Evaluation method and device for cable crimping pipe sand hole

Abstract

The invention relates to an evaluation method and device for cable crimping pipe sand holes, and the method comprises the steps: obtaining the geometric parameters of a plurality of crimping pipe sand holes, such as a semi-major axis, a semi-minor axis, depth and the like, and constructing a sand hole evaluation reference data set; according to the data set, cable parameters, crimping pipe parameters and excitation conditions, a finite element model is established, the maximum value of electromagnetic loss power is calculated, and a sand hole evaluation reference electromagnetic loss power data set is obtained. Thirdly, constructing a finite element model without sand holes, calculating the maximum value of the electromagnetic loss power of the finite element model, classifying the sand hole evaluation data set based on the maximum value, and marking the sand hole evaluation data set as safe or dangerous; and constructing a logistic regression equation between the sand hole parameters and the electromagnetic loss power through the classified data set. And obtaining to-be-evaluated sand hole parameters, calculating the safety probability through the logistic regression equation, and evaluating whether the sand hole is safe or not. According to the method, the electromagnetic loss influence of the crimping pipe sand hole can be accurately evaluated, and a reliable basis is provided for safe use of a cable.

Description

Technical Field

[0001] The present invention belongs to the technical field of electrical equipment evaluation, and particularly relates to an evaluation method and device for sand holes in cable compression sleeves. Background Art

[0002] Medium-voltage cables in the distribution network are an important part of the power system, responsible for the transmission of medium-voltage electrical energy. The stability of their operation directly affects the reliability of the distribution network. In practical applications, due to the complexity of their structure, cable joints are subject to multiple stresses and are prone to problems such as electrical and thermal stress concentration, becoming a weak link in the cable system.

[0003] The compression sleeve in the cable joint is a common part where failures occur. During the manufacturing process of the compression sleeve, sand holes are a potential quality problem. Sand holes are caused by tiny defects in the manufacturing process, resulting in pores or voids on the surface. In alternating current power transmission, the skin effect causes the current to concentrate on the surface of the conductor, leading to significant differences in electromagnetic losses in different regions inside the compression sleeve. Defects such as sand holes further disturb the current distribution, increasing the local resistance and electromagnetic losses. This uneven loss not only reduces the transmission efficiency of the cable joint but may also cause excessive local electromagnetic losses, thus threatening the safety of the entire power transmission system.

[0004] Chinese Patent CN116297681A discloses a method for detecting defects in the axial thermal influence zone of a single-core cable including an intermediate joint, belonging to the technical field of cable defect detection. The present invention considers the influence of axial heat transfer, calculates the axial temperature field distribution of a single-core cable including an intermediate joint, focuses on analyzing the range of the axial thermal influence zone and the thermal equilibrium temperature of the single-core cable body including the intermediate joint, uses the overall-microelement method, analyzes the intermediate joint as a whole, divides the cable bodies on both sides of the intermediate joint into several microelements, calculates the thermal equilibrium temperature of the cable under steady state, iteratively obtains the range of the thermal influence zone, transfers the key point of cable fault detection along the line to the thermal influence zone, and detects defects in the cable body in the thermal influence zone by comparing the thermal conductivity coefficients. This patent analyzes the range of the axial thermal influence zone and the thermal equilibrium temperature by using a two-dimensional radial section model, and iteratively calculates the thermal conductivity coefficient through the steady-state heat transfer results to detect whether there are defects. The disadvantages of this method are as follows: The two-dimensional radial model structure is difficult to describe the local defects existing in the cable joint, and the sand holes affect the current density distribution in the compression sleeve and the heat source size of the two-dimensional heating model of the joint at different axial positions. Through this method, there will inevitably be differences in the thermal conductivity coefficient. Even for a perfect joint, due to the different two-dimensional joint heating models at different axial positions, it lacks persuasiveness for evaluating whether the joint is faulty.

[0005] Chinese Patent CN112989641A discloses a method for defect detection of high-voltage cable joints. According to the conditions of normal operation, air gap defects, and metal burr defects, a design scheme is formulated, and a multi-field coupling calculation model of cable joints based on "electromagnetism-temperature-flow" is constructed. The multi-field coupling analysis under air and water environments is carried out using Comsol finite element simulation software to obtain the temperature distribution of cable joints, and a data set of the operating state of the joints is formed. This method constructs a comparison and evaluation function between the measured temperature and the simulated temperature based on the least squares method, and obtains the defect conditions of the joints by determining the minimum value of the function. This patent uses Comsol finite element simulation software to analyze the heating conditions of the joint model under different defects, but the set defects are insulation layer defects and do not involve the influence of defects existing in the metal pressure pipe conductor on it.

[0006] In the prior art, there is a lack of an evaluation method for the influence of sand holes on the electromagnetic loss heating of the pressure pipe. In actual engineering, it is still unclear whether the pressure pipe with sand holes can be used for construction. Summary of the Invention

[0007] The purpose of the present invention is to overcome the above-mentioned defects existing in the prior art and provide an installation method and device for low-voltage commutation equipment.

[0008] The purpose of the present invention can be achieved through the following technical solutions:

[0009] On the one hand, the present invention provides an evaluation method for sand holes in cable pressure pipes, including the following steps:

[0010] Step S1: Obtain multiple sand hole parameters of the pressure pipe, and construct a sand hole evaluation reference data set according to the multiple sand hole parameters of the pressure pipe. The sand hole parameters of the pressure pipe include the semi-major axis, semi-minor axis, half of the depth, and the shortest distance between the sand hole center and the cross-section of the pressure pipe center.

[0011] Step S2: According to the sand hole evaluation reference data set, cable parameters, pressure pipe parameters, and excitation conditions, construct a finite element model corresponding to each set of sand hole parameters of the pressure pipe, and calculate the maximum value of the electromagnetic loss power of each model through the finite element model to obtain a sand hole evaluation reference electromagnetic loss power data set.

[0012] Step S3: Construct a finite element model without sand holes, and calculate the maximum power of the electromagnetic loss power of the finite element model without sand holes under the same excitation conditions.

[0013] Step S4: Classify the sand hole evaluation reference electromagnetic loss power data set according to the maximum power of the electromagnetic loss power of the finite element model without sand holes to obtain the classified sand hole evaluation reference electromagnetic loss power data set.

[0014] Step S5: Construct a logistic regression equation between the sand hole parameters of the compression joint and the maximum electromagnetic loss power through the classified sand hole evaluation reference electromagnetic loss power dataset;

[0015] Step S6: Obtain the sand hole parameters of the compression joint to be evaluated;

[0016] Step S7: Calculate the safety probability of the sand hole of the compression joint to be evaluated according to the sand hole parameters of the compression joint to be evaluated and the logistic regression equation, and evaluate whether the sand hole of the compression joint to be evaluated is safe according to the available probability of the sand hole of the compression joint to be evaluated.

[0017] Further, the cable parameters include the conductivity of the cable core, the compression joint parameters include the conductivity of the compression joint, and the excitation conditions include the magnitude and frequency of the conduction current.

[0018] Further, the sand hole evaluation reference electromagnetic loss power dataset includes multiple groups of sand hole evaluation reference electromagnetic loss power data, and the sand hole evaluation reference electromagnetic loss power data includes a set of sand hole parameters of the compression joint and the maximum electromagnetic loss power corresponding thereto.

[0019] Further, step S4 specifically includes the following steps: Determine whether the maximum electromagnetic loss power Q of each group of sand hole evaluation reference electromagnetic loss power data in the sand hole evaluation reference electromagnetic loss power dataset is greater than k times the maximum electromagnetic loss power Q of the finite element model without sand holes, where k is a constant greater than 1. If it is greater, classify this group of sand hole evaluation reference electromagnetic loss power data as dangerous; if it is less than or equal to, classify this group of sand hole evaluation reference electromagnetic loss power data as safe. 0 of the finite element model without sand holes, where k is a constant greater than 1. If it is greater, classify this group of sand hole evaluation reference electromagnetic loss power data as dangerous; if it is less than or equal to, classify this group of sand hole evaluation reference electromagnetic loss power data as safe.

[0020] Further, step S5 includes the following steps: Construct a logistic regression equation between the sand hole parameters of the compression joint and the maximum electromagnetic loss power:

[0021] Logit = w 1 ·α + w 2 ·b + w 3 ·a + w 4 ·L + z

[0022] where α, b, c, L are respectively the semi-major axis, semi-minor axis, half of the depth of the sand hole, and the shortest distance between the center of the sand hole and the cross-section of the center of the compression joint; w 1 、w 2 、w 3 、w 4 are the coefficients of the model, and z is the intercept of the fitting equation;

[0023] Determine the coefficients w 1 、w 2, w 3 , w 4 , the values of z.

[0024] Furthermore, the values of the coefficients w 1 , w 2 , w 3 , w 4 , z in the logistic regression equation are determined by the classified reference electromagnetic loss power dataset of sand holes, including the following steps: constructing the log-likelihood function of each coefficient in the logistic regression equation through the classified reference electromagnetic loss power dataset of sand holes, and gradually adjusting the values of each coefficient by the gradient descent method to make the value of the log-likelihood function gradually increase until the value of the log-likelihood function is locally maximum or globally maximum, so as to obtain the final values of the coefficients w 1 , w 2 , w 3 , w 4 , the numerical values of z.

[0025] Furthermore, the log-likelihood function is:

[0026]

[0027] where n is the number of groups of the classified reference electromagnetic loss power dataset of sand holes, X i is the crimping tube sand hole parameters a, b, c, L, D of the i-th group of the reference electromagnetic loss power data of sand holes, D i is the classification label corresponding to the crimping tube sand hole parameters of the i-th group of the reference electromagnetic loss power data of sand holes, Y i is the maximum power of the electromagnetic loss power of the i-th group of the reference electromagnetic loss power data of sand holes, P(D i |X i ) is the probability that its classification label is D i when the crimping tube sand hole parameters are X i .

[0028] Furthermore, the P(D i |X i ) is determined by statistically analyzing the classified reference electromagnetic loss power dataset of sand holes.

[0029] Furthermore, the safety probability of the crimping tube sand hole to be evaluated is calculated according to the sand hole parameters to be evaluated and the logistic regression equation, and the calculation formula is:

[0030]

[0031] Logit = w 1 ·α t +w 2 ·b t +w3 ·c t +w 4 ·L t +z

[0032] Among them, p is the safety probability of the sand hole in the crimping tube to be evaluated, a t 、b t 、c t 、L t are respectively the semi-major axis, semi-minor axis, half of the depth of the sand hole in the crimping tube to be evaluated, and the shortest distance between the center of the sand hole in the crimping tube to be evaluated and the cross-section of the center of the crimping tube.

[0033] On the other hand, the present invention provides a computer storage medium storing executable program code; the executable program code is used to execute the evaluation method for the sand hole in the cable crimping tube described in any one of the above.

[0034] Compared with the prior art, the present invention has the following advantages:

[0035] (1) By collecting general sand holes in the crimping tube, constructing a finite element model, simulating the electromagnetic characteristics of the sand hole, and calculating the maximum value of the electromagnetic loss power, the present invention provides quantitative electromagnetic loss data for sand hole evaluation. By comparing the maximum value of the electromagnetic loss power of the model without sand holes and the model with sand holes, the influence of sand holes on the cable performance can be effectively identified.

[0036] (2) Through the logistic regression model, the present invention quantifies the relationship between the geometric parameters of the sand hole in the crimping tube and the maximum value of the electromagnetic loss power into a mathematical formula, which is convenient for subsequent evaluation and prediction.

[0037] (3) The present invention uses the gradient descent method to optimize the coefficients in the logistic regression to ensure the best fitting effect of the model on all data sets. This optimization method can maximize the log-likelihood function of the data set, avoid the overfitting or underfitting problems in the traditional method, and improve the stability and accuracy of the model.

[0038] (4) The present invention does not need to consider the change of the current-carrying capacity and the change of the conductivity of the metal conductor, and effectively evaluates the influence of the position and size parameters of the sand hole on the electromagnetic loss heating. After fixing the model size parameters in the simulation calculation, the electromagnetic loss heat generation is linearly related to the current-carrying capacity and the conductivity. Therefore, according to the calculation results of any conductivity and current-carrying capacity set in the simulation model, it can be used to evaluate the maximum heating power Q of the electromagnetic loss of the sand hole for any copper core material and any current-carrying capacity in the actual project. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 is the flowchart of the method of the present invention;

[0040] Figure 2It is the cable model diagram of the present invention;

[0041] Figure 3 It is the method flow block diagram of the present invention. Specific implementation manners

[0042] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0043] Embodiment 1:

[0044] This embodiment provides an evaluation method for the sand holes of a cable compression joint. As Figure 1 shown, it includes the following steps:

[0045] Step S1: Obtain multiple sand hole parameters of the compression joint, and construct a sand hole evaluation reference data set according to the multiple sand hole parameters of the compression joint. The sand hole parameters of the compression joint include the semi-major axis, semi-minor axis, half of the depth of the sand hole, and the shortest distance between the center of the sand hole and the central section of the compression joint;

[0046] Step S2: Construct a finite element model corresponding to each set of sand hole parameters of the compression joint according to the sand hole evaluation reference data set, cable parameters, compression joint parameters, and excitation conditions. Calculate the maximum value of the electromagnetic loss power of each model through the finite element model to obtain a sand hole evaluation reference electromagnetic loss power data set;

[0047] Among them, the cable parameters include the conductivity of the cable core, the compression joint parameters include the conductivity of the compression joint, and the excitation conditions include the magnitude and frequency of the conduction current. The sand hole evaluation reference electromagnetic loss power data set includes multiple groups of sand hole evaluation reference electromagnetic loss power data. The sand hole evaluation reference electromagnetic loss power data includes a set of sand hole parameters of the compression joint and the maximum value of the electromagnetic loss power corresponding thereto.

[0048] Step S3: Construct a finite element model without sand holes, and calculate the maximum value of the electromagnetic loss power of the finite element model without sand holes under the same excitation conditions;

[0049] Step S4: Classify the sand hole evaluation reference electromagnetic loss power data set according to the maximum value of the electromagnetic loss power of the finite element model without sand holes to obtain a classified sand hole evaluation reference electromagnetic loss power data set;

[0050] Step S4 specifically includes the following steps: Determine whether the maximum power Q of the electromagnetic loss power in each group of electromagnetic loss power data in the sand hole evaluation reference electromagnetic loss power dataset is greater than k times the maximum power Q of the electromagnetic loss power of the finite element model without sand holes, where k is a constant greater than 1. If it is greater, classify this group of electromagnetic loss power data in the sand hole evaluation reference electromagnetic loss power dataset as dangerous; if it is less than or equal, classify this group of electromagnetic loss power data in the sand hole evaluation reference electromagnetic loss power dataset as safe. 0 If it is greater, classify this group of electromagnetic loss power data in the sand hole evaluation reference electromagnetic loss power dataset as dangerous; if it is less than or equal, classify this group of electromagnetic loss power data in the sand hole evaluation reference electromagnetic loss power dataset as safe.

[0051] Step S5: Construct a logistic regression equation between the sand hole parameters of the compression joint and the maximum power of the electromagnetic loss power through the classified sand hole evaluation reference electromagnetic loss power dataset;

[0052] Among them, step S5 includes the following steps: Construct a logistic regression equation between the sand hole parameters of the compression joint and the maximum power of the electromagnetic loss power:

[0053] Logit = w 1 ·α + w 2 ·b + w 3 ·c + w 4 ·L + z

[0054] Among them, α, b, c, and L are respectively the semi-major axis, semi-minor axis, half of the depth of the sand hole, and the shortest distance between the center of the sand hole and the cross-section of the center of the compression joint; w 1 , w 2 , w 3 , w 4 are the coefficients of the model, and z is the intercept of the fitting equation;

[0055] Determine the values of the coefficients w 1 , w 2 , w 3 , w 4 , z in the logistic regression equation through the classified sand hole evaluation reference electromagnetic loss power dataset.

[0056] Determine the values of the coefficients w 1 , w 2 , w 3 , w 4 , z in the logistic regression equation through the classified sand hole evaluation reference electromagnetic loss power dataset, including the following steps: Construct a log-likelihood function of each coefficient in the logistic regression equation through the classified sand hole evaluation reference electromagnetic loss power dataset, and use the gradient descent method to gradually adjust the values of each coefficient to make the value of the log-likelihood function gradually increase until the value of the log-likelihood function is locally maximum or globally maximum, and obtain the final values of the coefficients w 1 , w 2 , w 3 , w 4 , z.

[0057] The logarithmic likelihood function is as follows:

[0058]

[0059] Where n is the number of groups in the dataset of electromagnetic loss power for the evaluated sand hole, and X i is the crimping tube sand hole parameters a, b, c, L, D of the electromagnetic loss power data of the i-th group of evaluated sand holes i is the classification label corresponding to the crimping tube sand hole parameters of the electromagnetic loss power data of the i-th group of evaluated sand holes, and Y i is the maximum power of the electromagnetic loss power of the electromagnetic loss power data of the i-th group of evaluated sand holes, P(D i |X i ) is the probability that when the crimping tube sand hole parameters are X i , its classification label is D i . P(D i |X i ) is determined by statistically analyzing the dataset of electromagnetic loss power for the evaluated sand holes after classification.

[0060] Step S6: Obtain the crimping tube sand hole parameters to be evaluated;

[0061] Step S7: Calculate the safety probability of the crimping tube sand hole to be evaluated according to the crimping tube sand hole parameters to be evaluated and the logistic regression equation. The calculation formula is:

[0062]

[0063] Logit = w 1 ·α t + w 2 ·b t + w 3 ·c t + w 4 ·L t + z

[0064] Where p is the safety probability of the crimping tube sand hole to be evaluated, and a t , b t , c t , L t are respectively the semi-major axis, semi-minor axis, half of the depth, and the shortest distance between the center of the crimping tube sand hole to be evaluated and the center section of the crimping tube.

[0065] Evaluate whether the crimping tube sand hole to be evaluated is safe according to the available probability of the crimping tube sand hole to be evaluated.

[0066] Example 2:

[0067] Parts not mentioned in this example are the same as those in Example 1.

[0068] A 1:1 drawn cable model is set with the sand hole model being ellipsoidal in shape, as Figure 2 shown. The joint model with sand hole defects is the geometric difference set of the compression joint and the sand hole ellipsoid. The positioning of the ellipsoid is as follows: the center coincides with the outer diameter edge of the compression joint, and the distance from the center to the central cross-section of the compression joint is L. Taking the compression joint of a 35 kV AC cable as an example, the length of the compression joint is 12.6 mm, the outer diameter after pressing with the cable core is 16 mm, and the inner diameter is 12 mm. In the embodiment, the semi-axis lengths of the ellipsoid are a, b, and c respectively, and can all take values of 1 mm, 2 mm, and 3 mm. L can take values of 0 mm, 10 mm, 20 mm, 30 mm, 40 mm, 50 mm, and 60 mm.

[0069] This embodiment provides an evaluation method for sand holes in cable compression joints, as Figure 3 shown, including the following steps: constructing a finite element model, considering the skin effect, setting the current to 200 A, the frequency to 50 Hz, and the conductivity of both the cable core and the compression joint to 5.6×10 7 S / m. Under different values of a, b, c, and L, the maximum value Q of the electromagnetic loss power of the compression joint with the sand hole model. At the same time, calculate the maximum value Q 0 of the electromagnetic loss power of the compression joint without the sand hole model under the same excitation conditions, and use this as a parameter for the subsequent judgment criterion.

[0070] The parameters of the 4 dimensions of a, b, c, and L are used as independent variables, and a total of 189 permutations and combinations are generated under the above combinations. Therefore, there are 189 results of the dependent variable Q output. Set a safety standard threshold, such as 1.05Q 0 , mark the independent variables of the data less than 1.05Q 0 as safety labels, and mark the independent variables of the data greater than 1.05Q 0 as danger labels.

[0071] Use the logistic regression equation to judge the influence of the independent variables a, b, c, and L on the dependent variable Q, and calculate the Logit value to determine the weight relationship between the independent variables a, b, c, and L and the dependent variable Q. The Logit value formula is as follows,

[0072] Logit = w 1 ·a + w 2 ·b + w 3 ·c + w 4 ·L + z

[0073] where w 1 - w 4 are the coefficients of the model, corresponding to the evaluation weights of the input variables a, b, c, and L respectively. z is the intercept of the fitting equation. The mathematical calculation method for determining the coefficients is as follows: calculate the log-likelihood function to obtain w 1-w 4 , which is an equation with z being the model coefficient.

[0074]

[0075] Among them, n is the number of groups of the classified electromagnetic loss power datasets of the sand hole evaluation references, X i is the crimping tube sand hole parameters a, b, c, L, D of the i-th group of sand hole evaluation reference electromagnetic loss power data i is the classification label corresponding to the crimping tube sand hole parameters of the i-th group of sand hole evaluation reference electromagnetic loss power data, Y i is the maximum power of the electromagnetic loss power of the i-th group of sand hole evaluation reference electromagnetic loss power data, P(D i |X i ) is the probability that when the crimping tube sand hole parameter is X i , its classification label is D i . P(D i |X i ) is determined by statistically analyzing the classified electromagnetic loss power datasets of the sand hole evaluation references.

[0076] To maximize the log-likelihood function, we take the derivatives of w 1 -w 4 and the intercept z.

[0077]

[0078]

[0079] The log-likelihood function is mostly a non-linear function. Usually, iterative numerical optimization methods are needed to find the optimal values of the coefficients. Through the gradient descent method, that is, gradually adjusting the parameters to make the value of the log-likelihood function increase step by step until the local maximum or global maximum is found, the final numerical values of w 1 -w 4 , z are obtained.

[0080] After determining the correlation coefficients, based on the actual sand hole size, measure and determine the parameter values of a, b, c, L, and substitute them into the sigmoid function to calculate the safety probability p value that the maximum electromagnetic loss heating power Q of this joint is higher than the safety standard threshold 1.05Q 0 .

[0081]

[0082] Generally, multiple cable joints are installed in the transmission line. Therefore, set the safety probability threshold p 0 = 1 / m, where m is the number of series-connected cable joints on this line. If the calculated p is less than the safety probability threshold p 0 , this joint can be used; otherwise, it is not recommended to be used.

[0083] After calculating and fitting 189 groups of data, the Logit of the 35 kV compression joint is 0.00400·a + 0.00200·b - 0.00199·c - 0.12970·L + 3.42161. This equation can be directly used for the feasibility evaluation of compression joints of other cable joints with the same specifications.

[0084] When the above functions are implemented in the form of software functional units and sold or used as independent products, they 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 a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can 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 storage medium includes: various media that can store program codes 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.

[0085] As described above, the above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A method for evaluating sand holes in cable crimping tubes, characterized in that: The following steps are involved: Step S1: Acquire multiple compression tube sand hole parameters, and construct a sand hole assessment reference data set according to the multiple compression tube sand hole parameters, wherein the compression tube sand hole parameters include the semi-major axis, semi-minor axis, half of the depth, and the shortest distance between the sand hole center and the center section of the compression tube; Step S2: According to the sand hole assessment reference data set, cable parameters, crimping tube parameters and excitation conditions, a finite element model corresponding to each set of crimping tube sand hole parameters is constructed, and the maximum value of the electromagnetic loss power of each model is calculated through the finite element model to obtain a sand hole assessment reference electromagnetic loss power data set; Step S3: constructing a finite element model without sand holes, and calculating the maximum power of the electromagnetic loss power of the finite element model without sand holes under the same excitation conditions; Step S4: labeling the sand hole assessment reference electromagnetic loss power dataset according to the maximum power of the electromagnetic loss power of the finite element model without sand holes, and obtaining the classified sand hole assessment reference electromagnetic loss power dataset; Step S5: constructing a logistic regression equation between the compression tube sand hole parameter and the maximum power of the electromagnetic loss power by using the classified sand hole evaluation reference electromagnetic loss power data set; Step S6: obtaining the parameters of the sand holes in the crimped tube to be evaluated; Step S7: Calculate the safety probability of the sand hole in the compression tube to be evaluated according to the sand hole parameters of the compression tube to be evaluated and the logistic regression equation, and evaluate whether the sand hole in the compression tube to be evaluated is safe according to the available probability of the sand hole in the compression tube to be evaluated.

2. The method for evaluating sand holes in cable crimping tubes according to claim 1, characterized in that: The cable parameters include the cable core conductivity, the crimping tube parameters include the crimping tube conductivity, and the excitation conditions include the conduction current size and frequency.

3. The method for evaluating sand holes in cable crimping tubes according to claim 1, characterized in that: The sand hole assessment reference electromagnetic loss power data set includes multiple groups of sand hole assessment reference electromagnetic loss power data, and the sand hole assessment reference electromagnetic loss power data includes a group of press-fit tube sand hole parameters and the maximum power of the electromagnetic loss power corresponding thereto.

4. A method for evaluating sand holes in cable crimping tubes according to claim 1 or 3, characterized in that: The step S4 specifically includes the following steps: determining whether the maximum power Q of the electromagnetic loss power of each group of sand hole assessment reference electromagnetic loss power data in the sand hole assessment reference electromagnetic loss power data set is greater than k times the maximum power Q0 of the electromagnetic loss power of the finite element model without sand holes, where k is a constant greater than 1; if greater than, classifying the group of sand hole assessment reference electromagnetic loss power data as dangerous; if less than or equal to, classifying the group of sand hole assessment reference electromagnetic loss power data as safe.

5. The method for evaluating sand holes in cable crimping tubes according to claim 1, characterized in that: The step S5 comprises the following steps: constructing a logistic regression equation between the crimping tube sand hole parameter and the maximum power of the electromagnetic loss power: Logit=w1·α+w2·b+w3·c+w4·L+z Among them, α, b, c, and L are the semi-major axis, semi-minor axis, half of the depth, and the shortest distance between the center of the sand hole and the center section of the crimping tube; w1, w2, w3, and w4 are the coefficients of the model, and z is the intercept of the fitting equation; The values ​​of coefficients w1, w2, w3, w4, and z in the logistic regression equation are determined by referring to the electromagnetic loss power data set through the classified sand hole assessment.

6. The method for evaluating sand holes in cable crimping tubes according to claim 5, characterized in that: The method of determining the values ​​of each coefficient w1, w2, w3, w4, and z in the logistic regression equation by referring to the classified sand hole assessment electromagnetic loss power data set comprises the following steps: constructing the logarithmic likelihood function of each coefficient in the logistic regression equation by referring to the classified sand hole assessment electromagnetic loss power data set, and gradually adjusting the value of each coefficient by the gradient descent method so that the value of the logarithmic likelihood function gradually increases until the value of the logarithmic likelihood function reaches a local maximum or a global maximum, thereby obtaining the final values ​​of each coefficient w1, w2, w3, w4, and z.

7. The method for evaluating sand holes in cable crimping tubes according to claim 6, characterized in that: The log-likelihood function is: Where n is the number of groups of reference electromagnetic loss power data sets for sand hole assessment after classification, X i The parameters a, b, c, L, and D of the crimped tube holes for evaluating the reference electromagnetic loss power data for the i-th group of holes i The classification label corresponding to the pressure tube sand hole parameter of the reference electromagnetic loss power data for the i-th group of sand holes, Y i The maximum power of electromagnetic loss power of the reference electromagnetic loss power data for evaluating the i-th group of sand holes, P(D i |X i ) is when the pressure tube sand hole parameter is X i When the classification label is D i probability.

8. The method for evaluating sand holes in cable crimping tubes according to claim 7, characterized in that: The P(D i |X i ) is statistically determined by evaluating the reference electromagnetic loss power data set after classification.

9. The method for evaluating sand holes in cable crimping tubes according to claim 1, characterized in that: The safety probability of the sand hole in the compression tube to be evaluated is calculated based on the sand hole parameters of the compression tube to be evaluated and the logistic regression equation, and the calculation formula is: Logit=w1·α t +w2·b t +w3·c t +w4·L t +z Among them, p is the safety probability of sand holes in the compression tube to be evaluated, α t , b t 、c t , L t They are respectively the semi-major axis, semi-minor axis, half of the depth of the sand hole in the compression tube to be evaluated, and the shortest distance between the center of the sand hole in the compression tube to be evaluated and the center section of the compression tube.

10. A computer storage medium, characterized in that: An executable program code is stored; the executable program code is used to execute the evaluation method for sand holes in cable crimping tubes as described in any one of claims 1 to 9.

Images