A power transmission and transformation project pre-audit state assessment method

Abstract

The application discloses a kind of power transmission and transformation engineering pre-trial state evaluation method, it is related to electric power engineering evaluation technical field, present and propose the following scheme, including the following steps: S1, data acquisition and pretreatment;S2, construction pre-trial state evaluation index system;S3, evaluation model construction and training;S4, pre-trial state quantitative evaluation;S5, state classification and result output;S6, evaluation report and control scheme output.The application realizes accurate risk positioning and intelligent control by standardizing data processing, constructing scientific index system, building accurate deduction model, solves many pain points of traditional power transmission and transformation engineering evaluation, realizes whole life cycle quantitative evaluation and intelligent management and control, improves evaluation accuracy and forward-looking, reduces security risk, effectively improves engineering operation stability and operation efficiency, provides efficient and reliable technical support for electric power engineering operation.

Description

Technical Field

[0001] This invention relates to the field of power engineering assessment technology, and in particular to a method for assessing the pre-approval status of power transmission and transformation projects. Background Technology

[0002] Power transmission and transformation projects are a core component of the power system, and their operational status directly affects the safety and stability of the power grid. Existing assessment methods rely heavily on manual inspections and simple indicator judgments, which have problems such as incomplete data collection, non-standard preprocessing, and inconsistent dimensions. The assessment indicator system is not comprehensive, and the weighting is subjective and arbitrary, making it difficult to fully reflect the overall status of construction quality, equipment operation, environmental adaptability, and aging and wear.

[0003] Meanwhile, traditional models do not take into account the aging mechanism and load characteristics of equipment, resulting in low prediction accuracy and strong lag. They cannot accurately predict short-term state fluctuations, medium-term performance degradation, and long-term life trends. In addition, the risk positioning is vague and the control plan is not targeted enough, which can easily lead to untimely discovery of hidden dangers, waste of operation and maintenance resources, and increased operational risks.

[0004] Therefore, there is an urgent need for a standardized, intelligent, and high-precision method for pre-approval status assessment of power transmission and transformation projects. Summary of the Invention

[0005] The purpose of this invention is to address the problems existing in the status assessment of power transmission and transformation projects, such as non-standard data processing, incomplete indicator system, insufficient accuracy of assessment models, vague risk positioning, and lack of targeted control schemes. This invention provides a pre-approval status assessment method for power transmission and transformation projects based on power big data and machine learning, which enables quantitative assessment of the status of the entire life cycle of the project, accurate risk positioning, and intelligent control, thereby improving the operational stability and maintenance efficiency of power transmission and transformation projects.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: A method for pre-approval status assessment of power transmission and transformation projects includes the following steps: S1. Data Acquisition and Preprocessing: Collect operational, construction, and environmental data throughout the entire lifecycle of the project, and then perform standardized cleaning, normalization, outlier removal, and missing value imputation to form a standardized dataset. The data collection scope covers the entire lifecycle of power transmission and transformation projects, including planning, construction, trial operation, routine operation and maintenance, and aging and decommissioning. Specifically, it includes: Construction-related: construction parameters, installation accuracy, equipment factory parameters, acceptance data; Operational parameters: load factor, voltage / current, insulation performance, temperature rise, power factor; Environmental factors: temperature and humidity, altitude, pollution level, lightning strike frequency, and geological conditions; Aging data: equipment service life, wear rate, fault records, and maintenance history; The preprocessing process is as follows: Dimensional unification: Converting data with different units such as voltage, temperature, load, and time into dimensionless data in the range [0,1]. Outlier removal: A threshold screening method is used to remove abnormal data (such as overpressure and overtemperature) that are outside the normal operating range of the equipment. Missing value imputation: Linear interpolation is used to fill in consecutive time-series missing data to ensure the integrity of the dataset; Data denoising: Filtering out interfering noise and outputting a standardized structured dataset; Normalization (Min-Max standardization) linearly maps the original data to the [0,1] interval, eliminating the influence of dimensions. The calculation formula is as follows: ; in, This is the normalized standard data; This is the original collected data; This is the historical minimum value of this indicator; This is the historical maximum value of this indicator.

[0007] It is worth mentioning that a unified data scale is needed to avoid the evaluation results being affected by differences in the numerical range of different indicators. S2. Construct a preliminary review status assessment index system: Build an index system covering construction, operation and maintenance and aging iteration, and use the analytic hierarchy process to determine the fixed weights of each index, with the total weights being 1; The indicator system architecture adopts the analytic hierarchy process (AHP) to construct a multi-level system of first-level dimensions and second-level sub-indicators. The weights are fixed and the sum is 1, with no dynamic fluctuations. Weight determination method (analytic hierarchy process): Construct a judgment matrix to compare the relative importance of indicators; Calculate the eigenvalues ​​and eigenvectors of the matrix to obtain the weight vector; Consistency checks are performed to ensure that the weights are reasonable and consistent. Output fixed weight coefficients: First-level dimension weight × Second-level indicator weight = Final indicator weight; The formula for calculating the total weight of the indicators is as follows: ; in, This represents the total weight of the i-th secondary indicator; The weight of the j-th first-level dimension; Let be the weight of the i-th secondary indicator within its respective dimension; Constraints: To ensure that the total weights are 1; S3. Evaluation Model Construction and Training: Based on the equipment aging mechanism, load characteristics and environmental impact, a machine learning life cycle prediction model is built, which is trained with historical data to predict the state changes and lifespan decline trends. Model principle: Based on equipment aging mechanism, load characteristics and environmental impact patterns, a machine learning life cycle prediction model is built, and random forest / gradient boosting tree (GBDT) is selected as the base model to adapt to time series data and life cycle prediction. The model training process is as follows: Input: Historical full lifecycle standardized dataset (input features + state labels); Learning: Fitting the mapping relationship between state changes, performance degradation, and lifetime threshold; Output: A fixed model that can accurately predict three types of parameters: short-term fluctuations, medium-term decay, and long-term lifespan; The lifespan decay fitting (exponential decay model) is used to estimate the aging trend and remaining lifespan of equipment, closely matching the actual aging patterns of power equipment. The calculation formula is as follows: ; in, The percentage of the equipment's remaining lifespan after t years of service; This represents the initial lifespan of the device (1 for brand new condition). This is the aging rate coefficient (determined through training with historical data); This refers to the actual service life of the equipment. It is a natural constant, approximately 2.71828, used to characterize the exponential aging degradation law of equipment. S4. Quantitative assessment of pre-review status: Substitute real-time data into the model and calculate the overall pre-review status score through a weighted summation algorithm. The result is retained to two decimal places. Evaluation Logic: Real-time standardized data is substituted into a fixed model to obtain scores for each indicator. These scores are then weighted and summed using fixed weights to output an overall preliminary score, rounded to two decimal places. The calculation logic is fixed and free from random bias, employing a weighted summation scoring algorithm. The formula is as follows: ; in, Scoring the overall preliminary review status of the project; The real-time score (0-100 points) for the i-th secondary indicator; This represents the total weight of the i-th secondary indicator; This represents the total number of secondary indicators; Dimensional scoring formula: ; By first calculating the scores for each dimension and then summing the overall scores, a tiered quantitative assessment can be achieved. S5. Status Classification and Result Output: The status level is determined according to the preset four-level thresholds of excellent, qualified, warning and fault, and the index score is compared to locate potential risk points, equipment and links. The table below shows the threshold values ​​for Level 4 states (fixed range): Risk positioning logic: Compare the scores of secondary indicators with the thresholds one by one to pinpoint the equipment locations, operational processes, and risk types corresponding to the non-compliant indicators, thereby achieving precise positioning; S6. Assessment Report and Control Plan Output: Output a standardized assessment report containing data, scores, levels and risk points, as well as operation and maintenance rectification, load control and equipment maintenance support plans that match the risk level; The standardized evaluation report contains the following: Data statistics: Comprehensive data collection and preprocessing results; Scoring details: Preliminary score for each indicator, each dimension, and the overall pre-screening; Status level: Level 4 judgment result; Risk points: substandard equipment, processes, and types of risks; The intelligent control scheme (matched by level) is as follows: Excellent: Routine inspections and regular maintenance; Pass: Shortened inspection cycle, localized optimization; Early warning: load regulation, insulation enhancement, and key monitoring; Faults: Emergency shutdown, equipment replacement, load reconfiguration.

[0008] Furthermore, the data preprocessing in S1 specifically includes: unifying the dimensional standards of all collected data, removing abnormal data that exceeds the normal operating range through threshold screening, supplementing missing data using linear interpolation, completing data noise reduction processing, and forming a standardized structured dataset. The dataset fully covers the entire life cycle of power transmission and transformation projects, including planning, construction, trial operation, and routine operation and maintenance.

[0009] Furthermore, the construction of the evaluation index system in S2 specifically includes: the index system is divided into four core dimensions: construction quality index, equipment operation index, environmental adaptability index and aging loss index. Each dimension has fixed secondary sub-indicators. The fixed weight coefficients of each secondary indicator and primary dimension are determined one by one through the analytic hierarchy process. The total weight coefficient is 1, and there is no dynamic fluctuation range.

[0010] Furthermore, the construction and operation of the life cycle estimation model in S3 specifically includes: building a machine learning estimation model based on the aging mechanism of power transmission and transformation equipment, load operation characteristics and environmental impact laws, completing the model solidification training with historical full life cycle data as training samples, and accurately predicting the changing trends of three core parameters: short-term operating status fluctuations, medium-term performance degradation and long-term lifespan threshold.

[0011] Furthermore, the status score calculation in S4 specifically includes: retrieving real-time standardized data, matching the weight coefficients of each indicator, calculating the dimension score through a weighted summation algorithm, and then combining the weights of each dimension to obtain the overall pre-approval status score of the project. The score result is retained to two decimal places, and the scoring logic is fixed with no random bias.

[0012] Furthermore, the status level determination and risk positioning in S5 specifically includes: pre-setting four fixed scoring threshold ranges for excellent, qualified, warning and fault, matching the corresponding status level based on the overall score; comparing the scoring thresholds of each secondary indicator one by one, accurately locking the equipment location, operation link and risk type corresponding to the indicator not meeting the standard, and completing the accurate risk positioning.

[0013] Furthermore, the output of the assessment report and control plan in S6 specifically includes: the assessment report includes data statistics, indicator scoring details, status level and risk point information; the control plan matches fixed corresponding operation and maintenance rectification, load control and equipment maintenance measures for different risk levels to ensure the continuous and stable operation of the power transmission and transformation project.

[0014] Compared with existing technologies, the beneficial effects of this invention are: 1. This invention standardizes the collection and preprocessing of data throughout the entire lifecycle of power transmission and transformation projects. Through unification of dimensions, removal of outliers, filling in missing values, and data noise reduction, a standardized structured dataset is formed. Min-Max standardization eliminates differences in the dimensions and numerical ranges of different indicators, avoiding data bias from affecting the evaluation results. Linear interpolation ensures the integrity of time-series data, providing accurate and complete data support for subsequent evaluation models. This invention solves the problems of chaotic and error-prone traditional evaluation data processing from the source, and significantly improves the accuracy and usability of the basic evaluation data. 2. This invention uses the analytic hierarchy process (AHP) to construct a multi-level indicator system with four core dimensions, covering all aspects of construction quality, equipment operation, environmental adaptability, and aging loss. The weights are fixed and the total weight is 1. The weight allocation is verified for consistency to ensure that it is reasonable and without contradiction. The system takes into account the entire process of engineering construction, operation and maintenance, and aging, and overcomes the shortcomings of traditional evaluation indicators that are one-sided and have arbitrary weights. It achieves a comprehensive and thorough measurement of the status of power transmission and transformation projects, making the evaluation results more consistent with the actual status of the project and improving the comprehensiveness and scientific nature of the status assessment. 3. This invention builds a machine learning lifecycle prediction model based on equipment aging mechanism, load characteristics and environmental impact. It is trained and solidified with historical full lifecycle data, which can accurately predict short-term state fluctuations, medium-term performance degradation and long-term life threshold. Combined with the exponential decay model, it fits the aging law of power equipment, solves the problems of insufficient accuracy and fuzzy prediction of traditional models, and can predict equipment life and performance changes in advance, providing a forward-looking basis for operation and maintenance decisions, and effectively improving the accuracy of fault prediction and life assessment. 4. This invention sets four-level status thresholds and quantifies the evaluation results through weighted scoring. It can quickly identify the equipment, links, and risk types corresponding to non-compliant indicators, achieving precise risk positioning. At the same time, it matches exclusive operation and maintenance rectification, load regulation, and equipment maintenance plans according to status level and outputs standardized evaluation reports. This changes the problems of vague risk positioning and general control measures in traditional assessments, making operation and maintenance more efficient and targeted, and significantly improving the operational stability and operation and maintenance management efficiency of power transmission and transformation projects. In summary, this method not only addresses many pain points in traditional power transmission and transformation project assessment by standardizing data processing, constructing a scientific indicator system, building a precise inference model, and achieving accurate risk positioning and intelligent control, but also realizes full life-cycle quantitative assessment and intelligent management, improves the accuracy and foresight of assessments, reduces safety hazards, effectively improves the stability of project operation and maintenance efficiency, and provides efficient and reliable technical support for power engineering operation and maintenance. Attached Figure Description

[0015] Figure 1 This is a flowchart illustrating the steps of a preliminary assessment method for power transmission and transformation projects proposed in this invention. Figure 2 This is a block diagram of the evaluation system module for a pre-approval status evaluation method for power transmission and transformation projects proposed in this invention. Detailed Implementation

[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0017] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," and "counterclockwise," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0018] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of the stated features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified. Furthermore, the terms "installed," "connected," and "linked" should be interpreted broadly; for example, they may refer to a fixed connection, a detachable connection, or an integral connection; they may refer to a mechanical connection or an electrical connection; they may refer to a direct connection or an indirect connection through an intermediate medium; and they may refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0019] Example 1 Reference Figure 1 - Figure 2 A pre-approval status assessment method for power transmission and transformation projects is applied to the routine operation and maintenance assessment of 220kV power transmission and transformation projects in urban central areas. The assessment cycle is monthly, and the specific implementation steps are as follows: S1. Data Acquisition and Preprocessing: The entire lifecycle data of the project is collected through the data acquisition and preprocessing module, including: Construction parameters, installation accuracy, and final acceptance data for construction projects; Operational data including load factor, voltage and current, insulation performance, and temperature rise. Environmental data, including station temperature and humidity, pollution levels, and geological stability. Service life, wear rate, fault records, and maintenance history data for aging products.

[0020] The collected data were standardized in terms of units and normalized to the [0,1] interval using Min-Max. Three abnormal data points of over-temperature and over-pressure were removed using the threshold screening method. Two sets of missing time-series data were supplemented using linear interpolation; noise reduction was performed, and a standardized structured dataset was output.

[0021] S2. Construct a preliminary review status assessment index system: The indicator system is constructed by building a four-level primary dimension indicator system. The weights are calculated and fixed using the analytic hierarchy process: construction quality indicator 0.30, equipment operation indicator 0.35, environmental adaptability indicator 0.15, and aging loss indicator 0.20. Each dimension has a secondary sub-indicator. The total weight is 1, with no dynamic fluctuation, thus completing the construction of the indicator system.

[0022] S3. Evaluation of Model Construction and Training: Through the life cycle estimation module, based on the equipment aging mechanism, load characteristics and environmental impact, a machine learning life cycle estimation model is built using gradient boosting tree (GBDT). The model is trained by importing 7 years of historical full life cycle data of the project, fitting the mapping relationship between state changes, performance degradation and lifespan threshold, and training the aging rate coefficient in combination with the exponential decay model to complete the model solidification. This enables the estimation of short-term state fluctuations, medium-term performance degradation and long-term lifespan threshold.

[0023] S4. Quantitative assessment of preliminary review status: The status scoring assessment module inputs real-time standardized data into the solidified model and calculates the secondary indicator scores, dimension scores and overall pre-review scores one by one according to the weighted summation algorithm, with the results retained to two decimal places. The project received an overall score of 87.42, with 89.15 points for equipment operation, 91.20 points for construction quality, 85.33 points for environmental adaptability, and 82.69 points for aging and wear.

[0024] S5. Status Classification and Result Output: Based on the risk assessment and positioning module and the four-level threshold, the score of 87.42 points is considered to be at the qualified level. By comparing the scores of the secondary indicators one by one, the "loss rate" indicator under the aging loss dimension is found to be close to the warning threshold. The main transformer insulation component is identified as the risk point, and the risk type is identified as slight insulation aging.

[0025] S6. Output of Assessment Report and Control Plan: Closed-loop output is achieved through the intelligent optimization and control module: The fault analysis unit summarized risk data from the past 12 months and identified insulation loss as a high-frequency weak point. The self-learning unit stores the assessment data, scores, and risk information for this evaluation, and iterates the model parameters. The parameter optimization unit fine-tunes the weights of the aging loss dimension to improve the evaluation sensitivity of similar equipment. The final output is a standardized evaluation report, along with a qualified control plan that "shortens the inspection cycle and locally enhances insulation and heat dissipation".

[0026] Example 2 A pre-approval status assessment method for power transmission and transformation projects is applied to the trial operation assessment of newly built 110kV power transmission and transformation projects in mountainous areas. The assessment node is one month of trial operation. The specific implementation steps are as follows: S1. Data Acquisition and Preprocessing: The data acquisition and preprocessing module collects construction data, trial operation data, mountain environment data, and initial aging data. It unifies the dimensions and normalizes the data, removes one abnormal data point caused by monitoring interference, and uses linear interpolation to fill in two sets of missing pollution tolerance data. The output is a standardized dataset covering the construction and trial operation phases.

[0027] S2. Construct a preliminary review status assessment index system: The indicator system construction module uses the analytic hierarchy process to construct a four-dimensional fixed-weight indicator system, focusing on strengthening the rationality of the weights of environmental adaptability indicators and construction quality indicators. After consistency verification, all weights are solidified to meet the assessment needs of mountainous areas with high altitude, heavy pollution, and complex geology.

[0028] S3. Evaluation of Model Construction and Training: Based on the operating mechanism of equipment in mountainous areas, the characteristics of small load fluctuations and the influence of complex environments, the life cycle estimation module uses random forest to construct a life cycle estimation model. It is trained by combining historical data from three existing 110kV projects in the same area with the trial operation data of this project to achieve accurate prediction of short-term trial operation status, medium-term adaptability performance and long-term life trend.

[0029] S4. Quantitative assessment of preliminary review status: By inputting real-time trial data into the status scoring evaluation module, a weighted summation was performed to obtain an overall score of 92.68 points. All scores in each dimension were higher than 90 points. The calculation process was free of random bias, and the result was rounded to two decimal places.

[0030] S5. Status Classification and Result Output: The risk assessment and positioning module determined the level to be excellent. Each indicator was compared and found to be normal. There were no risk points or risky links. The quality of the project construction and the operating status of the equipment met the requirements for commissioning.

[0031] S6. Output of Assessment Report and Control Plan: Intelligent optimization and management module is used to optimize and manage power transmission and transformation projects in mountainous areas: The fault analysis unit confirmed that no risk records were found during the trial operation. The self-learning unit stores data on outstanding case studies from mountainous areas, solidifying environmental assessment standards for mountainous regions. The parameter optimization unit optimizes environmental adaptation index parameters to improve the accuracy of similar engineering models; Output excellent rating assessment reports and implement the "routine inspection and regular maintenance" plan.

[0032] Example 3 A pre-approval status assessment method for power transmission and transformation projects is applied to the emergency fault assessment of 35kV power transmission and transformation projects in old industrial areas. This method is used when a special assessment is initiated due to multiple insulation alarms in the equipment. The specific implementation steps are as follows: S1. Data Acquisition and Preprocessing: The data acquisition and preprocessing module comprehensively collects construction archives, abnormal operation data, industrial zone environmental data, and aging fault data from 15 years of operation. It unifies and normalizes the units, batch removes 11 abnormal data points of over-temperature, over-pressure, and flicker, and uses linear interpolation to fill in 6 sets of missing historical maintenance data. It also completes noise reduction and forms a standardized dataset containing fault characteristics.

[0033] S2. Construct a preliminary review status assessment index system: A four-dimensional indicator system is constructed through the indicator system construction module. The hierarchical analysis method is used to strengthen the weight allocation of the dimensions of equipment operation and aging loss. The judgment matrix calculation, eigenvector solution and consistency verification are completed, and the fixed weights of all indicators are solidified, with the total weight sum being 1.

[0034] S3. Evaluation of Model Construction and Training: Based on the accelerated aging mechanism of old equipment, the characteristics of sudden changes in industrial load, and the impact of harsh environments, a machine learning life cycle estimation model is built using the life cycle estimation module. The model is trained using 15 years of historical data from this project and data from similar old and faulty projects to accurately predict short-term failure risks, rapid performance degradation in the medium term, and long-term remaining lifespan thresholds.

[0035] S4. Quantitative assessment of preliminary review status: By inputting real-time abnormal data into the status scoring assessment module, the weighted summation of the overall score was 64.73 points, of which the equipment operation dimension scored 61.28 points and the aging and wear dimension scored 57.94 points. Both dimensions were seriously low, and the score was rounded to two decimal places.

[0036] S5. Status Classification and Result Output: The risk assessment and location module determined the level to be a fault. By comparing each secondary indicator, it was found that the insulation performance, loss rate, and fault frequency were seriously exceeding the standards. The main transformer and high-voltage switchgear were identified as the core risk equipment, and the risk types were identified as insulation aging failure and long-term overload.

[0037] S6. Output of Assessment Report and Control Plan: Through intelligent optimization and management module: The fault analysis unit traced the fault to the following causes: equipment exceeding its service life, long-term overload, and continuous insulation deterioration. The self-learning unit stores the entire fault process data, enhancing the learning of fault characteristics; The parameter optimization unit significantly increases the weight of aging losses and equipment operation, and optimizes the fault identification strategy; Output a fault level assessment report and implement a fault-level handling plan of "emergency shutdown, replacement of aging main equipment, and reconfiguration of industrial area load distribution".

[0038] Example 4 A pre-approval status assessment method for power transmission and transformation projects is applied to the annual long-term status assessment of 500kV power transmission and transformation projects in coastal high-salt-fog areas. The specific implementation steps are as follows: S1. Data Acquisition and Preprocessing: The data acquisition and preprocessing module collects comprehensive data on salt spray corrosion, operation, geology, and aging; it completes dimensional unification, anomaly removal, missing data completion, and Min-Max normalization to eliminate salt spray monitoring noise and output a standardized dataset.

[0039] S2. Construct a preliminary review status assessment index system: By constructing an indicator system module using the hierarchical analysis method, a four-dimensional system is built to improve the rationality of the weights of environmental adaptability indicators, solidify all weights, and adapt to assessment scenarios of high salt spray, high humidity, and strong corrosion in coastal areas.

[0040] S3. Evaluation of Model Construction and Training: Based on the salt spray-accelerated aging mechanism, high-load characteristics, and the impact of the coastal environment, a machine learning-based life cycle estimation model is constructed using the life cycle estimation module. The aging rate coefficient is trained to achieve accurate prediction of long-term lifespan decline.

[0041] S4. Quantitative assessment of preliminary review status: By inputting real-time annual data into the status scoring assessment module, the overall score was calculated using a weighted sum and was 76.35 points. The scores for environmental adaptability and aging loss dimensions were relatively low, and the results were rounded to two decimal places.

[0042] S5. Status Classification and Result Output: The risk assessment and positioning module determined the risk level to be a warning; the main risks were identified as equipment insulation aging and metal component damage caused by salt spray corrosion.

[0043] S6. Output of Assessment Report and Control Plan: Through intelligent optimization and management module: The fault analysis unit summarizes the salt spray corrosion patterns and weak points; The parameters of the coastal engineering model are iteratively learned by the self-learning unit. The parameter optimization unit optimizes the environmental adaptation index weights and control strategies. Output early warning level reports and formulate long-term operation and maintenance plans such as "strengthening salt spray protection, increasing monitoring frequency, and appropriately adjusting load".

[0044] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A method for assessing the pre-approval status of power transmission and transformation projects, characterized in that, Includes the following steps: S1. Data Acquisition and Preprocessing: Collect operational, construction, and environmental data throughout the entire lifecycle of the project, and then perform standardized cleaning, normalization, outlier removal, and missing value imputation to form a standardized dataset. S2. Construct a preliminary review status assessment index system: Build an index system covering construction, operation and maintenance and aging iteration, and use the analytic hierarchy process to determine the fixed weights of each index, with the total weights being 1; S3. Evaluation Model Construction and Training: Based on the equipment aging mechanism, load characteristics and environmental impact, a machine learning life cycle prediction model is built, which is trained with historical data to predict the state changes and lifespan decline trends. S4. Quantitative assessment of pre-review status: Substitute real-time data into the model and calculate the overall pre-review status score through a weighted summation algorithm. The result is retained to two decimal places. S5. Status Classification and Result Output: The status level is determined according to the preset four-level thresholds of excellent, qualified, warning and fault, and the index score is compared to locate potential risk points, equipment and links. S6. Assessment Report and Control Plan Output: Output a standardized assessment report containing data, scores, levels, and risk points, as well as operation and maintenance rectification, load control, and equipment maintenance support plans that match the risk levels.

2. The method for pre-approval status assessment of power transmission and transformation projects according to claim 1, characterized in that, The data preprocessing in S1 specifically includes: unifying the dimensional standards of all collected data, removing abnormal data that exceeds the normal operating range through threshold screening, supplementing missing data using linear interpolation, completing data noise reduction processing, and forming a standardized structured dataset. The dataset fully covers the entire lifecycle of power transmission and transformation projects, including planning, construction, trial operation, and routine operation and maintenance.

3. The method for pre-approval status assessment of power transmission and transformation projects according to claim 1, characterized in that, The evaluation index system in S2 is specifically constructed as follows: the index system is divided into four core dimensions: construction quality index, equipment operation index, environmental adaptability index and aging loss index. Each dimension has fixed secondary sub-indicators. The fixed weight coefficients of each secondary indicator and primary dimension are marked one by one through the analytic hierarchy process. The total weight coefficient is 1, and there is no dynamic fluctuation range.

4. The method for pre-approval status assessment of power transmission and transformation projects according to claim 1, characterized in that, The construction and operation of the life cycle estimation model in S3 specifically includes: building a machine learning estimation model based on the aging mechanism of power transmission and transformation equipment, load operation characteristics and environmental impact laws, completing the model solidification training with historical full life cycle data as training samples, and accurately predicting the changing trends of three core parameters: short-term operating status fluctuations, medium-term performance degradation and long-term lifespan threshold.

5. The method for pre-approval status assessment of power transmission and transformation projects according to claim 1, characterized in that, The status score calculation in S4 specifically includes: retrieving real-time standardized data, matching the weight coefficients of each indicator, calculating the dimension score through a weighted summation algorithm, and then combining the weights of each dimension to obtain the overall pre-approval status score of the project. The score result is retained to two decimal places, and the score calculation logic is fixed and has no random deviation.

6. The method for pre-approval status assessment of power transmission and transformation projects according to claim 1, characterized in that, The status level determination and risk positioning in S5 specifically includes: pre-setting four fixed scoring threshold ranges for excellent, qualified, warning and fault, and matching the corresponding status level according to the overall score; By comparing the scoring thresholds of each secondary indicator one by one, the equipment locations, operational processes, and risk types corresponding to the failure to meet the indicators are accurately identified, thus completing the precise risk positioning.

7. The method for pre-approval status assessment of power transmission and transformation projects according to claim 1, characterized in that, The specific output of the assessment report and control plan in S6 includes: the assessment report always includes data statistical results, indicator scoring details, status level and risk point information; The control plan matches fixed maintenance rectification, load regulation, and equipment maintenance measures to different risk levels to ensure the continuous and stable operation of power transmission and transformation projects.

8. A pre-approval status assessment system for power transmission and transformation projects, applied to the assessment method described in any one of claims 1-7, characterized in that, It includes a data acquisition and preprocessing module, an indicator system construction module, a life cycle estimation module, a status scoring and evaluation module, a risk assessment and positioning module, and an intelligent optimization and control module; The data acquisition and preprocessing module is used to collect various types of operational data throughout the entire life cycle of power transmission and transformation projects, and to complete standardized cleaning, normalization, outlier removal, and missing value completion. The indicator system construction module is used to build a multi-level pre-approval status evaluation indicator system and uses the analytic hierarchy process to solidify the weight parameters of each indicator.

9. The power transmission and transformation project pre-approval status assessment system according to claim 8, characterized in that, The life cycle estimation module is used to build an engineering life cycle estimation model based on machine learning algorithms, complete model training, and deduce the engineering operation status and lifespan decay trend. The status scoring and evaluation module is used to input real-time data into the model and use a weighted summation algorithm to calculate the overall score and dimension score of the project pre-approval status. The risk assessment and positioning module is used to determine the status level based on the scoring threshold and to locate risk points, equipment, and processes.

10. The power transmission and transformation project pre-approval status assessment system according to claim 8, characterized in that, The intelligent optimization and control module is used to output standardized evaluation reports and targeted control schemes, and to complete model iteration and parameter optimization. It includes a fault analysis unit, an autonomous learning unit, and a parameter optimization unit. The fault analysis unit is used to summarize risk data from previous assessments, statistically analyze the patterns of risk occurrence and the most frequent weak links, and complete the source analysis of the problem. The self-learning unit is used to store evaluation data and rectification results from previous evaluations, and to iteratively solidify accurate model inference parameters and scoring criteria. The parameter optimization unit is used to dynamically optimize indicator weights, model parameters, and control strategies based on historical assessments and rectification results, thereby improving the accuracy of assessment and control.

Images