A power distribution line additional loss prediction method and device, a terminal and a medium

Abstract

The application discloses a power distribution line additional loss prediction method and device, a terminal and a medium, wherein the power distribution line additional loss prediction method comprises the following steps: collecting multi-source data; calculating distributed additional loss according to the multi-source data; inputting a line infrared thermal image and a visible light image into a prediction model to predict each point additional loss, so as to calculate total additional loss; by fusing a thermal balance equation and a machine learning algorithm, the application realizes accurate decomposition, calculation and tracing of the power distribution line additional loss, dynamically solves the conductor temperature and resistance by using multi-source data, accurately quantifies the loss contribution of the skin effect, harmonics and connection point aging, and solves the core problems of feature omission and decoupling loss by using the prediction model, thereby providing accurate local data support for line total additional loss calculation.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power distribution line operation and maintenance, and particularly relates to a power distribution line additional loss prediction method and device, a terminal and a medium. BACKGROUND

[0002] In the operation of the distribution network, the line loss rate is the core index to measure the economic operation level. The additional loss is an important part of the line loss, mainly caused by the heat generated when the current flows through the line and the equipment. Precise calculation, monitoring and tracing of the additional loss are the key prerequisites for formulating loss reduction and energy saving strategies and improving the operation efficiency of the power grid.

[0003] The existing additional loss calculation and monitoring methods mainly rely on traditional theoretical formulas and local measurement, and generally have the following problems: insufficient calculation accuracy, unable to reflect the dynamic operating environment. The actual resistance value of the conductor is highly dependent on its operating temperature, and the operating temperature is a dynamic variable determined by multiple factors such as current, ambient temperature, wind speed, and solar intensity. The existing technology fails to effectively integrate these dynamic environmental parameters, making it impossible to accurately calculate the true resistance and loss of the conductor under actual operating conditions, resulting in a large deviation between the calculation results and the actual situation. Secondly, the data utilization is insufficient, and there is a lack of multi-source information fusion capability: with the development of intelligent distribution networks, SCADA systems, power quality monitoring, unmanned aerial vehicle inspection, and meteorological services provide massive multi-source data. However, the existing technology fails to fully utilize these data assets. The model is often static and isolated, lacking a framework for deep fusion analysis of electrical operation data, macro environmental data, micro image data, and power grid physical topology, resulting in a serious information island phenomenon and the failure to fully exploit the value of data to improve the accuracy and depth of state perception. Furthermore, the fusion of multi-modal data such as infrared, visible light, electricity, and environment often uses a general fusion architecture of "pixel-level superposition" or "single feature vector splicing", without feature decoupling processing for the multi-cause characteristics of point loss: different loss mechanisms interfere with each other during the fusion process, making it impossible to achieve precise mapping of "specific features to specific loss types", resulting in inaccurate loss type judgment and ultimately causing loss type misjudgment. SUMMARY

[0004] In order to overcome the defects in the prior art, the present application provides a power distribution line additional loss prediction method, comprising: collecting multi-source data; calculating distributed additional loss according to the multi-source data; inputting the line infrared thermal image and the visible light image into the prediction model to predict each point additional loss and calculate the total additional loss.

[0005] As a preferred scheme of the power distribution line additional loss prediction method of the present application, wherein: the multi-source data includes line current I, harmonic current Ih , ambient temperature T amb , wind speed V wind , sunshine intensity S rad , DC resistance of conductor R dc , infrared thermal image, visible light image.

[0006] As a preferred scheme of the power distribution line additional loss prediction method of the present application, wherein: the calculation of the distributed additional loss according to the multi-source data comprises:

[0007] ;

[0008] In the formula, is the distributed additional loss, is the AC resistance under the 50Hz fundamental frequency, is the AC resistance under the hth harmonic frequency.

[0009] As a preferred scheme of the power distribution line additional loss prediction method of the present application, wherein: further comprising:

[0010] Step 1: initialize the conductor temperature T cond1 ;

[0011] Step 2: calculate the DC resistance R cond1 under the conductor temperature T dct :

[0012] R dct = R dc [1+α(T cond1 - 20)];

[0013] In the formula, α is the resistance temperature coefficient;

[0014] Step 3: calculate the heat generation power P heat and the heat dissipation power P cool :

[0015] P heat = I²R dct;

[0016] Heat dissipation power P cool :

[0017] P cool =Q conv +Q rad -Q sun;

[0018] In the formula, Q conv is the convection heat dissipation power, Q rad is the radiation heat dissipation power, and Q sun is the sunshine heat absorption power.

[0019] Step four: calculate the heat balance deviation ΔP and correct:

[0020] ΔP = P heat - P cool;

[0021] Step five: if abs(ΔP) is less than 0.001, the current T cond1 is the actual temperature T cond of the conductor to be calculated, and the loop is exited, and the distributed additional loss is calculated accordingly; otherwise, adjust T cond according to the heat balance deviation ΔP and the Newton-Raphson method, and return to step two to start the next iteration calculation. cond

[0022] As a preferred scheme of the power distribution line additional loss prediction method described in the application, wherein: the prediction model comprises a feature extraction layer, a decoupling layer, a residual network layer and a BiLSTM layer; the decoupling layer comprises two independent feature subspaces, which are a contact resistance loss subspace and an environmental interference loss subspace; the residual network layer comprises a spatial pyramid pooling layer and a full connection layer; the feature extraction layer is used to screen temperature rise features from infrared thermal images and extract physical defect features of point targets from visible light images; the temperature rise features and the physical defect features of the point targets are input into the contact resistance loss subspace, and the features are processed through a 1D convolution layer to output a contact resistance loss feature vector; the wind speed V wind , the solar intensity S rad , the environmental loss coefficient K n , and the temperature rise features are input into the environmental interference loss subspace, and are processed through a 2D convolution layer to output an environmental interference loss feature vector; the contact resistance loss feature vector and the environmental interference loss feature vector are weighted and fused, and are output through the residual network layer and the BiLSTM layer to output the additional loss values of each point.

[0023] As a preferred scheme of the power distribution line additional loss prediction method described in the application, wherein: the environmental loss coefficient is:

[0024] K n = 1 + 0.01S rad + 0.02(1-V wind / 15).

[0025] As a preferred scheme of the power distribution line additional loss prediction method described in the application, wherein: the total additional loss comprises:

[0026] ;

[0027] In the formula, L is the total additional loss,​ for each point-like additional loss value.

[0028] The application further provides a power distribution line additional loss prediction device for implementing the power distribution line additional loss prediction method according to any one of the above, and the power distribution line additional loss prediction device comprises: a collection module configured to perform collection of multi-source data; a calculation module configured to perform calculation of distributed additional loss according to the multi-source data; and a prediction module configured to perform input of a line infrared thermal image and a visible light image into a prediction model, prediction of each point-like additional loss, and calculation of total additional loss.

[0029] The application further provides a terminal device, comprising:

[0030] one or more processors;

[0031] a memory coupled to the processor and configured to store one or more programs;

[0032] When the one or more programs are executed by the one or more processors, the one or more processors implement the power distribution line additional loss prediction method according to any one of the above.

[0033] The application further provides a computer readable storage medium having a computer program stored thereon, and the computer program is executed by a processor to implement the power distribution line additional loss prediction method according to any one of the above.

[0034] The application has the following beneficial effects: the application realizes accurate decomposition, calculation and tracing of power distribution line additional loss by fusing a thermal balance equation and a machine learning algorithm, dynamically solves conductor temperature and resistance by using multi-source data, accurately quantifies loss contribution of each of skin effect, harmonics and connection point aging, and solves the core problems of feature omission and decoupling loss by using a prediction model, thereby providing accurate local data support for line total additional loss calculation. BRIEF DESCRIPTION OF DRAWINGS

[0035] In order to more clearly illustrate the technical solutions of the embodiments of the application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the application, and for those skilled in the art, other drawings can also be obtained without creative labor. Among them:

[0036] Fig. 1 a flowchart of the power distribution line additional loss prediction method according to the first embodiment of the application;

[0037] Fig. 2 a flowchart of the iteration calculation of the actual conductor temperature according to the first embodiment of the application. DETAILED DESCRIPTION

[0038] In order to make the above objectives, features and advantages of the present application more clear and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all the other embodiments obtained by those of ordinary skill in the art without creative work should belong to the protection scope of the present application.

[0039] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. However, it will be apparent to one skilled in the art that the present application can be practiced without the specific details presented herein. In other instances, well-known methods have not been described in detail in order to avoid obscuring aspects of the present application.

[0040] Secondly, the "one embodiment" or "embodiment" referred to herein means that the specific features, structures or characteristics can be included in at least one implementation of the present application. The "in one embodiment" appearing in different places in the specification does not mean the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments.

[0041] The present application is described in detail with reference to the accompanying drawings. In the detailed description of the embodiments of the present application, the sectional view of the device structure is partially enlarged without the general proportion for the convenience of description, and the schematic view is only an example, which should not limit the scope of protection of the present application herein. In addition, the three-dimensional spatial dimensions of length, width and depth should be included in actual manufacture.

[0042] Meanwhile, in the description of the present application, it should be noted that the terms "upper, lower, inner and outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application. In addition, the terms "first, second or third" are only for the purpose of description, and cannot be understood as indicating or implying relative importance.

[0043] In the present application, unless otherwise explicitly specified and limited, the terms "mounting, connecting, connection" should be understood broadly, for example: it can be fixed connection, detachable connection or integral connection; it can also be mechanical connection, electrical connection or direct connection, it can also be indirectly connected through intermediate medium, or it can be the communication inside two elements. For those of ordinary skill in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0044] Example 1

[0045] Referring to Figs. 1-2 , for the first embodiment of the present application, the embodiment provides a power distribution line additional loss prediction method, comprising:

[0046] S1: Collect multi-source data.

[0047] The multi-source data includes line current I collected by the SCADA system, harmonic current I h collected by the power quality monitoring device, meteorological data (ambient temperature T amb , wind speed V wind , and solar radiation intensity S rad ), conductor DC resistance R dc obtained from the equipment account database, infrared thermal image and visible light image collected by the unmanned aerial vehicle. All data are aligned and synchronized on the time scale to form a unified data set.

[0048] S2: Calculate distributed additional loss according to multi-source data.

[0049] Take the IEEE 738 heat balance equation as the core mechanism model to calculate the actual conductor temperature T cond and AC resistance. Specifically, refer to Fig. 2 , the actual conductor temperature is iteratively calculated according to the following steps:

[0050] Step one: initialize the conductor temperature T cond1 ;

[0051] Step two: calculate the DC resistance R dct under the conductor temperature T cond1 :

[0052] R dct = R dc [1+α(T cond1 - 20)];

[0053] In the formula, α is the resistance temperature coefficient;

[0054] Step three: calculate the heat generation power P heat and heat dissipation power P cool :

[0055] P heat = I²R dct;

[0056] Heat dissipation power P cool :

[0057] P cool =Q conv +Q rad -Q sun ;

[0058] wherein, ;

[0059] ;

[0060] Q sun = DS rad ;

[0061] wherein Q conv is the heat dissipation power, Q rad is the radiation heat dissipation power, Q sun is the solar heat absorption power, D is the diameter of the wire, is the air density, μ is the dynamic viscosity of air, k f is the thermal conductivity of air, is the emissivity of the wire surface, and σ is the Stefan-Boltzmann constant;

[0062] Step four: calculate the heat balance deviation ΔP and correct it:

[0063] ΔP = P heat - P cool;

[0064] Step five: if abs(ΔP) is less than 0.001, the current T cond1 is the actual temperature of the wire T cond , exit the loop, and calculate the AC resistance of the wire under the 50Hz fundamental frequency R and the AC resistance of the wire under the hth harmonic frequency R , respectively, to calculate the distributed additional loss; wherein abs() is the abbreviation of absolute value.

[0065] Otherwise, adjust T cond according to the heat balance deviation ΔP:

[0066] If ΔP > 0 (heat > heat dissipation), it means that the guessed actual temperature of the wire T cond is too low, and the guess value of the next iteration should be increased;

[0067] If ΔP < 0 (heat < heat dissipation), it means that the guessed actual temperature of the wire T cond is too high, and the guess value of the next iteration should be decreased.

[0068] Further, with the updated T cond , return to step two and start the next iteration calculation.

[0069] Since there is a value error in the calculation of the heat dissipation power, it will cause T condTherefore, the embodiment is corrected by machine learning, and the accuracy of the actual conductor temperature T cond is further improved.

[0070] The embodiment uses a short-term uncooked high-precision temperature sensor to directly measure the real temperature T condreal of the conductor. [I, T amb , V wind , S rad ] is the feature data X, and the theoretical conductor temperature T condtheoretical is predicted by the regression model LightGBM.

[0071] Calculate the deviation:

[0072] ΔT_error = T condreal - T condtheoretical;

[0073] Form a data set: Collect a large number of (X, ΔT_error) data pairs at different times to form a training data set, and predict ΔT_error by gradient boosting tree model such as XGBoost, so as to correct the conductor temperature T cond .

[0074] Further, calculate the alternating current resistance under the 50Hz fundamental frequency :

[0075] ;

[0076] In the formula, is the skin effect coefficient under 50Hz, and α is the resistance temperature coefficient;

[0077] Calculate the alternating current resistance under the hth harmonic frequency :

[0078] ;

[0079] In the formula, is the skin effect coefficient under the hth harmonic frequency;

[0080] Calculate the distributed additional loss:

[0081] ;

[0082] In the formula, is the distributed additional loss, is the alternating current resistance under the 50Hz fundamental frequency, is the alternating current resistance under the hth harmonic frequency.

[0083] Preferably, the embodiment takes into account the cost and technical feasibility, that is, to directly and continuously measure the conductor temperature on the entire line, it is necessary to install an online monitoring device (such as a temperature sensor with wireless communication function or a tension sag monitor) at each measurement point, and a power distribution line can be tens of kilometers long, with hundreds or thousands of towers, and the hardware cost, installation cost and later maintenance cost of installing expensive sensors and communication modules at each point are astronomical figures, which is completely economically unfeasible for power distribution companies. Moreover, the conductor is high-voltage, how to power the sensor? How to realize reliable data transmission? These are technical challenges. Based on this, a fusion model based on physical mechanism iterative calculation and machine learning correction of sparse measured data is proposed, which not only meets the economic requirements of global estimation, but also ensures the accuracy of the results through the measurement of key points.

[0084] S3: inputting the line infrared thermal image and the visible light image into the prediction model to predict each point-like additional loss, so as to calculate the total additional loss.

[0085] The prediction model comprises a feature extraction layer, a decoupling layer, a residual network layer and a BiLSTM layer; the decoupling layer comprises two independent feature subspaces, which are constructed according to the causes of point-like loss (contact resistance and environmental interference), and are respectively a contact resistance loss subspace and an environmental interference loss subspace; the residual network layer comprises a spatial pyramid pooling layer and a full connection layer.

[0086] The feature extraction layer is used to screen the temperature rise features (the average value of temperature rise of all pixel points in the point-like target region, the difference between the highest temperature in the point-like target region and the environmental temperature, and the temperature rise variance) from the infrared thermal image and to extract the physical defect features of the point-like target from the visible light image; the physical defect features of the point-like target specifically comprise:

[0087] rust grade F r : divided into 0-3 levels according to the proportion of rust area (0 level: no rust; 1 level: rust area <10%; 2 level: 10%-30%; 3 level: >30%);

[0088] loose clamp grade F c : divided into 0-2 levels according to the displacement amount (0 level: no looseness; 1 level: displacement 1-3mm; 2 level: displacement >3mm);

[0089] contact area ratio F s : the ratio of the actual contact area to the standard design contact area (calculated by image pixels).

[0090] The temperature rise features and the physical defect features of the point-like target are input into the contact resistance loss subspace, the features are processed through a 1D convolution layer, and a contact resistance loss feature vector is output;

[0091] The wind speed V wind , the sunshine intensity S rad , the environmental loss coefficient K n , and the temperature rise characteristic are input into the environmental interference loss subspace, are processed through a 2D convolution layer, and an environmental interference loss characteristic vector is output; wherein the environmental loss coefficient is:

[0092] K n = 1 + 0.01S rad + 0.02(1-V wind / 15).

[0093] The contact resistance loss characteristic vector and the environmental interference loss characteristic vector are fused by weighting, the fused characteristic vector is input into a residual network layer, the extraction ability of the characteristic degradation and the key loss characteristic (such as the insulator damage-local discharge correlation characteristic and the joint corrosion-contact resistance correlation characteristic) is eliminated, and finally the time sequence fluctuation rule of the point loss is captured through a BiLSTM layer, and each point additional loss value is output.

[0094] Further, the total additional loss is calculated as:

[0095] ;

[0096] In the formula, is the total additional loss, is the predicted point additional loss value.

[0097] Embodiment 2

[0098] The present application provides a power distribution line additional loss prediction device for realizing the steps of the power distribution line additional loss prediction method of any one of the above embodiments, and the power distribution line additional loss prediction device comprises:

[0099] A collection module configured to perform collection of multi-source data;

[0100] A calculation module configured to perform calculation of distributed additional loss according to the multi-source data;

[0101] A prediction module configured to perform input of the line infrared thermal image and the visible light image into a prediction model, prediction of each point additional loss, and calculation of the total additional loss.

[0102] Embodiment 3

[0103] The present embodiment provides a terminal device, comprising:

[0104] One or more processors;

[0105] A memory coupled to the processor, configured to store one or more programs;

[0106] When the one or more programs are executed by the one or more processors, the one or more processors implement the power distribution line additional loss prediction method as described above.

[0107] The processor is configured to control overall operations of the terminal device to complete all or part of the steps of the power distribution line additional loss prediction method described above. The memory is configured to store various types of data to support operations of the terminal device, which can include, for example, instructions for any application or method operating on the terminal device, and application-related data. The memory can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0108] The terminal device can be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic elements, to execute the power distribution line additional loss prediction method described in any of the above embodiments and achieve the same technical effects as the above method.

[0109] Embodiment 4

[0110] The embodiment provides a computer readable storage medium, and program instructions are executed by a processor to implement steps of the power distribution line additional loss prediction method according to any one of the above embodiments. For example, the computer readable storage medium can be the above-mentioned memory including program instructions, and the above-mentioned program instructions can be executed by the processor of the terminal device to complete the power distribution line additional loss prediction method according to any one of the above embodiments, and achieve the technical effects consistent with the above method.

[0111] It should be appreciated that embodiments of the application can be realized by computer hardware, a combination of hardware and software, or through computer instructions stored in a non-transitory computer readable memory. The method can be implemented in a computer program using standard programming techniques, including non-transitory computer readable storage medium configured with a computer program, wherein the storage medium thus configured causes a computer to operate in a specific and predefined manner according to the method described in the specific embodiments and the accompanying drawings. Each program can be implemented in a high-level procedural or object-oriented programming language to communicate with a computer system. However, if necessary, the program can be implemented in assembly or machine language. In any case, the language can be a compiled or interpreted language. In addition, the program can be run on a programmed special-purpose integrated circuit for this purpose.

[0112] In addition, the operations of the processes described herein can be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. The processes described herein (or variations and / or combinations thereof) can be performed under the control of one or more computer systems configured with executable instructions (e.g., computer programs, one or more computer programs, or one or more applications) to perform operations, and can be implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications) executing collectively on one or more processors, by hardware, or combinations thereof. The computer programs include a plurality of instructions executable by one or more processors.

[0113] Further, the methods can be implemented in any type of computing platform operatively coupled to a suitable computing platform, including but not limited to a personal computer, a mini-computer, a mainframe, a workstation, a network or distributed computing environment, a stand-alone or integrated computer platform, or in communication with a charged particle tool or other imaging device, and the like. Aspects of the present application can be implemented in machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated to the computing platform, such as a hard disk, an optical read and / or write storage medium, RAM, ROM, and the like, such that it can be read by a programmable computer to configure and operate the computer to perform the processes described herein when the storage medium or device is read by the computer. In addition, the machine-readable code, or portions thereof, can be transmitted over a wired or wireless network. The present application, as described herein, includes these and other non-transitory computer readable storage media of different types when such media include instructions or programs implementing the steps described above in connection with a microprocessor or other data processor. The present application also includes the computer itself when programmed according to the methods and techniques described herein. The computer program can be applied to input data to perform the functions described herein and thereby transform the input data into output data that can be stored to non-volatile memory. The output information can further be applied to one or more output devices such as a display. In a preferred embodiment of the present application, the transformed data represents a physical and tangible object, including a particular visual depiction of a physical and tangible object produced on a display.

[0114] As used in this application, the terms "component," "module," "system" and the like are intended to refer to a computer-related entity, either hardware, firmware, a combination of hardware and software, software, or software in execution. For example, a component can be, but is not limited to being, a process running on a processor, a processor, an object, an executable, a thread of execution, a program, and / or a computer. By way of illustration, both an application running on a computing device and the computing device can be a component. One or more components can reside within a process and / or thread of execution and a component can be localized, partially and / or entirely, in one computer or distributed between two or more computers. In addition, these components can execute from various computer readable media having various data structures stored thereon. The components can communicate by way of local and / or remote processes such as in accordance with a signal having one or more data packets (e.g., data from one component interacting with another component in a local system, distributed system, and / or across a network such as the Internet with other systems via the signal).

[0115] It should be noted that the above examples are only used to illustrate the technical solutions of the present application but not limit the present application. Although the present application is described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or equivalently replaced, without departing from the spirit and scope of the technical solutions of the present application, which should be covered in the scope of the claims of the present application.

Claims

1. A method of predicting distribution line additional loss, characterized by, The method comprises: collecting multi-source data; calculating distributed additional loss according to the multi-source data; inputting line infrared thermal image and visible light image into a prediction model to predict each point-like additional loss and calculate total additional loss; wherein the prediction model comprises a feature extraction layer, a decoupling layer, a residual network layer and a BiLSTM layer; the decoupling layer comprises two independent feature subspaces, which are a contact resistance loss subspace and an environmental interference loss subspace; the residual network layer comprises a spatial pyramid pooling layer and a full connection layer; the feature extraction layer is used to screen temperature rise features from the infrared thermal image and extract physical defect features of point-like targets from the visible light image; the temperature rise features and the physical defect features of the point-like targets are input into the contact resistance loss subspace, and feature processing is performed through a 1D convolution layer to output a contact resistance loss feature vector; The wind speed V wind , the sunshine intensity S rad , the environmental loss coefficient K n , the temperature rise characteristic is input to the environmental interference loss subspace, is handled through 2D convolution layer, and the environmental interference loss characteristic vector is output. the contact resistance loss feature vector and the environmental interference loss feature vector are weightedly fused, and each point-like additional loss value is output through the residual network layer and the BiLSTM layer.

2. The power distribution line additional loss prediction method of claim 1, wherein The multi-source data includes line current I, harmonic current I h , ambient temperature T amb , wind speed V wind , sunshine intensity S rad , conductor DC resistance R dc , infrared thermal image, visible light image.

3. The power distribution line additional loss prediction method of claim 2, wherein The calculation of the distributed additional loss according to the multi-source data comprises: ; wherein is the distributed additional loss, is the AC resistance at the fundamental frequency of 50 Hz, is the AC resistance at the hth harmonic frequency.

4. The power distribution line additional loss prediction method as claimed in claim 3, characterized by, The method further comprises: Step one: initialize set wire temperature T cond1 ; Step two: Calculate the conductor temperature T cond1 The DC resistance R dct : R dct = R dc [1+α(T cond1 - 20)] wherein, α is the resistance temperature coefficient; Step three: Calculate the heat power P heat and the heat dissipation power P cool : P heat = I²R dct Heat dissipation power P cool : P cool =Q conv +Q rad -Q sun where Q conv is the convective heat loss power, Q rad is the radiative heat loss power, Q sun is the solar heat gain power; Step four: calculate the thermal equilibrium deviation ΔP and correct: ΔP = P heat - P cool Step 5: If abs(ΔP) is less than 0.001, then the current T cond1 This is the actual temperature T of the conductor. cond If the loop is broken, the distributed additional losses are calculated accordingly; otherwise, T is adjusted according to the thermal balance deviation ΔP and the Newton-Raphson method. cond Using the adjusted T cond Return to step two and begin the next iteration of the calculation.

5. The method of predicting distribution line additional loss according to claim 4, wherein, The environmental loss coefficient is: K n = 1 + 0.01S rad + 0.02(1-V wind / 15).

6. The method of predicting distribution line additional loss according to claim 5, wherein, The total additional loss comprises: ; wherein is the total additional loss, is the predicted individual point-like additional loss value.

7. A power distribution line additional loss prediction device for implementing the power distribution line additional loss prediction method according to any one of claims 1 to 6, characterized by The power distribution line additional loss prediction device comprises: a collection module configured to perform the collection of multi-source data; a calculation module configured to perform the calculation of distributed additional loss according to the multi-source data; a prediction module configured to perform the input of line infrared thermal image and visible light image into a prediction model to predict each point-like additional loss and calculate total additional loss.

8. A terminal device, comprising: The device comprises: one or more processors; a memory coupled to the processor(s) for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the power distribution line additional loss prediction method according to any one of claims 1 to 6.

9. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the power distribution line additional loss prediction method according to any one of claims 1 to 6.

Images