Thermal defect evaluation method and device of cable joint and storage medium

Abstract

The invention discloses a thermal defect evaluation method and device for a cable joint and a storage medium. The method comprises the following steps: acquiring first initial temperature data of a wire core in a cable joint and second initial temperature data of a skin in the cable joint; determining first target temperature data of the wire core based on the first initial temperature data, and determining second target temperature data of the skin based on the second initial temperature data; and inputting the first target temperature data and the second target temperature data into a target thermal defect evaluation model of the cable joint, evaluating thermal defect data of the cable joint, and outputting an evaluation result of the cable joint, the target thermal defect evaluation model is established through the first historical temperature data of the cable core, the second historical temperature data of the skin and the historical thermal defect data of the cable joint, and the evaluation result is used for representing the thermal defect state, corresponding to the thermal defect data, of the cable joint. The technical problem that the thermal defect evaluation efficiency of the cable joint is low is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of cable joints, and in particular to a thermal defect evaluation method, device and storage medium for a cable joint. Background Art

[0002] During the long-term use of cable lines, cable joints are prone to thermal defects due to overheating, aging, external force damage, etc., which can lead to failures. At present, infrared thermal imaging technology and regular inspections are often used to evaluate the thermal defects of cable joints. Infrared thermal imaging technology evaluates the thermal state of cable joints through thermal radiation on the surface of cable joints. However, this method is greatly affected by ambient temperature and humidity, and usually requires regular inspections. The evaluation cost of regular inspections is high, resulting in a technical problem of low efficiency in evaluating thermal defects in cable joints.

[0003] With respect to the technical problem of low efficiency in thermal defect evaluation of the above-mentioned cable joints, no effective solution has been proposed so far. Summary of the invention

[0004] The embodiments of the present invention provide a method, a device and a storage medium for thermal defect evaluation of a cable joint, so as to at least solve the technical problem of low efficiency in thermal defect evaluation of a cable joint.

[0005] According to one aspect of the embodiment of the invention, a thermal defect evaluation method for a cable joint is provided. The method may include: collecting the first initial temperature data of the core in the cable joint, and the second initial temperature data of the skin in the cable joint; determining the first target temperature data of the core based on the first initial temperature data, and determining the second target temperature data of the skin based on the second initial temperature data; inputting the first target temperature data and the second target temperature data into the target thermal defect evaluation model of the cable joint, evaluating the thermal defect data of the cable joint, and outputting the evaluation result of the cable joint, wherein the target thermal defect evaluation model is established through the first historical temperature data of the core, the second historical temperature data of the skin, and the historical thermal defect data of the cable joint, and the evaluation result is used to characterize the thermal defect state of the cable joint corresponding to the thermal defect data.

[0006] Optionally, the method also includes: using a simulation model of the cable joint to obtain first historical temperature data of the wire core and second historical temperature data of the skin; using a finite element model of the cable joint to obtain historical thermal defect data of the cable joint; based on the first historical temperature data, the second historical temperature data and the historical thermal defect data, training an initial thermal defect evaluation model of the cable joint to obtain a target thermal defect evaluation model, wherein the initial thermal defect evaluation model is established based on parameter information of the environment in which the cable joint is located.

[0007] Optionally, based on the first historical temperature data, the second historical temperature data and the historical thermal defect data, an initial thermal defect evaluation model of the cable joint is trained to obtain a target thermal defect evaluation model, including: determining a training data set of the cable joint based on the first historical temperature data, the second historical temperature data and the historical thermal defect data; using the training data set to train the initial thermal defect evaluation model to obtain a target thermal defect evaluation model.

[0008] Optionally, based on the first historical temperature data, the second historical temperature data and the historical thermal defect data, a training data set for the cable joint is determined, including: performing feature extraction on the first historical temperature data to obtain a first characteristic value of the wire core; performing feature extraction on the second historical temperature data to obtain a second characteristic value of the skin; and determining the training data set based on the first characteristic value, the second characteristic value and the historical thermal defect data.

[0009] Optionally, the initial thermal defect evaluation model is trained using the training data set to obtain a target thermal defect evaluation model, including: based on the training data set, using the target loss function of the cable connector to train the initial thermal defect evaluation model to obtain the target thermal defect evaluation model.

[0010] Optionally, based on the first initial temperature data, the first target temperature data of the wire core is determined, and based on the second initial temperature data, the second target temperature data of the skin is determined, including: denoising the first initial temperature data to obtain the first target temperature data, and denoising the second initial temperature data to obtain the second target temperature data.

[0011] Optionally, the evaluation result includes the thermal defect type and thermal defect fault information, wherein the thermal defect fault information is used to characterize the degree of thermal defect fault of the cable joint.

[0012] According to one aspect of an embodiment of the present invention, a thermal defect evaluation device for a cable joint is provided. The device may include: a collection unit for collecting the first initial temperature data of the core in the cable joint, and the second initial temperature data of the skin in the cable joint; a determination unit for determining the first target temperature data of the core based on the first initial temperature data, and determining the second target temperature data of the skin based on the second initial temperature data; an evaluation unit for inputting the first target temperature data and the second target temperature data into a target thermal defect evaluation model of the cable joint, evaluating the thermal defect data of the cable joint, and outputting the evaluation result of the cable joint, wherein the target thermal defect evaluation model is established through the first historical temperature data of the core, the second historical temperature data of the skin, and the historical thermal defect data of the cable joint, and the evaluation result is used to characterize the thermal defect state of the cable joint corresponding to the thermal defect data.

[0013] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium includes a stored program, wherein when the program is executed by a processor, the device where the storage medium is located is controlled to execute the method in the embodiment of the present invention.

[0014] According to another aspect of an embodiment of the present invention, a processor is provided. The processor is used to run a program, wherein the method in the embodiment of the present invention is executed when the program is run.

[0015] According to another aspect of the embodiments of the present invention, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the method in the embodiments of the present invention is implemented.

[0016] According to another aspect of an embodiment of the present invention, an electronic device is provided, the electronic device comprising a processor and a memory for storing instructions executable by the processor, wherein the processor is configured to execute the instructions to implement the method in the embodiment of the present invention.

[0017] In an embodiment of the present invention, the first initial temperature data of the core in the cable joint and the second initial temperature data of the skin in the cable joint are collected; based on the first initial temperature data, the first target temperature data of the core is determined, and based on the second initial temperature data, the second target temperature data of the skin is determined; the first target temperature data and the second target temperature data are input into the target thermal defect evaluation model of the cable joint, the thermal defect data of the cable joint is evaluated, and the evaluation result of the cable joint is output, wherein the target thermal defect evaluation model is established by the first historical temperature data of the core, the second historical temperature data of the skin and the historical thermal defect data of the cable joint, and the evaluation result is used to characterize the thermal defect state of the cable joint corresponding to the thermal defect data. That is to say, in an embodiment of the present invention, the first initial temperature data of the core in the cable joint and the second initial temperature data of the skin in the cable joint can be collected first, and then the first target temperature data of the core can be determined according to the first initial temperature data obtained above, and the second target temperature data of the skin can be determined according to the second initial temperature data obtained above, and finally the first target temperature data and the second target temperature data can be input into the target thermal defect evaluation model to evaluate the thermal defect data of the cable joint so as to output the evaluation result of the cable joint. Taking into account that the first target temperature data is determined based on the first initial temperature data obtained, and the second target temperature data is determined based on the second initial temperature data, and then according to the first target temperature data and the second target temperature data, the target thermal defect evaluation model is called to achieve the purpose of obtaining the evaluation result of the cable joint, so as to solve the technical problem of low efficiency of thermal defect evaluation of cable joints, and achieve the technical effect of improving the efficiency of thermal defect evaluation of cable joints. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0019] Figure 1 is a flow chart of a thermal defect evaluation method for a cable joint according to an embodiment of the present invention;

[0020] Figure 2 is a flow chart of a cable joint thermal defect evaluation method based on real-time temperature sensing according to an embodiment of the present invention;

[0021] Figure 3 is a schematic diagram of a deep neural network according to an embodiment of the present invention;

[0022] Figure 4 is a schematic diagram of a thermal defect evaluation device for a cable joint according to an embodiment of the present invention. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] According to an embodiment of the present invention, a thermal defect evaluation method for a cable joint is provided. It should be noted that in the flowchart of the accompanying drawings, the steps shown therein can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in an order different from that shown here.

[0026] The following is an introduction to the thermal defect evaluation method of the cable joint according to the embodiment of the present invention.

[0027] Figure 1 is a flow chart of a thermal defect evaluation method for a cable joint according to an embodiment of the present invention. Figure 1 As shown, the method may include the following steps:

[0028] Step S101, collecting first initial temperature data of the wire core in the cable joint and second initial temperature data of the surface of the cable joint.

[0029] In the technical solution provided in step S101 of the present invention, the first initial temperature data of the core in the cable joint and the second initial temperature data of the skin in the cable joint can be collected. The first initial temperature data of the core can be referred to as the initial temperature data of the core. The second initial temperature data of the skin can be referred to as the initial temperature data of the skin.

[0030] Optionally, a temperature sensor may be used to collect the first initial temperature data of the wire core and the second initial temperature data of the skin in real time. For example, the collected initial temperature data of the wire core may be 20 degrees Celsius (°C), and the initial temperature data of the skin may be 28 degrees Celsius.

[0031] It should be noted that this is only a preferred implementation method for obtaining the first initial temperature data of the wire core in the cable joint and the second initial temperature data of the surface of the cable joint, and does not specifically limit the process and method of obtaining the first initial temperature data of the wire core in the cable joint and the second initial temperature data of the surface of the cable joint.

[0032] Step S102, determining first target temperature data of the core based on the first initial temperature data, and determining second target temperature data of the skin based on the second initial temperature data.

[0033] In the technical solution provided in the above step S102 of the present invention, after obtaining the first initial temperature data and the second initial temperature data, the first target temperature data of the wire core can be determined according to the first initial temperature data, and the second target temperature data of the epidermis can be determined according to the second initial temperature data.

[0034] Optionally, feature extraction is performed on the first initial temperature data to obtain first target temperature data of the core, and feature extraction is performed on the second initial temperature data to obtain second target temperature data of the epidermis. The feature extraction method for the data may be statistical feature extraction, frequency domain feature extraction, and time series feature extraction. Here, only an example is given to illustrate the feature extraction method of the data, and the feature extraction method of the data is not specifically limited.

[0035] It can be understood that this is only a preferred implementation method for determining the first target temperature data of the wire core and the second target temperature data of the skin, and the process and method for determining the first target temperature data of the wire core and the second target temperature data of the skin are not specifically limited. As long as the first target temperature data of the wire core is determined based on the first initial temperature data, and the second target temperature data of the skin is determined based on the second initial temperature data, the process and method are within the protection scope of the present invention and will not be listed here.

[0036] Step S103, inputting the first target temperature data and the second target temperature data into a target thermal defect evaluation model of the cable joint, evaluating the thermal defect data of the cable joint, and outputting the evaluation result of the cable joint.

[0037] In the technical solution provided in the above step S103 of the present invention, after obtaining the first target temperature data and the second target temperature data in step S102, the first target temperature data and the second target temperature data can be input into the target thermal defect evaluation model of the cable joint, so as to evaluate the thermal defect data of the cable joint, thereby outputting the evaluation result of the cable joint. The target thermal defect evaluation model can be a trained artificial intelligence model.

[0038] Optionally, the target thermal defect evaluation model is established by using the first historical temperature data of the wire core, the second historical temperature data of the skin, and the historical thermal defect data of the cable joint, and the evaluation result is used to characterize the thermal defect state of the cable joint corresponding to the thermal defect data. The thermal defect state is used to characterize whether the cable joint has an abnormally high temperature phenomenon.

[0039] For example, a temperature sensor is used to collect the temperature data of the core and surface of the cable joint in real time, and the temperature data is denoised. The denoised temperature data is then input into a trained artificial intelligence model, which can output the evaluation results of the cable joint to achieve real-time evaluation of thermal defects of the cable joint.

[0040] It should be noted that this is only a preferred implementation method for determining the evaluation results of cable joints, and does not specifically limit the process and method for determining the evaluation results of cable joints. As long as the first target temperature data and the second target temperature data are input into the target thermal defect evaluation model of the cable joint, the purpose of outputting the evaluation results of the cable joint is achieved, which is within the protection scope of the present invention and will not be listed here.

[0041] In the above steps S101 to S103 of the present invention, the first initial temperature data of the core in the cable joint and the second initial temperature data of the skin in the cable joint can be first collected, and then the first target temperature data of the core can be determined based on the first initial temperature data obtained above, and the second target temperature data of the skin can be determined based on the second initial temperature data obtained above, and finally the first target temperature data and the second target temperature data can be input into the target thermal defect evaluation model to evaluate the thermal defect data of the cable joint so as to output the evaluation result of the cable joint. Considering that the first target temperature data is determined based on the first initial temperature data obtained, and the second target temperature data is determined based on the second initial temperature data, and then the target thermal defect evaluation model is called based on the first target temperature data and the second target temperature data to achieve the purpose of obtaining the evaluation result of the cable joint, so as to solve the technical problem of low efficiency of thermal defect evaluation of the cable joint, and achieve the technical effect of improving the efficiency of thermal defect evaluation of the cable joint.

[0042] The above method of this embodiment is further introduced below.

[0043] As an optional implementation method, the method also includes: using a simulation model of the cable joint to obtain first historical temperature data of the wire core and second historical temperature data of the skin; using a finite element model of the cable joint to obtain historical thermal defect data of the cable joint; based on the first historical temperature data, the second historical temperature data and the historical thermal defect data, training an initial thermal defect evaluation model of the cable joint to obtain a target thermal defect evaluation model, wherein the initial thermal defect evaluation model is established based on parameter information of the environment in which the cable joint is located.

[0044] In this embodiment, the simulation model of the cable joint can be used to obtain the first historical temperature data of the wire core and the second historical temperature data of the skin, and the finite element model of the cable joint can be used to obtain the historical thermal defect data of the cable joint. Then, based on the first historical temperature data, the second historical temperature data and the historical thermal defect data obtained above, the initial thermal defect evaluation model of the cable joint can be trained to obtain the target thermal defect evaluation model.

[0045] Optionally, a finite element model of electromagnetic thermal coupling of the cable joint is established through finite element analysis software, which includes structures such as the cable core, semiconductor layer, insulation layer, metal shielding layer, inner and outer sheaths, and sets the types and degrees of possible thermal defects, including core overheating, insulation layer damage, sheath short circuit, etc.

[0046] For example, run the simulation model, set the heat conduction analysis data for different defects of the cable joint, obtain the temperature distribution data of the cable joint under different defects, and record the temperature values ​​of the core and the skin to obtain the first historical temperature data of the core and the second historical temperature data of the skin at this time.

[0047] For another example, after obtaining the first historical temperature data, the second historical temperature data and the historical thermal defect data, the parameters of the established initial thermal defect evaluation model may be optimized to obtain a target thermal defect evaluation model.

[0048] As an optional implementation method, an initial thermal defect evaluation model of a cable joint is trained based on the first historical temperature data, the second historical temperature data and the historical thermal defect data to obtain a target thermal defect evaluation model, including: determining a training data set of the cable joint based on the first historical temperature data, the second historical temperature data and the historical thermal defect data; using the training data set to train the initial thermal defect evaluation model to obtain a target thermal defect evaluation model.

[0049] In this embodiment, based on the first historical temperature data, the second historical temperature data and the historical thermal defect data, a training data set of the cable joint can be determined, and then the initial thermal defect evaluation model can be trained using the training data set to achieve the purpose of obtaining the target thermal defect evaluation model.

[0050] For example, based on the first historical temperature data, the second historical temperature data, and the historical thermal defect data, the initial thermal defect evaluation model can be trained to obtain the target thermal defect evaluation model. For example, assuming that there are m training samples for this model optimization, each sample contains 6 eigenvalues, and the defect type and degree information are used as labels to train the initial thermal defect evaluation model, the training data set can be expressed as:

[0051]

[0052] Among them, X i ∈R 6 , is the feature vector of the i-th sample, y i For the corresponding label.

[0053] As an optional implementation method, based on the first historical temperature data, the second historical temperature data and the historical thermal defect data, a training data set of the cable joint is determined, including: performing feature extraction on the first historical temperature data to obtain a first characteristic value of the wire core; performing feature extraction on the second historical temperature data to obtain a second characteristic value of the skin; and determining the training data set based on the first characteristic value, the second characteristic value and the historical thermal defect data.

[0054] In this embodiment, the first historical temperature data may be feature extracted to obtain a first characteristic value of the core, and the second historical temperature data may be feature extracted to obtain a second characteristic value of the skin, and then the training data set of the cable joint may be determined based on the first characteristic value, the second characteristic value, and the historical thermal defect data obtained above. The first characteristic value of the core may be the temperature characteristic data of the core, which may be referred to as the temperature characteristic value of the core, and the second characteristic value of the skin may be the temperature characteristic data of the skin, which may be referred to as the temperature characteristic value of the skin.

[0055] Optionally, the average temperature of the core and the skin of the cable joint, or the temperature rise rate, or the temperature rise difference before and after the defect can be extracted respectively, and the above data can be used as the temperature characteristic data of the core and the skin. Among them, the average temperature of the core can be obtained by θ c The temperature rise rate of the wire core can be expressed by k c The temperature rise difference before and after the defect can be expressed by Δθ c The average temperature of the skin can be expressed by θ h The temperature rise rate of the skin can be expressed by k h The temperature rise difference before and after the skin defect can be expressed by Δθ h It should be noted that only the temperature characteristic data of the core and the temperature characteristic data of the skin are exemplified here, and the data types of the temperature characteristic data of the core and the temperature characteristic data of the skin are not specifically limited.

[0056] Optionally, the average temperature of the core and the average temperature of the skin are calculated in the same way and can both be recorded as θ, which can be expressed by the following formula:

[0057]

[0058] Among them, θ i It can be the temperature of the i-th sampling point, and n can be the total number of sampling points. Within a period of time, the temperature rise rate of the core and the temperature rise rate of the skin are calculated in the same way and can be uniformly recorded as k and expressed by the following formula:

[0059]

[0060] Among them, θ i and θ i-1 It can be the temperature value of two consecutive time points, and Δt can be the time interval. The calculation method of the temperature rise difference of the core before and after the defect and the temperature rise difference of the skin before and after the defect are the same, and can be uniformly recorded as Δθ and expressed by the following formula:

[0061] Δθ=θ max -θmin ,

[0062] Among them, θ max and θ min They are the highest and lowest temperatures measured within the total time nΔt, respectively.

[0063] As an optional implementation method, the initial thermal defect evaluation model is trained using a training data set to obtain a target thermal defect evaluation model, including: based on the training data set, using the target loss function of the cable connector to train the initial thermal defect evaluation model to obtain the target thermal defect evaluation model.

[0064] In this embodiment, after obtaining the training data set, the target loss function of the cable connector can be used to train the initial thermal defect evaluation model to obtain the target thermal defect evaluation model. The target loss function can be a preset loss function, such as a cross entropy loss function. It should be noted that the target loss function is only illustrated here, and the target loss function is not specifically limited.

[0065] Optionally, the initial thermal defect evaluation model can be trained by training a deep neural network. The deep neural network includes three layers: an input layer, a hidden layer, and an output layer. The input layer contains 6 neurons, corresponding to 6 eigenvalues; the hidden layer contains k neurons, and the activation function is ReLU(); the output layer can output defect type and defect degree information.

[0066] For example, suppose there are c types of defects, the output layer contains c neurons, the activation function is softmax(), and the input of the i-th layer is a (i) , then the calculation from the input layer to the hidden layer is:

[0067] z (1) =W (1) X+b (1) ,

[0068] a (1) =ReLU(z (1) ),

[0069] And the calculation from the hidden layer to the output layer is:

[0070] z (2) =W (2) a (1) +b (2) ,

[0071] a (2) =softmax(z (2) ),

[0072] Among them, W (1) and W(2) is the weight matrix, b (1) and b (2) is the bias vector. The loss function selects the cross entropy loss function, which can be expressed by the following formula:

[0073]

[0074] In the above formula, is the predicted probability, y i is the true label value. In the process of training the initial thermal defect evaluation model, the back propagation algorithm is used to calculate and the optimization algorithm is used to update the model parameters W and b. The back propagation calculation steps include:

[0075] First, calculate the gradient of the loss function with respect to the output layer input:

[0076] δ (2) =a (2) -y,

[0077] Calculate the gradient of the loss function with respect to the hidden layer input:

[0078] δ (1) =(W (2) ) T δ (2) ⊙ReLU ′ (z (1 )),

[0079] Compute the gradients of weights and biases:

[0080]

[0081]

[0082] Finally, the Adam optimizer is used to update the parameters:

[0083]

[0084] Among them, α can be the learning rate, and are the first-order and second-order momentum estimates, respectively, and ∈ is a small constant to prevent division by zero. After repeatedly performing forward propagation, loss calculation, back propagation, and parameter update on the initial thermal defect evaluation model until the loss function converges, the target thermal defect evaluation model can be obtained.

[0085] As an optional implementation method, based on the first initial temperature data, the first target temperature data of the core is determined, and based on the second initial temperature data, the second target temperature data of the skin is determined, including: denoising the first initial temperature data to obtain the first target temperature data, and denoising the second initial temperature data to obtain the second target temperature data.

[0086] In this embodiment, after obtaining the first initial temperature data, the first initial temperature data may be subjected to denoising to obtain the first target temperature data, and after obtaining the second initial temperature data, the second initial temperature data may be subjected to denoising to obtain the second target temperature data. For example, a temperature sensor is used to collect temperature data of the core and the skin of a cable connector in real time, and the temperature data is subjected to denoising to obtain the first target temperature data and the second target temperature data.

[0087] As an optional embodiment, the evaluation result includes the thermal defect type and thermal defect fault information, wherein the thermal defect fault information is used to characterize the degree of thermal defect fault of the cable joint.

[0088] In this embodiment, the evaluation result may include a thermal defect type and thermal defect fault information, wherein the thermal defect type may be referred to as a defect type, and the thermal defect fault information may be referred to as defect fault degree information.

[0089] Optionally, after obtaining the thermal defect data of the cable joint, the thermal defect type can be determined according to the thermal defect data. Based on the thermal defect state corresponding to the thermal defect data, the thermal defect fault information can be determined, wherein the thermal defect state can be a cold state, a warm state, an overheated state, a hot state, and a fiery state, etc. Here, only examples are given for the thermal defect state, and the thermal defect state is not specifically limited.

[0090] For example, after the obtained first target temperature data of the wire core and the second target temperature data are input into the trained artificial intelligence model of the cable joint, the model can output defect type and defect fault degree information to realize real-time preliminary assessment of thermal defects of the cable joint.

[0091] In this embodiment, the first initial temperature data of the wire core in the cable joint and the second initial temperature data of the skin in the cable joint can be collected first, and then the first target temperature data of the wire core can be determined based on the first initial temperature data obtained above, and the second target temperature data of the skin can be determined based on the second initial temperature data obtained above, and finally the first target temperature data and the second target temperature data can be input into the target thermal defect evaluation model to evaluate the thermal defect data of the cable joint so as to output the evaluation result of the cable joint. Considering that the first target temperature data is determined based on the first initial temperature data obtained, and the second target temperature data is determined based on the second initial temperature data, and then the target thermal defect evaluation model is called based on the first target temperature data and the second target temperature data to achieve the purpose of obtaining the evaluation result of the cable joint, so as to solve the technical problem of low efficiency of thermal defect evaluation of the cable joint, and achieve the technical effect of improving the efficiency of thermal defect evaluation of the cable joint.

[0092] The technical solution of the embodiment of the present invention is illustrated below in conjunction with preferred implementation modes.

[0093] With the rapid development of the national economy and the continuous growth of energy demand, the stable operation of the power system as the foundation for supporting social and economic development is particularly important. As an important part of the power system, cable lines undertake the important task of power transmission. Especially in urban distribution networks and high-voltage transmission lines, cables are used more and more widely. The cable joint is the transition part connecting two sections of cable. Due to the complex structure, small contact area, and poor heat dissipation conditions of the cable joint, it has become a weak link in the cable line. In the long-term operation process, the cable joint is prone to thermal defects due to overheating, aging, external force damage, etc., which leads to failures. Furthermore, the existence of thermal defects not only affects the reliability and safety of the power system, but may also cause serious accidents such as fires.

[0094] At present, the thermal defect assessment of cable joints mainly relies on regular inspections and offline detection methods, such as infrared thermal imaging technology, partial discharge detection and resistance measurement methods. Infrared thermal imaging technology forms a temperature distribution image by detecting the thermal radiation on the surface of the cable joint, thereby evaluating the thermal state of the joint. This method can quickly detect abnormal temperature points in a non-contact manner. However, this method is greatly affected by ambient temperature and humidity, and usually requires regular inspections. Furthermore, by detecting the partial discharge signal around the cable joint, the insulation state of the joint can be evaluated. The abnormal increase in partial discharge is usually related to thermal defects. However, for early and minor thermal defects, the partial discharge signal may not be obvious enough, making it difficult to detect or evaluate, and it is easily affected by on-site electromagnetic interference, affecting the accuracy of the estimated results.

[0095] Furthermore, the resistance measurement method measures the resistance value of the cable joint regularly, and by comparing it with the resistance value during normal operation, evaluates whether the joint has poor contact or overheating. However, this method can only reflect the overall contact condition of the joint, cannot accurately locate the location of the thermal defect, and requires power outage for measurement, which affects the normal operation of the power system. In summary, although these methods can detect thermal defects to a certain extent, they still cannot achieve real-time evaluation, it is difficult to detect potential thermal defects in time, and the estimated cost is high, resulting in low efficiency in thermal defect evaluation of cable joints.

[0096] Therefore, in order to solve the above problems, the present invention proposes a cable joint thermal defect evaluation method based on real-time temperature sensing. This method uses a thermal defect finite element model and a deep neural network model of the cable joint, based on real-time temperature sensing data, and combined with data analysis and processing to achieve the evaluation of the thermal defect type and fault degree information of the cable joint, and ensure the timely discovery of potential safety hazards of the cable joint. This not only effectively improves the stability and safety of the power system, but also provides strong support for the maintenance and management of power equipment, so as to improve the technical effect of the thermal defect evaluation efficiency of the cable joint.

[0097] In an embodiment of the present invention, Figure 2 is a flow chart of a cable joint thermal defect evaluation method based on real-time temperature sensing according to an embodiment of the present invention. Figure 2 As shown, the flow chart includes the following steps:

[0098] Step S201, using a simulation model, obtaining thermal defect data of a cable joint, and temperature values ​​of a core and a skin of the cable joint.

[0099] In this embodiment, the simulation model can be used to obtain the thermal defect data of the cable joint.

[0100] Optionally, a finite element model of electromagnetic thermal coupling of the cable joint is established through finite element analysis software, which includes structures such as the cable core, semiconductor layer, insulation layer, metal shielding layer, inner and outer sheaths, and sets the types and degrees of possible thermal defects, including core overheating, insulation layer damage, sheath short circuit, etc.

[0101] Optionally, the simulation model is run, and heat conduction analysis data is set for different defects of the cable joint, the temperature distribution data of the cable joint under different defects is obtained, and the temperature values ​​of the core and the skin are recorded.

[0102] Step S202, extracting temperature characteristic values ​​of the temperature values ​​of the wire core and the skin.

[0103] In this embodiment, the average temperature of the core and the skin of the cable joint, or the temperature rise rate, or the temperature rise difference before and after the defect is extracted, and the above data can be used as the temperature characteristic data of the core and the skin. The average temperature of the core can be obtained by θ c The temperature rise rate of the wire core can be expressed by k c The temperature rise difference before and after the defect can be expressed by Δθ c The average temperature of the skin can be expressed by θ h The temperature rise rate of the skin can be expressed by k h The temperature rise difference before and after the skin defect can be expressed by Δθ h To express.

[0104] Optionally, the average temperature of the core and the average temperature of the skin are calculated in the same way and can both be recorded as θ, which can be expressed by the following formula:

[0105]

[0106] Among them, θ i It can be the temperature of the i-th sampling point, and n can be the total number of sampling points. Within a period of time, the temperature rise rate of the core and the temperature rise rate of the skin are calculated in the same way and can be uniformly recorded as k and expressed by the following formula:

[0107]

[0108] Among them, θ i and θ i-1 It can be the temperature value of two consecutive time points, and Δt can be the time interval. The calculation method of the temperature rise difference of the core before and after the defect and the temperature rise difference of the skin before and after the defect are the same, and can be uniformly recorded as Δθ and expressed by the following formula:

[0109] Δθ=θ max -θ min ,

[0110] Among them, θ max and θ min They are the highest and lowest temperatures measured within the total time nΔt, respectively.

[0111] Step S203, obtaining a training data set.

[0112] In this embodiment, the temperature characteristic values ​​and defect fault information can be organized into a training data set. Assuming that there are m training samples for this model optimization, each sample contains 6 characteristic values, and the defect type and degree information are used as labels to train the initial thermal defect evaluation model, the training data set can be expressed as:

[0113]

[0114] Among them, X i ∈R 6 , is the feature vector of the i-th sample, y i For the corresponding label.

[0115] Step S204: training a deep neural network.

[0116] In this embodiment, a deep neural network can be trained. Figure 3 is a schematic diagram of a deep neural network according to an embodiment of the present invention, such as Figure 3 As shown in the figure, the deep neural network consists of three layers: input layer, hidden layer, and output layer. The input layer contains 6 neurons, corresponding to 6 eigenvalues; the hidden layer contains k neurons, and the activation function is ReLU(); the output layer can output defect type and defect degree information.

[0117] For example, suppose there are c types of defects, the output layer contains c neurons, the activation function is softmax(), and the input of the i-th layer is a (i) , then the calculation from the input layer to the hidden layer is:

[0118] z (1) =W (1) X+b (1) ,

[0119] a (1) =ReLU(z (1) ),

[0120] And the calculation from the hidden layer to the output layer is:

[0121] z (2) =W (2) a (1) +b (2) ,

[0122] a (2) =softmax(z (2) ),

[0123] Among them, W (1) and W (2) is the weight matrix, b (1) and b (2) is the bias vector. The loss function selects the cross entropy loss function, which can be expressed by the following formula:

[0124]

[0125] In the above formula, is the predicted probability, y iis the true label value. In the process of training the initial thermal defect evaluation model, the back propagation algorithm is used to calculate and the optimization algorithm is used to update the model parameters W and b. The back propagation calculation steps include:

[0126] First, calculate the gradient of the loss function with respect to the output layer input:

[0127] δ (2) =a (2 )-y,

[0128] Calculate the gradient of the loss function with respect to the hidden layer input:

[0129] δ (1) =(W (2) ) T δ (2) ⊙ReLU ′ (z (1) ),

[0130] Compute the gradients of weights and biases:

[0131]

[0132] Finally, the Adam optimizer is used to update the parameters:

[0133]

[0134]

[0135] Among them, α can be the learning rate, and are the first-order and second-order momentum estimates, respectively, and ∈ is a small constant to prevent division by zero. After repeatedly performing forward propagation, loss calculation, back propagation, and parameter update on the initial thermal defect evaluation model until the loss function converges, the target thermal defect evaluation model can be obtained.

[0136] Step S205: real-time temperature collection and thermal defect evaluation.

[0137] In this embodiment, a temperature sensor is used to collect temperature data of the core and skin of the cable connector in real time, and the temperature data is denoised. The denoised temperature data is then input into a trained artificial intelligence model, which can output defect type and defect fault degree information to achieve real-time preliminary assessment of thermal defects in the cable connector.

[0138] In this embodiment, the first initial temperature data of the wire core in the cable joint and the second initial temperature data of the skin in the cable joint can be collected first, and then the first target temperature data of the wire core can be determined based on the first initial temperature data obtained above, and the second target temperature data of the skin can be determined based on the second initial temperature data obtained above, and finally the first target temperature data and the second target temperature data can be input into the target thermal defect evaluation model to evaluate the thermal defect data of the cable joint so as to output the evaluation result of the cable joint. Considering that the first target temperature data is determined based on the first initial temperature data obtained, and the second target temperature data is determined based on the second initial temperature data, and then the target thermal defect evaluation model is called based on the first target temperature data and the second target temperature data to achieve the purpose of obtaining the evaluation result of the cable joint, so as to solve the technical problem of low efficiency of thermal defect evaluation of the cable joint, and achieve the technical effect of improving the efficiency of thermal defect evaluation of the cable joint.

[0139] According to an embodiment of the present invention, a thermal defect evaluation device for a cable joint is provided. It should be noted that the thermal defect evaluation device for a cable joint can be used to execute a thermal defect evaluation method for a cable joint in Example 1.

[0140] Figure 4 Schematic diagram of a thermal defect evaluation device for a cable joint according to an embodiment of the present invention. Figure 4 As shown, a thermal defect evaluation device 400 for a cable joint may include: a collection unit 401 , a determination unit 402 and an evaluation unit 403 .

[0141] The collecting unit 401 is used to collect the first initial temperature data of the wire core in the cable joint and the second initial temperature data of the surface of the cable joint.

[0142] The determination unit 402 is used to determine first target temperature data of the wire core based on the first initial temperature data, and to determine second target temperature data of the skin based on the second initial temperature data.

[0143] The evaluation unit 403 is used to input the first target temperature data and the second target temperature data into the target thermal defect evaluation model of the cable joint, evaluate the thermal defect data of the cable joint, and output the evaluation result of the cable joint, wherein the target thermal defect evaluation model is established through the first historical temperature data of the wire core, the second historical temperature data of the skin and the historical thermal defect data of the cable joint, and the evaluation result is used to characterize the thermal defect state of the cable joint corresponding to the thermal defect data.

[0144] Optionally, the device also includes: a first acquisition unit, used to acquire first historical temperature data of the wire core and second historical temperature data of the skin by using a simulation model of the cable joint; a second acquisition unit, used to acquire historical thermal defect data of the cable joint by using a finite element model of the cable joint; and a third acquisition unit, used to train an initial thermal defect evaluation model of the cable joint based on the first historical temperature data, the second historical temperature data and the historical thermal defect data to obtain a target thermal defect evaluation model, wherein the initial thermal defect evaluation model is established based on parameter information of the environment in which the cable joint is located.

[0145] Optionally, the third acquisition unit also includes: a determination module, used to determine the training data set of the cable joint based on the first historical temperature data, the second historical temperature data and the historical thermal defect data; a training module, used to use the training data set to train the initial thermal defect evaluation model to obtain the target thermal defect evaluation model.

[0146] Optionally, the determination module may include: a first acquisition submodule, used to perform feature extraction on the first historical temperature data to obtain a first characteristic value of the wire core; a second acquisition submodule, used to perform feature extraction on the second historical temperature data to obtain a second characteristic value of the skin; an acquisition submodule, used to determine a training data set based on the first characteristic value, the second characteristic value and historical thermal defect data.

[0147] Optionally, the training module may include: a training submodule, configured to train the initial thermal defect evaluation model based on the training data set and using the target loss function of the cable joint to obtain a target thermal defect evaluation model.

[0148] Optionally, the determination unit 402 includes: a processing module, configured to perform denoising processing on the first initial temperature data to obtain first target temperature data, and perform denoising processing on the second initial temperature data to obtain second target temperature data.

[0149] Optionally, the evaluation result includes the thermal defect type and thermal defect fault information, wherein the thermal defect fault information is used to characterize the degree of thermal defect fault of the cable joint.

[0150] In this embodiment, a first initial temperature data of a core in a cable joint and a second initial temperature data of a skin in a cable joint are collected by a collection unit; a first target temperature data of a core is determined based on the first initial temperature data by a determination unit, and a second target temperature data of a skin is determined based on the second initial temperature data; the first target temperature data and the second target temperature data are input into a target thermal defect evaluation model of the cable joint by an evaluation unit, the thermal defect data of the cable joint is evaluated, and an evaluation result of the cable joint is output, wherein the target thermal defect evaluation model is established by the first historical temperature data of the core, the second historical temperature data of the skin and the historical thermal defect data of the cable joint, and the evaluation result is used to characterize the thermal defect state of the cable joint corresponding to the thermal defect data, thereby solving the technical problem of low thermal defect evaluation efficiency of the cable joint and achieving the technical effect of improving the thermal defect evaluation efficiency of the cable joint.

[0151] According to an embodiment of the present invention, a computer-readable storage medium is also provided, which includes a stored program, wherein when the program is executed by a processor, the device where the readable storage medium is located is controlled to execute the thermal defect evaluation method for the cable joint in the embodiment.

[0152] According to an embodiment of the present invention, a processor is further provided, and the processor is used to run a program, wherein the thermal defect evaluation method for a cable joint in the embodiment is executed when the program is run.

[0153] According to an embodiment of the present invention, a computer program product is also provided, including a computer program, and when the computer program is executed by a processor, the thermal defect evaluation method for a cable joint in the embodiment of the present invention is implemented.

[0154] According to an embodiment of the present invention, an electronic device is also provided, the electronic device comprising a processor and a memory for storing instructions executable by the processor, wherein the processor is configured to execute the instructions to implement the thermal defect evaluation method of the cable joint in the embodiment of the present invention.

[0155] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0156] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0157] In the several embodiments provided by the present invention, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic, for example, the division of units can be a logical function division, and there can be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0158] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed over multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0159] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0160] 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 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, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0161] The above are only preferred embodiments of the present invention. It should be pointed out that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for evaluating thermal defects of a cable joint, characterized in that: include: Collecting first initial temperature data of the wire core in the cable joint and second initial temperature data of the surface of the cable joint; Determine first target temperature data of the core based on the first initial temperature data, and determine second target temperature data of the skin based on the second initial temperature data; The first target temperature data and the second target temperature data are input into a target thermal defect evaluation model of the cable joint, the thermal defect data of the cable joint is evaluated, and the evaluation result of the cable joint is output, wherein the target thermal defect evaluation model is established through the first historical temperature data of the wire core, the second historical temperature data of the skin and the historical thermal defect data of the cable joint, and the evaluation result is used to characterize the thermal defect state of the cable joint corresponding to the thermal defect data.

2. The method according to claim 1, characterized in that The method further comprises: Using the simulation model of the cable joint, obtaining first historical temperature data of the wire core and second historical temperature data of the skin; Using a finite element model of the cable joint, obtaining historical thermal defect data of the cable joint; Based on the first historical temperature data, the second historical temperature data and the historical thermal defect data, the initial thermal defect evaluation model of the cable joint is trained to obtain the target thermal defect evaluation model, wherein the initial thermal defect evaluation model is established based on parameter information of the environment in which the cable joint is located.

3. The method according to claim 2, characterized in that Based on the first historical temperature data, the second historical temperature data and the historical thermal defect data, the initial thermal defect evaluation model of the cable joint is trained to obtain the target thermal defect evaluation model, including: Determining a training data set for the cable joint based on the first historical temperature data, the second historical temperature data, and the historical thermal defect data; The initial thermal defect evaluation model is trained using the training data set to obtain the target thermal defect evaluation model.

4. The method according to claim 3, characterized in that Determining a training data set for the cable joint based on the first historical temperature data, the second historical temperature data, and the historical thermal defect data includes: Performing feature extraction on the first historical temperature data to obtain a first feature value of the wire core; Performing the feature extraction on the second historical temperature data to obtain a second feature value of the epidermis; The training data set is determined based on the first feature value, the second feature value, and the historical thermal defect data.

5. The method according to claim 3, characterized in that: Using the training data set, training the initial thermal defect evaluation model to obtain the target thermal defect evaluation model includes: Based on the training data set, the initial thermal defect evaluation model is trained using the target loss function of the cable joint to obtain the target thermal defect evaluation model.

6. The method according to claim 1, characterized in that Determining first target temperature data of the core based on the first initial temperature data, and determining second target temperature data of the skin based on the second initial temperature data, comprises: The first initial temperature data is subjected to denoising processing to obtain the first target temperature data, and the second initial temperature data is subjected to denoising processing to obtain the second target temperature data.

7. The method according to claim 1, characterized in that The evaluation result includes a thermal defect type and thermal defect fault information, wherein the thermal defect fault information is used to characterize the degree of the thermal defect fault of the cable joint.

8. A thermal defect evaluation device for a cable joint, characterized in that: include: A collection unit, used for collecting first initial temperature data of the wire core in the cable joint and second initial temperature data of the surface of the cable joint; a determining unit, configured to determine first target temperature data of the wire core based on the first initial temperature data, and to determine second target temperature data of the skin based on the second initial temperature data; An evaluation unit is used to input the first target temperature data and the second target temperature data into a target thermal defect evaluation model of the cable joint, evaluate the thermal defect data of the cable joint, and output the evaluation result of the cable joint, wherein the target thermal defect evaluation model is established through the first historical temperature data of the wire core, the second historical temperature data of the skin and the historical thermal defect data of the cable joint, and the evaluation result is used to characterize the thermal defect state of the cable joint corresponding to the thermal defect data.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed by a processor, the device where the storage medium is located is controlled to execute the method according to any one of claims 1 to 7.

10. A computer program product comprising computer instructions, characterized in that: When the computer instructions are executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images