Grid equipment operation and maintenance data security management system based on artificial intelligence

Abstract

The invention discloses a power grid equipment operation and maintenance data security management system based on artificial intelligence, and relates to the technical field of power system equipment operation and maintenance security management, and the system comprises the following steps: S1, constructing a data element mapping model with a credibility identifier; s2, performing cross dimension logic consistency verification according to the credibility data; s3, constructing a multi-stage evolution trajectory diagram according to the consistency verification data; s4, conflict evolution path screening is carried out based on the state diagram model; s5, performing asynchronous disturbance propagation modeling according to the purification path diagram; s6, performing nested structure encryption processing based on a disturbance propagation model; s7, performing data output and system feedback adjustment according to the encrypted data structure; by arranging a state evolution vector field modeling module and a multi-dimensional path jump graph construction module, the problems that equipment state modeling lacks a dynamic evolution mechanism and a path analysis means lacks graph structure expression ability in the prior art are solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power system equipment operation and maintenance safety management, in particular to an electric power grid equipment operation and maintenance data safety management system based on artificial intelligence. BACKGROUND

[0002] In the current electric power grid equipment operation and maintenance process, the equipment state data presents characteristics such as high dimensionality, nonlinearity and asynchronous disturbance. Traditional operation and maintenance data management mainly focuses on rule matching, static monitoring or threshold-based alarm strategies, and it is difficult to effectively cope with complex dynamic changes in the equipment state evolution process, especially in data structure modeling, state anomaly tracking and risk propagation identification.

[0003] 1. In the prior art, the traditional equipment state modeling method is mainly based on static statistical models or fixed discriminant conditions, and the dynamic evolution path and directional transition process between states cannot be constructed, resulting in insufficient recognition ability of the system to continuous state changes and inability to describe the evolution trajectory in the disturbance trend and state transition process.

[0004] 2. In the prior art, in the modeling of complex state jump relationships, the existing methods mainly use time series chain modeling or linear correlation analysis based on event-driven, lack of graph structure support, and are difficult to depict multi-path coupled evolution, asynchronous jump and disturbance aggregation path, which seriously limits the tracking and tracing ability of the system to the propagation behavior of the operation and maintenance risk chain. SUMMARY

[0005] In view of the deficiencies of the prior art, the present application provides an electric power grid equipment operation and maintenance data safety management system based on artificial intelligence to solve the problems raised in the background art.

[0006] To achieve the above-mentioned purpose, the present application provides the following technical scheme:

[0007] In a first aspect, the present application provides an electric power grid equipment operation and maintenance data safety management system based on artificial intelligence, characterized in that it comprises the following steps:

[0008] S1, a data element mapping model with credibility identification is constructed;

[0009] S2, cross-dimension logical consistency verification is performed according to the credibility data;

[0010] S3, a multi-stage evolution trajectory graph is constructed according to the consistency verification data;

[0011] S4, conflict evolution path is screened out based on the state graph model;

[0012] S5, non-synchronous disturbance propagation modeling is performed according to the purified path graph;

[0013] S6, based on the disturbance propagation model, nested structure encryption processing is carried out;

[0014] S7, according to the encrypted data structure, data output and system feedback adjustment are carried out.

[0015] Further optimize the technical scheme, the step S3 uses state evolution vector field mapping model to describe the evolution intensity and direction trend between state evolution trajectory, and then constructs the trajectory graph structure in stages, which contains state transition tensor function;

[0016] State node set is ;

[0017] Each pair of state transition is represented by tensor function as:

[0018] ;

[0019] Wherein:

[0020] : the transition tensor from state to ;

[0021] : state coupling coefficient, indicating the associated topological tensor between state and ;

[0022] : the structural disturbance difference function of two states at time , defined as:

[0023] ;

[0024] Wherein is the disturbance index value of state , is the disturbance normalization factor;

[0025] : the evolution direction index function between states:

[0026] ;

[0027] Indicates the joint influence between the migration direction and the disturbance intensity, is the direction sensitivity adjustment coefficient.

[0028] Further optimize the technical scheme, the state evolution vector field mapping model in step S3 is constructed by constructing state evolution vector field tensor function , which represents the direction and intensity of state evolution in the evolution process, and the state evolution field is:

[0029] .

[0030] Further optimize the technical solution, the trajectory graph construction process in step S3 as follows:

[0031] The state sequence after consistency check as input;

[0032] Calculate all state node pair transition tensor , and form the state transition graph structure;

[0033] According to the dominant direction of evolution field , the state sequence path is constructed, and the stage trajectory graph is formed;

[0034] Each stage is composed of hierarchical structure of dominant vector direction change rate, forming a multi-stage atlas.

[0035] Further optimize the technical solution, the state evolution stage division standard in step S3 is:

[0036] Evolution vector field direction switching exceeds angle threshold , determine to enter a new stage;

[0037] Adjacent stages are segmented by the gradient breakpoint of tensor density change .

[0038] Further optimize the technical solution, the step S4 further constructs the disturbance correlation mapping domain by analyzing the state node transition relationship and tensor evolution direction in the trajectory graph, which contains the disturbance response mapping function, which is used to measure the response coupling degree of state node In the vector field :

[0039] ;

[0040] Where, : State transition tensor;

[0041] : Local evolution field component:

[0042] ;

[0043] Where is a trace stable term to prevent division by zero error.

[0044] Further optimize the technical solution, the step S4 contains high-dimensional disturbance correlation domain construction function:

[0045] ;

[0046] Where: : the angle between state pairs and migration vectors:

[0047] ;

[0048] The greater the value of the state pair, the more resonance coupling relationship exists in the perturbation field domain, and the correlation domain mapping needs to be constructed.

[0049] Further optimize the technical solution, the step S4 contains the perturbation domain aggregation function:

[0050] ;

[0051] Wherein is the coupling strength threshold.

[0052] Further optimize the technical solution, the perturbation response mapping function, the high-dimensional perturbation correlation domain construction function and the perturbation domain aggregation function in the step S4 have the following application process:

[0053] Calculate the perturbation response function of all state nodes ;

[0054] Based on the perturbation coupling strength function between state pairs , a high-dimensional coupling matrix is constructed;

[0055] According to the threshold , the coupling region is extracted , and mapped into a visual perturbation aggregation domain structure;

[0056] The perturbation response atlas is constructed with the aggregation domain as a unit, which is used for path evaluation and early warning simulation in subsequent steps.

[0057] Further optimize the technical solution, the safety management system includes the following modules: data credibility construction module, data consistency verification module, state evolution vector field modeling module, multi-dimensional path jump graph construction module, path perturbation propagation modeling module, safety boundary projection modeling module and system feedback adjustment and output module.

[0058] In a second aspect, the embodiment of the present application provides a computer device, comprising a memory and a processor, and the memory stores a computer program, wherein: the computer program instructions are executed by the processor to realize the steps of the power grid equipment operation and maintenance data security management system based on artificial intelligence according to the first aspect of the present application.

[0059] In a third aspect, the embodiment of the present application provides a computer readable storage medium, which stores a computer program, wherein: the computer program instructions are executed by the processor to realize the steps of the power grid equipment operation and maintenance data security management system based on artificial intelligence according to the first aspect of the present application.

[0060] Compared with the prior art, the power grid equipment operation and maintenance data security management system based on artificial intelligence has the following beneficial effects:

[0061] The power grid equipment operation and maintenance data security management system based on artificial intelligence solves the problems of lack of dynamic evolution mechanism in equipment state modeling and lack of graph structure expression ability in path analysis means in the prior art by setting the state evolution vector field modeling module and the multi-dimensional path jump graph construction module. The system constructs a state evolution vector field model based on a state disturbance density function and an evolution intensity function, can continuously depict the nonlinear evolution trajectory of the state of the power grid equipment, and improves the recognition accuracy of the state transition trend and the disturbance path. On this basis, the system further constructs a multi-dimensional path jump graph by using state vector mapping, realizes the graph theory expression of the multi-path asynchronous jump and disturbance propagation relationship between the states of the equipment, and effectively enhances the structure tracking ability and the aggregation recognition ability of the operation and maintenance risk chain. BRIEF DESCRIPTION OF DRAWINGS

[0062] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0063] Fig. 1 A structure schematic diagram of the power grid equipment operation and maintenance data security management system based on artificial intelligence is provided for the present application.

[0064] Fig. 2 A trajectory graph construction process schematic diagram of the power grid equipment operation and maintenance data security management system based on artificial intelligence is provided for the present application.

[0065] Fig. 3 A conflict evolution path screening process schematic diagram of the power grid equipment operation and maintenance data security management system based on artificial intelligence is provided for the present application. DETAILED DESCRIPTION

[0066] In order to make the above-mentioned purposes, features and advantages of the present application more apparent and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the drawings of the specification.

[0067] In the following description, many specific details are set forth in order to provide a thorough understanding of the present application, but the present application can also be implemented in other ways different from the description, and those skilled in the art can make similar generalizations without departing from the connotation of the present application, therefore the present application is not limited to the specific embodiments disclosed below.

[0068] Second, the "one embodiment" or "an embodiment" described herein refers to a particular feature, structure, or characteristic described in one or more implementations. The following detailed description is, therefore, not to be taken in a literal or limiting sense, as such descriptions may be used in

[0069] Embodiment one:

[0070] Referring to Figs. 1-3 For the first embodiment of the application, the embodiment provides an artificial intelligence-based power grid equipment operation and maintenance data security management system, characterized in that it comprises the following steps:

[0071] S1, construct a data element mapping model with credibility identification;

[0072] As the starting point of system modeling, the original data credibility vector is:

[0073] ;

[0074] Among them, : acquisition source stability factor;

[0075] : transmission link signal-to-noise ratio;

[0076] : terminal receiving bit error rate;

[0077] Further construct the credibility mapping tensor:

[0078] ;

[0079] Among them, : data value;

[0080] : credibility factor;

[0081] : acquisition time.

[0082] S2, cross-dimension logical consistency check according to credibility data;

[0083] After ensuring the quality of data input, cross-consistency check is performed on the tensor group , and the logical consistency judgment function is defined:

[0084] ;

[0085] All data pairs of are removed, and the consistency data set is retained.

[0086] S3. Constructing multi-stage evolution trajectory graph according to consistency check data;

[0087] The step S3 employs a state evolution vector field mapping model to depict the evolution intensity and direction trend between state evolution trajectories, and further constructs a stage trajectory graph structure, which contains a state transition tensor function;

[0088] The state node set is ;

[0089] Each pair of state transitions is represented by a tensor function as:

[0090] ;

[0091] Wherein:

[0092] : transition tensor from state to ;

[0093] : state coupling coefficient, representing the associated topological tensor between state and ;

[0094] : structural disturbance difference function of two states at time , defined as:

[0095] ;

[0096] Wherein is the disturbance index value of state , is the disturbance normalization factor;

[0097] : evolution direction index function between states:

[0098] ;

[0099] , representing the joint influence between transition directionality and disturbance intensity, is the direction sensitivity adjustment coefficient;

[0100] The state evolution vector field mapping model in the step S3 constructs a state evolution vector field tensor function , representing the direction and intensity of state evolution in the evolution process, and the state evolution field is:

[0101] ;

[0102] The trajectory graph construction process in the step S3 is as follows:

[0103] with consistency check as input;

[0104] calculate transition tensor of all state node pairs and form state transition graph structure;

[0105] according to the dominant direction of evolution field , construct state sequence path and form stage trajectory graph;

[0106] each stage is composed of hierarchical structure of dominant vector direction change rate, forming multi-stage graph;

[0107] the state evolution stage division standard in step S3 is:

[0108] evolution vector field direction switching exceeds angle threshold , determine entering new stage;

[0109] adjacent stages are segmented by gradient breakpoints of tensor density change ;

[0110] in step S3, the device operation state evolution trajectory is constructed with state disturbance density function and evolution intensity , unlike the traditional static risk model based on threshold judgment, the state evolution vector field model can dynamically describe the nonlinear transition process between different device states, with directionality and continuity characteristics, providing mathematical basis for subsequent path disturbance analysis.

[0111] S4, conflict evolution path screening based on state graph model;

[0112] step S4 further constructs disturbance correlation mapping domain by analyzing the state node transition relationship and tensor evolution direction in the trajectory graph, which contains disturbance response mapping function, used to measure the response coupling degree of state node in vector field :

[0113] ;

[0114] where, : state transition tensor;

[0115] : local evolution field component:

[0116] ;

[0117] where is a trace stability term to prevent division by zero error;

[0118] The high-dimensional perturbation correlation domain construction function in the step S4 includes:

[0119] ;

[0120] Wherein: : the angle between the state pair transition vector:

[0121] ;

[0122] The greater the value of the state pair in the perturbation field domain, the higher the resonance coupling relationship, and the need to be constructed into a correlation domain mapping;

[0123] The perturbation domain aggregation function in the step S4 includes:

[0124] ;

[0125] Wherein is the coupling strength threshold;

[0126] The perturbation response mapping function, the high-dimensional perturbation correlation domain construction function and the perturbation domain aggregation function in the step S4 have the following application process:

[0127] Calculate the perturbation response function of all state nodes ;

[0128] Based on the perturbation coupling strength function between the state pairs , a high-dimensional coupling matrix is constructed;

[0129] According to the threshold , the coupling region is extracted , and is mapped into a visual perturbation aggregation domain structure;

[0130] The perturbation response atlas based on the aggregation domain as a unit is constructed, which is used for path evaluation and early warning simulation in the subsequent steps;

[0131] The jump graph structure between the perturbation states is constructed by multi-dimensional vector mapping, and the vector relationship of the state evolution strength in the previous step is fused. Compared with the traditional causal chain analysis of time series, this method can realize the graph theory expression of the heterogeneous state evolution path and the traceable modeling of the path risk transmission chain, and has stronger structural analysis ability.

[0132] S5, according to the purification path graph, the non-synchronous perturbation propagation modeling is carried out;

[0133] On the basis of the state graph , the perturbation time delay of each jump path is analyzed:

[0134] ;

[0135] Further construct the disturbance propagation asynchronous deviation function:

[0136] ;

[0137] Wherein, The description of the impact deviation strength of the disturbance propagation on the path stability is the asynchronous quantification factor of the path disturbance;

[0138] If , mark the path as "asynchronous disturbance abnormal area", and the parameter in the boundary projection model of S6 model participate in the model judgment as the boundary evolution gain factor.

[0139] S6, based on the disturbance propagation model, carries out nested structure encryption processing;

[0140] The running safety boundary prediction analysis model is introduced in step S6, which is used to judge whether the system state has approached or is about to cross the running safety limit, and then realize the system boundary early warning judgment;

[0141] The model structure is as follows:

[0142] Boundary projection index function

[0143] ;

[0144] Wherein, : the disturbance path The projection risk index of the running safety boundary interface;

[0145] : the disturbance path The direction evolution matrix in the state evolution stage;

[0146] : the boundary tensor function of the equipment state on the disturbance path ;

[0147] : the reference tensor value of the running safety boundary interface, which is constructed by the engineering safety domain;

[0148] : the modulus of the vector / tensor, which is used to measure the proximity of the current path state to the boundary;

[0149] Direction evolution matrix

[0150] ;

[0151] Wherein:

[0152] ​: perturbation path direction derivative, used to capture path acceleration;

[0153] : state transition intensity gradient;

[0154] : path perturbation coupling modulation factor;

[0155] Boundary tensor function

[0156] ;

[0157] wherein represents the tensor product of the tensor and the state vector, used to fuse the current state field and the transition intensity field to form the boundary driving tensor;

[0158] The model is used as follows:

[0159] Path selection and classification: first, the current dominant path is screened out from the perturbation path set , and the state evolution stage to which it belongs is identified , the corresponding direction matrix and tensor are extracted; ;

[0160] Projection calculation and early warning judgment: project onto the boundary reference surface , and judge the system risk through the change trend of the index :

[0161] If : the running state is stable;

[0162] If : enter the boundary transition zone;

[0163] If : determine that the system risk evolution enters the critical state, and rapid feedback adjustment should be performed;

[0164] Risk state trajectory mapping diagram construction: map all in the risk phase space to form a "risk state-boundary surface tensor field atlas";

[0165] The step S6 can simultaneously represent the path perturbation intensity and the boundary dynamic response ability, realize the joint mapping of space-state, and improve the accuracy and response ability of the safety situation assessment, which is a structural upgrade to the existing risk assessment system.

[0166] S7, data output and system feedback adjustment according to the encrypted data structure;

[0167] The system output stage not only outputs the encapsulated data, but also feeds back and adjusts the system running state, and the risk index is based on , the system feedback response quantity is:

[0168] ;

[0169] Among them, : the average boundary risk projection of the first period;

[0170] : feedback adjustment response rate, used for dynamically adjusting model parameters;

[0171] Finally, the feedback adjustment mapping is formed:

[0172] ;

[0173] Among them is the adjustment sensitivity coefficient, which ensures that the system automatically adjusts the model parameters according to the disturbance state, and realizes adaptive stable operation.

[0174] Embodiment two:

[0175] Referring to Figs. 1-3 , the second embodiment of the application provides a power grid equipment operation and maintenance data security management system based on artificial intelligence, which includes the following modules:

[0176] Data credibility construction module: constructs a tensor structure with credibility for input operation and maintenance data, fuses factors such as acquisition source stability, link quality, and bit error rate, and ensures that the data input basis has evaluation and structural uniformity;

[0177] Data consistency verification module: based on a logical consistency judgment function, the data with credibility is verified in the structure layer for physical relationship, the logical conflict data is removed, and a data cluster that can be used for modeling is formed;

[0178] State evolution vector field modeling module: constructs the dynamic evolution vector trajectory of the equipment running state on the time axis, quantifies the state jump trend and disturbance density, and lays the foundation for state-driven modeling;

[0179] Multi-dimensional path jump graph construction module: maps the state evolution vector to a multi-dimensional jump path graph, constructs the jump structure between device states, and realizes the graph theory expression and topological tracking of complex path disturbance chains;

[0180] Path disturbance propagation modeling module: based on the disturbance propagation delay and evolution intensity, a non-synchronous disturbance deviation function is constructed, the path abnormal propagation characteristics are extracted, and disturbance input factors are provided for safety boundary judgment;

[0181] Security boundary projection modeling module: generate dynamic risk projection boundary through disturbance path mapping, replace traditional security margin model, realize multi-layer dynamic defense boundary modeling;

[0182] System feedback regulation and output module: dynamically adjust model parameters, output system running state and security feedback information, realize closed-loop adaptive operation.

[0183] Embodiment three:

[0184] The embodiment also provides a computer device suitable for the case of the power grid equipment operation and maintenance data security management system based on artificial intelligence, including a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions to realize the power grid equipment operation and maintenance data security management system based on artificial intelligence as proposed in the above embodiment.

[0185] The embodiment also provides a storage medium having a computer program stored thereon, and the program is executed by a processor to realize the power grid equipment operation and maintenance data security management system based on artificial intelligence as proposed in the above embodiment.

[0186] The computer device can be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner. The wireless manner can be achieved through WIFI, operator network, NFC (near field communication) or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computer device. In addition, the input device can be an external keyboard, touchpad or mouse, etc.

[0187] If the functions are implemented in software, the functions can be stored in or implemented as one or more instructions or code on a computer-readable medium. Computer-readable media include both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage medium can be any available medium that can be accessed by a computer. By way of example, and not limitation, such computer-readable media can comprise RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. Also, any connection is properly termed a computer-readable medium. For example, if the software is transmitted from a website, server, or other remote source using a coaxial cable, fiber optic cable, or twisted pair, then the coaxial cable, fiber optic cable, or twisted pair are included in the definition of medium. Disk and disc, as used herein, include compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), and Blu-Ray® disc where disks usually reproduce data magnetically, while discs reproduce data optically with lasers. Combinations of the above should also be included within the scope of computer-readable media.

[0188] In other words, like a human driver of a vehicle, the autonomous vehicle 100 can be programmed to follow traffic laws and rules of the road, and to make decisions based on its programming and the information it receives from its sensors and other sources. The autonomous vehicle 100 can also be programmed to make decisions based on its programming and the information it receives from its sensors and other sources, even if those decisions are not in accordance with traffic laws and rules of the road. For example, the autonomous vehicle 100 can be programmed to avoid a collision with another vehicle, even if doing so would violate a traffic law or rule of the road.

[0189] In other words, like a human driver of a vehicle, the autonomous vehicle 100 can be programmed to follow traffic laws and rules of the road, and to make decisions based on its programming and the information it receives from its sensors and other sources. The autonomous vehicle 100 can also be programmed to make decisions based on its programming and the information it receives from its sensors and other sources, even if those decisions are not in accordance with traffic laws and rules of the road. For example, the autonomous vehicle 100 can be programmed to avoid a collision with another vehicle, even if doing so would violate a traffic law or rule of the road.

[0190] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0191] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A data security management system for power grid equipment operation and maintenance based on artificial intelligence, characterized in that, Includes the following steps: S1. Construct a data element mapping model with credibility identifiers; S2. Perform cross-dimensional logical consistency verification based on credibility data; S3. Construct a multi-stage evolution trajectory diagram based on the consistency verification data; S4. Conflict evolution path filtering based on state diagram model; S5. Model asynchronous disturbance propagation based on the purification path diagram; S6. Nested structure encryption processing based on the perturbation propagation model; S7. Adjust data output and system feedback based on the encrypted data structure.

2. The power grid equipment operation and maintenance data security management system based on artificial intelligence according to claim 1, characterized in that, In step S3, the state evolution vector field mapping model is used to characterize the evolution intensity and directional trend between state evolution trajectories, thereby constructing a phased trajectory diagram structure, which includes a state transition tensor function. The set of state nodes is ; Each pair of state transitions is represented by a tensor function as follows: ； in: From state arrive The migration tensor; State coupling coefficient, representing the state and The related topological tensors between them; :time The structural perturbation difference function for the next two states is defined as: ； in For state The disturbance index value, This is the perturbation normalization factor; The exponential function representing the direction of evolution between states: ； This indicates the combined effect between migration directionality and disturbance intensity. This is the directional sensitivity adjustment coefficient.

3. The power grid equipment operation and maintenance data security management system based on artificial intelligence according to claim 2, characterized in that, In step S3, the state evolution vector field mapping model is constructed by establishing a state evolution vector field tensor function. , representing the direction and intensity of a state during its evolution, the state evolution field is: 。 4. The power grid equipment operation and maintenance data security management system based on artificial intelligence according to claim 2, characterized in that, The trajectory map construction process in step S3 is as follows: The state sequence after consistency verification is used as input; Calculate the transition tensor for all pairs of state nodes. And form a state transition diagram structure; Based on the evolution field The dominant direction is to construct a state sequence path and form a stage trajectory diagram; Each stage is structured by the rate of change of the dominant vector direction, forming a multi-stage map.

5. The power grid equipment operation and maintenance data security management system based on artificial intelligence according to claim 2, characterized in that, The criteria for dividing the state evolution stages in step S3 are as follows: The direction switching of the evolution vector field exceeds the angle threshold. This indicates that the process has entered a new phase. Adjacent stages through tensor density changes The gradient breakpoints are used for segmentation.

6. The power grid equipment operation and maintenance data security management system based on artificial intelligence according to claim 1, characterized in that, Step S4 further constructs a perturbation correlation mapping domain by analyzing the state node migration relationships and tensor evolution directions in the trajectory graph. This domain includes a perturbation response mapping function used to measure the state nodes. In vector field The degree of response coupling in: ； in, : State transition tensor; Local evolution field components: ； in This is a small, stable term to prevent division by zero error.

7. The power grid equipment operation and maintenance data security management system based on artificial intelligence according to claim 5, characterized in that, Step S4 includes a high-dimensional perturbation correlation domain construction function: ； in: Angle between state pairs and transition vectors: ； The larger the value, the more resonant coupling relationship exists between the state pairs in the perturbed field, and it is necessary to construct an association domain mapping.

8. A power grid equipment operation and maintenance data security management system based on artificial intelligence according to claim 5, characterized in that, Step S4 includes a perturbation domain aggregation function: ； in This is the coupling strength threshold.

9. A power grid equipment operation and maintenance data security management system based on artificial intelligence according to claim 5, characterized in that, The perturbation response mapping function, high-dimensional perturbation correlation domain construction function, and perturbation domain aggregation function in step S4 have the following application flow: Calculate the disturbance response function for all state nodes. ; Based on the perturbation coupling strength function between state pairs Construct a high-dimensional coupling matrix; Based on threshold Extracting the coupling region And mapped to a visible perturbation aggregation domain structure; A disturbance response map with aggregation domains as units is constructed for path evaluation and early warning simulation in subsequent steps.

10. A power grid equipment operation and maintenance data security management system based on artificial intelligence according to claims 1-9, characterized in that, The security management system includes the following modules: data credibility construction module, data consistency verification module, state evolution vector field modeling module, multi-dimensional path jump graph construction module, path disturbance propagation modeling module, security boundary projection modeling module, and system feedback adjustment and output module.

Images