Technical transformation scale prediction system and method based on power grid equipment scrap rate and service age distribution

Abstract

The technical transformation scale prediction system based on the service age distribution of power grid equipment scrapping rate includes a data source management module, a data processing module, a data feature distribution analysis module, and a technical transformation scale prediction module. When the system is running, the data source management module obtains the basic data information of power grid equipment from the external system, and then the data processing module performs multi-source data fusion matching on the basic data information of power grid equipment, and obtains the service age distribution of the scale of in-service equipment, the service age probability distribution of the scale of equipment to be scrapped and scrapped, and the scale proportion of the service age distribution of all equipment based on the matched data statistics. Then the data feature distribution analysis module performs data fitting on the service age probability distribution of the scale of equipment to be scrapped and scrapped, and obtains the scrap probability fitting function about the service age. Finally, the technical transformation scale prediction module combines the fitting function and the asset wall analysis to predict the scale of technical transformation investment. The prediction result of this design is accurate, which is conducive to the formulation of technical transformation planning schemes for power grid equipment in the future.

Description

Technical Field

[0001] The present invention belongs to the technical field of power grid investment prediction, and in particular relates to a system and method for predicting the scale of technical transformation based on the scrap rate and age distribution of power grid equipment. Background Art

[0002] With the rapid development of my country's power industry, increased investment in grid construction has significantly increased the proportion of fixed assets in power supply companies, and the corresponding operation and maintenance projects and costs have also shown a trend of increasing year by year. As a result, the centralized commissioning of power equipment and the expansion of technical upgrades and overhauls have placed significant pressure on power grid companies. A reasonable forecast of the scale of future technical upgrade investment is of great practical significance to the safe and stable operation of the power grid.

[0003] Currently, most power grid companies still employ traditional management models for equipment asset management, relying on past operational experience and specialized reports from grassroots departments. Ultimately, this is due to a lack of overall understanding within decision-making departments. Furthermore, as described in the document "Research on Cost Management of Overhaul and Technical Transformation Projects in Power Supply Enterprises" (Chen Hu, [D]. North China Electric Power University (Beijing), 2009), under traditional management models, power grid companies manage equipment assets with a single objective or task-based approach, focusing primarily on the cost management of individual projects or short-term investment plans. This approach lacks long-term planning and makes it impossible to predict the scale of future technical transformations.

[0004] Drawing on the experience of foreign power grid companies in equipment asset management, many domestic researchers have made some explorations. The document "Research on the Full Life Cycle Management of Power Grid Enterprise Assets Based on Value Chain" (Jiang Xiaojun, Li Fei. [J]. Finance and Accounting Communications, 2011(11): 103-104) proposed the full life cycle management of assets, with the goal of pursuing cost minimization. Although it can achieve greater economic benefits, it still cannot achieve the technical transformation investment forecast of the power grid. The document "Research and Implementation of the Scale Estimation Method of the Power Company's Capital Project Plan" (Qin Guoqiang. [D]. University of Electronic Science and Technology of China, 2013) established a power grid enterprise investment forecast model based on gray theory. By studying the internal relationship between selected evaluation indicators such as asset-to-income ratio and load growth value and investment amount, it predicts the power grid investment for the next year. Although the forecast model method is simple, it does not take into account the equipment life factor and cannot make long-term investment forecasts. The paper "Research on Technological Transformation Prediction Based on the Physical "Asset Wall" of Power Grids" (Zhang Junbo, Shao Yonggang. [J]. China Management Informationization, 2016, 19(14): 18-20) introduces the asset wall theory, using the service life of equipment assets as the translation period to predict future investment in corresponding years. However, simply shifting the period based on the original historical investment scale is obviously inconsistent with the actual development status and poses a significant asset wall risk. Therefore, how to accurately realize the investment forecast of power grid equipment is a major bottleneck that needs to be urgently resolved. Summary of the Invention

[0005] The purpose of the present invention is to solve the prediction limitations and inaccuracies of the existing technology and to provide a reasonable and accurate system and method for predicting the scale of technical transformation based on the scrap rate and age distribution of power grid equipment.

[0006] To achieve the above objectives, the present invention provides the following technical solutions:

[0007] A technical transformation scale prediction system based on the age distribution of power grid equipment scrapping rates includes a data source management module, a data processing module, a prediction model, and a calculation module. The prediction model and calculation module include a data feature distribution analysis module and a technical transformation scale prediction module. The signal input end of the data feature distribution analysis module is connected to the signal output end of the data source management module via the data processing module, and the signal output end of the data feature distribution analysis module is connected to the signal input end of the technical transformation scale prediction module.

[0008] The data source management module is used to obtain basic data information of power grid equipment, which includes information on in-service equipment and information on scrapped power grid equipment in recent years;

[0009] The data processing module is used to perform multi-source data fusion and matching on the basic data information of power grid equipment, and obtain the service age distribution of the scale of in-service equipment, the service age probability distribution of the scale of equipment to be scrapped and scrapped, and the scale and service age distribution of the proportion of equipment to be scrapped and scrapped in all equipment based on the statistics of the fused and matched data;

[0010] The data feature distribution analysis module is used to perform data fitting on the service age probability distribution of the scale of the equipment to be scrapped and scrapped output by the data processing module, and obtain the scrap probability fitting function of the equipment to be scrapped and scrapped with respect to service age;

[0011] The technical transformation scale prediction module predicts the technical transformation investment scale of different types of power grid equipment based on the scrap probability fitting function of the equipment to be scrapped and scrapped with respect to the service age and through asset wall analysis.

[0012] The data processing module includes a device information fusion management module and a data statistics management module. The signal input end of the device information fusion management module is connected to the signal output end of the device data acquisition module. The signal output end of the device information fusion management module is connected to the signal input end of the data feature distribution analysis module through the data statistics management module.

[0013] The equipment information fusion management module is used to perform multi-source data fusion and matching on the basic data information of power grid equipment;

[0014] The data statistics management module is used to combine the constructed indicators, dimensions and matching methods to perform statistics on the fused and matched data to obtain the service age distribution of the scale of in-service equipment, the service age probability distribution of the scale of equipment to be scrapped and scrapped, and the scale proportion of equipment to be scrapped and scrapped in all equipment in the power grid.

[0015] The indicator is at least one of the quantity scale, technology scale, value scale, newness rate, and quantity / technology / value scale ratio of power grid equipment; the dimension is at least one of the equipment type, voltage level, operating status, health status, service age, and management unit; the matching method is at least one of matching by the code or physical ID of the individual equipment, matching by voltage level, matching by equipment type, matching by station line layer, and matching by organizational layer.

[0016] A method for predicting the scale of technical transformation based on the age distribution of power grid equipment obsolescence rate is implemented by the above-mentioned prediction system and includes the following steps in sequence:

[0017] Step A: The data source management module obtains basic data information of power grid equipment from an external system and sends it to the data processing module;

[0018] Step B: The data processing module performs multi-source data fusion and matching on the basic data information of the power grid equipment, and obtains the service age distribution of the scale of in-service equipment, the service age probability distribution of the scale of equipment to be scrapped and scrapped, and the scale proportion of equipment to be scrapped and scrapped in all equipment based on the statistics of the fused and matched data;

[0019] Step C: the data feature distribution analysis module performs data fitting on the service age probability distribution of the scale of the equipment to be scrapped and scrapped output by the data processing module to obtain a fitting function of the scrap probability of the equipment to be scrapped and scrapped with respect to service age;

[0020] Step D: The technical transformation scale prediction module predicts the scale of technical transformation investment of power grid equipment based on the scrap probability fitting function of the equipment to be scrapped and scrapped with respect to the service age and through asset wall analysis.

[0021] In step C, the scrap probability fitting function of the equipment to be scrapped and scrapped with respect to service age is:

[0022] h(t)=a0+a1t+a2t 2 +a3t 3 +a4t 4 +a5t 5 +a6t 6 +a7t 7

[0023] In the above formula, h(t) is the scrap probability of the equipment to be scrapped and scrapped with respect to the service age t, and a0, a1, a2, a3, a4, a5, a6, and a7 are the coefficients of the constant term, linear term, quadratic term, cubic term, quartic term, quintic term, sextic term, and septic term of the fitting function, respectively.

[0024] The step D comprises the following steps in sequence:

[0025] Step D1, using the scrap probability fitting function of the equipment to be scrapped and scrapped with respect to the service age to calculate the scrap probability of the equipment at different service ages;

[0026] Step D2: Based on the scrap probability of the equipment at different service ages, the service age value is shifted backward by the corresponding number of years based on the following shift function to obtain the asset wall data after the shift, wherein the number of asset wall data groups after the shift is equal to the maximum scrap service age:

[0027] f i (T+j,V i (k),P i (k),R i (k))=V i (n-j+1)P i (n-j+1)R i (n-j+1)

[0028] In the above formula, f i (T+j,V i (k),P i (k),R i (k)) is the asset wall of the i-th type of equipment after j years of translation, T is the maximum year of the asset wall, j is the number of years of translation, k is the service age, k = n-j+1, V i (n-j+1) is the value of the equipment in operation of type i in year n-j+1, P i (n-j+1) is the probability of scrapping of the i-th type of equipment in the n-j+1th year calculated by the fitting function, R i (n-j+1) is the proportion of equipment to be scrapped and scrapped in the i-th category of equipment in the n-j+1 year among all equipment;

[0029] Step D3: Superimpose the translated asset wall data by age to obtain the predicted value of technological transformation investment scale for each year:

[0030]

[0031] In the above formula, g i (T+j) is the predicted value of the technical transformation investment scale of the i-th type of equipment in the T+j year, n is the maximum scrapped age, V i (k) is the scale of equipment in operation under the service age k of the i-th type of equipment, Pi (k) is the probability of scrapping of type i equipment at service age k, R i (k) is the proportion of equipment of category i that is to be scrapped and scrapped at age k in all equipment;

[0032] Step D4: Determine the predicted value of the technical transformation investment scale of power grid equipment according to the following formula:

[0033]

[0034] In the above formula, g(T+j) is the forecast value of the technical transformation investment scale of power grid equipment in the T+j year, and m is the total number of power grid equipment types that require technical transformation investment scale forecast.

[0035] In step B, the scale is quantity scale, technology scale or value scale.

[0036] Compared with the prior art, the present invention has the following beneficial effects:

[0037] 1. The technical transformation scale prediction system based on the service age distribution of power grid equipment scrapping rate of the present invention includes a data source management module, a data processing module, a prediction model and a calculation module. The prediction model and the calculation module include a data feature distribution analysis module and a technical transformation scale prediction module. The data source management module is used to obtain basic data information of power grid equipment. The data processing module is used to perform multi-source data fusion matching on the basic data information of power grid equipment, and obtain the service age distribution of the scale of in-service equipment, the service age probability distribution of the scale of equipment to be scrapped and scrapped, and the scale proportion of equipment to be scrapped and scrapped in all equipment based on the statistics of the fusion and matching data. The data feature distribution analysis module is used to analyze the scale of equipment to be scrapped and scrapped output by the data processing module. The service age probability distribution of the model is used to fit the data, and the scrap probability fitting function of the equipment to be scrapped and scrapped with respect to service age is obtained. The technical transformation scale prediction module is based on the scrap probability fitting function of the equipment to be scrapped and scrapped with respect to service age and predicts the scale of technical transformation investment of different types of power grid equipment through asset wall analysis. The system is based on the information of each historical scrapped equipment and the real-time information of the currently operating equipment, and determines the scrap probability fitting function of the equipment to be scrapped and scrapped with respect to service age according to the service age probability distribution and scale proportion of the power grid equipment scale, and accurately predicts the future equipment technical transformation investment by combining the scrap probability and asset wall analysis, thereby ensuring the reasonable accuracy of the prediction results and providing a reliable scientific basis for the future formulation of technical transformation planning schemes for power grid equipment. Therefore, the prediction results of the present invention are reasonable and accurate, which is conducive to the formulation of technical transformation planning schemes for power grid equipment in the future.

[0038] 2. In the technical transformation scale prediction method based on the age distribution of power grid equipment scrapping rates, the present invention uses a multi-item fitting approach to fit the scrapping probability fitting function for both pending and scrapped equipment. This not only effectively fits each statistical data point, addressing the data fluctuations that cannot be accounted for by traditional methods using linear prediction curves, but also effectively avoids overfitting by limiting the order to below 8. Therefore, the present invention avoids overfitting while ensuring accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is a structural block diagram of the system of the present invention. DETAILED DESCRIPTION

[0040] The present invention will be further described below with reference to the accompanying drawings and specific embodiments.

[0041] The present invention establishes a complete power grid equipment technical transformation investment scale prediction system with complete functional modules. The system integrates and manages the different operating states of power grid equipment and scrapped equipment records collected through the data source management module 1, converts the data according to standard requirements and sends it to the data processing module 2 for statistical analysis of power grid equipment information data, including the service age distribution of the scale of in-service equipment, the service age probability distribution of the scale of equipment to be scrapped and scrapped, and the scale proportion of equipment to be scrapped and scrapped in all equipment. Through the prediction model and measurement module 3, combined with the fitted scrap probability function of the equipment to be scrapped and scrapped with respect to service age, the scale proportion of scrapped equipment, and the asset wall analysis tool, the investment scale of the technical transformation project is predicted. Overall, the various functional modules are intertwined, coordinating the management links of the entire equipment cycle, automatically completing asset data analysis and technical transformation investment prediction, and effectively improving the level of equipment management.

[0042] The prediction method selected by the present invention has high efficiency and reliability, and the prediction process has the characteristics of standardization and normalization. First, the asset wall distribution of various types of equipment is obtained based on the statistics of equipment type or voltage level, and the scale of equipment in the operating status of being scrapped and scrapped, as well as the proportion of all equipment in each service age distribution under different service age distributions can be quickly counted; secondly, based on the individual information of equipment to be scrapped and actually scrapped of different equipment types or voltage levels, the probability of scrapping of equipment with different service ages can be quickly calculated, and data fitting is performed to obtain the fitting function of the probability of scrapping of equipment with respect to service age. Based on the distribution characteristics of the original data, a multi-item fitting method is selected. Under the condition of controlling the order of the fitting function to prevent overfitting, combined with statistical data such as the asset wall, the proportion of the scale of equipment to be scrapped and scrapped, the asset wall analysis tool is used to calculate the investment scale of equipment with different service ages. Finally, the measurement results are aggregated and summed according to the service age, and the prediction results of the investment scale of technical transformation of various types of equipment can be accurately obtained.

[0043] This forecasting method uses consecutive integers ranging from 1 to n for trend extrapolation of the asset wall. A probability value is assigned for each extrapolation period. This probability value is derived from a combination of the calculated scrap probability fitting function for the age of equipment to be scrapped and scrapped, and the scale ratio of equipment to be scrapped and scrapped at different ages. It reflects the probability that equipment commissioned in different years within the asset wall will be scrapped and retired due to technological upgrades in the next few years (the extrapolation period). The inclusion of this probability value improves the accuracy of the trend extrapolation process. Traditional asset wall extrapolation analysis methods use a single statistical value for the period, typically representing average service life, economic life, or equipment life. Regardless of the extrapolation period, the theoretical probability is assumed to be 100%. Therefore, this forecasting method offers significant advantages over traditional asset wall extrapolation analysis methods.

[0044] In the present invention, the statistical method for the probability distribution of the service age of the equipment to be scrapped and the scale of scrapped equipment is: based on the collected data set, first count the number of recorded data to calculate the service age, then count the number of recorded data corresponding to each service age, and then calculate the proportion of the number of recorded data corresponding to different service ages in the total amount of recorded data, that is, to obtain the probability distribution according to service age.

[0045] Example 1:

[0046] See also Figure 1 A technical transformation scale prediction system based on the scrap rate and age distribution of power grid line equipment includes a data source management module 1, a data processing module 2, and a prediction model and calculation module 3. The data processing module 2 includes an equipment information fusion management module 21 and a data statistical method management module 22. The prediction model and calculation module 3 includes a data feature distribution analysis module 31 and a technical transformation scale prediction module 32. The signal input end of the equipment information fusion management module 21 is connected to the signal output end of the data source management module 1. The signal output end of the equipment information fusion management module 21 is connected to the signal input end of the data feature distribution analysis module 31 through the data statistical method management module 22. The signal output end of the data feature distribution analysis module 31 is connected to the signal input end of the technical transformation scale prediction module 32.

[0047] This embodiment uses the above-mentioned prediction system to make predictions for the next 20 years, and proceeds in the following steps:

[0048] 1. The data source management module 1 obtains basic data information of power grid equipment from the ERP system and sends it to the equipment information fusion management module 21, wherein the basic data information of power grid equipment includes information on in-service equipment and information on scrapped power grid equipment in recent years. The in-service equipment information includes the commissioning date, quantity, scale of technical transformation, original value and net value of equipment assets, etc. The scrapped power grid equipment information in recent years includes the commissioning date, scrapping date, scrapping reason, scrapping scale (partial or full), original value and net value of scrapped equipment assets, etc.;

[0049] 2. The equipment information fusion management module 21 performs multi-source data fusion and matching on the basic data information of power grid equipment according to the equipment type;

[0050] 3. The data statistics management module 22 combines the constructed quantity scale, technology and value scale indicators, equipment type dimensions and matching methods to perform statistics on the fused and matched data to obtain the age distribution of the value scale of the in-service equipment, i.e., the asset wall distribution data of the power grid line equipment, and the age distribution of the value and quantity scale of the equipment to be scrapped and scrapped. Subsequently, based on the age distribution of the value scale of the equipment to be scrapped and scrapped and the age of the value scale of the in-service equipment, the value scale proportion distribution of the equipment to be scrapped and scrapped in all the equipment in the power grid is determined step by step. Based on the age distribution of the quantity scale of the equipment to be scrapped and scrapped, the scrap rate age distribution of the quantity and technology scale of the equipment to be scrapped and scrapped is determined respectively.

[0051] 4. The data feature distribution analysis module 31 performs data fitting on the scrap rate and service age distribution of the received number and scale of equipment to be scrapped and scrapped, and obtains a fitting function of the scrap probability of the number and scale of equipment to be scrapped and scrapped with respect to service age:

[0052] h(t)=a0+a1t+a2t 2 +a3t 3 +a4t 4 +a5t 5 +a6t 6 +a7t 7

[0053] In the above formula, h(t) is the scrap probability of the equipment to be scrapped and scrapped with respect to the service age t, a0, a1, a2, a3, a4, a5, a6, and a7 are the coefficients of the constant term, linear term, quadratic term, cubic term, quartic term, quintic term, sextic term, and septic term of the fitting function respectively;

[0054] The coefficients of the function obtained by fitting in this embodiment are shown in Table 1:

[0055] Table 1 Fitting function coefficients

[0056]

[0057]

[0058] 5. The technical transformation scale prediction module 32 calculates the scrap probability values ​​of equipment to be scrapped and scrapped with service age based on the scrap probability fitting function of the equipment to be scrapped and scrapped with service age between 1 and 50 years. Combined with the aforementioned data on the proportion of equipment to be scrapped and scrapped in different service age groups and the asset wall distribution data of power grid line equipment, the module 32 shifts the corresponding years from 1 year to 50 years based on the following shift function to obtain 50 sets of shifted asset wall data:

[0059] f i (T+j,V i (k),P i (k),R i (k))=V i (n-j+1)P i (n-j+1)R i (n-j+1)

[0060] In the above formula, f i (T+j,V i (k),P i (k),R i (k)) is the asset wall of the i-th type of equipment after j years of translation, T is the maximum year of the asset wall, j is the number of years of translation, k is the service age, k = n-j+1, V i (n-j+1) is the value of the equipment in operation of type i in year n-j+1, P i (n-j+1) is the probability of scrapping of the i-th type of equipment in the n-j+1th year calculated by fitting function h(t), R i (n-j+1) is the proportion of equipment to be scrapped and scrapped in the i-th category of equipment in the n-j+1 year among all equipment;

[0061] 6. Superimpose the 50 sets of translated asset wall data by age to obtain the predicted scale of technological transformation investment in each year:

[0062]

[0063] In the above formula, g i (T+j) is the predicted value of the technical transformation investment scale of the i-th type of equipment in the T+j year, n is the maximum scrapped age, V i (k) is the scale of equipment in operation under the service age k of the i-th type of equipment, P i (k) is the probability of scrapping of type i equipment at service age k, R i (k) is the proportion of equipment of category i that is to be scrapped and scrapped at age k in all equipment;

[0064] 7. Determine the forecast value of the technical transformation investment scale of power grid equipment according to the following formula:

[0065]

[0066] In the above formula, g(T+j) is the predicted value of the technical transformation investment scale of power grid equipment in the T+j year, and m is the total number of power grid equipment types that require technical transformation investment scale forecast;

[0067] In this embodiment, the calculated data of the corresponding column 20 years backward from the current year T is the predicted scale of technical transformation investment required for power grid line equipment each year in the next 20 years; the predicted value of the technical transformation investment scale in recent years obtained by using this method is obtained by moving the current year T forward several years. Based on the indicator data statistically collected by this method, the traditional asset wall analysis method is used to predict the scale of technical transformation investment in the same number of years in the future. The predicted values ​​obtained by this method and the predicted values ​​obtained by the traditional asset wall analysis method are compared with the actual values ​​of investment scale in recent years. The results are shown in Table 2:

[0068] Table 2 Comparison between the predicted values ​​obtained by this method and the actual values ​​of investment scale in the past three years

[0069]

[0070] From the results shown in Table 2, it can be seen that the investment scale forecast value obtained by this method is highly consistent with the actual investment scale value of the corresponding year and has high accuracy; while the forecast value obtained by using the traditional asset wall analysis method is very different from the actual investment scale value of the corresponding year, and its forecast value has no reference significance.

Claims

1. A method for predicting the scale of technical transformation based on the age distribution of power grid equipment obsolescence rate, characterized by: The prediction method comprises the following steps in sequence: Step A: The data source management module (1) obtains basic data information of power grid equipment from an external system and sends it to the data processing module (2); Step B, the data processing module (2) performs multi-source data fusion matching on the basic data information of the power grid equipment, and obtains the service age distribution of the scale of the in-service equipment, the service age probability distribution of the scale of the equipment to be scrapped and scrapped, and the scale proportion of the equipment to be scrapped and scrapped in all the equipment based on the statistics of the fusion matched data; Step C: The data feature distribution analysis module (31) performs data fitting on the service age probability distribution of the scale of the equipment to be scrapped and scrapped output by the data processing module (2), and obtains a scrap probability fitting function of the equipment to be scrapped and scrapped with respect to service age, wherein the scrap probability fitting function of the equipment to be scrapped and scrapped with respect to service age is: h(t)=a0+a1t+a2t 2 +a3t 3 +a4t 4 +a5t 5 +a6t 6 +a7t 7 In the above formula, h(t) is the scrap probability of the equipment to be scrapped and scrapped with respect to the service age t, a0, a1, a2, a3, a4, a5, a6, a7 are the coefficients of the constant term, first order term, second order term, third order term, fourth order term, fifth order term, sixth order term, and seventh order term of the fitting function respectively; Step D, the technical transformation scale prediction module (32) predicts the technical transformation investment scale of power grid equipment based on the scrap probability fitting function of the equipment to be scrapped and scrapped with respect to the service age and through asset wall analysis, and comprises the following steps in sequence: Step D1, using the scrap probability fitting function of the equipment to be scrapped and scrapped with respect to the service age to calculate the scrap probability of the equipment at different service ages; Step D2: According to the scrap probability of the equipment at different service ages, the corresponding years are shifted backward according to the service age value based on the following shift function to obtain the asset wall data after the array shift, wherein the number of asset wall data groups after the shift is equal to the maximum scrap service age number: f i (T+j,V i (k),P i (k),R i (k))=V i (n-j+1)P i (n-j+1)R i (n-j+1) In the above formula, f i (T+j,V i (k),P i (k),R i (k)) is the asset wall of the i-th type of equipment after j years of translation, T is the maximum year of the asset wall, j is the number of years of translation, k is the service life, k = n-j+1, V i (n-j+1) is the value scale of the equipment in operation of the i-th type of equipment in the n-j+1th year, P i (n-j+1) is the scrap probability of the i-th type of equipment in the n-j+1th year calculated by the fitting function h(t), R i (n-j+1) is the proportion of equipment to be scrapped and scrapped in the i-th category of equipment in the n-j+1th year among all equipment; Step D3: Superimpose the translated asset wall data by age to obtain the predicted value of technological transformation investment scale in each year: In the above formula, g i (T+j) is the predicted value of the technical transformation investment scale of the i-th type of equipment in the T+j year, n is the maximum scrapped age, V i (k) is the scale of equipment in operation at the age k of the i-th type of equipment, P i (k) is the probability of scrapping of the i-th type of equipment at the service age k, R i (k) is the proportion of equipment of category i that is to be scrapped and scrapped at age k in all equipment; Step D4: Determine the predicted value of the technical transformation investment scale of power grid equipment according to the following formula: In the above formula, g(T+j) is the predicted value of the technical transformation investment scale of power grid equipment in the T+jth year, and m is the total number of power grid equipment types that require technical transformation investment scale forecast.

2. The method for predicting the scale of technical transformation based on the scrap rate and age distribution of power grid equipment according to claim 1 is characterized by: In step B, the scale is quantity scale, technology scale or value scale.

3. A technical transformation scale prediction system based on the scrap rate and age distribution of power grid equipment, characterized by: The prediction system is used to execute the prediction method according to claim 1, comprising a data source management module (1), a data processing module (2), a prediction model and a calculation module (3), wherein the prediction model and the calculation module (3) comprises a data feature distribution analysis module (31) and a technical transformation scale prediction module (32), wherein the signal input end of the data feature distribution analysis module (31) is connected to the signal output end of the data source management module (1) through the data processing module (2), and the signal output end of the data feature distribution analysis module (31) is connected to the signal input end of the technical transformation scale prediction module (32); The data source management module (1) is used to obtain basic data information of power grid equipment, wherein the basic data information of power grid equipment includes in-service equipment information and historical power grid scrapped equipment information in recent years; The data processing module (2) is used to perform multi-source data fusion matching on basic data information of power grid equipment, and obtain the service age distribution of the scale of in-service equipment, the service age probability distribution of the scale of equipment to be scrapped and scrapped, and the scale proportion of equipment to be scrapped and scrapped in all equipment based on the statistics of the fusion-matched data; The data feature distribution analysis module (31) is used to perform data fitting on the service age probability distribution of the scale of the equipment to be scrapped and scrapped output by the data processing module (2), and obtain a scrap probability fitting function of the equipment to be scrapped and scrapped with respect to service age; The technical transformation scale prediction module (32) predicts the scale of technical transformation investment of different types of power grid equipment based on the scrap probability fitting function of the equipment to be scrapped and scrapped with respect to the service age and through asset wall analysis.

4. The technical transformation scale prediction system based on the scrap rate and service age distribution of power grid equipment according to claim 3 is characterized by: The data processing module (2) comprises a device information fusion management module (21) and a data statistics mode management module (22); the signal input end of the device information fusion management module (21) is connected to the signal output end of the data source management module (1); the signal output end of the device information fusion management module (21) is connected to the signal input end of the data feature distribution analysis module (31) via the data statistics mode management module (22); The equipment information fusion management module (21) is used to perform multi-source data fusion matching on basic data information of power grid equipment; The data statistics management module (22) is used to combine the constructed indicators, dimensions and matching methods to perform statistics on the fused and matched data to obtain the service age distribution of the scale of in-service equipment, the service age probability distribution of the scale of equipment to be scrapped and scrapped, and the scale proportion distribution of equipment to be scrapped and scrapped in all equipment in the power grid.

5. The technical transformation scale prediction system based on the scrap rate and service age distribution of power grid equipment according to claim 4 is characterized by: The indicator is at least one of the quantity scale, technology scale, value scale, newness rate, and quantity / technology / value scale ratio of power grid equipment; the dimension is at least one of the equipment type, voltage level, operating status, health status, service age, and management unit; the matching method is at least one of matching by the code or physical ID of the individual equipment, matching by voltage level, matching by equipment type, matching by station line layer, and matching by organizational layer.

Images