Method and device for evaluating a thermal fault of a cable

Abstract

The application discloses a kind of evaluation method and device of cable thermal fault, its method includes: obtaining the basic data and historical temperature measurement data of to-be-measured cable, according to the preset environmental factor structure condition and preset boundary condition, the 3D model of cable corresponding to basic data is constructed, based on historical temperature measurement data, whether the error of 3D model and actual cable is greater than preset threshold value is judged, if yes, then adjust boundary condition, return to execute the model construction step, if no, then the attribute data of 3D model is calculated by orthogonal control method, based on attribute data, in combination with preset support vector regression machine clustering model, the evaluation result data of to-be-measured cable thermal fault is obtained.There is advantage in solving the technical problem that existing cable thermal fault monitoring method cannot reflect the change situation of contact resistance, and the evaluation efficiency of cable thermal fault is improved.

Description

Technical Field

[0001] This invention relates to the technical field of cable overheating faults, and in particular to a method and apparatus for evaluating cable thermal faults. Background Technology

[0002] Power cables are a crucial component of primary equipment in power systems. However, poor contact at cable joints can lead to overheating, which in turn increases contact resistance, creating a vicious cycle. This cycle accelerates insulation thermal aging and reduces material mechanical strength, while also causing joint seal failure, allowing moisture intrusion and partial discharge. The combined effect of these factors frequently results in insulation breakdown. Since the conductor is encased inside the cable joint, and the degree of heating is closely related to the current magnitude, cable joints exhibit a degree of concealment and latency, leaving blind spots in traditional monitoring methods. Therefore, in-depth research into methods for sensing the internal hotspot heating state of cable joints, real-time detection of joint hotspot temperatures, and assessment of conductor contact conditions are essential for early warning of overheating faults and have significant engineering application value.

[0003] Three-core cables, because they can be considered to contain three heat sources, have their thermal characteristics coupled together, and temperature sensing based on surface features often suffers from significant accuracy loss.

[0004] Existing technologies mainly suffer from the following two shortcomings: 1) Most existing power cable thermal fault monitoring technologies based on surface temperature measurement cannot establish a direct link between the surface temperature of the power cable and the internal hot spot temperature; 2) Simple temperature field-based simulation calculations can only reflect the fault-temperature relationship under a single operating condition and have no practical industrial value. If industrial applications are required, multiple fault simulations need to be performed based on the simulation model. Most importantly, regression algorithms must be used. If the results are obtained by simply setting up defects, no mapping relationship is established between temperature and fault in the results. At the same time, the above algorithms cannot reflect the changes in contact resistance. Contact resistance is the direct determining factor of thermal faults. Only by constructing a mapping model between contact resistance and surface temperature or surface temperature rise can actual cable-cable joint fault diagnosis be performed in industrial practice.

[0005] Therefore, in order to improve the evaluation efficiency of cable thermal faults and solve the technical problem that existing cable thermal fault monitoring methods cannot reflect changes in contact resistance, it is urgent to construct an evaluation method for cable thermal faults. Summary of the Invention

[0006] This invention provides a method and apparatus for evaluating cable thermal faults, which solves the technical problem that existing cable thermal fault monitoring methods cannot reflect changes in contact resistance.

[0007] In a first aspect, the present invention provides a method for evaluating cable thermal faults, comprising:

[0008] Step S1: Obtain the basic data of the cable under test and the historical temperature measurement data of the cable database;

[0009] Step S2: Construct a 3D model of the cable corresponding to the basic data based on the preset environmental factors, structural conditions, and boundary conditions.

[0010] Step S3: Based on the historical temperature measurement data, determine whether the error between the cable 3D model and the actual cable is greater than a preset threshold; if yes, adjust the preset boundary conditions and return to step S2; if no, proceed to step S4.

[0011] Step S4: The attribute data of the cable 3D model is calculated using an orthogonal control method; the attribute data includes contact resistance value, load rate, surface temperature values, and internal hot spot temperature.

[0012] Step S5: Based on the contact resistance value, the load rate, the surface temperature values, and the internal hot spot temperature, and combined with a preset support vector regression clustering model, calculate the thermal fault evaluation result data of the cable under test.

[0013] Optionally, step S3 includes:

[0014] Step S31: Under the condition of stable heat source, set the point in the 3D model of the cable with the most obvious surface temperature increase as the temperature measurement position.

[0015] Step S32: Extract historical temperature measurement data corresponding to the temperature measurement location from the historical temperature measurement data;

[0016] Step S33: Determine whether the error between the temperature at the temperature measurement location and the corresponding historical temperature measurement data is greater than the preset threshold; if yes, adjust the preset boundary conditions and return to step S2; if no, proceed to step S4.

[0017] Optionally, step S33 includes:

[0018] Step S331: Calculate the difference between the temperature at the temperature measurement location and the corresponding historical temperature measurement data;

[0019] Step S332: Determine whether the difference is greater than the preset threshold; if yes, adjust the preset boundary conditions and return to step S2; if no, proceed to step S4.

[0020] Optionally, step S5 includes:

[0021] Step S51: According to the regularization principle, the preset support vector regression machine clustering model is constrained to obtain a hard-margin support vector regression machine clustering model.

[0022] Step S52: Based on preset slack variables and preset penalty coefficients, optimize the hard-margin support vector regression machine clustering model to obtain the optimal support vector regression machine clustering model;

[0023] Step S53: Input the contact resistance value, the load rate, the surface temperature values ​​and the internal hot spot temperature into the optimal support vector regression clustering model to calculate the thermal fault evaluation result data of the cable under test.

[0024] Optionally, step S53 includes:

[0025] Step S531: Input the contact resistance value, the load rate, the surface temperature values ​​and the internal hot spot temperature into the optimal support vector regression machine clustering model to calculate the relationship data between surface temperature and contact resistance of the cable under test.

[0026] Step S532: Based on the relationship data, generate thermal fault evaluation result data for the cable under test.

[0027] Secondly, the present invention provides an evaluation device for cable thermal faults, comprising:

[0028] The acquisition module is used to acquire basic data of the cable under test and historical temperature measurement data from the cable database;

[0029] The construction module is used to construct a 3D model of the cable corresponding to the basic data based on preset environmental factors, structural conditions, and preset boundary conditions.

[0030] The judgment module is used to determine, based on the historical temperature measurement data, whether the error between the cable 3D model and the actual cable is greater than a preset threshold; if so, the preset boundary conditions are adjusted and the process returns to the execution construction module; if not, the calculation module is executed.

[0031] The calculation module is used to calculate the attribute data of the cable 3D model through an orthogonal control method; the attribute data includes contact resistance value, load rate, surface temperature value and internal hot spot temperature;

[0032] The evaluation module is used to calculate the thermal fault evaluation result data of the cable under test based on the contact resistance value, the load rate, the surface temperature values ​​and the internal hot spot temperature, combined with a preset support vector regression clustering model.

[0033] Optionally, the determination module includes:

[0034] The submodule is configured to set the point in the 3D model of the cable where the surface temperature rises most significantly as the temperature measurement location under stable heat source conditions.

[0035] An extraction submodule is used to extract historical temperature measurement data corresponding to the temperature measurement location from the historical temperature measurement data.

[0036] The judgment submodule is used to determine whether the error between the temperature at the temperature measurement location and the corresponding historical temperature measurement data is greater than the preset threshold; if yes, the preset boundary conditions are adjusted and the execution of the construction module is returned; if no, the calculation module is executed.

[0037] Optionally, the determination submodule includes:

[0038] The difference unit is used to calculate the difference between the temperature at the temperature measurement location and the corresponding historical temperature measurement data;

[0039] The judgment unit is used to determine whether the difference is greater than the preset threshold; if so, the preset boundary conditions are adjusted and the execution of the construction module is returned; if not, the calculation module is executed.

[0040] Optionally, the evaluation module includes:

[0041] The constraint submodule is used to constrain the preset support vector regression machine clustering model according to the regularization principle to obtain a hard-margin support vector regression machine clustering model.

[0042] The optimization submodule is used to optimize the hard-margin support vector regression machine clustering model based on preset slack variables and preset penalty coefficients, so as to obtain the optimal support vector regression machine clustering model.

[0043] The evaluation submodule is used to input the contact resistance value, the load rate, the surface temperature values ​​and the internal hot spot temperature into the optimal support vector regression machine clustering model to calculate the thermal fault evaluation result data of the cable under test.

[0044] Optionally, the evaluation submodule includes:

[0045] The calculation unit is used to input the contact resistance value, the load rate, the surface temperature values ​​and the internal hot spot temperature into the optimal support vector regression machine clustering model to calculate the relationship data between the surface temperature and the contact resistance of the cable under test.

[0046] The generation unit is used to generate thermal fault evaluation result data of the cable under test based on the relational data.

[0047] As can be seen from the above technical solution, the present invention has the following advantages: The present invention provides a method for evaluating cable thermal faults. Step S1 involves acquiring basic data of the cable under test and historical temperature measurement data from a cable database. Step S2 involves constructing a 3D model of the cable corresponding to the basic data based on preset environmental factors, structural conditions, and boundary conditions. Step S3 involves determining, based on the historical temperature measurement data, whether the error between the 3D model and the actual cable exceeds a preset threshold. If so, the preset boundary conditions are adjusted, and step S2 is returned to execution. If not, step S4 is executed. Step S4 involves calculating the attribute data of the 3D model of the cable using an orthogonal control method. The attribute data includes contact resistance value, load rate, surface temperature values, and internal hot spot temperature. Step S5 involves calculating the thermal fault evaluation result data of the cable under test based on the contact resistance value, load rate, surface temperature values, and internal hot spot temperature, combined with a preset support vector regression clustering model. This method for evaluating cable thermal faults solves the technical problem that existing cable thermal fault monitoring methods cannot reflect changes in contact resistance, thus improving the evaluation efficiency of cable thermal faults. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 This is a flowchart illustrating the steps of an embodiment of the cable thermal fault evaluation method of the present invention.

[0050] Figure 2 This is a flowchart illustrating the second embodiment of the cable thermal fault evaluation method of the present invention.

[0051] Figure 3 This is a structural block diagram of an embodiment of a cable thermal fault evaluation device according to the present invention. Detailed Implementation

[0052] This invention provides a method and apparatus for evaluating cable thermal faults, which addresses the technical problem that existing cable thermal fault monitoring methods cannot reflect changes in contact resistance.

[0053] To make the objectives, features, and advantages of this invention more apparent and understandable, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described below are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0054] Example 1, please refer to Figure 1 , Figure 1 This is a flowchart illustrating the steps of an embodiment of the cable thermal fault evaluation method of the present invention, including:

[0055] Step S101: Obtain the basic data of the cable under test and the historical temperature measurement data of the cable database;

[0056] Step S102: Construct a 3D model of the cable corresponding to the basic data based on preset environmental factors, structural conditions, and preset boundary conditions.

[0057] Step S103: Based on the historical temperature measurement data, determine whether the error between the cable 3D model and the actual cable is greater than a preset threshold; if yes, adjust the preset boundary conditions and return to step S102; if no, proceed to step S104.

[0058] It should be noted that the historical temperature measurement data corresponding to the temperature measurement location refers to the temperature of the same hot spot location obtained from cables of the same type, material and heat source as the cable under test.

[0059] In this embodiment of the invention, under the condition of stable heat source, the point in the 3D model of the cable with the most obvious surface temperature increase is set as the temperature measurement position. Historical temperature measurement data corresponding to the temperature measurement position is extracted from the historical temperature measurement data. It is determined whether the error between the temperature at the temperature measurement position and the corresponding historical temperature measurement data is greater than the preset threshold. If yes, the preset boundary conditions are adjusted and the process returns to step S102. If no, step S104 is executed.

[0060] Step S104: Attribute data of the cable 3D model is calculated using an orthogonal control method; the attribute data includes contact resistance value, load rate, surface temperature values, and internal hot spot temperature.

[0061] Step S105: Based on the contact resistance value, the load rate, the surface temperature values ​​and the internal hot spot temperature, and combined with the preset support vector regression clustering model, calculate the thermal fault evaluation result data of the cable under test.

[0062] In this embodiment of the invention, the preset support vector regression machine clustering model is constrained according to the regularization principle to obtain a hard-interval support vector regression machine clustering model. Based on preset slack variables and preset penalty coefficients, the hard-interval support vector regression machine clustering model is optimized to obtain the optimal support vector regression machine clustering model. The contact resistance value, the load rate, the surface temperature values ​​and the internal hot spot temperature are input into the optimal support vector regression machine clustering model to calculate the thermal fault evaluation result data of the cable under test.

[0063] The cable thermal fault evaluation method provided in this embodiment of the invention includes the following steps: Step S1, acquiring basic data of the cable under test and historical temperature measurement data from a cable database; Step S2, constructing a 3D model of the cable corresponding to the basic data based on preset environmental factors, structural conditions, and boundary conditions; Step S3, determining whether the error between the 3D model and the actual cable exceeds a preset threshold based on the historical temperature measurement data; if so, adjusting the preset boundary conditions and returning to Step S2; otherwise, proceeding to Step S4; Step S4, calculating the attribute data of the 3D model of the cable using an orthogonal control method, including contact resistance value, load rate, surface temperature values, and internal hot spot temperature; and Step S5, calculating the thermal fault evaluation result data of the cable under test based on the contact resistance value, load rate, surface temperature values, and internal hot spot temperature, combined with a preset support vector regression clustering model. This cable thermal fault evaluation method solves the technical problem that existing cable thermal fault monitoring methods cannot reflect changes in contact resistance, thus improving the evaluation efficiency of cable thermal faults.

[0064] Example 2, please refer to Figure 2 , Figure 2 The flowchart of a cable thermal fault evaluation method according to the present invention includes:

[0065] Step S201: Obtain the basic data of the cable under test and the historical temperature measurement data of the cable database;

[0066] Step S202: Construct a 3D model of the cable corresponding to the basic data based on preset environmental factors, structural conditions, and preset boundary conditions.

[0067] In this embodiment of the invention, a corresponding 3D model of the cable is constructed based on the basic data of the cable under test, preset environmental factors and structural conditions, and preset boundary conditions.

[0068] In the specific implementation, the thermal boundary conditions, thermal expansion coefficient, thermal conductivity coefficient, heat flux density, and convective heat transfer coefficient of the cable joint and the surrounding environmental factors in the cable trench are set. The software's built-in structure discretization method is used to divide the model structure to be calculated into an appropriate mesh. The mesh construction is realized by the mesh generation function of commercial finite element simulation software. The boundary conditions are set by commercial finite element simulation software. Based on the basic data of the cable under test, the environmental factor structural conditions, and the boundary conditions, the structural model of the power cable / joint is constructed using commercial modeling software such as SolidWorks.

[0069] Step S203: Under the condition of stable heat source, set the point in the 3D model of the cable with the most obvious surface temperature increase as the temperature measurement position.

[0070] In this embodiment of the invention, based on the simulation results, k points on the surface of the power cable with the most significant temperature rise under stable heat source conditions are selected as temperature measurement points. This is because the temperature values ​​obtained at the temperature measurement points with the most significant temperature rise have the highest signal-to-noise ratio, which can maximize the accuracy of the data.

[0071] Step S204: Extract historical temperature measurement data corresponding to the temperature measurement location from the historical temperature measurement data;

[0072] It should be noted that the historical temperature measurement data corresponding to the temperature measurement location refers to the temperature of the same hot spot location obtained from cables of the same type, material and heat source as the cable under test.

[0073] In this embodiment of the invention, historical temperature measurement data corresponding to the temperature measurement location is extracted from the historical temperature measurement data. The historical temperature measurement data corresponding to the temperature measurement location refers to the temperature of the same hot spot location obtained from a cable of the same type, material and heat source as the cable under test.

[0074] Step S205: Determine whether the error between the temperature at the temperature measurement location and the corresponding historical temperature measurement data is greater than the preset threshold; if yes, adjust the preset boundary conditions and return to step S202; if no, proceed to step S206.

[0075] In an optional embodiment, step S205 includes:

[0076] Step S2051: Calculate the difference between the temperature at the temperature measurement location and the corresponding historical temperature measurement data;

[0077] Step S2052: Determine whether the difference is greater than the preset threshold; if yes, adjust the preset boundary conditions and return to step S202; if no, proceed to step S206.

[0078] In this embodiment of the invention, the difference between the temperature at the temperature measurement location and the corresponding historical temperature measurement data is calculated, and it is determined whether the difference is greater than the preset threshold. If so, the preset boundary conditions are adjusted, and the process returns to step S202. If not, step S206 is executed.

[0079] In the specific implementation, the same cable as the simulation model, the same heat source as the simulation, and the same historical temperature measurement data as the temperature measurement points selected in the above steps are obtained. The difference between the data and the simulation results is calculated, and error analysis is performed. If the error is less than or equal to a preset threshold, it matches the simulation results within the allowable error range, and step S206 is performed. If the error is greater than the preset threshold, it does not match the simulation results within the allowable error range, the boundary condition settings are adjusted, and the process returns to execute S202 until a match is achieved.

[0080] Step S206: The attribute data of the cable 3D model is calculated using an orthogonal control method; the attribute data includes contact resistance value, load rate, surface temperature values, and internal hot spot temperature.

[0081] In this embodiment of the invention, the contact resistance value, load rate, surface temperature values ​​and internal hot spot temperature of the cable 3D model are calculated by an orthogonal control method. The above data are the attribute data of the cable 3D model.

[0082] In practical implementation, calculating the control variables for different operating conditions requires a large amount of computation. To reduce this computational burden, orthogonal control is adopted. For example, this involves calculating the control variables for two contact resistors (R1, R2) and the load factor L. r The following table shows the configuration:

[0083]

[0084]

[0085] Among them, L rx x = 1, 2, 3… represents different load rates, R 1y y = 1, 2, 3… represents different values ​​of R1, R 2z z = 1, 2, 3… represents R z Different values ​​of L rx R 1y R 2z It is a state combination that includes the contact resistance value, load rate setting, and the obtained surface temperature measurement point temperature and internal hot spot temperature.

[0086] Step S207: According to the regularization principle, the preset support vector regression machine clustering model is constrained to obtain a hard-margin support vector regression machine clustering model.

[0087] In this embodiment of the invention, the preset support vector regression machine clustering model is constrained to obtain a hard-margin support vector regression machine clustering model.

[0088] In practical implementation, traditional regression methods calculate different errors for each sample point. The Support Vector Regression (SVR) clustering model, by providing a positive number ε and ensuring that each sample satisfies the following formula, has the following pre-defined SVR clustering model:

[0089] |y i -f(x i )|≤ε, i=1, 2, 3...n;

[0090] Where ε is a positive number, ω is a constant, x is the load factor, y is the surface temperature, and f(x) is the contact resistance.

[0091] Under the interval ε, the hyperplane f(x) regresses y without loss. At this time, all samples fall between the two hyperplanes f(x)=ωT·x+b+ε and f(x)=ωT·x+b-ε. The support vectors fall on the hyperplane, so it has a strong generalization ability.

[0092] Based on the principle of regularization, in order to limit overfitting, ω is constrained, resulting in the basic form of SVR, the hard-margin form. The hard-margin form of the support vector regression clustering model is as follows:

[0093]

[0094] st|y i -(ωT·x i +b)|≤ε;

[0095] Where ε is a positive number, ω is a constant, x is the load factor, y is the surface temperature, and f(x) is the contact resistance.

[0096] Step S208: Based on preset slack variables and preset penalty coefficients, optimize the hard-margin support vector regression machine clustering model to obtain the optimal support vector regression machine clustering model;

[0097] In this embodiment of the invention, the hard-margin support vector regression machine clustering model is optimized by combining preset slack variables and preset penalty coefficients to obtain the optimal support vector regression machine clustering model.

[0098] In practical implementation, to prevent overfitting, a portion of the samples are allowed to exceed the constraints. Slack variables and a penalty coefficient C are introduced to control the slack variables and limit the number of erroneous samples, thereby transforming the original optimization problem into a soft-margin form. The optimal hyperplane obtained at this time is called the generalized hyperplane. Obviously, when the penalty coefficient C is infinite, the soft-margin form is consistent with the hard-margin form, and the optimal support vector regression machine clustering model is obtained.

[0099] The optimal support vector regression machine clustering model is specifically as follows:

[0100]

[0101]

[0102] Where ε is a positive number, ω is a constant, x is the load factor, y is the surface temperature, and f(x) is the contact resistance ξ. i , This is the loss function.

[0103] Step S209: Input the contact resistance value, the load rate, the surface temperature values ​​and the internal hot spot temperature into the optimal support vector regression machine clustering model to calculate the thermal fault evaluation result data of the cable under test;

[0104] In an optional embodiment, step S209 includes:

[0105] Step S2091: Input the contact resistance value, the load rate, the surface temperature values ​​and the internal hot spot temperature into the optimal support vector regression machine clustering model to calculate the relationship data between surface temperature and contact resistance of the cable under test.

[0106] Step S2092: Based on the relationship data, generate thermal fault evaluation result data for the cable under test.

[0107] In this embodiment of the invention, the contact resistance value, the load rate, the surface temperature values, and the internal hot spot temperature are input into the optimal support vector regression machine clustering model using methods such as the Lagrange method to calculate the relationship data between the surface temperature and the contact resistance of the cable under test. Based on the relationship data, thermal fault evaluation result data of the cable under test is generated.

[0108] The cable thermal fault evaluation method provided in this embodiment of the invention includes the following steps: Step S1, acquiring basic data of the cable under test and historical temperature measurement data from a cable database; Step S2, constructing a 3D model of the cable corresponding to the basic data based on preset environmental factors, structural conditions, and boundary conditions; Step S3, determining whether the error between the 3D model and the actual cable exceeds a preset threshold based on the historical temperature measurement data; if so, adjusting the preset boundary conditions and returning to Step S2; otherwise, proceeding to Step S4; Step S4, calculating the attribute data of the 3D model of the cable using an orthogonal control method, including contact resistance value, load rate, surface temperature values, and internal hot spot temperature; and Step S5, calculating the thermal fault evaluation result data of the cable under test based on the contact resistance value, load rate, surface temperature values, and internal hot spot temperature, combined with a preset support vector regression clustering model. This cable thermal fault evaluation method solves the technical problem that existing cable thermal fault monitoring methods cannot reflect changes in contact resistance, thus improving the evaluation efficiency of cable thermal faults.

[0109] Please see Figure 3 , Figure 3 This is a structural block diagram of an embodiment of a cable thermal fault evaluation device according to the present invention, comprising:

[0110] The acquisition module 301 is used to acquire basic data of the cable under test and historical temperature measurement data from the cable database;

[0111] The construction module 302 is used to construct a 3D model of the cable corresponding to the basic data based on preset environmental factors, structural conditions, and preset boundary conditions.

[0112] The judgment module 303 is used to determine, based on the historical temperature measurement data, whether the error between the cable 3D model and the actual cable is greater than a preset threshold; if so, the preset boundary conditions are adjusted and the execution of the construction module is returned; if not, the calculation module is executed.

[0113] The calculation module 304 is used to calculate the attribute data of the cable 3D model through an orthogonal control method; the attribute data includes contact resistance value, load rate, surface temperature value and internal hot spot temperature;

[0114] The evaluation module 305 is used to calculate the thermal fault evaluation result data of the cable under test based on the contact resistance value, the load rate, the surface temperature values ​​and the internal hot spot temperature, combined with a preset support vector regression clustering model.

[0115] In an optional embodiment, the determining module 303 includes:

[0116] The submodule is configured to set the point in the 3D model of the cable where the surface temperature rises most significantly as the temperature measurement location under stable heat source conditions.

[0117] An extraction submodule is used to extract historical temperature measurement data corresponding to the temperature measurement location from the historical temperature measurement data.

[0118] The judgment submodule is used to determine whether the error between the temperature at the temperature measurement location and the corresponding historical temperature measurement data is greater than the preset threshold; if yes, the preset boundary conditions are adjusted and the execution of the construction module is returned; if no, the calculation module is executed.

[0119] In an optional embodiment, the determination submodule includes:

[0120] The difference unit is used to calculate the difference between the temperature at the temperature measurement location and the corresponding historical temperature measurement data;

[0121] The judgment unit is used to determine whether the difference is greater than the preset threshold; if so, the preset boundary conditions are adjusted and the execution of the construction module is returned; if not, the calculation module is executed.

[0122] In an optional embodiment, the evaluation module 305 includes:

[0123] The constraint submodule is used to constrain the preset support vector regression machine clustering model according to the regularization principle to obtain a hard-margin support vector regression machine clustering model.

[0124] The optimization submodule is used to optimize the hard-margin support vector regression machine clustering model based on preset slack variables and preset penalty coefficients, so as to obtain the optimal support vector regression machine clustering model.

[0125] The evaluation submodule is used to input the contact resistance value, the load rate, the surface temperature values ​​and the internal hot spot temperature into the optimal support vector regression machine clustering model to calculate the thermal fault evaluation result data of the cable under test.

[0126] In an optional embodiment, the evaluation submodule includes:

[0127] The calculation unit is used to input the contact resistance value, the load rate, the surface temperature values ​​and the internal hot spot temperature into the optimal support vector regression machine clustering model to calculate the relationship data between the surface temperature and the contact resistance of the cable under test.

[0128] The generation unit is used to generate thermal fault evaluation result data of the cable under test based on the relational data.

[0129] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0130] In the several embodiments provided in this application, it should be understood that the methods and apparatus disclosed in this invention can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between devices or units, and may be electrical, mechanical, or other forms.

[0131] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0132] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0133] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a readable storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned readable storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0134] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for evaluating cable thermal faults, characterized in that, include: Step S1: Obtain the basic data of the cable under test and the historical temperature measurement data of the cable database; Step S2: Construct a 3D model of the cable corresponding to the basic data based on the preset environmental factors, structural conditions, and boundary conditions. Step S3: Based on the historical temperature measurement data, determine whether the error between the cable 3D model and the actual cable is greater than a preset threshold. If yes, adjust the preset boundary conditions and return to step S2; if no, proceed to step S4. Step S4: The attribute data of the cable 3D model is calculated using an orthogonal control method; the attribute data includes contact resistance value, load rate, surface temperature values, and internal hot spot temperature. Step S5: Based on the contact resistance value, the load rate, the surface temperature values ​​and the internal hot spot temperature, and combined with the preset support vector regression clustering model, calculate the thermal fault evaluation result data of the cable under test. Step S5 includes: Step S51: According to the regularization principle, the preset support vector regression machine clustering model is constrained to obtain a hard-margin support vector regression machine clustering model. Step S52: Based on preset slack variables and preset penalty coefficients, optimize the hard-margin support vector regression machine clustering model to obtain the optimal support vector regression machine clustering model; Step S53: Input the contact resistance value, the load rate, the surface temperature values ​​and the internal hot spot temperature into the optimal support vector regression machine clustering model to calculate the thermal fault evaluation result data of the cable under test; Step S53 includes: Step S531: Input the contact resistance value, the load rate, the surface temperature values ​​and the internal hot spot temperature into the optimal support vector regression machine clustering model to calculate the relationship data between surface temperature and contact resistance of the cable under test. Step S532: Based on the relationship data, generate thermal fault evaluation result data for the cable under test.

2. The method for evaluating cable thermal faults according to claim 1, characterized in that, Step S3 includes: Step S31: Under the condition of stable heat source, set the point in the 3D model of the cable with the most obvious surface temperature increase as the temperature measurement position. Step S32: Extract historical temperature measurement data corresponding to the temperature measurement location from the historical temperature measurement data; Step S33: Determine whether the error between the temperature at the temperature measurement location and the corresponding historical temperature measurement data is greater than the preset threshold; if yes, adjust the preset boundary conditions and return to step S2; if no, proceed to step S4.

3. The method for evaluating cable thermal faults according to claim 2, characterized in that, Step S33 includes: Step S331: Calculate the difference between the temperature at the temperature measurement location and the corresponding historical temperature measurement data; Step S332: Determine whether the difference is greater than the preset threshold; if yes, adjust the preset boundary conditions and return to step S2; if no, proceed to step S4.

4. A device for evaluating cable thermal faults, characterized in that, include: The acquisition module is used to acquire basic data of the cable under test and historical temperature measurement data from the cable database; The construction module is used to construct a 3D model of the cable corresponding to the basic data based on preset environmental factors, structural conditions, and preset boundary conditions. The judgment module is used to determine, based on the historical temperature measurement data, whether the error between the cable 3D model and the actual cable is greater than a preset threshold. If so, adjust the preset boundary conditions and return to the execution of the construction module; If not, then execute the calculation module; The calculation module is used to calculate the attribute data of the cable 3D model through an orthogonal control method; the attribute data includes contact resistance value, load rate, surface temperature value and internal hot spot temperature; The evaluation module is used to calculate the thermal fault evaluation result data of the cable under test based on the contact resistance value, the load rate, the surface temperature values ​​and the internal hot spot temperature, combined with a preset support vector regression clustering model. The evaluation module includes: The constraint submodule is used to constrain the preset support vector regression machine clustering model according to the regularization principle to obtain a hard-margin support vector regression machine clustering model. The optimization submodule is used to optimize the hard-margin support vector regression machine clustering model based on preset slack variables and preset penalty coefficients, so as to obtain the optimal support vector regression machine clustering model. The evaluation submodule is used to input the contact resistance value, the load rate, the surface temperature value and the internal hot spot temperature into the optimal support vector regression machine clustering model to calculate the thermal fault evaluation result data of the cable under test. The evaluation submodule includes: The calculation unit is used to input the contact resistance value, the load rate, the surface temperature values ​​and the internal hot spot temperature into the optimal support vector regression machine clustering model to calculate the relationship data between the surface temperature and the contact resistance of the cable under test. The generation unit is used to generate thermal fault evaluation result data of the cable under test based on the relational data.

5. The cable thermal fault evaluation device according to claim 4, characterized in that, The judgment module includes: The submodule is configured to set the point in the 3D model of the cable where the surface temperature rises most significantly as the temperature measurement location under stable heat source conditions. An extraction submodule is used to extract historical temperature measurement data corresponding to the temperature measurement location from the historical temperature measurement data. The judgment submodule is used to determine whether the error between the temperature at the temperature measurement location and the corresponding historical temperature measurement data is greater than the preset threshold; if yes, the preset boundary conditions are adjusted and the execution of the construction module is returned; if no, the calculation module is executed.

6. The cable thermal fault evaluation device according to claim 5, characterized in that, The judgment submodule includes: The difference unit is used to calculate the difference between the temperature at the temperature measurement location and the corresponding historical temperature measurement data; The judgment unit is used to determine whether the difference is greater than the preset threshold; if so, the preset boundary conditions are adjusted and the execution of the construction module is returned; if not, the calculation module is executed.

Images