Power grid engineering risk dynamic early warning method based on data model analysis
Through the dynamic early warning method of grid engineering risk based on data model analysis, risks in grid engineering construction projects are identified and classified, and risk quantitative indicator system and model are established, which accurately identify and dynamic early warning of risks in the entire process of grid engineering construction, and the risk avoidance ability and project safety are improved.
Patent Information
- Application Number
- CN202510188918.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-20
- Publication Date
- 2025-06-06
AI Technical Summary
The existing risk assessment methods for power grid engineering construction projects lack unified planning and information limitations, making it difficult to efficiently identify and solve risks, affecting the high-quality development of power grid engineering construction projects.
A dynamic early warning method for risk based on power grid engineering based on data model analysis is adopted, and a risk is identified and graded through subjective and objective analysis, data analysis, natural language processing and expert system methods is used to identify and classify risks, and a multi-type risk quantitative index system is established. Combined with multimodal data and knowledge fusion technology, a risk quantification method based on probability statistics, CVaR and decision tree models is established to conduct dynamic early warning of risk.
It has achieved accurate identification and dynamic early warning of risks throughout the construction of power grid engineering projects, improved risk avoidance capabilities, and ensured the safety of project investment and construction.
Smart Images
Figure CN120106570A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of power grid engineering construction risk assessment, and in particular to a power grid engineering risk dynamic early warning method based on data model analysis. Background Art
[0002] As a capital-intensive project, power grid construction projects face the characteristics of huge investment scale, wide geographical coverage, numerous management contents and long construction period. This requires that its execution and monitoring must be a sophisticated and systematic project. However, there is currently no unified standard and evaluation system for power grid project risk management. With the advancement of informatization, the accelerated construction of new power systems has made power grid project management more complex. The increasing proportion of new energy projects, the dual challenges of power supply safety and power quality, and the higher requirements of distributed energy for power grid coordination have added more uncertainties and diverse risk sources to the original project characteristics.
[0003] However, the existing risk assessment methods for power grid engineering construction projects lack unified planning and information limitations. In addition, since risk assessment belongs to the end of the entire power grid engineering construction project business chain, it requires close cooperation with multiple links such as infrastructure, equipment, and finance. This cross-domain cooperation model is difficult to efficiently identify and resolve risks due to problems such as inconsistent standards, information islands, and analysis limitations, thus affecting the high-quality development of power grid engineering construction projects. Summary of the invention
[0004] The purpose of the present invention is to provide a dynamic early warning method for power grid engineering risks based on data model analysis to solve the problems raised in the above background technology.
[0005] To achieve the above object, the present invention provides the following technical solution: a dynamic early warning method for power grid engineering risk based on data model analysis, comprising:
[0006] Through subjective and objective analysis methods, risks are identified and graded, the impact of internal and external factors on the entire process of power grid construction projects is determined, and typical treatment cases for dealing with such impacts are generated accordingly. Data analysis, natural language processing (NLP), and expert system methods are used to identify risks in the entire process of power grid construction projects, and the classification categories of risk projects that appear in the entire process of power grid construction projects are confirmed accordingly. The risk matrix analysis method is used to evaluate the possibility of occurrence of confirmed risk projects;
[0007] Based on the possibility of confirmed risk projects and typical treatment cases, risk information is extracted. Reliability and validity analysis and event tree analysis are used to establish a multi-type risk quantification indicator system. A method for data dimensionality reduction using feature extraction and feature selection is developed. Based on the established multi-type risk quantification indicator system, risk feature extraction methods are studied to extract various risk feature vector information at different stages of the entire process of power grid project construction.
[0008] Dynamic risk warning is carried out for the entire process of power grid project construction. By combining multimodal data and knowledge fusion technology, a risk quantification method based on probability statistics, CVaR and decision tree model is established to determine key variables and establish probability distribution, combined with the acquired risk feature vector information and risk dynamic warning information.
[0009] Optionally, the entire process of the power grid construction project includes investment decision-making, engineering design, procurement and construction, and operation and maintenance, so that the risks that may arise during the power grid construction project can be gradually analyzed according to the progress of the project, thereby ensuring that the identification and judgment of risk projects are more accurate, which helps to improve the risk avoidance capabilities of the entire process of the power grid construction project. The risk project classification includes three dimensions: data quality, business management, and external environment, which helps to clarify the dynamic risk warning boundaries.
[0010] Optionally, the probability level of occurrence of the risk project is set to five levels: will not occur, rarely occur, may occur, sometimes occur, and often occur, and the severity corresponding to the risk project is divided into four situations: weak, general, serious and very serious. At the same time, the risk level corresponding to the risk project is set to four levels: low risk, medium risk, high risk, and major risk. In this way, the risk projects that may occur in the entire process of the previously determined power grid construction project are divided into detailed levels based on the probability of occurrence of the risk project, the severity when it occurs, and the risk level generated after the occurrence, so that project staff can accurately understand and judge the risk possibilities in the process of the power grid construction project.
[0011] Optionally, the multi-type risk quantification indicator system includes market, financial, management and environmental construction dimensions, and the feature extraction method includes principal component analysis, linear discriminant analysis and feature compression clustering, and the feature selection method includes filtering, encapsulation and embedding, so as to ensure that the multi-type risk quantification indicator system has a high level of accuracy while ensuring operational efficiency, thereby facilitating staff to more accurately simulate and judge the risks that may be faced throughout the entire process of the power grid construction project.
[0012] Optionally, after determining the key variables and establishing the probability distribution, it is necessary to determine the warning thresholds of the structured and unstructured risk feature vectors in combination with historical data, and to correlate and merge the data information of the risk probability distribution, risk impact degree and risk warning threshold corresponding to the risk feature vectors, so as to digitize and quantify the risks that may arise in the entire process of power grid engineering project construction, so as to facilitate model building and calculation.
[0013] Optionally, the input of the risk dynamic early warning model includes quantitative data on project environment changes and market condition changes throughout the entire process of power grid engineering project construction, and further integrates project environment and market condition factors as variables into the risk dynamic early warning model to achieve adaptive adjustment of the risk characteristic vector early warning threshold.
[0014] Optionally, the use of hidden Markov model (HMM) and dynamic Bayesian network model also includes using historical data or simulation data to verify the accuracy and reliability of the model, and regularly updating model parameters and data during the operation of the model to continuously monitor changes in risks and adjust risk management strategies in a timely manner. By integrating HMM and DBN to establish a risk evolution path model, the dynamic changes in risks and the impact of external factors can be more effectively captured.
[0015] The present invention proposes a dynamic early warning device for power grid engineering risks based on data model analysis, comprising:
[0016] The assessment module is used to identify and grade risks through subjective and objective analysis methods, study and judge the impact of internal and external forms on the entire process of power grid construction projects, and generate typical treatment cases to deal with the impact, identify the risks in the entire process of power grid construction projects, and confirm the classification categories of risk projects that appear in the entire process of power grid construction projects, and evaluate the possibility of occurrence of confirmed risk projects;
[0017] The extraction module is used to extract risk information based on the confirmed risk items’ probability of occurrence and typical treatment cases. It uses reliability and validity analysis and event tree analysis to establish a multi-type risk quantification indicator system. Based on the established multi-type risk quantification indicator system, it extracts various risk feature vector information at different stages in the entire process of power grid project construction.
[0018] The early warning module is used to provide dynamic risk warning for the entire process of power grid project construction. It combines multimodal data and knowledge fusion technology to establish a risk quantification method based on probability statistics, CVaR and decision tree model, determine key variables and establish probability distribution, and combine the acquired risk feature vector information and risk dynamic warning information.
[0019] The present invention provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method described above is implemented.
[0020] The present invention also proposes a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and when the computer instructions are executed on a computer device, the computer device executes the method.
[0021] Compared with the prior art, the present invention provides a dynamic early warning method for power grid engineering risks based on data model analysis, which has the following beneficial effects:
[0022] 1. This method of dynamic early warning of power grid project risks based on data model analysis adopts probability statistics, CVaR and decision tree model methods to quantify risks. Combined with changes in project environment and market conditions, it proposes a dynamic early warning technology for investment execution risks throughout the entire process based on time series analysis, multi-factor analysis and machine learning, to achieve dynamic tracking of risks and adaptive adjustment of early warning thresholds. It also simulates the dynamic relationship between risk feature vectors and the impact of external factors on feature vectors based on hidden Markov models or dynamic Bayesian networks, and models the risk evolution path. Based on the modeling, we can intuitively understand the various risks and corresponding treatment methods in the construction process of power grid projects from the data level, effectively avoid risks, and ensure the safety of project investment and construction.
[0023] 2. This dynamic early warning method for power grid project risks based on data model analysis starts from the perspective of the entire process of project investment execution, and uses the model to analyze the impact of new power system construction and internal and external situations of the dual carbon goals on the entire process of power grid project investment execution. It proposes a power grid project investment execution risk identification method based on data analysis, natural language processing, and expert system, and forms a risk classification for the entire process of power grid project investment execution covering data quality, business management, and external environmental factors. It also constructs an investment execution risk grading method based on risk matrix analysis to evaluate the possibility and severity of various risks and thus achieve grading.
[0024] 3. The dynamic early warning method for power grid engineering risks based on data model analysis can help project staff to accurately understand and judge the risk possibilities in the power grid construction project by carefully classifying the possibility of risk projects that may occur during the power grid construction project, the severity of the corresponding events after occurrence, and the corresponding risk levels. BRIEF DESCRIPTION OF THE DRAWINGS
[0025] Figure 1 A schematic diagram of the risk identification and grading process of the present invention;
[0026] Figure 2 This is a schematic diagram of the risk information extraction process of the present invention;
[0027] Figure 3 It is a schematic diagram of the risk dynamic early warning process of the present invention. DETAILED DESCRIPTION
[0028] like Figure 1-Figure 3 As shown, the present invention provides a technical solution: a dynamic early warning method for power grid engineering risks based on data model analysis, comprising:
[0029] Through subjective and objective analysis methods, risks are identified and graded, the impact of internal and external factors on the entire process of power grid construction projects is determined, and typical treatment cases for dealing with such impacts are generated accordingly. Data analysis, natural language processing (NLP), and expert system methods are used to identify risks in the entire process of power grid construction projects, and the classification categories of risk projects that appear in the entire process of power grid construction projects are confirmed accordingly. The risk matrix analysis method is used to evaluate the possibility of occurrence of confirmed risk projects;
[0030] Based on the possibility of confirmed risk projects and typical treatment cases, risk information is extracted. Reliability and validity analysis and event tree analysis are used to establish a multi-type risk quantification indicator system. A method for data dimensionality reduction using feature extraction and feature selection is developed. Based on the established multi-type risk quantification indicator system, risk feature extraction methods are studied to extract various risk feature vector information at different stages of the entire process of power grid project construction.
[0031] Dynamic risk early warning is carried out for the entire process of power grid engineering project construction. Combining multimodal data and knowledge fusion technology, a risk quantification method based on probability statistics, CVaR and decision tree model is established, key variables are determined and probability distribution is established. Combined with the acquired risk feature vector information, a dynamic risk early warning model for the entire process of power grid engineering project construction is established through time series analysis, multi-factor analysis and machine learning methods. Based on the hidden Markov model (HMM) and dynamic Bayesian network model, the dynamic relationship between risk feature vectors and the influence of external factors on feature vectors are simulated, and a risk evolution path model is established.
[0032] In one embodiment of the present invention, the subjective and objective analysis method includes consulting literature, consulting experts, analyzing historical cases, and the internal and external forms that affect the entire process of the power grid construction project include new power system construction, digital intelligent technology, dual carbon goals, and changes in electricity demand, so that the impact of different internal and external changes that may be encountered during the entire process of the power grid project construction on the power grid construction project can be analyzed. At the same time, generating typical processing cases can improve the results of the research and judgment and propose more adaptable solutions, thereby avoiding risks and improving the investment security of power grid projects;
[0033] At the same time, the entire process of power grid construction projects includes four stages: investment decision-making, engineering design, procurement and construction, and operation and maintenance. Data analysis, natural language processing (NLP), and expert system methods are used to generate corresponding risk project classification categories according to different stages of power grid construction projects. In this way, the risks that may arise during the power grid construction project can be gradually analyzed according to the progress of the project, thereby ensuring that the identification and judgment of risk projects are more accurate, which helps to improve the risk avoidance ability of the entire process of power grid construction projects. Risk project classification includes three dimensions: data quality, business management, and external environment, which helps to clarify the dynamic risk warning boundaries.
[0034] Furthermore, the probability levels of risk projects are set to five levels: no occurrence, rare occurrence, possible occurrence, occasional occurrence, and frequent occurrence, and the severity of risk projects is divided into four situations: weak, general, serious, and very serious. At the same time, the risk levels corresponding to risk projects are set to four levels: low risk, medium risk, high risk, and major risk. This allows for a detailed classification of risk projects that may occur throughout the entire process of a previously determined power grid construction project based on the probability of occurrence of risk projects, the severity of occurrence, and the risk level generated after occurrence, so that project staff can accurately recognize and judge the risk possibilities during the power grid construction project.
[0035] In addition, the multi-type risk quantification indicator system includes market, financial, management and environmental construction dimensions. At the same time, the feature extraction methods include principal component analysis, linear discriminant analysis and feature compression clustering. The feature selection methods include filtering, encapsulation and embedding, so as to ensure that the multi-type risk quantification indicator system can maintain a high level of accuracy while ensuring operation efficiency, so as to facilitate the staff to simulate and judge the risks that may be faced in the whole process of power grid construction projects more accurately. Specifically, the risk feature extraction methods include feature extraction first and then feature selection, feature selection first and then feature extraction, independent and iterative. Feature extraction first and then feature selection can first reduce the dimension of data and reduce the computational complexity, and then perform refined feature selection. Feature selection first and then feature extraction can first ensure that the selected features are highly correlated with risks, and then perform feature extraction to improve the accuracy and effectiveness of extraction. The independent method is highly flexible and can select appropriate feature extraction and feature selection methods according to specific needs and data characteristics. Iterative method can gradually approach the optimal feature set, improve the performance and stability of the model, and judge different data in different ways, so as to ensure the efficiency of data extraction under the premise of ensuring the accuracy of risk feature extraction, so as to improve the efficiency of extracting risk feature vector information for different types.
[0036] In an embodiment of the present invention, after determining the key variables and establishing the probability distribution, it is necessary to determine the warning thresholds of the structured and unstructured risk feature vectors in combination with historical data, and to merge the data information of the risk probability distribution, risk impact degree and risk warning threshold corresponding to the risk feature vector in a correlated manner, so as to digitize and quantify the risks that may arise in the entire process of power grid engineering project construction, so as to facilitate model building and calculation. At the same time, the input of the risk dynamic warning model includes quantitative data on the changes in the project environment and market conditions throughout the construction process of the power grid engineering project, and further integrates the project environment and market conditions factors as variables into the risk dynamic warning model to achieve adaptive adjustment of the risk feature vector warning threshold.
[0037] In the present invention, the use of hidden Markov model (HMM) and dynamic Bayesian network model also includes using historical data or simulation data to verify the accuracy and reliability of the model, and regularly updating model parameters and data during the operation of the model to continuously monitor the changes in risks and adjust the risk management strategy in time. By integrating HMM and DBN to establish a risk evolution path model, the dynamic changes in risks and the influence of external factors can be more effectively captured.
[0038] It is worth noting that the present invention also includes a dynamic early warning calculation device, which is provided with a storage device and a computing simulation device. The storage device stores the above-mentioned dynamic early warning simulation calculation method, and the dynamic early warning simulation calculation method is executed by the computing simulation device, thereby simulating and calculating the risk information of the power grid project, and then realizing prediction, so as to avoid risks and ensure the safety of power grid investment.
[0039] The above generally describes the present invention in detail, but it is obvious to a person skilled in the art that some modifications or improvements can be made to the present invention. Therefore, modifications or improvements that do not depart from the spirit of the present invention are within the scope of protection of the present invention.
[0040] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may 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) containing computer-usable program codes. The scheme in the embodiments of the present invention may be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript.
[0041] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0042] Computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, the instruction device being implemented in the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0043] Computer program instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide the instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0044] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.
[0045] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.
Claims
1. A dynamic early warning method for power grid engineering risks based on data model analysis, characterized by: include: Identify and grade risks through subjective and objective analysis methods, study and judge the impact of internal and external factors on the entire process of power grid construction projects, and generate typical treatment cases to deal with the impact, identify the risks in the entire process of power grid construction projects, and confirm the classification categories of risk projects that appear in the entire process of power grid construction projects, and evaluate the possibility of occurrence of confirmed risk projects; Based on the possibility of occurrence of confirmed risk projects and typical treatment cases, risk information is extracted. Reliability and validity analysis and event tree analysis are used to establish a multi-type risk quantification indicator system. Based on the established multi-type risk quantification indicator system, various risk feature vector information at different stages in the entire process of power grid project construction is extracted; Dynamic risk warning is carried out for the entire process of power grid project construction. By combining multimodal data and knowledge fusion technology, a risk quantification method based on probability statistics, CVaR and decision tree model is established to determine key variables and establish probability distribution, combined with the acquired risk feature vector information and risk dynamic warning information.
2. The method for dynamic early warning of power grid engineering risk based on data model analysis according to claim 1 is characterized by: The entire process of the power grid construction project includes investment decision-making, engineering design, procurement and construction, and operation and maintenance. The risk project classification includes data quality, business management, and external environment.
3. The method for dynamic early warning of power grid engineering risk based on data model analysis according to claim 2 is characterized by: The probability levels of occurrence of the risk items are set to five levels: no occurrence, rare occurrence, possible occurrence, occasional occurrence, and frequent occurrence. The severity corresponding to the risk items is divided into four situations: weak, general, serious, and very serious. At the same time, the risk levels corresponding to the risk items are set to low risk, medium risk, high risk, and major risk levels.
4. The method for dynamic early warning of power grid engineering risk based on data model analysis according to claim 3 is characterized by: The multi-type risk quantification indicator system includes market, financial, management and environmental construction dimensions. The feature extraction method includes principal component analysis, linear discriminant analysis and feature compression clustering. The feature selection method includes filtering, encapsulation and embedding.
5. The method for dynamic early warning of power grid engineering risk based on data model analysis according to claim 4 is characterized by: After determining the key variables and establishing the probability distribution, it is necessary to determine the warning thresholds of the structured and unstructured risk feature vectors in combination with historical data, and to associate and merge the data information of the risk probability distribution, risk impact degree and risk warning threshold corresponding to the risk feature vectors.
6. A method for dynamic early warning of power grid engineering risk based on data model analysis according to claim 5, characterized in that: The input of the risk dynamic early warning model includes quantitative data of project environment changes and market condition changes during the entire process of power grid project construction.
7. A method for dynamic early warning of power grid engineering risk based on data model analysis according to claim 6, characterized in that: The use of hidden Markov models (HMM) and dynamic Bayesian network models also includes using historical data or simulation data to verify the accuracy and reliability of the models, and regularly updating model parameters and data during the model operation process.
8. A power grid engineering risk dynamic early warning device based on data model analysis, characterized in that: include: The assessment module is used to identify and grade risks through subjective and objective analysis methods, study and judge the impact of internal and external forms on the entire process of power grid construction projects, and generate typical treatment cases to deal with the impact, identify the risks in the entire process of power grid construction projects, and confirm the classification categories of risk projects that appear in the entire process of power grid construction projects, and evaluate the possibility of occurrence of confirmed risk projects; The extraction module is used to extract risk information based on the confirmed risk items’ probability of occurrence and typical treatment cases. It uses reliability and validity analysis and event tree analysis to establish a multi-type risk quantification indicator system. Based on the established multi-type risk quantification indicator system, it extracts various risk feature vector information at different stages in the entire process of power grid project construction. The early warning module is used to provide dynamic risk warning for the entire process of power grid project construction. It combines multimodal data and knowledge fusion technology to establish a risk quantification method based on probability statistics, CVaR and decision tree model, determine key variables and establish probability distribution, and combine the acquired risk feature vector information and risk dynamic warning information.
9. A computer device, characterized in that: The computer device comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method according to any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, which, when executed on a computer device, cause the computer device to perform the method according to any one of claims 1 to 7.