined prediction model, including: Establish a preliminary time series combined prediction model corresponding to the historical cable temperature data and the corresponding sample class labels; According to the historical cable temperature data and the corresponding sample class labels, train the preliminary time series combined prediction model to obtain the trained preliminary time series combined prediction model; Based on the historical cable temperature data and the corresponding sample class labels, verify the trained preliminary time series combined prediction model to obtain the time series combined prediction model.

3. The prediction method of cable temperature according to claim 2, characterized in that, According to the historical cable temperature data and the corresponding sample class labels, train the preliminary time series combined prediction model to obtain the trained preliminary time series combined prediction model, including: Input the cable thermal path parameters and cable stationary temperature sequence data in the historical cable temperature data into the preliminary time series combined prediction model to generate corresponding sample classes; According to the cable thermal path parameters and cable stationary temperature sequence data in the historical cable temperature data, the corresponding sample class labels and the sample classes, determine the training error; Based on the training error, adjust the preliminary time series combined prediction model to obtain the optimal parameters, and use the optimal parameters to optimize the preliminary time series combined prediction model to obtain the trained preliminary time series combined prediction model.

4. A prediction device for cable temperature, characterized in that, Including: An acquisition module for acquiring the thermal path parameters of the cable to be measured and the cable temperature training samples in the cable database; The cable temperature training samples include historical cable temperature data and corresponding sample class labels; A sequence module, configured to calculate the core temperature sequence data of the cable to be measured according to the thermal path parameters; A smoothing module, configured to perform smoothing processing on the core temperature sequence data by using the empirical mode decomposition method and the complete ensemble empirical mode decomposition method to obtain smoothed temperature sequence data; A model building module, configured to build a time series combined prediction model based on the historical cable temperature data and the corresponding sample class labels; A calculation module, configured to input the thermal path parameters and the smoothed sequence data into the time series combined prediction model to calculate the real-time temperature prediction result data of the cable to be measured; The sequence module includes: A construction sub-module, configured to construct a transient thermal path model of the cable body of the cable to be measured corresponding to the thermal path parameters; A sequence sub-module, configured to calculate the core temperature sequence data of the cable to be measured according to the transient thermal path model of the cable body; The smoothing module includes: A smoothing sub-module, configured to perform smoothing processing on the core temperature sequence data by using the empirical mode decomposition method to obtain preliminary smoothed temperature sequence data; A decomposition sub-module, configured to decompose the preliminary smoothed temperature sequence data by using the complete ensemble empirical mode decomposition method to obtain the smoothed temperature sequence data.

5. The predicting device for cable temperature according to claim 4, wherein The model building module includes: A building sub-module, configured to build a preliminary time series combined prediction model corresponding to the historical cable temperature data and the corresponding sample class labels; A training sub-module, configured to train the preliminary time series combined prediction model according to the historical cable temperature data and the corresponding sample class labels to obtain a trained preliminary time series combined prediction model; A verification sub-module, configured to verify the trained preliminary time series combined prediction model based on the historical cable temperature data and the corresponding sample class labels to obtain the time series combined prediction model.

6. The prediction device for cable temperature according to claim 5, wherein The training sub-module includes: A generation unit, configured to input the cable thermal path parameters and the cable smoothed temperature sequence data in the historical cable temperature data into the preliminary time series combined prediction model to generate corresponding sample classes; An error unit, configured to determine a training error according to the cable thermal path parameters and the cable smoothed temperature sequence data in the historical cable temperature data, the corresponding sample class labels, and the sample classes; An optimization unit, configured to adjust the preliminary time series combined prediction model based on the training error to obtain optimal parameters, and use the optimal parameters to optimize the preliminary time series combined prediction model to obtain the trained preliminary time series combined prediction model.

Images