Method, device and equipment for measuring and calculating maintenance cost of 110kV power transmission line and storage medium

Abstract

The invention discloses a 110kV power transmission line maintenance cost measuring and calculating method, device and equipment and a storage medium, which are used for solving the technical problem of low accuracy of an existing cost measuring and calculating model based on artificial intelligence. The method comprises the following steps: acquiring process information of multiple maintenance processes of the 110kV power transmission line; inputting the process information into a pre-trained engineering quantity prediction model, and predicting the engineering quantity of the maintenance process; the pre-trained engineering quantity prediction model is obtained through training of a support vector machine; obtaining the comprehensive unit price of the maintenance process from a preset quota process comprehensive unit price calculation model; and calculating the total engineering maintenance cost of the 110kV power transmission line by adopting the engineering quantities of all the maintenance procedures and the corresponding comprehensive unit prices.

Description

Technical Field

[0001] The present invention relates to the technical field of line maintenance, and particularly to a method, device, equipment and storage medium for calculating the cost of 110 kV transmission line maintenance. Background Art

[0002] As an important part of the national industry, the power industry shoulders the responsibility of providing stable and reliable power supply for all walks of life. To ensure the stable operation and development of the power system and provide high-quality power consumption, it is necessary to periodically update, expand and transform the power system. However, this brings a large number of technical renovation and maintenance projects, and at the same time, the requirements for project management are getting higher and higher, and the whole process control of project funds is more stringent. At present, power industry practitioners often lack professional cost knowledge and cannot proficiently master the professional knowledge of power engineering cost quotas, while cost professionals lack on-site experience in technical renovation and maintenance and cannot judge the specific workload of a certain process of power engineering based on experience. Therefore, a cost calculation method that combines the skills of both power industry practitioners and cost professionals is needed.

[0003] In view of this, the prior art combines machine learning models and technologies to calculate the project cost. For example, convolutional neural network, deep neural network, extreme learning machine, etc.

[0004] However, the cost calculation model based on artificial intelligence shows strong uncertainty, with different training effects on the same training set and insufficient stability, which cannot meet the requirements of calculation accuracy. Summary of the Invention

[0005] The present invention provides a method, device, equipment and storage medium for calculating the cost of 110 kV transmission line maintenance, which is used to solve the technical problem of the low accuracy of the existing cost calculation model based on artificial intelligence.

[0006] The present invention provides a method for calculating the cost of 110 kV transmission line maintenance, including:

[0007] Obtaining the process information of multiple maintenance processes of the 110 kV transmission line;

[0008] Inputting the process information into a pre-trained engineering quantity prediction model to predict the engineering quantity of the maintenance process; the pre-trained engineering quantity prediction model is obtained by training with a support vector machine;

[0009] Obtaining the comprehensive unit price of the maintenance process from a pre-set quota process comprehensive unit price calculation model;

[0010] Calculating the total maintenance cost of the 110 kV transmission line by using the engineering quantity of all the maintenance processes and the corresponding comprehensive unit prices.

[0011] Optionally, the training process of the pre-trained engineering quantity prediction model includes:

[0012] Obtain the historical settlement data of the 110 kV transmission line maintenance project;

[0013] Perform data preprocessing on the historical settlement data to obtain historical process information and the corresponding historical engineering quantity of the historical process information;

[0014] Determine the kernel function;

[0015] Train a preset support vector machine through the historical process information, the historical engineering quantity, and a preset RBF kernel function to obtain the weight coefficient and offset of the estimation function of the preset support vector machine;

[0016] Update the preset support vector machine with the weight coefficient and offset to obtain a pre-trained engineering quantity prediction model.

[0017] Optionally, the step of obtaining the comprehensive unit price of the maintenance process from the pre-set quota process comprehensive unit price measurement model includes:

[0018] Obtain the end cost types of the quota processes corresponding to each maintenance process;

[0019] Obtain the costs of each end cost type;

[0020] Input the costs into the pre-set quota process comprehensive unit price measurement model to obtain the comprehensive unit price of the maintenance process.

[0021] Optionally, the step of calculating the total maintenance cost of the 110 kV transmission line using the engineering quantities and corresponding comprehensive unit prices of all the maintenance processes includes:

[0022] Calculate the product of the engineering quantity and the corresponding comprehensive unit price of each maintenance process to obtain the process budget;

[0023] Add up the process budgets of all the maintenance processes to obtain the total maintenance cost of the 110 kV transmission line.

[0024] The present invention also provides a device for measuring the maintenance cost of a 110 kV transmission line, including:

[0025] A process information acquisition module for acquiring the process information of multiple maintenance processes of a 110 kV transmission line;

[0026] An engineering quantity prediction module for inputting the process information into a pre-trained engineering quantity prediction model to predict the engineering quantity of the maintenance process; the pre-trained engineering quantity prediction model is obtained by training a support vector machine;

[0027] The comprehensive unit price acquisition module is used to obtain the comprehensive unit price of the maintenance process from the pre-set comprehensive unit price measurement model of the quota process;

[0028] The total project maintenance cost calculation module is used to calculate the total project maintenance cost of the 110kV transmission line by using the quantities of all the maintenance processes and the corresponding comprehensive unit prices.

[0029] Optionally, the training process of the pre-trained quantity prediction model includes:

[0030] The historical settlement data acquisition module is used to obtain the historical settlement data of the 110kV transmission line maintenance project;

[0031] The preprocessing module is used to preprocess the historical settlement data to obtain historical process information and the historical quantities corresponding to the historical process information;

[0032] The kernel function determination module is used to determine the kernel function;

[0033] The weight coefficient and offset acquisition module is used to train a pre-set support vector machine through the historical process information, the historical quantities, and a pre-set RBF kernel function to obtain the weight coefficient and offset of the estimation function of the pre-set support vector machine;

[0034] The model training module is used to update the pre-set support vector machine with the weight coefficient and offset to obtain a pre-trained quantity prediction model.

[0035] Optionally, the comprehensive unit price acquisition module includes:

[0036] The end cost type acquisition sub-module is used to obtain the end cost types of the quota processes corresponding to each maintenance process;

[0037] The cost acquisition sub-module is used to obtain the costs of each end cost type;

[0038] The comprehensive unit price calculation sub-module is used to input the costs into the pre-set comprehensive unit price measurement model of the quota process to obtain the comprehensive unit price of the maintenance process.

[0039] Optionally, the total project maintenance cost calculation module includes:

[0040] The process budget calculation sub-module is used to calculate the product of the quantity of each maintenance process and the corresponding comprehensive unit price to obtain the process budget;

[0041] The total project maintenance cost calculation sub-module is used to add up the process budgets of all the maintenance processes to obtain the total project maintenance cost of the 110kV transmission line.

[0042] The present invention also provides an electronic device, which includes a processor and a memory:

[0043] The memory is used to store program codes and transmit the program codes to the processor;

[0044] The processor is used to execute the 110 kV transmission line maintenance cost calculation method according to the instructions in the program codes as described in any one of the above.

[0045] The present invention also provides a computer-readable storage medium, which is used to store program codes, and the program codes are used to execute the 110 kV transmission line maintenance cost calculation method as described in any one of the above.

[0046] As can be seen from the above technical solutions, the present invention has the following advantages: The present invention obtains the process information of multiple maintenance processes of the 110 kV transmission line; inputs the process information into a pre-trained engineering quantity prediction model to predict the engineering quantity of the maintenance process; the engineering quantity prediction model is trained by a support vector machine; obtains the comprehensive unit price of the maintenance process from a pre-set quota process comprehensive unit price calculation model; calculates the total maintenance cost of the 110 kV transmission line by using the engineering quantity of all maintenance processes and the corresponding comprehensive unit prices. Thereby improving the accuracy of the 110 kV transmission line maintenance cost calculation. Description of the Drawings

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0048] Figure 1 It is a step flow chart of a 110 kV transmission line maintenance cost calculation method provided by an embodiment of the present invention;

[0049] Figure 2 It is a schematic diagram of the maintenance process of the 110 kV transmission line;

[0050] Figure 3 It is a step flow chart of a 110 kV transmission line maintenance cost calculation method provided by another embodiment of the present invention;

[0051] Figure 4 It is a schematic diagram of a typical cost structure of a standard process;

[0052] Figure 5 It is a schematic diagram of the 110 kV transmission line maintenance cost calculation process provided by an embodiment of the present invention;

[0053] Figure 6 This is a structural block diagram of a device for calculating the maintenance cost of a 110 kV transmission line provided by an embodiment of the present invention. Specific embodiments

[0054] Embodiments of the present invention provide a method, device, equipment and storage medium for calculating the maintenance cost of a 110 kV transmission line, which are used to solve the technical problem that the accuracy of the existing cost calculation model based on artificial intelligence is relatively low.

[0055] In order to make the objectives, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the embodiments described below are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0056] Please refer to Figure 1 , Figure 1 This is a step flowchart of a method for calculating the maintenance cost of a 110 kV transmission line provided by an embodiment of the present invention.

[0057] A method for calculating the maintenance cost of a 110 kV transmission line provided by the present invention may specifically include the following steps:

[0058] Step 101, obtaining the process information of multiple maintenance processes of the 110 kV transmission line;

[0059] In the embodiments of the present invention, the maintenance processes of the 110 kV transmission line maintenance project usually include replacing the suspension composite insulator string of the straight tower 110 kV (double string), replacing the conductor suspension clamp of the straight tower 110 kV single conductor, replacing the pre-twisted wire (damping wire) 110 kV (double string), replacing the anti-bird equalizing ring 110 kV, replacing the suspension insulator string 110 kV single string (jumper wire), replacing the conductor suspension clamp 110 kV single conductor (jumper wire), replacing the weight piece 110 kV, adjusting the conductor sag 110 kV single conductor, replacing the conductor tension clamp 110 kV single conductor, replacing the jumper wire 110 kV single conductor, replacing the tension glass insulator string 110 kV (double string), replacing the tension glass insulator string 110 kV (single string), line insulation resistance measurement and phase checking 110 kV single circuit, crossing the energized 10 kV line, spraying PRTV (manually) on the glass insulator string 110 kV. Specifically as Figure 2 shown.

[0060] The process information includes factors affecting the engineering quantity, such as terrain, number of tower bases, number of phases (single-phase or three-phase), number of circuits, and number of strings. Among them, the number of tower bases and the number of strings have a strong correlation with the engineering quantity and are key influencing factors.

[0061] Step 102: Input the process information into the pre-trained engineering quantity prediction model to predict the engineering quantity of the maintenance process; the pre-trained engineering quantity prediction model is obtained by training with a support vector machine.

[0062] After obtaining the process information, it can be input into the pre-trained engineering quantity prediction model to predict the engineering quantity corresponding to the maintenance process.

[0063] In one example, the pre-trained engineering quantity prediction model can be obtained by training with a support vector machine.

[0064] Support Vector Machine (SVM) is a powerful supervised learning algorithm widely used in classification and regression tasks. Its core idea is to find an optimal hyperplane to separate data points of different classes while maximizing the classification margin (i.e., the distance from the support vector to the hyperplane).

[0065] Step 103: Obtain the comprehensive unit price of the maintenance process from the pre-set comprehensive unit price calculation model for rated processes.

[0066] In the actual scenario, currently, power industry practitioners often lack professional cost knowledge and cannot proficiently master the professional knowledge of power engineering cost quotas. Therefore, the embodiment of the present invention constructs a comprehensive unit price calculation model for rated processes based on the "Regulations for the Preparation and Calculation of Grid Maintenance Project Budgets" (pre-regulations) to calculate the comprehensive unit price of the maintenance process.

[0067] A rated process is a process for which the standard usage amounts of labor, machinery, and materials per unit can be found in various quota books or documents issued by the industry, also known as a standard process. After knowing the rated process, the typical cost structure of the rated process can be generated, thereby determining the business logic and calculation method corresponding to each cost type in the rated process, and then calculating the comprehensive unit price of the rated process. Finally, combining the actual engineering quantity and the corresponding comprehensive unit price of the maintenance process, the maintenance cost of the maintenance process can be calculated.

[0068] Step 104: Calculate the total maintenance cost of the 110 kV transmission line using the engineering quantities and corresponding comprehensive unit prices of all maintenance processes.

[0069] After obtaining the engineering quantities of all maintenance processes, the total maintenance cost of the 110 kV transmission line can be obtained by combining the maintenance costs calculated for each maintenance process.

[0070] The present invention obtains the process information of multiple maintenance processes of a 110 kV transmission line; inputs the process information into a pre-trained engineering quantity prediction model to predict the engineering quantity of the maintenance process; the engineering quantity prediction model is trained by a support vector machine; obtains the comprehensive unit price of the maintenance process from a pre-set quota process comprehensive unit price measurement model; and calculates the total maintenance cost of the 110 kV transmission line by using the engineering quantity of all maintenance processes and the corresponding comprehensive unit price. Thereby, the accuracy of the maintenance cost measurement of the 110 kV transmission line is improved.

[0071] Please refer to Figure 3 , Figure 3 which is a step flowchart of a method for measuring the maintenance cost of a 110 kV transmission line provided in another embodiment of the present invention. Specifically, it may include the following steps:

[0072] Step 301, obtain the process information of multiple maintenance processes of a 110 kV transmission line;

[0073] Step 302, input the process information into a pre-trained engineering quantity prediction model to predict the engineering quantity of the maintenance process; the pre-trained engineering quantity prediction model is trained by a support vector machine;

[0074] In the embodiment of the present invention, the training process of the pre-trained engineering quantity prediction model includes the following steps:

[0075] S21, obtain the historical settlement data of the 110 kV transmission line maintenance project;

[0076] S22, perform data preprocessing on the historical settlement data to obtain historical process information and the corresponding historical engineering quantity of the historical process information;

[0077] S23, determine the kernel function;

[0078] S24, train a preset support vector machine through the historical process information, the historical engineering quantity, and a preset RBF kernel function to obtain the weight coefficient and offset of the estimation function of the preset support vector machine;

[0079] S25, update the preset support vector machine by using the weight coefficient and offset to obtain a pre-trained engineering quantity prediction model.

[0080] In a specific implementation, the process of the support vector machine for prediction is as follows:

[0081] For the set to be solved , where is the input vector, is the output vector, and the regression theory is to introduce a non-linear mapping to transform the sample space from a low dimension to a high dimension, solve the non-linear problem, and the estimation function is transformed into the form:

[0082]

[0083] Among them, the weight coefficient is W, and the offset is b.

[0084] The non-linear solution problem adopts , when a linear problem conversion is involved in the process, is introduced, to search for the parameters W and b, as shown in the following formula:

[0085]

[0086] Among them, is the description function, is the penalty factor.

[0087] When the estimation function processes data, due to 's influence, it is impossible to directly estimate the data, so it is necessary to introduce Two factors are used to solve the regression function. When making model predictions, to minimize the expected risk coefficient, the loss function is used for solution, and its expression is:

[0088]

[0089] Among them, "+" means taking the positive value. When the interval is greater than y while correctly classifying a sample, there is no loss, otherwise it is , and the accumulation of all losses constitutes a part of F(x).

[0090] Expected function:

[0091]

[0092] Among them, is the empirical risk; measures 's complexity, is the default existing training set.

[0093] The empirical risk and jointly determine the maximum value of the expected risk. Using the kernel function in the low dimension to simplify the solution, after the transformation of the support vector machine, the problem of the model becomes:

[0094]

[0095] Combining with the Lagrangian function, the problem will be optimized into a dual problem, and the expression of the estimation function becomes:

[0096]

[0097] Among them, and is the Lagrange factor; is the radial basis function.

[0098] For non - linear training samples such as the project quantities of processes, SVM can convert low - dimensional samples into high - dimensional space data through a suitable kernel function, and process the data as linear data. Therefore, choosing a suitable kernel function is crucial. The expression of the SVM kernel function is:

[0099]

[0100] If the kernel function is a symmetric function, for , it can be written as:

[0101]

[0102] Different kernel functions will cause differences in the prediction results of the support vector machine model. The kernel function used in the embodiments of the present invention is RBF (radial basis kernel function).

[0103] This function can be expressed in the SVM model to solve the prediction problem. The expression of the RBF kernel function is:

[0104]

[0105] Selecting the RBF kernel function can perform a non - linear to linear conversion on the initial data of the samples, and the expression is:

[0106]

[0107] Based on the above prediction process, when training the project quantity prediction model, first, the historical settlement data of the 110kV transmission line maintenance project can be obtained; perform data pre - processing on the historical settlement data to obtain historical process information and the corresponding historical project quantities; then select a suitable kernel function, such as the RBF kernel function mentioned above. Next, use the historical process information as the input and the project quantity as the output, and combine with the kernel function to train the weight coefficients and offsets of the estimation function, so as to obtain a pre - trained project quantity prediction model.

[0108] Step 303: Obtain the end - cost types of the quota processes corresponding to each maintenance process;

[0109] Step 304: Obtain the costs of each end - cost type;

[0110] Step 305: Input the costs into a pre - set quota process comprehensive unit price measurement model to obtain the comprehensive unit price of the maintenance process;

[0111] In the embodiments of the present invention, the maintenance project of the 10kV transmission line consists of multiple processes. Each process includes various types of costs such as labor costs, construction machinery costs, material costs, and indirect costs. By deconstructing all the cost types included in the standard process and dividing all the costs level by level, the end - cost types can be obtained.

[0112] Figure 4 FIG. 4 is a schematic diagram of a typical cost structure of a standard process, including direct costs, indirect costs, profits, and price differences in the preparation reference period; direct costs include direct project costs and measure costs; direct project costs include labor costs, construction machinery usage costs, priced material costs provided by Party A, priced material costs provided by Party B, non - priced material costs provided by Party A (including material costs, insurance quotation costs, loss costs, procurement and storage costs, and distribution costs), and non - priced material costs provided by Party B; measure costs include increased costs for construction in winter, rainy seasons and night, increased costs for night construction, usage costs of construction tools and appliances, increased costs for construction in special areas, temporary facility costs, safety and civilized construction costs, increased costs for multiple entries and exits, and construction organization relocation costs; indirect costs include regulatory fees (including social insurance fees and housing provident funds) and enterprise management fees; price differences in the preparation reference period include labor price difference costs, machinery price difference costs, priced material price difference costs provided by Party A, and priced material price difference costs provided by Party B.

[0113] From Figure 4 the typical cost structure of the standard process in FIG. 4, it can be seen that the costs of all superior nodes are equal to the sum of all cost types of their subordinate nodes. For example, Figure 4 the regulatory fees in FIG. 5 = social insurance fees + housing provident funds, and indirect costs = regulatory fees + enterprise management fees. In addition, each type of cost should be divided into a tax - free part and a value - added tax part for further distinction. Finally, only the business logics and calculation methods of all end - level costs need to be studied, and then the results of each end - level cost are added up level by level upwards to obtain the comprehensive unit price of this standard process. Therefore, the business logics and calculation methods of all end - type costs can be used to generate a measurement model for the comprehensive unit price of the preset quota process. By inputting the market prices of labor, materials and other costs, the comprehensive unit price of the corresponding process can be obtained.

[0114] Step 306, calculate the total maintenance cost of the 110kV transmission line by using the quantities of work of all maintenance processes and the corresponding comprehensive unit prices.

[0115] In the embodiments of the present invention, step 306 may include the following sub - steps:

[0116] S61, calculate the product of the quantity of work of each maintenance process and the corresponding comprehensive unit price to obtain the process budget;

[0117] S62, add up the process budgets of all maintenance processes to obtain the total maintenance cost of the 110kV transmission line.

[0118] After obtaining the quantities of work for all maintenance processes, the total maintenance cost of the 110 kV transmission line can be obtained by combining the maintenance costs calculated for each maintenance process. The specific process is as Figure 5 shown.

[0119] The present invention obtains the process information of multiple maintenance processes of a 110 kV transmission line; inputs the process information into a pre-trained work quantity prediction model to predict the work quantity of the maintenance process; the work quantity prediction model is trained by a support vector machine; obtains the comprehensive unit price of the maintenance process from a pre-set quota process comprehensive unit price measurement model; and calculates the total maintenance cost of the 110 kV transmission line by using the work quantities of all maintenance processes and the corresponding comprehensive unit prices. Thereby, the accuracy of the measurement of the maintenance cost of the 110 kV transmission line is improved.

[0120] Please refer to Figure 6 , Figure 6 which is a structural block diagram of a device for measuring the maintenance cost of a 110 kV transmission line provided by an embodiment of the present invention.

[0121] An embodiment of the present invention provides a device for measuring the maintenance cost of a 110 kV transmission line, including:

[0122] A process information acquisition module 601, configured to acquire the process information of multiple maintenance processes of a 110 kV transmission line;

[0123] A work quantity prediction module 602, configured to input the process information into a pre-trained work quantity prediction model to predict the work quantity of the maintenance process; the pre-trained work quantity prediction model is trained by a support vector machine;

[0124] A comprehensive unit price acquisition module 603, configured to acquire the comprehensive unit price of the maintenance process from a pre-set quota process comprehensive unit price measurement model;

[0125] A total maintenance cost calculation module 604, configured to calculate the total maintenance cost of the 110 kV transmission line by using the work quantities of all maintenance processes and the corresponding comprehensive unit prices.

[0126] In the embodiment of the present invention, the training process of the pre-trained work quantity prediction model includes:

[0127] A historical settlement data acquisition module, configured to acquire the historical settlement data of the 110 kV transmission line maintenance project;

[0128] A preprocessing module, configured to perform data preprocessing on the historical settlement data to obtain historical process information and the historical work quantity corresponding to the historical process information;

[0129] A kernel function determination module, configured to determine the kernel function;

[0130] A weight coefficient and offset acquisition module, configured to train a preset support vector machine through historical process information, historical engineering quantities, and a preset RBF kernel function to obtain the weight coefficient and offset of the estimation function of the preset support vector machine;

[0131] A model training module, configured to update the preset support vector machine by using the weight coefficient and offset to obtain a pre-trained engineering quantity prediction model.

[0132] In an embodiment of the present invention, the comprehensive unit price acquisition module 603 includes:

[0133] An end cost type acquisition sub-module, configured to acquire the end cost type of the quota process corresponding to each maintenance process;

[0134] A cost acquisition sub-module, configured to acquire the costs of each end cost type;

[0135] A comprehensive unit price calculation sub-module, configured to input the costs into a preset quota process comprehensive unit price measurement model to obtain the comprehensive unit price of the maintenance process.

[0136] In an embodiment of the present invention, the total engineering maintenance cost calculation module 604 includes:

[0137] A process budget calculation sub-module, configured to calculate the product of the engineering quantity of each maintenance process and the corresponding comprehensive unit price to obtain the process budget;

[0138] A total engineering maintenance cost calculation sub-module, configured to add up the process budgets of all maintenance processes to obtain the total engineering maintenance cost of the 110 kV transmission line.

[0139] An embodiment of the present invention further provides an electronic device, which includes a processor and a memory:

[0140] The memory is used to store program codes and transmit the program codes to the processor;

[0141] The processor is configured to execute the 110 kV transmission line maintenance cost measurement method according to the instructions in the program codes.

[0142] An embodiment of the present invention further provides a computer-readable storage medium, which is used to store program codes, and the program codes are used to execute the 110 kV transmission line maintenance cost measurement method.

[0143] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the foregoing method embodiments, and will not be described herein again.

[0144] Each embodiment in this specification is described in a progressive manner. Each embodiment focuses on the differences from other embodiments. For the same or similar parts among the embodiments, reference can be made to each other.

[0145] Those skilled in the art should understand that the embodiments of the present invention can be provided as methods, devices, or computer program products. Therefore, the embodiments of the present invention can take the form of all-hardware embodiments, all-software embodiments, or embodiments combining software and hardware aspects. Moreover, the embodiments of the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0146] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the processes and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal devices generate a device for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0147] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device implements the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0148] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device, so that a series of operation steps are executed on the computer or other programmable terminal device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable terminal device provide steps for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0149] While the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concepts. Therefore, the appended claims are intended to be construed to include the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0150] Finally, it should also be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or terminal device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or terminal device. Without further limitation, an element defined by the statement "comprising one..." does not exclude the presence of additional identical elements in the process, method, article or terminal device comprising the said element.

[0151] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for calculating the maintenance cost of a 110kV transmission line, characterized in that: include: Obtain process information of multiple maintenance processes of 110kV transmission lines; Inputting the process information into a pre-trained engineering quantity prediction model to predict the engineering quantity of the maintenance process; the pre-trained engineering quantity prediction model is obtained by training a support vector machine; Obtaining the comprehensive unit price of the maintenance process from a preset quota process comprehensive unit price calculation model; The total maintenance cost of the 110kV transmission line is calculated using the engineering quantities of all the maintenance processes and the corresponding comprehensive unit prices.

2. The method according to claim 1, characterized in that The training process of the pre-trained engineering quantity prediction model includes: Obtain historical settlement data of 110kV transmission line maintenance projects; Performing data preprocessing on the historical settlement data to obtain historical process information and historical engineering quantities corresponding to the historical process information; Determine the kernel function; Training a preset support vector machine through the historical process information, the historical engineering quantity and a preset RBF kernel function to obtain a weight coefficient and an offset of an estimation function of the preset support vector machine; The weight coefficient and the offset are used to update the preset support vector machine to obtain a pre-trained engineering quantity prediction model.

3. The method according to claim 1, characterized in that The step of obtaining the comprehensive unit price of the maintenance process from the preset quota process comprehensive unit price calculation model includes: Obtain the terminal cost type of the quota process corresponding to each maintenance process; Get the cost of each terminal cost type; The cost is input into the comprehensive unit price calculation model of the preset quota process to obtain the comprehensive unit price of the maintenance process.

4. The method according to claim 1, characterized in that: The step of calculating the total engineering maintenance cost of the 110kV transmission line by using the engineering quantities of all the maintenance processes and the corresponding comprehensive unit prices comprises: Calculate the product of the engineering quantity of each maintenance process and the corresponding comprehensive unit price to obtain the process budget; The process budgets of all maintenance processes are added together to obtain the total maintenance cost of the 110kV transmission line project.

5. A 110kV transmission line maintenance cost calculation device, characterized in that: include: The process information acquisition module is used to obtain the process information of multiple maintenance processes of 110kV transmission lines; A project quantity prediction module, used for inputting the process information into a pre-trained project quantity prediction model to predict the project quantity of the maintenance process; the pre-trained project quantity prediction model is obtained by training a support vector machine; A comprehensive unit price acquisition module is used to obtain the comprehensive unit price of the maintenance process from a preset quota process comprehensive unit price calculation model; The total engineering maintenance cost calculation module is used to calculate the total engineering maintenance cost of the 110kV transmission line by using the engineering quantities of all the maintenance processes and the corresponding comprehensive unit prices.

6. The device according to claim 5, characterized in that The training process of the pre-trained engineering quantity prediction model includes: The historical settlement data acquisition module is used to obtain the historical settlement data of the 110kV transmission line maintenance project; A preprocessing module, used to perform data preprocessing on the historical settlement data to obtain historical process information and historical engineering quantities corresponding to the historical process information; A kernel function determination module, used to determine the kernel function; A weight coefficient and offset acquisition module, used to train a preset support vector machine through the historical process information, the historical engineering quantity and a preset RBF kernel function, and obtain the weight coefficient and offset of the estimation function of the preset support vector machine; The model training module is used to update the preset support vector machine using the weight coefficient and offset to obtain a pre-trained engineering quantity prediction model.

7. The device according to claim 5, characterized in that The comprehensive unit price acquisition module includes: The terminal cost type acquisition submodule is used to obtain the terminal cost type of the quota process corresponding to each maintenance process; The fee acquisition submodule is used to obtain the fees of each terminal fee type; The comprehensive unit price calculation submodule is used to input the cost into the comprehensive unit price calculation model of the preset quota process to obtain the comprehensive unit price of the maintenance process.

8. The device according to claim 5, characterized in that The engineering total maintenance cost calculation module includes: The process budget calculation submodule is used to calculate the product of the engineering quantity of each maintenance process and the corresponding comprehensive unit price to obtain the process budget; The total maintenance cost calculation submodule is used to add up the process budgets of all maintenance processes to obtain the total maintenance cost of the 110kV transmission line project.

9. An electronic device, characterized in that: The device comprises a processor and a memory: The memory is used to store program code and transmit the program code to the processor; The processor is used to execute the 110kV transmission line maintenance cost estimation method described in any one of claims 1-4 according to the instructions in the program code.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store program code, and the program code is used to execute the 110kV transmission line maintenance cost estimation method described in any one of claims 1-4.

Images