Method and device for predicting comprehensive disposal cost of old transformer

Abstract

The invention provides an old transformer comprehensive disposal cost prediction method and device, and the method comprises the steps: obtaining a technical cost factor, an economic cost factor and an environmental protection cost factor of old transformer disposal, and constructing an old transformer disposal factor vector; and inputting the old transformer disposal factor vector into the least square support vector machine model after optimization training to obtain the comprehensive disposal cost of the old transformer. By comprehensively considering the cost problems in the aspects of technology, economy and environmental protection in the transformer disposal process, the disposal cost of the old transformer is predicted in combination with dynamic changes, and the comprehensiveness and reliability of the disposal cost prediction value of the old transformer are improved.

Description

Technical Field

[0001] The present invention relates to the field of electric power equipment, and in particular to a method and device for predicting the comprehensive disposal cost of old transformers. Background Art

[0002] As one of the main carriers of the power system, the safe and stable operation of the transformer is related to the overall risk resistance of the power grid. For transformers with a long operating life, the equipment has gradually entered the aging period, and the equipment defect detection rate, maintenance workload and maintenance costs have all increased. In addition, due to the limitations of the early manufacturing process, the loss of old transformers is quite different from that of newly produced transformers. Therefore, from the perspective of improving reliability and saving power grid losses, old transformers need to be disposed of.

[0003] Considering that transformers are valuable assets of power grid companies, at present, when power grid companies conduct asset management and investment decisions on transformers, they usually use the periodic cost within the life of the transformer as the standard, establish a power grid equipment investment decision model based on the full life cycle cost, and use the model to perform optimization analysis to solve the optimal transformer disposal strategy.

[0004] The overall service life of my country's power grid equipment is relatively short. Combined with my country's actual national conditions, the calculation of the comprehensive cost of transformers should focus on cost accounting in the future operating period to make full use of the available value of transformers. The existing transformer life cycle cost calculation methods all use given static costs for preliminary calculations. In addition, the operating cycle of old transformers is relatively long, and it is difficult to obtain comprehensive cost data during their life cycle, and the actual data collection cycle is long. With the gradual refinement of the division of cost input stages, the amount of calculation increases, and a large amount of manpower and material resources are consumed. Human subjective factors have a greater impact on the division and calculation of transformer costs, which reduces the objectivity of the calculation results of the comprehensive disposal cost of transformers. Therefore, the significant disadvantage of the existing transformer life cycle cost calculation is the lack of an effective method that can scientifically and accurately predict the comprehensive disposal cost of transformers. Summary of the invention

[0005] Based on this, the present invention provides a method and device for predicting the comprehensive disposal cost of old transformers. By comprehensively considering the technical, economic and environmental cost issues in the transformer disposal process, the disposal cost of old transformers is predicted in combination with dynamic changes, thereby improving the comprehensiveness and reliability of the predicted value of the disposal cost of old transformers.

[0006] In a first aspect, the present invention provides a method for predicting the comprehensive disposal cost of old transformers, comprising:

[0007] Obtain technical cost factors, economic cost factors and environmental cost factors for the disposal of old transformers, and construct a factor vector for the disposal of old transformers;

[0008] The old transformer disposal factor vector is input into the least squares support vector machine model after optimization training to obtain the comprehensive disposal cost of the old transformer.

[0009] Furthermore, the technical cost factors for the disposal of old transformers include the power interruption caused by the old transformer failure, the compensation cost per unit power outage caused by the old transformer, and the power production ratio per unit power shortage caused by the old transformer;

[0010] The economic cost factors for the disposal of old transformers include the initial investment cost of old transformers, the average annual fault repair cost of old transformers, the average annual maintenance cost of old transformers, the inflation rate, the operation and maintenance rate of old transformers, the average annual failure rate of old transformers, the average annual repair time of old transformers, the operating years of old transformers and the scrap rate of old transformer equipment;

[0011] The environmental cost factors for the disposal of old transformers include the energy consumption of manufacturing old transformers, the energy consumption of reusing and disposing old transformers, the typical pollutant emissions of manufacturing old transformers and the pollutant emission reduction of reusing old transformers;

[0012] The comprehensive disposal cost of old transformers includes the total technical cost of old transformer disposal, the total economic cost of old transformer disposal and the total environmental protection cost of old transformer disposal.

[0013] Furthermore, the specific expression of the least squares support vector machine model is:

[0014]

[0015] in, The comprehensive disposal cost of old transformers is is the historical disposal factor vector of old transformers, is the old transformer disposal factor vector, is the sample number of the historical disposal factor vector of old transformers, is the kernel function of the least squares support vector machine model, , is the bandwidth parameter of the kernel function, is the Lagrange multiplier, is the bias vector.

[0016] Furthermore, the optimization objective function of the least squares support vector machine model is:

[0017]

[0018] in, is the optimization objective function of the least squares support vector machine, is the weight matrix, , is the error vector, is the regularization parameter, is the trace of the matrix.

[0019] Furthermore, the optimization training process of the least squares support vector machine model includes:

[0020] Step S201, obtaining a historical disposal data set of old transformers, wherein the historical disposal data set includes a plurality of historical disposal factor vectors of old transformers and a plurality of historical comprehensive disposal costs of old transformers;

[0021] Step S202, setting initial population parameters, randomly generating an initialization population based on the initial population parameters, and initializing an iteration value, wherein the initialization population includes a plurality of elements, each element includes a regularization parameter and a bandwidth parameter;

[0022] Step S203, selecting a regularization parameter and a bandwidth parameter corresponding to any element in the initialization population and applying them to a least squares support vector machine model to obtain an initialized least squares support vector machine model;

[0023] Step S204, inputting the historical disposal factor vector of any old transformer into the initialized least squares support vector machine model to obtain the historical comprehensive disposal prediction cost of the old transformer;

[0024] Step S205, repeatedly executing step S204 until the historical comprehensive disposal prediction cost of the old transformer corresponding to the historical disposal factor vector of each old transformer is obtained;

[0025] Step S206, obtaining the fitness of the element according to the historical comprehensive treatment prediction cost and the historical comprehensive treatment cost corresponding to the historical treatment factor vector;

[0026] Step S207, repeating the above steps S203 to S206 until the fitness of all elements in the initialized population is obtained;

[0027] Step S208, taking the minimum value of the fitness of all elements as the optimal fitness, and obtaining the optimal regularization parameter and the optimal bandwidth parameter contained in the element corresponding to the optimal fitness;

[0028] Step S209, if the iteration value is less than the maximum number of iterations in the initialization population parameters, further process the iteration value, update the positions of the leader and the follower in the initialization population, and repeat steps S203 to S208 until the iteration value is greater than the maximum number of iterations in the initialization population parameters;

[0029] Step S210, taking the minimum value of all the best fitness as the best fitness, and obtaining the optimal regularization parameter and the optimal bandwidth parameter contained in the element corresponding to the best fitness, and combining the optimal regularization parameter and the optimal bandwidth parameter to obtain the optimized trained minimum squares support vector machine model.

[0030] Furthermore, the initial population number includes the number of search agents, the maximum number of iterations, the number of variables, the upper bound and the lower bound;

[0031] The expression for randomly generating the initialized population based on the initial population parameters is:

[0032]

[0033] in, Indicates the number of initialized populations The first elements, For elements The random function of For the The upper boundary of the row, For the The bottom edge of the row.

[0034] Furthermore, the specific expression for obtaining the fitness of the element according to the historical comprehensive treatment prediction cost and the historical comprehensive treatment cost corresponding to the historical treatment factor vector is:

[0035]

[0036] in, For elements The fitness of For elements The corresponding historical comprehensive disposal cost, For elements The corresponding historical comprehensive disposal forecast cost, is the number of training samples.

[0037] In a second aspect, the present invention further provides a device for predicting the comprehensive disposal cost of old transformers, comprising:

[0038] A factor vector acquisition module is used to obtain technical cost factors, economic cost factors and environmental cost factors for the disposal of old transformers, and to construct a factor vector for the disposal of old transformers;

[0039] The disposal cost prediction module is used to input the old transformer disposal factor vector into the least squares support vector machine model after optimization training to obtain the comprehensive disposal cost of the old transformer.

[0040] In a third aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any one of the methods for predicting the comprehensive disposal cost of old transformers in the first aspect.

[0041] In a fourth aspect, the present invention further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the processor executes the steps of any one of the methods for predicting the comprehensive disposal cost of old transformers in the first aspect.

[0042] The beneficial effects of adopting the above technical solution are as follows: this embodiment obtains the disposal factor vector of the old transformer by comprehensively considering the technical, economic and environmental aspects, and obtains the comprehensive disposal cost of the old transformer based on the comprehensive disposal factor vector, so that the disposal cost of the old transformer can be obtained more comprehensively and in accordance with the actual situation during the disposal process, providing objective reference data for subsequent disposal plans for old transformers and improving the disposal efficiency of old transformers. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art are briefly introduced below.

[0044] Figure 1 This is a schematic diagram of a method for predicting the comprehensive disposal cost of old transformers in one embodiment of the present application;

[0045] Figure 2 A schematic diagram of parameters of the comprehensive disposal cost of old transformers in one embodiment of the present application;

[0046] Figure 3 This is a flow chart of a method for predicting the comprehensive disposal cost of old transformers in one embodiment of the present application;

[0047] Figure 4 Schematic diagram of a device for predicting the comprehensive disposal cost of old transformers in one embodiment of the present application. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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 in the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. In order to explain the present invention in more detail, the method and device for predicting the comprehensive disposal cost of old transformers provided by the present invention are specifically described below in combination with the drawings.

[0049] Unless otherwise defined, the technical terms or scientific terms used in the disclosure of this application should be understood by people with ordinary skills in the field to which the present invention belongs. The "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. Similarly, similar words such as "one", "one" or "the" do not indicate a quantitative limit, but indicate that there is at least one. Similar words such as "include" or "include" mean that the elements or objects appearing in front of the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. Similar words such as "connect" or "connected" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship can also change accordingly.

[0050] As one of the main carriers of the power system, the safe and stable operation of the transformer is related to the overall risk resistance of the power grid. For transformers with a long operating life, the equipment has gradually entered the aging period, and the equipment defect detection rate, maintenance workload and maintenance costs have all increased. In addition, due to the limitations of the early manufacturing process, the loss of old transformers is quite different from that of newly produced transformers. Therefore, from the perspective of improving reliability and saving power grid losses, old transformers need to be disposed of.

[0051] Considering that transformers are valuable assets of power grid companies, at present, when power grid companies conduct asset management and investment decisions on transformers, they usually use the periodic cost within the life of the transformer as the standard, establish a power grid equipment investment decision model based on the full life cycle cost, and use the model to perform optimization analysis to solve the optimal transformer disposal strategy.

[0052] The operation cycle of old transformers is long, and it is difficult to obtain the comprehensive cost data during their life cycle, and the actual data collection cycle is long. With the gradual refinement of the division of cost input stages, the amount of calculation increases, and a large amount of manpower and material resources are consumed. Human subjective factors have a great influence on the division and calculation of transformer costs, which reduces the objectivity of the calculation results of the comprehensive disposal cost of transformers.

[0053] In this regard, the present invention provides a dynamic prediction method for the comprehensive disposal cost of old transformers. By comprehensively considering the technical, economic and environmental cost issues in the transformer disposal process, the disposal cost of old transformers is predicted in combination with dynamic changes, thereby improving the comprehensiveness and reliability of the prediction value of the disposal cost of old transformers. This method is applied to terminal equipment as an example for explanation. Figure 1 Schematic diagram of the dynamic prediction method for the comprehensive disposal cost of old transformers is shown.

[0054] The embodiment of the present application provides an application scenario of a dynamic prediction method for the comprehensive disposal cost of old transformers, and the application scenario includes a terminal device provided in the embodiment, and the terminal device includes but is not limited to a smart phone and a computer device, wherein the computer device can be at least one of a desktop computer, a portable computer, a laptop computer, a mainframe computer, a tablet computer, etc. The user operates the terminal device to obtain the predicted comprehensive disposal cost of the old transformer. For the specific process, please refer to the embodiment of the dynamic prediction method for the comprehensive disposal cost of the old transformer.

[0055] Step S101, obtaining technical cost factors, economic cost factors and environmental cost factors for the disposal of old transformers, and constructing a factor vector for the disposal of old transformers.

[0056] Specifically, as attached Figure 2 As shown in the figure, the technical cost factors for the disposal of old transformers include the fault interruption power of the old transformer (denoted as )、Compensation for power outages caused by old transformers (recorded as ) and the power production ratio per unit of power shortage caused by old transformers (denoted as );

[0057] The economic cost factors for the disposal of old transformers include the initial investment cost of the old transformer (denoted as ), the average annual fault repair cost of old transformers (denoted as ), the average annual maintenance cost of old transformers (denoted as ), inflation rate (denoted as )、Operation and maintenance rate of old transformers (denoted as ), the average annual failure rate of old transformers (denoted as ), the average annual repair time of old transformers (denoted as )、Operation life of old transformers (recorded as ) and the scrap rate of old transformer equipment (denoted as );

[0058] The environmental cost factors for the disposal of old transformers include the energy consumption of old transformer manufacturing (denoted as ), energy consumption of recycling and disposal of old transformers (recorded as ), typical pollutant emissions from manufacturing of old transformers (denoted as ) and the reduction in pollutant emissions from the reuse of old transformers (recorded as );

[0059] The above-mentioned old transformer disposal factor vector can be recorded as .

[0060] Step S102, inputting the old transformer disposal factor vector into the least squares support vector machine model after optimization training to obtain the comprehensive disposal cost of the old transformer.

[0061] Specifically, the comprehensive disposal cost of old transformers includes the total technical cost of old transformer disposal (denoted as ), the total economic cost of disposing of old transformers (denoted as ) and the total environmental cost of old transformer disposal (denoted as ), therefore, the comprehensive disposal cost of old transformers can be recorded as .

[0062] In this embodiment, the specific expression of the least squares support vector machine model is:

[0063] ,

[0064] in, The comprehensive disposal cost of old transformers is is the historical disposal factor vector of old transformers, , is the old transformer disposal factor vector, is the number of samples of the historical disposal factor vector of old transformers. In this embodiment, the kernel function of the least squares support vector machine adopts the RBF function. is the kernel function of the least squares support vector machine model, , is the bandwidth parameter of the kernel function. According to the above kernel function, the kernel matrix can be obtained . is the Lagrange multiplier used to optimize the kernel function, is the bias vector.

[0065] On this basis, the optimization objective function of the above least squares support vector machine model is:

[0066]

[0067] in, is the optimization objective function of the least squares support vector machine, is the weight matrix, , is the error vector, is the regularization parameter, is the trace of the matrix, which is the sum of the diagonal elements of the matrix.

[0068] For the above process of Lagrange multiplier optimization kernel function, the specific expression is:

[0069]

[0070] in, is the collection of comprehensive disposal costs of old transformers. .

[0071] Furthermore, in this embodiment, the bandwidth parameter of the kernel function is , the regularization parameter of the optimization objective function The hyperparameters of the model usually need to be given in advance. Based on the above least squares support vector machine model, this embodiment uses the Sparrow Search Algorithm (SSA) algorithm to determine the characteristic parameters of the least squares support vector machine model established above. and , in order to achieve the effect of optimizing the training of the least squares support vector machine model, and finally build a comprehensive cost prediction model for the disposal of old transformers based on the SSA-LS-SVM method. Figure 2 As shown, the optimization training process for the least squares support vector machine model is as follows:

[0072] Step S201, obtaining a historical disposal data set of old transformers, wherein the historical disposal data set includes historical disposal factor vectors of multiple old transformers and historical comprehensive disposal costs of multiple old transformers.

[0073] Among them, the historical disposal factor vector of old transformers is recorded as , the historical disposal data set of old transformers contains multiple historical disposal factor vectors of old transformers, recorded as , is the number of samples of the historical disposal factor vector, that is, the number of historical data samples used for training; the historical comprehensive disposal cost of old transformers is recorded as , the historical disposal data set of old transformers contains the historical comprehensive disposal costs of multiple old transformers, recorded as .

[0074] Step S202, setting initial population parameters, randomly generating an initialization population based on the initial population parameters, and initializing iteration values, wherein the initialization population includes multiple elements, each element includes a regularization parameter and a bandwidth parameter.

[0075] The initial population size includes the number of search agents SAN, which ranges from 1 to 100; the maximum number of iterations , the value range is 1-1000; the number of variables In this embodiment ; Upper boundary , , in this embodiment ; and the lower boundary , , in this embodiment .

[0076] The expression for randomly generating the initialized population based on the initial population parameters is:

[0077]

[0078] in, Indicates the number of initialized populations The first elements, For elements The random function of For the The top edge of the row element, For the The bottom edge of the row element.

[0079] Let the initial iteration value be 1.

[0080] Step S203 , selecting a regularization parameter and a bandwidth parameter corresponding to any element in the initialization population and applying them to a least squares support vector machine model to obtain an initialized least squares support vector machine model.

[0081] That is to say, each element in the initialized population corresponds to a regularization parameter and a bandwidth parameter, and the least squares support vector machine model is adjusted by specific regularization parameters and bandwidth parameters.

[0082] Step S204, input the historical disposal factor vector of any old transformer into the initialized least squares support vector machine model to obtain the historical comprehensive disposal prediction cost of the old transformer.

[0083] Step S205, repeating step S204 until the historical comprehensive disposal prediction cost of the old transformer corresponding to the historical disposal factor vector of each old transformer is obtained.

[0084] Step S206, obtaining the fitness of the element according to the historical comprehensive treatment prediction cost and the historical comprehensive treatment cost corresponding to the historical treatment factor vector.

[0085] Specifically, the specific expression for obtaining the fitness of the element in step S206 is:

[0086]

[0087] in, For elements The fitness of For elements The corresponding historical comprehensive disposal cost, For elements The corresponding historical comprehensive disposal forecast cost, is the number of training samples. Therefore, The smaller the value, the closer the historical comprehensive disposal forecast cost is to the actual historical comprehensive disposal cost.

[0088] Step S207, repeat the above steps S203 to S206 until the fitness of all elements in the initialized population is obtained.

[0089] Step S208: taking the minimum value of the fitness of all elements as the optimal fitness, and obtaining the optimal regularization parameter and the optimal bandwidth parameter contained in the element corresponding to the optimal fitness.

[0090] Step S209, if the iteration value is less than the maximum number of iterations in the initialization population parameters, further process the iteration value, update the positions of the leader and follower in the initialization population, and repeat steps S203-S208 until the iteration value is greater than the maximum number of iterations in the initialization population parameters.

[0091] Step S210, taking the minimum value of all the best fitness as the best fitness, and obtaining the optimal regularization parameter and the optimal bandwidth parameter contained in the element corresponding to the best fitness, and combining the optimal regularization parameter and the optimal bandwidth parameter to obtain the optimized trained minimum squares support vector machine model.

[0092] It should be noted that this embodiment continuously searches for the optimal regularization parameters and optimal bandwidth parameters applied to the minimum squares support vector machine model through the sparrow search algorithm, so that the comprehensive disposal cost of the old transformers obtained by optimizing the trained minimum squares support vector machine model is closest to the actual comprehensive disposal cost, providing objective and effective reference information for subsequent comprehensive disposal plans for old transformers, and also improving the efficiency of the comprehensive disposal of old transformers.

[0093] It should be understood that although the Figure 1 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Figure 1 At least part of the steps may include multiple sub-steps or sub-stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0094] The above embodiments of the present invention describe in detail the method for predicting the comprehensive disposal cost of old transformers. The above method disclosed in the present invention can be implemented by various types of equipment. Therefore, the present invention also discloses a device for predicting the comprehensive disposal cost of old transformers. Figure 4 , specific embodiments are given below to explain in detail.

[0095] The factor vector acquisition module 301 is used to acquire the technical cost factors, economic cost factors and environmental cost factors of the old transformer disposal and construct the old transformer disposal factor vector;

[0096] The disposal cost prediction module 302 is used to input the old transformer disposal factor vector into the least squares support vector machine model after optimization training to obtain the comprehensive disposal cost of the old transformer.

[0097] The prediction device for the comprehensive disposal cost of old transformers can be fully referred to the above definition of the method, which will not be repeated here. Each module in the above device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above modules can be embedded in or independent of the processor of the terminal device in the form of hardware, or can be stored in the memory of the terminal device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0098] In one embodiment, the present invention further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the method for predicting the comprehensive disposal cost of old transformers are implemented.

[0099] The computer-readable storage medium may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read-only memory), an EPROM (erasable programmable read-only memory), a hard disk or a ROM. Optionally, the computer-readable storage medium includes a non-transitory computer-readable storage medium. The computer-readable storage medium has a storage space for program codes for executing any method step of the above method. These program codes may be read from or written into one or more computer program products, and the program codes may be compressed in an appropriate form.

[0100] In one embodiment, the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the above-mentioned method for predicting the comprehensive disposal cost of old transformers when executing the computer program.

[0101] The computer device includes a memory, a processor, and one or more computer programs, wherein the one or more computer programs can be stored in the memory and configured to be executed by one or more processors, and the one or more application programs are configured to execute the above-mentioned method for predicting the comprehensive disposal cost of old transformers.

[0102] The processor may include one or more processing cores. The processor uses various interfaces and lines to connect the various parts of the entire computer device, and executes various functions of the computer device and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory, and calling data stored in the memory. Optionally, the processor can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor can integrate one or more combinations of a central processing unit (Central Processing Unit, CPU), a reporting verifier (Graphics Processing Unit, GPU) for buried data, and a modem. Among them, the CPU mainly processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing display content; and the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor, but may be implemented separately through a communication chip.

[0103] The memory may include a random access memory (RAM) or a read-only memory (ROM). The memory may be used to store instructions, programs, codes, code sets or instruction sets. The memory may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc. The data storage area may also store data created by the terminal device during use, etc.

[0104] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for predicting the comprehensive disposal cost of old transformers. It is characterized in that include: Obtain the technical cost factors, economic cost factors and environmental cost factors of the disposal of old transformers, and construct the factor vector of the disposal of old transformers; The old transformer disposal factor vector is input into the least squares support vector machine model after optimization training to obtain the comprehensive disposal cost of the old transformer.

2. The method for predicting the comprehensive disposal cost of old transformers as claimed in claim 1, It is characterized in that The technical cost factors for the disposal of old transformers include the power interruption caused by the old transformer failure, the compensation cost per unit of power outage caused by the old transformer, and the power production ratio per unit of power shortage caused by the old transformer; The economic cost factors for the disposal of old transformers include the initial investment cost of old transformers, the average annual fault repair cost of old transformers, the average annual maintenance cost of old transformers, the inflation rate, the operation and maintenance rate of old transformers, the average annual failure rate of old transformers, the average annual repair time of old transformers, the operating years of old transformers and the scrap rate of old transformer equipment; The environmental cost factors for the disposal of old transformers include the energy consumption of manufacturing old transformers, the energy consumption of reusing and disposing old transformers, the typical pollutant emissions of manufacturing old transformers and the pollutant emission reduction of reusing old transformers; The comprehensive disposal cost of old transformers includes the total technical cost of old transformer disposal, the total economic cost of old transformer disposal and the total environmental protection cost of old transformer disposal.

3. The method for predicting the comprehensive disposal cost of old transformers as claimed in claim 2, It is characterized in that The specific expression of the least squares support vector machine model is: ， in, The comprehensive disposal cost of old transformers is is the historical disposal factor vector of old transformers, is the old transformer disposal factor vector, is the sample number of the historical disposal factor vector of old transformers, is the kernel function of the least squares support vector machine model, , is the bandwidth parameter of the kernel function, is the Lagrangian operator, is the bias vector.

4. The method for predicting the comprehensive disposal cost of an aging transformer according to claim 3, It is characterized in that The optimization objective function of the least squares support vector machine model is: ， in, is the optimization objective function of the least squares support vector machine, is the weight matrix, , is the error vector, is the regularization parameter, is the trace of the matrix.

5. The method for predicting the comprehensive disposal cost of an aging transformer according to claim 4, It is characterized in that The optimization training process of the least squares support vector machine model includes: Step S201, obtaining a historical disposal data set of old transformers, wherein the historical disposal data set includes a plurality of historical disposal factor vectors of old transformers and a plurality of historical comprehensive disposal costs of old transformers; Step S202, setting initial population parameters, randomly generating an initialization population based on the initial population parameters, and initializing an iteration value, wherein the initialization population includes a plurality of elements, each element includes a regularization parameter and a bandwidth parameter; Step S203, selecting a regularization parameter and a bandwidth parameter corresponding to any element in the initialization population and applying them to a least squares support vector machine model to obtain an initialized least squares support vector machine model; Step S204, inputting the historical disposal factor vector of any old transformer into the initialized least squares support vector machine model to obtain the historical comprehensive disposal prediction cost of the old transformer; Step S205, repeatedly executing step S204 until the historical comprehensive disposal prediction cost of the old transformer corresponding to the historical disposal factor vector of each old transformer is obtained; Step S206, obtaining the fitness of the element according to the historical comprehensive treatment prediction cost and the historical comprehensive treatment cost corresponding to the historical treatment factor vector; Step S207, repeating the above steps S203 to S206 until the fitness of all elements in the initialized population is obtained; Step S208, taking the minimum value of the fitness of all elements as the optimal fitness, and obtaining the optimal regularization parameter and the optimal bandwidth parameter contained in the element corresponding to the optimal fitness; Step S209, if the iteration value is less than the maximum number of iterations in the initialization population parameters, further process the iteration value, update the positions of the leader and the follower in the initialization population, and repeat steps S203 to S208 until the iteration value is greater than the maximum number of iterations in the initialization population parameters; Step S210, taking the minimum value of all the best fitness as the best fitness, and obtaining the optimal regularization parameter and the optimal bandwidth parameter contained in the element corresponding to the best fitness, and combining the optimal regularization parameter and the optimal bandwidth parameter to obtain the optimized trained minimum squares support vector machine model.

6. The method for predicting the comprehensive disposal cost of an aging transformer according to claim 5, It is characterized in that The initial population number includes the number of search agents, the maximum number of iterations, the number of variables, the upper bound and the lower bound; The expression for randomly generating the initialized population based on the initial population parameters is: ， in, Indicates the number of initialized populations The first elements, For elements The random function of For the The upper boundary of the row, For the The bottom edge of the row.

7. The method for predicting the comprehensive disposal cost of an aging transformer according to claim 6, It is characterized in that The specific expression of the fitness of the element obtained according to the historical comprehensive treatment prediction cost and the historical comprehensive treatment cost corresponding to the historical treatment factor vector is: ， in, For elements The fitness of For elements The corresponding historical comprehensive disposal cost, For elements The corresponding historical comprehensive disposal forecast cost, is the number of training samples.

8. A device for predicting the comprehensive disposal cost of old transformers. It is characterized in that include: A factor vector acquisition module is used to obtain technical cost factors, economic cost factors and environmental cost factors for the disposal of old transformers, and to construct a factor vector for the disposal of old transformers; The disposal cost prediction module is used to input the old transformer disposal factor vector into the least squares support vector machine model after optimization training to obtain the comprehensive disposal cost of the old transformer.

9. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of the method for predicting the comprehensive disposal cost of old transformers according to any one of claims 1 to 7 are implemented.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program. It is characterized in that When the processor executes the computer program, it performs the method for predicting the comprehensive disposal cost of old transformers according to any one of claims 1 to 7.

Images