Extra-high voltage converter station dynamic risk prediction method, management and control method, system, equipment and medium

Abstract

The invention discloses a prediction method, a management and control method, a system, equipment and a medium for dynamic risks of an extra-high voltage converter station, and the prediction method comprises the steps: carrying out the risk association analysis of risk association points, obtaining a risk association network, and determining a risk prevention and control strategy; a multi-dimensional risk calibration framework is constructed based on space coordinates and three-dimensional modeling, after static calibration and dynamic calibration are completed, a risk prevention and control strategy is introduced for static and dynamic risk integration, and a risk calibration system is obtained; constructing a dynamic risk identification mechanism based on biological multi-modal identification and behavior trend early warning; and introducing a dynamic risk identification mechanism into the risk calibration system to carry out risk prediction. Based on space coordinates of the extra-high voltage converter station, after static calibration and dynamic calibration are completed, a risk prevention and control strategy is introduced for static and dynamic risk integration, and a risk calibration system is obtained; and then a dynamic risk identification mechanism is introduced to carry out risk prediction, so that accurate identification and grade evaluation of risk points are realized, and the risk predictability is enhanced.

Description

Technical Field

[0001] The present invention relates to the field of electrical detection technology, and in particular to a prediction method, a control method, a system, a device and a medium for dynamic risk of an ultra-high voltage converter station. Background Art

[0002] With the rapid development of DC transmission technology, DC transmission systems have become the main cross-regional and cross-provincial energy transmission channels, and the safety of DC transmission systems has become an important part of the safety of large power grids. In the on-site operation of UHV converter stations, unsafe behaviors of people, unsafe conditions of objects and unsafe factors of the environment objectively exist. Compared with substations, on-site operations of UHV converter stations also present the characteristics of more centralized maintenance, more outsourced operations, more special equipment, and more cross-operations. Especially during centralized maintenance, each operation surface is widely exposed to risks such as proximity to electricity, falling from heights, cross-operation, and mechanical injuries. Once out of control, it may lead to personal and equipment incidents (accidents), which may directly threaten the safety of large power grids in severe cases. Therefore, it is urgent to improve the level of perception, identification, and early warning in on-site operations through technical means, and enhance the ability of safety management and control at the operation site.

[0003] The existing risk identification and calibration of UHV converter stations have the following problems:

[0004] 1. Limitations of static analysis: Although the construction of a static risk database can provide information on known risks, it lacks the ability to update and adjust in real time, and cannot promptly reflect changes in risks due to changes in the environment, personnel behavior, and equipment status.

[0005] 2. Single dimension of risk calibration: Traditional risk calibration methods are limited to a plane or a specific perspective, ignoring the multidimensional characteristics of risk in space and time, resulting in incomplete risk identification and inability to accurately assess the impact of compound risks.

[0006] 3. Lack of intelligent and personalized response strategies: Existing risk identification technologies rely on rules and threshold settings, lack in-depth analysis of individual differences and behavioral trends, and are difficult to provide personalized early warning and intervention measures, especially in terms of personnel behavior identification and trend prediction. Summary of the invention

[0007] Purpose of the invention: The present invention aims to provide a method for predicting the dynamic risks of a multi-dimensional ultra-high voltage converter station based on spatial coordinates; the second purpose of the present invention is to provide a method for controlling the dynamic risks of an ultra-high voltage converter station; the third purpose of the present invention is to provide a prediction system, control system, equipment and medium for the dynamic risks of an ultra-high voltage converter station.

[0008] Technical solution: The method for predicting the dynamic risk of a UHV converter station according to the present invention comprises the following steps:

[0009] Conduct risk correlation analysis on risk correlation points to obtain a risk correlation network, and determine risk prevention and control strategies based on the risk correlation network;

[0010] Based on spatial coordinates and three-dimensional modeling, a multi-dimensional risk calibration framework is constructed. After static and dynamic calibration of the multi-dimensional risk calibration framework, risk prevention and control strategies are introduced to integrate static and dynamic risks to obtain a risk calibration system.

[0011] Build a dynamic risk identification mechanism based on biological multimodal recognition and behavioral trend warning;

[0012] Introduce a dynamic risk identification mechanism into the risk calibration system to conduct risk prediction.

[0013] Furthermore, risk association analysis is performed on risk association points to obtain a risk association network, as follows:

[0014] Identify risk points based on operational scenarios to classify and characterize risks;

[0015] Extract risk features based on risk feature description and risk level assessment to determine risk association points;

[0016] The risk association network is obtained by performing association analysis on the time series, spatial location, operation process and behavior pattern of risk association points.

[0017] Further, static and dynamic risk integration is as follows:

[0018] Calculate the adaptive risk calibration value R(x) at the spatial position x:

[0019]

[0020]

[0021] Among them, ω i represents the weight of the ith risk source, indicating the contribution of this risk source to the total risk; G(x,c i ,σ i ,S i ) is a Gaussian function, which represents the contribution of the i-th risk source at position x; c i represents the central position of the i-th risk source; σ i represents the impact radius of the ith risk source; S i represents the covariance matrix of the impact range of the i-th risk source; T represents the transpose of the matrix.

[0022] Furthermore, a dynamic risk identification mechanism is constructed based on biological multimodal recognition and behavioral trend warning, as follows:

[0023] Based on biological multimodal recognition, the biological multimodal risk fusion feature f at time t is obtained fusion (t):

[0024]

[0025] Where k represents the number of biological multimodal signals, ω z represents the weight of the zth signal for risk identification, f z (t) represents the feature vector of the kth biological multimodal signal at time t.

[0026] The biological multimodal risk fusion feature at each moment during the period from time t-n+1 to t is f fusion (t-n+1),...,f fusion (t), the behavior trend vector v(t) is

[0027]

[0028] The prediction system for dynamic risk of UHV converter station of the present invention comprises:

[0029] The strategy determination module is used to perform risk association analysis on risk association points, obtain a risk association network, and determine the risk prevention and control strategy based on the risk association network;

[0030] The risk calibration system construction module is used to build a multi-dimensional risk calibration framework based on spatial coordinates and three-dimensional modeling. After completing static calibration and dynamic calibration, the risk prevention and control strategy is introduced to integrate static and dynamic risks to obtain a risk calibration system; then the dynamic risk identification mechanism is introduced to perform risk prediction;

[0031] A dynamic risk identification mechanism building module is used to build a dynamic risk identification mechanism based on biological multimodal recognition and behavioral trend warning.

[0032] Furthermore, the strategy determination module determines the risk prevention and control strategy as follows:

[0033] Identify risk points based on the operation scenario, classify risks and describe risk characteristics;

[0034] Extract risk features based on risk feature description and risk level assessment to determine risk association points;

[0035] Conduct correlation analysis on risk-related points in terms of time series, spatial location, operation process and behavior pattern;

[0036] Obtain the risk association network and build a risk prevention and control strategy.

[0037] Furthermore, the risk calibration system construction module, static and dynamic risk integration is as follows:

[0038] Calculate the adaptive risk calibration value R(x) at the spatial position x:

[0039]

[0040]

[0041] Among them, ω i represents the weight of the ith risk source, indicating the contribution of this risk source to the total risk; G(x,c i ,σ i ,S i ) is a Gaussian function, which represents the contribution of the i-th risk source at position x; c i represents the central position of the i-th risk source; σ i represents the impact radius of the ith risk source; S i represents the covariance matrix of the impact range of the i-th risk source; T represents the transpose of the matrix.

[0042] Furthermore, the dynamic risk identification mechanism construction module constructs a dynamic risk identification mechanism based on biological multimodal recognition and behavioral trend warning, as follows:

[0043] Based on biological multimodal recognition, the biological multimodal risk fusion feature f at time t is obtained fusion (t):

[0044]

[0045] Where k represents the number of biological multimodal signals, ω z represents the weight of the zth signal for risk identification, f z (t) represents the feature vector of the kth biological multimodal signal at time t.

[0046] During the period from time t-n+1 to t, the fusion feature is f fusion (t-n+1),...,f fusion (t), the behavior trend vector v(t) is

[0047]

[0048] The method for controlling dynamic risks of a UHV converter station according to the present invention comprises the following steps:

[0049] Collect and integrate information, transmit and share information, and update information feedback through the information base;

[0050] According to the risk prediction results obtained by the above-mentioned UHV converter station dynamic risk prediction system, the operation process risk control and overall risk control are carried out; among which, the operation process risk control is the cross-control of personnel, machinery, and before and during operation, and the overall risk control includes operation control, real-time location control and control intervention measures;

[0051] The dynamic risk prediction system of UHV converter stations is optimized through comprehensive evaluation results.

[0052] The UHV converter station dynamic risk management and control system of the present invention comprises:

[0053] Information base module, used for information collection and integration, information transmission and sharing, and information feedback and update;

[0054] The risk control module is used to perform operation process risk control and overall risk control according to the risk prediction results obtained by the above-mentioned UHV converter station dynamic risk prediction system; among which, the operation process risk control is the cross-control of personnel, machinery, and before and during operation, and the overall risk control includes operation control, real-time location control and control intervention measures;

[0055] The evaluation module is used to optimize the dynamic risk prediction system of UHV converter stations through comprehensive evaluation results.

[0056] The computer device of the present invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor, and the steps of the above method are implemented when the processor executes the computer program.

[0057] The computer-readable storage medium of the present invention stores a computer program thereon, and the computer program implements the steps of the above method when executed by a processor.

[0058] Beneficial effects: Compared with the prior art, the present invention has the following significant advantages: 1. Based on the spatial coordinates of the UHV converter station, after completing static calibration and dynamic calibration, the present invention introduces a risk prevention and control strategy to integrate static and dynamic risks to obtain a risk calibration system; then introduces a dynamic risk identification mechanism to predict risks, thereby achieving accurate identification and grading of risk points and enhancing risk predictability; 2. The present invention combines the dynamic risk identification mechanism with information management and control throughout the life cycle of the operation to ensure the real-time and comprehensiveness of risk monitoring, improve operational safety, optimize resource allocation, promote scientific decision support, and achieve multiple goals of reducing safety accidents and improving work efficiency and stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 A schematic diagram of a process for determining a risk association network according to the present invention;

[0060] Figure 2A schematic diagram of the process of constructing a risk calibration system for the present invention;

[0061] Figure 3 It is a structural schematic diagram of the dynamic risk management and control system of the ultra-high voltage converter station of the present invention. DETAILED DESCRIPTION

[0062] The present invention will be further described below in conjunction with the accompanying drawings.

[0063] The method for predicting the dynamic risk of a UHV converter station according to the present invention comprises the following steps:

[0064] (1) Conduct risk correlation analysis on risk correlation points to obtain a risk correlation network, and determine risk prevention and control strategies based on the risk correlation network.

[0065] Conduct scenario-based analysis on the operation, maintenance and inspection of UHV converter stations, identify risk points based on the operating environment, personnel behavior and operating procedures, and conduct risk classification and risk characteristic description.

[0066] The risk level is assessed based on the likelihood of risk occurrence, severity of risk consequences and comprehensive expert evaluation.

[0067] Risk features are extracted based on risk characteristic description and risk level assessment to build a risk feature library. This risk feature library is a highly integrated risk hazard feature library with capability opening standards, which can be dynamically updated to provide data support for the formulation of subsequent risk prevention and control strategies.

[0068] Determine risk association points from the extracted risk features, analyze the coupling degree between risk points based on time series association, spatial location association, operation process association, behavior pattern association, etc., combine the risk features to be associated with the risks, determine the risk association network, and build a risk prevention and control strategy.

[0069] (2) A multidimensional risk calibration framework is constructed based on spatial coordinates and three-dimensional modeling. After static and dynamic calibration of the multidimensional risk calibration framework, risk prevention and control strategies are introduced to integrate static and dynamic risks to obtain a risk calibration system.

[0070] Based on the basic static data such as the physical structure layout of the UHV converter station, the technical parameters of the equipment, and the operation flow chart, the static risk calibration is carried out. Relying on real-time monitoring technology, the risk value of specific risk points is dynamically calibrated based on the specific attributes of the risk source, and a three-dimensional, multi-level risk calibration system is constructed, realizing the multi-level risk hazard calibration covering physical, plane, and space.

[0071] In the process of risk value calibration, by directly associating the Gaussian function with the specific attributes of the risk source, a more intuitive and application-oriented adaptive risk calibration value calculation model is created, so that the parameters of each risk source can be determined based on historical data, expert knowledge or field surveys, thereby achieving the purpose of dynamic adjustment of the model.

[0072] The details of static and dynamic risk integration are as follows:

[0073] Calculate the adaptive risk calibration value R(x) at the spatial position x:

[0074]

[0075]

[0076] Among them, ω i represents the weight of the ith risk source, indicating the contribution of this risk source to the total risk; G(x,c i ,σ i ,S i ) is a Gaussian function, which represents the contribution of the i-th risk source at position x; c i represents the central position of the i-th risk source; σ i represents the impact radius of the ith risk source; S i represents the covariance matrix of the impact range of the i-th risk source; T represents the transpose of the matrix.

[0077] (3) Construct a dynamic risk identification mechanism based on biological multimodal recognition and behavioral trend warning.

[0078] Based on biological multimodal recognition, the biological multimodal risk fusion feature f at time t is obtained fusion (t):

[0079]

[0080] Where k represents the number of biological multimodal signals, ω z represents the weight of the zth signal for risk identification, f z (t) represents the feature vector of the kth biological multimodal signal at time t.

[0081] The biological multimodal risk fusion feature at each moment during the period from time t-n+1 to t is f fusion (t-n+1),...,f fusion (t), the behavior trend vector v(t) is

[0082]

[0083] In order to evaluate the impact of fusion features and behavioral trends on risk, a scoring model is constructed, which is based on a machine learning classifier or regression model. The risk score output by the model is

[0084] γ(t)=M(f fusion (t),v(t))

[0085] Here, M is the pre-trained scoring model.

[0086] (4) Introduce a dynamic risk identification mechanism into the risk calibration system to conduct risk prediction.

[0087] The prediction system for dynamic risk of UHV converter station of the present invention comprises:

[0088] The strategy determination module is used to perform risk association analysis on risk association points, obtain a risk association network, and determine the risk prevention and control strategy based on the risk association network;

[0089] The risk calibration system construction module is used to build a multi-dimensional risk calibration framework based on spatial coordinates and three-dimensional modeling. After completing static calibration and dynamic calibration, the risk prevention and control strategy is introduced to integrate static and dynamic risks to obtain a risk calibration system; then the dynamic risk identification mechanism is introduced to perform risk prediction;

[0090] A dynamic risk identification mechanism building module is used to build a dynamic risk identification mechanism based on biological multimodal recognition and behavioral trend warning.

[0091] Furthermore, the strategy determination module determines the risk prevention and control strategy as follows:

[0092] Identify risk points based on the operation scenario, classify risks and describe risk characteristics;

[0093] Extract risk features based on risk feature description and risk level assessment to determine risk association points;

[0094] Conduct correlation analysis on risk-related points in terms of time series, spatial location, operation process and behavior pattern;

[0095] Obtain the risk association network and build a risk prevention and control strategy.

[0096] Furthermore, the risk calibration system construction module, static and dynamic risk integration is as follows:

[0097] Calculate the adaptive risk calibration value R(x) at the spatial position x:

[0098]

[0099]

[0100] Among them, ωi represents the weight of the ith risk source, indicating the contribution of this risk source to the total risk; G(x,c i ,σ i ,S i ) is a Gaussian function, which represents the contribution of the i-th risk source at position x; c i represents the central position of the i-th risk source; σ i represents the impact radius of the ith risk source; S i represents the covariance matrix of the impact range of the i-th risk source; T represents the transpose of the matrix.

[0101] Furthermore, the dynamic risk identification mechanism construction module constructs a dynamic risk identification mechanism based on biological multimodal recognition and behavioral trend warning, as follows:

[0102] Based on biological multimodal recognition, the biological multimodal risk fusion feature f at time t is obtained fusion (t):

[0103]

[0104] Where k represents the number of biological multimodal signals, ω z represents the weight of the zth signal for risk identification, f z (t) represents the feature vector of the kth biological multimodal signal at time t.

[0105] During the period from time t-n+1 to t, the fusion feature is f fusion (t-n+1),...,f fusion (t), the behavior trend vector v(t) is

[0106]

[0107] The method for controlling dynamic risks of a UHV converter station according to the present invention comprises the following steps:

[0108] Collect and integrate information, transmit and share information, and update information feedback through the information base;

[0109] According to the risk prediction results obtained by the above-mentioned UHV converter station dynamic risk prediction system, the operation process risk control and overall risk control are carried out; among which, the operation process risk control is the cross-control of personnel, machinery, and before and during operation, and the overall risk control includes operation control, real-time location control and control intervention measures;

[0110] The dynamic risk prediction system of UHV converter stations is optimized through comprehensive evaluation results.

[0111] The UHV converter station dynamic risk management and control system of the present invention comprises:

[0112] Information base module, used for information collection and integration, information transmission and sharing, and information feedback and update;

[0113] The risk control module is used to perform operation process risk control and overall risk control according to the risk prediction results obtained by the above-mentioned UHV converter station dynamic risk prediction system; among which, the operation process risk control is the cross-control of personnel, machinery, and before and during operation, and the overall risk control includes operation control, real-time location control and control intervention measures;

[0114] The evaluation module is used to optimize the dynamic risk prediction system of UHV converter stations through comprehensive evaluation results.

[0115] The computer device of the present invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor, and the steps of the above method are implemented when the processor executes the computer program.

[0116] The computer-readable storage medium of the present invention stores a computer program thereon, and the computer program implements the steps of the above method when executed by a processor.

[0117] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code. The scheme in the embodiments of the present application can be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0118] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes 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 generate 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.

[0119] These 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, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0120] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing 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.

Claims

1. A method for predicting dynamic risk of a UHV converter station, characterized in that: The following steps are involved: Conduct risk correlation analysis on risk correlation points to obtain a risk correlation network, and determine risk prevention and control strategies based on the risk correlation network; Based on spatial coordinates and three-dimensional modeling, a multi-dimensional risk calibration framework is constructed. After static and dynamic calibration of the multi-dimensional risk calibration framework, risk prevention and control strategies are introduced to integrate static and dynamic risks to obtain a risk calibration system. Build a dynamic risk identification mechanism based on biological multimodal recognition and behavioral trend warning; Introduce a dynamic risk identification mechanism into the risk calibration system to conduct risk prediction.

2. The method for predicting dynamic risk of a UHV converter station according to claim 1, characterized in that: Perform risk association analysis on risk association points to obtain a risk association network, as follows: Identify risk points based on operational scenarios to classify and characterize risks; Extract risk features based on risk feature description and risk level assessment to determine risk association points; The risk association network is obtained by performing association analysis on the time series, spatial location, operation process and behavior pattern of risk association points.

3. The method for predicting dynamic risk of a UHV converter station according to claim 1, characterized in that: Static and dynamic risk integration, as follows: Calculate the adaptive risk calibration value R(x) at the spatial position x: Among them, ω i represents the weight of the ith risk source, indicating the contribution of this risk source to the total risk; G(x,c i ,σ i ,S i ) is a Gaussian function, which represents the contribution of the i-th risk source at position x; c i represents the central position of the i-th risk source; σ i represents the impact radius of the ith risk source; S i represents the covariance matrix of the impact range of the i-th risk source; T represents the transpose of the matrix.

4. The method for predicting dynamic risk of a UHV converter station according to claim 3 is characterized in that: A dynamic risk identification mechanism is constructed based on biological multimodal recognition and behavioral trend warning, as follows: Based on biological multimodal recognition, the biological multimodal risk fusion feature f at time t is obtained fusion (t): Where k represents the number of biological multimodal signals, ω z represents the weight of the zth signal for risk identification, f z (t) represents the feature vector of the kth biological multimodal signal at time t; The biological multimodal risk fusion feature at each moment during the period from time t-n+1 to t is f fusion (t-n+1),...,f fusion (t), the behavior trend vector v(t) is 5. A prediction system for dynamic risks of ultra-high voltage converter stations, characterized in that: include The strategy determination module is used to perform risk association analysis on risk association points, obtain a risk association network, and determine the risk prevention and control strategy based on the risk association network; The risk calibration system construction module is used to build a multi-dimensional risk calibration framework based on spatial coordinates and three-dimensional modeling. After completing static calibration and dynamic calibration, the risk prevention and control strategy is introduced to integrate static and dynamic risks to obtain a risk calibration system. Then introduce dynamic risk identification mechanism to conduct risk prediction; A dynamic risk identification mechanism building module is used to build a dynamic risk identification mechanism based on biological multimodal recognition and behavioral trend warning.

6. The prediction system for dynamic risk of UHV converter station according to claim 5, characterized in that: The strategy determination module determines the risk prevention and control strategy as follows: Identify risk points based on the operation scenario, classify risks and describe risk characteristics; Extract risk features based on risk feature description and risk level assessment to determine risk association points; Conduct correlation analysis on risk-related points in terms of time series, spatial location, operation process and behavior pattern; Obtain the risk association network and build a risk prevention and control strategy.

7. The prediction system for dynamic risk of UHV converter station according to claim 5, characterized in that: The risk calibration system building modules and static and dynamic risk integration are as follows: Calculate the adaptive risk calibration value R(x) at the spatial position x: Among them, ω i represents the weight of the ith risk source, indicating the contribution of this risk source to the total risk; G(x,c i ,σ i ,S i ) is a Gaussian function, which represents the contribution of the i-th risk source at position x; c i represents the central position of the i-th risk source; σ i represents the impact radius of the ith risk source; S i represents the covariance matrix of the impact range of the i-th risk source; T represents the transpose of the matrix.

8. The prediction system for dynamic risk of UHV converter station according to claim 7, characterized in that: The dynamic risk identification mechanism construction module constructs a dynamic risk identification mechanism based on biological multimodal recognition and behavioral trend warning, as follows: Based on biological multimodal recognition, the biological multimodal risk fusion feature f at time t is obtained fusion (t): Where k represents the number of biological multimodal signals, ω z represents the weight of the zth signal for risk identification, f z (t) represents the feature vector of the kth biological multimodal signal at time t. During the period from time t-n+1 to t, the fusion feature is f fusion (t-n+1),...,f fusion (t), the behavior trend vector v(t) is 9. A method for controlling dynamic risks of a UHV converter station, characterized in that: The following steps are involved: Collect and integrate information, transmit and share information, and update information feedback through the information base; According to the risk prediction results obtained by the UHV converter station dynamic risk prediction system according to any one of claims 5 to 8, the operation process risk control and the overall risk control are carried out; wherein, the operation process risk control is the cross-control of personnel, machinery, before and during operation, and the overall risk control includes operation control, real-time location control and control intervention means; The dynamic risk prediction system of UHV converter stations is optimized through comprehensive evaluation results.

10. A dynamic risk management and control system for ultra-high voltage converter stations, characterized in that: include Information base module, used for information collection and integration, information transmission and sharing, and information feedback and update; A risk control module, used for performing operation process risk control and overall risk control according to the risk prediction results obtained by the UHV converter station dynamic risk prediction system according to any one of claims 5 to 8; wherein the operation process risk control is cross-control of personnel, machinery, pre-operation and operation, and the overall risk control includes operation control, real-time location control and control intervention measures; The evaluation module is used to optimize the dynamic risk prediction system of UHV converter stations through comprehensive evaluation results.

11. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method described in any one of claims 1 to 4 and claim 9 are implemented.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method described in any one of claims 1 to 4 and claim 9 are implemented.

Images