Multi-source risk comprehensive research and judgment auxiliary decision-making method and system based on object-number fusion

Abstract

The embodiment of the invention provides a multi-source risk comprehensive research and judgment auxiliary decision-making method and system based on object-number fusion, and belongs to the technical field of electric power system risk research and judgment. The invention discloses a multi-source risk comprehensive research and judgment aid decision-making method based on object-number fusion, and the method comprises the steps: deploying a field collection device, and collecting related data based on the field collection device; carrying out preprocessing operation on the collected related data; constructing a simulation environment by using the preprocessed data; in a simulation environment, designing and simulating multiple types of risk scenes based on field conditions; and based on simulation verification results for simulating multiple types of risk scenes in a simulation environment, combining real-time data to assist decision making of the multiple types of scenes. Compared with a previous multi-source risk research and judgment technology, the problem that the prior art is one-sided is solved; data fusion and utilization are insufficient; dynamic performance and real-time performance are lacked; and the decision support is insufficient.

Description

Technical Field

[0001] The present invention relates to the technical field of power system risk assessment, and in particular to a multi-source risk comprehensive assessment and decision-making assistance method and system based on physical-digital fusion. Background Art

[0002] Ultra-high voltage (UHV) transmission plays a critical role in power delivery. A stable power supply is crucial for the normal operation of society and the provision of public services. Multi-source risk assessment of UHV transmission systems can help identify potential issues in advance, ensure the continuity and stability of power supply, and reduce the occurrence of power outages. However, previous multi-source risk assessment techniques have focused solely on a single type of risk, such as meteorological or equipment aging, while ignoring other potential multi-source risks. Furthermore, existing technologies lack effective fusion methods for processing data from diverse sources (such as meteorology, geology, and equipment monitoring), resulting in the data's value not being fully exploited. Furthermore, traditional risk assessments, based on fixed models and periodic testing, cannot reflect real-time changes. Existing technologies also fall short in providing clear and robust support for operations and management decisions, failing to provide a more reliable basis for risk assessment.

[0003] In order to solve the above problems, the present invention proposes a multi-source risk comprehensive assessment and decision-making support method and system based on object-data fusion. Summary of the Invention

[0004] The purpose of the embodiments of the present invention is to provide a multi-source risk comprehensive assessment and decision-making assistance method and system based on physical-digital fusion to solve the problems raised in the background technology.

[0005] To achieve the above objectives, an embodiment of the present invention provides a multi-source risk comprehensive assessment and decision-making assistance method based on physical-digital fusion, comprising:

[0006] Collect relevant data;

[0007] Perform pre-processing operations on the collected relevant data;

[0008] Use the preprocessed data to build a simulation environment;

[0009] In a simulation environment, design and simulate multiple risk scenarios based on on-site conditions;

[0010] The simulation verification results of multiple risk scenarios in a simulation environment are combined with real-time data to assist in multiple scenario decision-making.

[0011] Optionally, the relevant data include wind speed, wind direction, temperature, humidity, rainfall, soil displacement, mountain inclination, underground water level, conductor temperature, conductor sag, insulator contamination level, and tower vibration amplitude in the on-site environment.

[0012] Optionally, simulation verification results based on multiple risk scenarios in a simulation environment can be combined with real-time data to assist in decision-making in multiple scenarios, including:

[0013] Perform feature fusion of collected multi-source real-time data and corresponding data in the simulation environment;

[0014] Set corresponding risk assessment indicators based on different risk scenarios and calculate risk assessment indicator values ​​based on fused data;

[0015] Conduct decision-level fusion assessment based on risk assessment indicator values;

[0016] Provide decision-making recommendations based on the results of the fusion assessment and the corresponding risk assessment indicator values.

[0017] Optionally, feature fusion is performed on the collected multi-source real-time data with the corresponding data in the simulation environment, including:

[0018] The collected multi-source real-time data and the corresponding data in the simulation environment are standardized. The data features of the standardized data are extracted based on the optimized convolutional neural network, and then the attention mechanism is integrated for feature fusion. The optimized convolutional neural network is integrated with the residual unit, as follows:

[0019] H z+1 =D×λ z ×CNN

[0020] Among them, H is the residual unit set; z is the number of residual units; λ z is the learning parameter in the residual unit; D is the reference function in the residual unit; CNN is the convolutional neural network with optimized parameters;

[0021] The parameters of the convolutional neural network and residual unit are optimized based on the adaptive optimization algorithm, as follows:

[0022]

[0023] Among them, η is the parameter to be optimized; t is the number of updates; γ0 is the initial learning rate; γ t is the learning rate of the tth iteration; δ, ξ and σ are adjustable hyperparameters; Q1 and Q2 are the first-order and second-order distance estimates of the gradient;

[0024] The feature fusion is specifically as follows:

[0025] Data fusion is performed based on multimodal feature fusion, as follows:

[0026] G c =w1(U1·softmax(w p *(U1·U2)+bp ))+w2(U2·softmax(w p *(U1·U2)+b p ))

[0027] Among them, U1 is the text data feature; U2 is the image data feature; G c Output features for fusion data; w p is the attention weight parameter; b p is the attention bias parameter; w1 and w2 are the joint weight parameters of text data features and image data features respectively.

[0028] Optionally, set corresponding risk assessment indicators based on different risk scenarios, including:

[0029] Design k risk scenarios, set risk assessment indicators for different risk scenarios, and calculate the value of the j-th risk assessment indicator based on the fusion data results:

[0030]

[0031] Among them, F i represents the risk assessment index value of node i; F represents the risk assessment index value of the system; x ijk represents the kth value of the jth risk of node i; - X ij represents the lower bound of the risk of the jth item of node i; + X ij represents the upper limit of the risk of the jth item of node i; β is the fusion weight; A(·) is the risk assessment importance evaluation function.

[0032] Optionally, based on the calculated risk assessment index values, feature extraction is performed through an optimized convolutional neural network, and further feature fusion is performed, and data fusion and decision making are performed based on a three-layer neural network;

[0033]

[0034] Among them, h v is the hidden layer output vector; y r Output vector for the output layer; E s is the feature fusion result of the input layer; ω ks 、ω vr is the weight parameter; b ks 、b vr is the bias parameter;

[0035] Among them, the parameters are optimized based on the adaptive algorithm.

[0036] On the other hand, the present invention also provides a multi-source risk comprehensive assessment and decision-making support system based on physical-digital fusion, comprising:

[0037] Deployment collection module (100): used for collecting relevant data;

[0038] Preprocessing module (200): used for performing preprocessing operations on the collected relevant data;

[0039] Environmental simulation module (300): used to construct a simulation environment using pre-processed data;

[0040] Risk verification module (400): used to design and simulate multiple risk scenarios based on field conditions in a simulation environment;

[0041] A decision-making assistance module (500): used to assist in multi-scenario decision-making based on the simulation verification results of the risk verification module combined with real-time data.

[0042] Optionally, the auxiliary decision module (500) includes:

[0043] Feature fusion unit (510): used for performing feature fusion on the collected multi-source real-time data and the corresponding data in the simulation environment;

[0044] Risk assessment unit (520): used to set corresponding risk assessment indicators in combination with different risk scenario types, and calculate the risk assessment indicator value based on the fused data;

[0045] Decision-level evaluation unit (530): used for performing decision-level fusion evaluation based on risk assessment index values;

[0046] Risk warning unit (540): used to issue corresponding warnings based on the decision-level fusion assessment results;

[0047] A decision support unit (550): used to provide decision suggestions based on the results of the fusion assessment and the corresponding risk assessment index values.

[0048] On the other hand, the present invention also provides a machine-readable storage medium, on which instructions are stored, and the instructions are used to enable a machine to execute a multi-source risk comprehensive assessment and decision-making support method based on physical-digital fusion as described above.

[0049] On the other hand, the present invention also provides a processor for running a program, wherein the program, when being run, is used to execute a multi-source risk comprehensive assessment and decision-making support method based on physical-digital fusion as described above.

[0050] Through the above technical solution, the multi-source risk comprehensive assessment and decision-making assistance method and system based on physical-digital fusion provided by the present invention is based on the deployment plan of on-site acquisition equipment, takes into account the conditions of the demonstration application site, builds a simulation environment, and verifies multiple risk scenarios. It integrates multi-modal and multi-category data to conduct incremental risk assessment and assist in decision-making in various scenarios such as annual comprehensive maintenance, overhaul and technical transformation, and emergency rescue. It also improves the accuracy of systematic early warning based on the multi-source risk comprehensive assessment and decision-making service system for ultra-high voltage dense transmission channels. It supports intelligent diagnosis and early warning of hidden dangers in dense transmission channels under multiple risks, prevents sudden accidents, and effectively extends the service life of the channel itself and improves the resilience of full-life operation.

[0051] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following detailed description, they are used to explain the embodiments of the present invention, but do not constitute a limitation of the embodiments of the present invention. In the accompanying drawings:

[0053] Figure 1 This is a flowchart of a multi-source risk comprehensive assessment and decision-making assistance method based on physical-digital fusion according to one embodiment of the present invention;

[0054] Figure 2 This is a flowchart of a decision-making method for comprehensive risk assessment and decision-making assistance based on physical-digital fusion according to an embodiment of the present invention;

[0055] Figure 3 It is a system block diagram of a multi-source risk comprehensive assessment and decision-making support system based on physical-digital fusion according to one embodiment of the present invention.

[0056] Description of Reference Numerals

[0057] 100, deployment acquisition module; 200, pre-processing module; 300, environment simulation module; 400, risk verification module; 500, decision support module; 510, feature fusion unit; 520, risk assessment unit; 530, decision-level assessment unit; 540, risk warning unit; 550, decision support unit. DETAILED DESCRIPTION

[0058] The following describes the specific implementation of the embodiment of the present invention in detail with reference to the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the embodiment of the present invention and is not used to limit the embodiment of the present invention.

[0059] In the embodiments of the present application, certain software, components, models and other existing solutions in the industry may be mentioned. They should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of the present application, but it does not mean that the applicant has or will necessarily use the solution.

[0060] Figure 1 This is a flow chart of a multi-source risk comprehensive assessment and decision-making support method based on physical-digital fusion according to one embodiment of the present invention. In the present invention, the process of this method may include:

[0061] In step S1, relevant data is collected.

[0062] In step S2, the collected relevant data is preprocessed.

[0063] In step S3, a simulation environment is constructed using the preprocessed data.

[0064] In step S4, multiple risk scenarios are designed and simulated based on the on-site conditions in a simulation environment;

[0065] In step S5, the simulation verification results of multiple risk scenarios in the simulation environment are combined with real-time data to assist in multiple scenario decision-making.

[0066] In the present invention, when making decisions, collection equipment can be deployed on-site first, and then relevant data can be collected based on the deployed collection equipment. For example, in the form of microservice applications, integrated applications such as the transmission channel visualization system, the Internet of Things perception micro-application system, and the transmission Internet of Things monitoring micro-application system can be used to design standards and specifications between system architectures to build a UHV dense transmission channel micro-application system to collect a number of relevant data along the UHV dense transmission channel. The data types collected by some equipment can be referred to in Table 1:

[0067] Table 1 Data types collected by different devices

[0068]

[0069] The relevant data collected by the above equipment over a period of time are summarized in Table 2:

[0070] Table 2 Collection data of different devices at different time points

[0071]

[0072]

[0073] Relevant data collected by field equipment can include: wind speed, wind direction, temperature, humidity, rainfall, soil displacement, mountain slope, groundwater level, conductor temperature, conductor sag, insulator contamination, and tower vibration amplitude. After collecting the relevant data, it can be preprocessed to ensure it meets the requirements. The collected data can be cleaned to remove outliers. For example, data with wind speeds exceeding a reasonable range (such as 40 m / s) can be considered outliers and removed. The data can be normalized to have a consistent dimension and range. Once the relevant data meets the requirements, professional power system simulation software can be used to construct a simulation model based on the UHV transmission channel's line parameters and tower structure. The preprocessed data can be input into the model for calibration. Within the simulation environment, various risk scenarios can be designed and simulated based on the site conditions. For example, a detailed simulation model can be built to simulate various possible risk scenarios. These scenarios can be designed based on actual conditions and historical data, covering a wide range of potential risk situations. Table 3 shows some of the simulated risk scenarios.

[0074] Table 3 Some risk scenarios

[0075]

[0076]

[0077] Assume that when simulating a magnitude 6 earthquake, the tower base displacement is 10 mm and the conductor tensile strain is 0.5%.

[0078] When simulating a severe landslide, the tower tilt angle is 5° and the probability of conductor breakage is 10%.

[0079] Under strong wind conditions, the conductor's swing amplitude is 2m, and the insulator's wind deflection angle is 15°. The simulation results of various risk scenarios simulated in the simulation environment can be combined with real-time data to assist in decision-making in various scenarios.

[0080] In one embodiment of the present invention, in a constructed simulation environment, conditions and variables corresponding to different scenarios can be input, so that multiple risk scenarios can be verified.

[0081] In one embodiment of the present invention, Figure 2 As shown, the decision-making process may include:

[0082] In step S6, feature fusion is performed on the collected multi-source real-time data and the corresponding data in the simulation environment.

[0083] In step S7, corresponding risk assessment indicators are set in combination with different risk scenario types, and the risk assessment indicator values ​​are calculated based on the fused data.

[0084] In step S8, a decision-level fusion evaluation is performed based on the risk assessment index value.

[0085] In step S9, decision recommendations are provided based on the results of the fusion assessment and the corresponding risk assessment index values.

[0086] In the present invention, when the collected data and the corresponding data in the simulation environment are subjected to feature fusion in S6, the collected multi-source real-time data and the corresponding data in the simulation environment can be standardized, and the data features of the standardized data can be extracted based on the optimized convolutional neural network, and then the attention mechanism is integrated to perform feature fusion; the optimized convolutional neural network is integrated into the residual unit, specifically as follows:

[0087] H z+1 =D×λ z ×CNN

[0088] Among them, H is the residual unit set; z is the number of residual units; λ z is the learning parameter in the residual unit; D is the reference function in the residual unit; CNN is the convolutional neural network with optimized parameters;

[0089] The parameters in the convolutional neural network and residual unit are optimized based on the adaptive optimization algorithm, as follows:

[0090]

[0091] Among them, η is the parameter to be optimized; t is the number of updates; γ0 is the initial learning rate; γ t is the learning rate of the tth iteration; δ, ξ and σ are adjustable hyperparameters; Q1 and Q2 are the first-order and second-order distance estimates of the gradient;

[0092] The feature fusion is as follows:

[0093] Data fusion is performed based on multimodal feature fusion, as follows:

[0094] G c =w1(U1·softmax(w p *(U1·U2)+b p ))+w2(U2·softmax(w p *(U1·U2)+b p ))

[0095] Among them, U1 is the text data feature; U2 is the image data feature; G c Output features for fusion data; w p is the attention weight parameter; b pis the attention bias parameter; w1 and w2 are the joint weight parameters of text data features and image data features respectively.

[0096] For example, the real-time wind speed data can be integrated with the line stress data under the same wind speed conditions in the simulation environment; or the real-time rainfall data can be integrated with the flood impact data in the simulation.

[0097] In S7, corresponding risk assessment indicators are set according to different wind direction scenarios, and when the risk assessment index values ​​are calculated based on the fused data, risk assessment indicators for different risk scenarios can be set according to the k risk scenarios designed in S4. For example, in the case of strong wind disaster risk, risk assessment index values ​​including but not limited to the maximum stress of the tower (MPa) and the conductor galloping amplitude (m) can be included.

[0098] During rainstorms and floods: including but not limited to risk assessment index values ​​of tower foundation immersion depth (m) and insulator flashover probability (%);

[0099] In geological landslides: including but not limited to the risk assessment index values ​​of the transmission tower tilt angle (°) and the possibility of line disconnection (%); the j-th risk assessment index value is calculated based on the fusion data results:

[0100]

[0101] Among them, F i represents the risk assessment index value of node i; F represents the risk assessment index value of the system; x ijk represents the kth value of the jth risk of node i; - X ij represents the lower bound of the risk of the jth item of node i; + X ij represents the upper limit of the risk of the jth item of node i; β is the fusion weight; A(·) is the risk assessment importance evaluation function.

[0102] When performing decision-level fusion evaluation based on the risk assessment index value in S8, feature extraction can be performed based on the calculated risk assessment index value through the optimized convolutional neural network in S6, and further feature fusion can be performed to perform data fusion and decision-making based on the three-layer neural network;

[0103]

[0104] Among them, h v is the hidden layer output vector; y r Output vector for the output layer; E s is the feature fusion result of the input layer; ω ks 、ω vr is the weight parameter; b ks、b vr is the bias parameter;

[0105] Among them, the parameters are optimized based on the adaptive algorithm.

[0106] Based on the above integration and decision-making process, the overall risk level of the UHV dense transmission channel system can be comprehensively given.

[0107] When providing decision recommendations based on the assessment results and the corresponding risk assessment index values ​​in S9, the comprehensive risk situation of the system can be obtained based on the comprehensive assessment value, and then a more accurate risk point screening decision can be obtained based on the risk assessment index value, such as:

[0108] When the comprehensive assessment value is high (e.g. greater than 80), line inspections can be strengthened, key locations can be reinforced, and emergency supplies can be prepared in advance; key locations can be identified based on risk assessment index values;

[0109] When the comprehensive assessment value is medium (e.g., 50-80), the monitoring frequency can be increased, attention can be paid to weather changes, and emergency plans can be formulated;

[0110] When the comprehensive evaluation value is low (e.g., less than 50), normal monitoring can be maintained and equipment maintained regularly;

[0111] If the risk assessment results show a high risk level, decision recommendations may include: increasing the frequency of line inspections, preparing emergency supplies in advance, and reinforcing key towers.

[0112] On the other hand, the present invention also provides a multi-source risk comprehensive assessment and decision-making support system based on physical-digital fusion, such as Figure 3As shown, the decision-making system may include: a deployment and collection module 100, a preprocessing module 200, an environment simulation module 300, a risk verification module 400, and a decision support module 500. The deployment and collection module 100 is used to deploy on-site collection equipment and collect relevant data based on the on-site collection equipment. The preprocessing module 200 is used to preprocess the collected relevant data. The environment simulation module 300 is used to construct a simulation environment using the preprocessed data. The risk verification module 400 is used to design and simulate multiple risk scenarios based on on-site conditions in the simulation environment. The decision support module 500 is used to assist in decision-making for multiple scenarios based on the simulation verification results of the risk verification module combined with real-time data. The decision support module 500 may include: a feature fusion unit 510, a risk assessment unit 520, a decision-level assessment unit 530, a risk warning unit 540, and a decision support unit 550. The feature fusion unit 510 is used to fuse features of collected multi-source real-time data with corresponding data in the simulation environment. The risk assessment unit 520 is used to set corresponding risk assessment indicators for different risk scenarios and calculate the risk assessment indicator values ​​based on the fused data. The decision-level evaluation unit 530 is used to perform a decision-level fusion evaluation based on the risk assessment index value. The risk warning unit 540 is used to issue corresponding warnings based on the decision-level fusion evaluation results. The auxiliary decision unit 550 is used to provide decision recommendations based on the fusion evaluation results and the corresponding risk assessment index value.

[0113] On the other hand, the present invention can also provide a machine-readable storage medium, on which instructions are stored, and the instructions are used to enable a machine to execute a multi-source risk comprehensive assessment and decision-making support method based on physical-digital fusion as described above.

[0114] On the other hand, the present invention can also provide a processor, which is used to run a program, wherein when the program is run, it is used to execute the multi-source risk comprehensive assessment and decision-making support method based on physical-digital fusion as described above.

[0115] Through the above technical solution, the multi-source risk comprehensive assessment and decision-making assistance method and system based on physical-digital fusion provided by the present invention is based on the deployment plan of on-site acquisition equipment, takes into account the conditions of the demonstration application site, builds a simulation environment, and verifies multiple risk scenarios. It integrates multi-modal and multi-category data to conduct incremental risk assessment and assist in decision-making in various scenarios such as annual comprehensive maintenance, overhaul and technical transformation, and emergency rescue. It also improves the accuracy of systematic early warning based on the multi-source risk comprehensive assessment and decision-making service system for ultra-high voltage dense transmission channels. It supports intelligent diagnosis and early warning of hidden dangers in dense transmission channels under multiple risks, prevents sudden accidents, and effectively extends the service life of the channel itself and improves the resilience of full-life operation.

[0116] 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 a complete hardware embodiment, a complete software embodiment, or an embodiment 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 magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0117] 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 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 steps in the process. 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.

[0118] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work 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 The function specified in one or more boxes.

[0119] These computer program instructions can 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, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0120] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0121] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0122] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0123] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0124] The above are merely embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A multi-source risk comprehensive assessment and decision-making support method based on physical-digital fusion, characterized by: include: Collect relevant data; Perform pre-processing operations on the collected relevant data; Use the preprocessed data to build a simulation environment; In a simulation environment, design and simulate multiple risk scenarios based on on-site conditions; The simulation verification results of multiple risk scenarios in a simulation environment are combined with real-time data to assist in multiple scenario decision-making.

2. The multi-source risk comprehensive assessment and decision-making support method based on physical-digital fusion according to claim 1 is characterized in that: The relevant data include wind speed, wind direction, temperature, humidity, rainfall, soil displacement, mountain inclination, underground water level, conductor temperature, conductor sag, insulator contamination level, and tower vibration amplitude in the on-site environment.

3. The multi-source risk comprehensive assessment and decision-making support method based on physical-digital fusion according to claim 1 is characterized in that: Based on the simulation verification results of multiple risk scenarios in the simulation environment, combined with real-time data, it assists in multiple scenario decisions, including: Perform feature fusion of collected multi-source real-time data and corresponding data in the simulation environment; Set corresponding risk assessment indicators based on different risk scenarios and calculate risk assessment indicator values ​​based on fused data; Conduct decision-level fusion assessment based on risk assessment indicator values; Provide decision-making recommendations based on the results of the fusion assessment and the corresponding risk assessment indicator values.

4. The multi-source risk comprehensive assessment and decision-making support method based on physical-digital fusion according to claim 1 is characterized in that: The collected multi-source real-time data is integrated with the corresponding data in the simulation environment, including: The collected multi-source real-time data and the corresponding data in the simulation environment are standardized. The data features of the standardized data are extracted based on the optimized convolutional neural network, and then the attention mechanism is integrated for feature fusion. The optimized convolutional neural network is integrated with the residual unit, as follows: H z+1 =D×λ z ×CNN Among them, H is the residual unit set; z is the number of residual units; λ z is the learning parameter in the residual unit; D is the reference function in the residual unit; CNN is the convolutional neural network with optimized parameters; The parameters of the convolutional neural network and residual unit are optimized based on the adaptive optimization algorithm, as follows: Among them, η is the parameter to be optimized; t is the number of updates; γ0 is the initial learning rate; γ t is the learning rate of the tth iteration; δ, ξ and σ are adjustable hyperparameters; Q1 and Q2 are the first-order and second-order distance estimates of the gradient; The feature fusion is specifically as follows: Data fusion is performed based on multimodal feature fusion, as follows: <h2 style=";text-align:left;direction:ltr">G<h2 style=";text-align:left;direction:ltr"> c <h2 style=";text-align:left;direction:ltr"> =w1(U1·softmax(w<h2 style=";text-align:left;direction:ltr"> p <h2 style=";text-align:left;direction:ltr"> *(U1·U2)+b<h2 style=";text-align:left;direction:ltr"> p <h2 style=";text-align:left;direction:ltr"> ))+w2(U2·softmax(w<h2 style=";text-align:left;direction:ltr"> p <h2 style=";text-align:left;direction:ltr"> *(U1·U2)+b<h2 style=";text-align:left;direction:ltr"> p <h2 style=";text-align:left;direction:ltr"> )) Among them, U1 is the text data feature; U2 is the image data feature; G c Output features for fusion data; w p is the attention weight parameter; b p is the attention bias parameter; w1 and w2 are the joint weight parameters of text data features and image data features respectively.

5. The multi-source risk comprehensive assessment and decision-making support method based on physical-digital fusion according to claim 4 is characterized in that: Set corresponding risk assessment indicators based on different risk scenarios, including: Design k risk scenarios, set risk assessment indicators for different risk scenarios, and calculate the value of the j-th risk assessment indicator based on the fusion data results: Among them, F i represents the risk assessment index value of node i; F represents the risk assessment index value of the system; x ijk represents the kth value of the jth risk of node i; - X ij represents the lower bound of the risk of the jth item of node i; + X ij represents the upper limit of the risk of the jth item of node i; β is the fusion weight; A(·) is the risk assessment importance evaluation function.

6. The multi-source risk comprehensive assessment and decision-making support method based on physical-digital fusion according to claim 5 is characterized by: Based on the calculated risk assessment index values, feature extraction is performed through an optimized convolutional neural network, and further feature fusion is performed, and data fusion and decision-making are performed based on a three-layer neural network; Among them, h v is the hidden layer output vector; y r Output vector for the output layer; E s is the feature fusion result of the input layer; ω ks 、ω vr is the weight parameter; b ks 、b vr is the bias parameter; Among them, the parameters are optimized based on the adaptive algorithm.

7. A multi-source risk comprehensive assessment and decision-making support system based on physical-digital fusion, characterized by: include: Deployment collection module (100): used for collecting relevant data; Preprocessing module (200): used for performing preprocessing operations on the collected relevant data; Environmental simulation module (300): used to construct a simulation environment using pre-processed data; Risk verification module (400): used to design and simulate multiple risk scenarios based on field conditions in a simulation environment; A decision-making assistance module (500): used to assist in multi-scenario decision-making based on the simulation verification results of the risk verification module combined with real-time data.

8. The multi-source risk comprehensive assessment and decision-making support system based on physical-digital fusion according to claim 7 is characterized by: The auxiliary decision module (500) comprises: Feature fusion unit (510): used for performing feature fusion on the collected multi-source real-time data and the corresponding data in the simulation environment; Risk assessment unit (520): used to set corresponding risk assessment indicators in combination with different risk scenario types, and calculate the risk assessment indicator value based on the fused data; Decision-level evaluation unit (530): used for performing decision-level fusion evaluation based on risk assessment index values; Risk warning unit (540): used to issue corresponding warnings based on the decision-level fusion assessment results; A decision support unit (550): used to provide decision suggestions based on the results of the fusion assessment and the corresponding risk assessment index values.

9. A machine-readable storage medium, characterized in that The machine-readable storage medium stores instructions for enabling a machine to execute a multi-source risk comprehensive assessment and decision-making assistance method based on object-data fusion as described in any one of claims 1 to 6.

10. A processor, characterized in that: The processor is used to run a program, wherein the program, when run, is used to execute a multi-source risk comprehensive assessment and decision-making assistance method based on physical-digital fusion as described in any one of claims 1 to 6.

Images