Power monitoring system based on visual intelligent platform

Abstract

The invention discloses an electric power monitoring system based on a visual intelligent platform, and relates to the technical field of electric power system monitoring, and the system comprises the following steps: S1, constructing a multi-source electric power state parameter correlation model; s2, establishing a graph driving association structure according to the state parameters; s3, establishing a multi-dimensional linkage display scene according to the graph-driven association structure; s4, establishing a real-time graph response mechanism based on the multi-dimensional linkage display scene; s5, setting a multi-period state evolution sequence according to a graph response mechanism; s6, performing anomaly identification based on the state evolution sequence; a mapping model of a node state attribute set and a combination attribute feature space is constructed by setting a graph attribute combination mapping mechanism, so that the problem of structural state information loss caused by independent expression among attributes in the existing method is solved; the structure expression capability of visual graphic state modeling is obviously enhanced, and the fineness and readability of power state visualization are improved.

Description

Technical Field

[0001] This invention relates to the field of power system monitoring technology, specifically to a power monitoring system based on a visual intelligent platform. Background Technology

[0002] As power system structures become increasingly complex, power monitoring systems place higher demands on real-time performance, state analysis capabilities, and anomaly identification accuracy. Existing power monitoring methods mainly rely on the traditional state acquisition-parameter modeling-anomaly detection process, typically employing linear models, rule-based threshold algorithms, or weighted clustering-based classification analysis methods. These methods have significant limitations in dealing with the state evolution of multidimensional graphical structures and the identification of dynamic disturbances.

[0003] 1. In the existing technology, most existing visualization models adopt static graphic mapping method, which only constructs simple primitive expression through the basic attributes of nodes. They lack the ability to map and model the relationship structure between the combination of node attributes and cannot reflect the structural change characteristics under the coupling state of multiple attributes.

[0004] 2. In the existing technology, the existing graphic response model is usually based on linear response or weighted scoring model. It lacks a response function model based on the internal structural evolution mechanism of the system. It cannot characterize the nonlinear evolution law and response path structure of the graphic state under the action of attribute perturbation, resulting in state recognition delay and decreased recognition accuracy. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides a power monitoring system based on a visual intelligent platform to solve the problems mentioned in the background section.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] In a first aspect, embodiments of the present invention provide a power monitoring system based on a visual intelligent platform, comprising the following steps:

[0008] S1. Construct a multi-source power state parameter correlation model;

[0009] S2. Establish a graphical-driven association structure based on state parameters;

[0010] S3. Establish multi-dimensional interactive display scenes based on the graphically driven association structure;

[0011] S4. Establish a real-time graphics response mechanism based on multi-dimensional interactive display scenarios;

[0012] S5. Establish a multi-time-period state evolution sequence based on the graphical response mechanism;

[0013] S6. Anomaly identification based on state evolution sequence.

[0014] To further optimize this technical solution, in step S1, the multi-source power state parameter correlation model selects voltage. Current ,frequency Active power reactive power Bus load rate Transformer load rate Based on these state parameters, establish the corresponding state matrix:

[0015] .

[0016] To further optimize this technical solution, in step S2, a logical topology graph is constructed based on the state parameter matrix using a node-edge model. Each node corresponds to an electrical component entity, and each edge represents the electrical connection relationship between devices. State parameters are mapped to a set of graphical node attributes. The node state attribute set is defined as follows:

[0017] ;

[0018] Node attributes are transformed into graphical visual features by the rendering engine, constructing a "state-graphics" mapping chain.

[0019] To further optimize this technical solution, in step S3, a state mapping tensor is constructed based on the node state attribute set:

[0020] ;

[0021] in, Represents the outer product of vectors. , is the state association tensor, representing the associated response structure between state parameters;

[0022] Elements of this tensor Indicates the first The and the first The interaction strength between parameters.

[0023] To further optimize this technical solution, step S3 includes a graphical attribute combination mapping function model, defining the graphical attribute mapping function. Used to extract key combined features from tensors and map them to different graph dimensions:

[0024] Node size : This characterizes the overall load level of the equipment, namely the busbar and transformer load;

[0025] Node outline : Voltage and current coupling characteristics;

[0026] Node texture frequency : Frequency variation and power response intensity;

[0027] Edge transparency : Sensitivity to changes in current and reactive power;

[0028] Edge color gradient : The difference between the proportion of active and reactive power, i.e., the dominance of power type;

[0029] in It is a constant term to prevent the denominator from being zero.

[0030] To further optimize this technical solution, step S3 includes the following process during implementation:

[0031] Obtain the state vector It originates from the node state attribute set in step S2;

[0032] Constructing tensors ;

[0033] Use mapping functions Extract key combined features;

[0034] Will Corresponding to the properties of the graphics component;

[0035] Construct the set of graphical attributes for each node in the visualization scene: .

[0036] To further optimize this technical solution, in step S4, the real-time graphics response mechanism adopts a graphics response function model, which includes the construction of a response difference tensor:

[0037] ;

[0038] in, Representing element-level nonlinear difference operators:

[0039] .

[0040] To further optimize this technical solution, in the graphical response function construction model of step S4, for each graphical attribute... Its update is based on the following decision function:

[0041] ;

[0042] in: Graphical attributes Should an update be triggered?

[0043] Graphical attribute correlation difference extraction function;

[0044] : Threshold for graphical attribute response;

[0045] Each Mapping function in step S3 It has an associated structure:

[0046] Graphic size The response difference function is Corresponding mapping function ;

[0047] Graphic outline The response difference function is Corresponding mapping function ;

[0048] Graphics texture frequency The response difference function is Corresponding mapping function ;

[0049] Graphic edge transparency The response difference function is Corresponding mapping function ;

[0050] Gradient of graphic edge colors The response difference function is Corresponding mapping function .

[0051] To further optimize this technical solution, in step S4, the response function model of the real-time graphics response mechanism is as follows:

[0052] ;

[0053] :time The synthesized status output of the device's graphical response;

[0054] : No. Differential response functions corresponding to each graphical attribute;

[0055] : The response difference tensor derived from the difference calculation between steps S3 and S4;

[0056] : No. Structural thresholds for graphical attribute response functions;

[0057] The combined weight parameters of each response attribute are configured statically.

[0058] To further optimize this technical solution, in step S5, state sequences from different historical periods are constructed and a set of graphical evolution trajectories is formed. The state parameter matrix is ​​aggregated by time index to form a state temporal tensor, thereby describing the structural state in the time dimension.

[0059] .

[0060] In a second aspect, embodiments of the present invention provide a computer device, including a memory and a processor, wherein the memory stores a computer program, and the computer program instructions, when executed by the processor, implement the steps of a power monitoring system based on a visual intelligent platform as described in the first aspect of the present invention.

[0061] Thirdly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program instructions are executed by a processor, they implement the steps of a power monitoring system based on a visual intelligent platform as described in the first aspect of the present invention.

[0062] Compared with existing technologies, the present invention provides a power monitoring system based on a visual intelligent platform, which has the following beneficial effects:

[0063] This power monitoring system based on a visualization intelligent platform solves the problem of missing structural state information caused by the independent expression of attributes in existing methods by setting up a graphical attribute combination mapping mechanism to construct a mapping model between the node state attribute set and the combined attribute feature space. This mechanism, based on the attribute combination mapping function, aggregates multi-dimensional node attributes into structural response feature vectors and establishes linkage combination relationships between graphical nodes, significantly enhancing the structural expressiveness of the visualized graphical state model and improving the precision and readability of power state visualization. By setting up a graphical response function model and defining the structural response mapping relationship based on the combined attribute perturbation path, it realizes a nonlinear function description from the combined attribute mapping field to the graphical state space. This model integrates the node state perturbation tensor and structural combination weight parameters to construct a response output function, enabling the linkage judgment of node structural evolution trends and state response abrupt changes. This breaks through the dependence of traditional models on weight addition and linear response, improving the foresight and sensitivity of state anomaly identification. Attached Figure Description

[0064] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0065] Figure 1 This is a schematic diagram of the structure of a power monitoring system based on a visual intelligent platform proposed in this invention;

[0066] Figure 2 This is a schematic diagram illustrating the construction process of a multi-dimensional linkage display scene for a power monitoring system based on a visual intelligent platform, as proposed in this invention.

[0067] Figure 3 This is a schematic diagram of the anomaly identification process of a power monitoring system based on a visual intelligent platform proposed in this invention. Detailed Implementation

[0068] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0069] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0070] Secondly, the term "an embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places throughout this specification does not necessarily refer to the same embodiment, nor is it a single embodiment or an embodiment selectively excluded from other embodiments.

[0071] Example 1:

[0072] Reference Figures 1-3 This is the first embodiment of the present invention, which provides a power monitoring system based on a visual intelligent platform, including the following steps:

[0073] S1. Construct a multi-source power state parameter correlation model;

[0074] In step S1, the multi-source power state parameter correlation model selects voltage. Current ,frequency Active power reactive power Bus load rate Transformer load rate Based on these state parameters, establish the corresponding state matrix:

[0075] .

[0076] S2. Establish a graphical-driven association structure based on state parameters;

[0077] In step S2, a logical topology graph is constructed based on the state parameter matrix using a node-edge model. Each node corresponds to an electrical component entity, and each edge represents the electrical connection relationship between devices. State parameters are mapped to a set of graphical node attributes. The node state attribute set is defined as follows:

[0078] ;

[0079] Node attributes are transformed into graphical visual features by the rendering engine, constructing a "state-graphics" mapping chain.

[0080] S3. Establish a multi-dimensional interactive display scene based on the graph-driven association structure; in step S3, construct a state mapping tensor based on the node state attribute set:

[0081] ;

[0082] in, Represents the cross product of vectors. , is the state association tensor, representing the associated response structure between state parameters;

[0083] Elements of this tensor Indicates the first The and the first The interaction strength between the parameters;

[0084] Step S3 includes a graphics attribute combination mapping function model, defining the graphics attribute mapping function. Used to extract key combined features from tensors and map them to different graph dimensions:

[0085] Node size : This characterizes the overall load level of the equipment, namely the busbar and transformer load;

[0086] Node outline : Voltage and current coupling characteristics;

[0087] Node texture frequency : Frequency variation and power response intensity;

[0088] Edge transparency : Sensitivity to changes in current and reactive power;

[0089] Edge color gradient : The difference between the proportion of active and reactive power, i.e., the dominance of power type;

[0090] in It is a constant term to prevent the denominator from being zero;

[0091] The implementation of step S3 includes the following process:

[0092] Obtain the state vector It originates from the node state attribute set in step S2;

[0093] Constructing tensors ;

[0094] Use mapping functions Extract key combined features;

[0095] Will Corresponding to the properties of the graphics component;

[0096] Construct the set of graphical attributes for each node in the visualization scene: ;

[0097] The graphical attribute combination mapping mechanism proposed in step S3 forms a structural response feature vector by constructing a combination function relationship between node state attribute sets. This breaks through the limitations of independent mapping of node attributes and lack of attribute linkage modeling in traditional methods. In contrast, existing methods only statically display a single attribute and cannot express the coupling state and complex association patterns between node attributes.

[0098] S4. Establish a real-time graphics response mechanism based on multi-dimensional interactive display scenarios;

[0099] In step S4, the real-time graphics response mechanism adopts a graphics response function model, which includes the construction of response difference tensors:

[0100] ;

[0101] in, Representing element-level nonlinear difference operators:

[0102] ;

[0103] In the model construction of the graphical response function in step S4, for each graphical attribute Its update is based on the following decision function:

[0104] ;

[0105] in: Graphical attributes Should an update be triggered?

[0106] Graphical attribute correlation difference extraction function;

[0107] : Threshold for graphical attribute response;

[0108] Each Mapping function in step S3 It has an associated structure:

[0109] Graphic size The response difference function is Corresponding mapping function ;

[0110] Graphic outline The response difference function is Corresponding mapping function ;

[0111] Graphics texture frequency The response difference function is Corresponding mapping function ;

[0112] Graphic edge transparency The response difference function is Corresponding mapping function ;

[0113] Gradient of graphic edge colors The response difference function is Corresponding mapping function ;

[0114] The response function model of the real-time graphics response mechanism is as follows:

[0115] ;

[0116] :time The synthesized status output of the device's graphical response;

[0117] : No. Differential response functions corresponding to each graphical attribute;

[0118] : The response difference tensor derived from the difference calculation between steps S3 and S4;

[0119] : No. Structural thresholds for graphical attribute response functions;

[0120] The combined weight parameters of each response attribute are configured statically.

[0121] During system operation, each node Corresponding graphical attribute difference data Input to each of the above response functions Output the corresponding response results respectively, and then map them to the mapping function established in step S3. Through comparison, the following is formed:

[0122] The "Combined Attribute Mapping-Graphic Response Function" matching matrix is ​​used to quantify the mapping and adjustment effect of attribute changes on visual graphics.

[0123] Enables fine-grained adjustment of power node status graphics within the platform, ensuring that visualization elements possess analytical driving capabilities;

[0124] Step S4 constructs a graphical response function model. Based on the combined attribute perturbation path, a nonlinear response function relationship is established to realize dynamic feedback of the state evolution of the graphical structure. Traditional response models are mostly based on linear weighting or static scoring methods, which cannot identify the state transmission law under complex perturbations. This step introduces a response function to realize graphical hierarchical response linkage modeling, which significantly improves the response recognition accuracy.

[0125] S5. Establish a multi-time-period state evolution sequence based on the graphical response mechanism;

[0126] In step S5, state sequences from different historical periods are constructed to form a set of graphical evolution trajectories. The state parameter matrix is ​​aggregated by time index to form a state temporal tensor, thereby describing the structural state in the time dimension.

[0127] .

[0128] S6. Anomaly identification based on state evolution sequences;

[0129] The anomaly identification process can be carried out through the following steps:

[0130] The expected state tensor under the normal operating trajectory of the system is According to step S5, the actual state tensor is Define a set of perturbation mapping functions:

[0131] ;

[0132] in: : Structural state perturbation tensor term, representing structural elements At any moment State offset intensity;

[0133] State trajectory deviation reflects changes in response behavior;

[0134] The time-derived state tensor is used to represent the rate of change of the trajectory.

[0135] The perturbation mapping function set is defined as follows:

[0136] ;

[0137] in, It is the structural disturbance response amplification factor, which is a fixed constant;

[0138] Constructing anomaly excitation functions based on state perturbation fields:

[0139] ;

[0140] in:

[0141] : Indicates the system in structural units ,time The abnormal excitation intensity;

[0142] : This is a structural constraint vector that describes the topological coupling relationship of the structural unit;

[0143] The exception triggering mapping function is defined as follows:

[0144] ;

[0145] Step S6 involves the following steps when using the model:

[0146] Based on S5 Construct the structural state perturbation field To characterize the temporal evolution perturbation of each structural unit;

[0147] Introducing the expected state trajectory It can be obtained through historical stable period statistics, and is not a traditional "mean" model;

[0148] Constructing anomaly triggering functions This forms an anomaly identification field, used to detect abnormal mutation states;

[0149] Set excitation threshold ,when When identified as an abnormal state response;

[0150] Step S6 constructs a power anomaly identification model based on state-time tensor. The state trajectory shift is analyzed by perturbation mapping function and nonlinear excitation function to achieve anomaly precursor identification. Compared with traditional anomaly identification methods that rely on static threshold or weighted clustering analysis, this model models the internal structure evolution behavior from the tensor perturbation field, which is more suitable for the accurate identification of complex graphical state anomalies.

[0151] Example 2:

[0152] This embodiment also provides a computer device applicable to a power monitoring system based on a visual intelligent platform, 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 a power monitoring system based on a visual intelligent platform as proposed in the above embodiment.

[0153] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, it implements a power monitoring system based on a visual intelligent platform as proposed in the above embodiments.

[0154] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0155] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0156] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0157] More specific examples (a non-exhaustive list) of computer-readable media include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0158] 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.

[0159] 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 power monitoring system based on a visual intelligent platform, characterized in that, Includes the following steps: S1. Construct a multi-source power state parameter correlation model; S2. Establish a graphical-driven association structure based on state parameters; S3. Establish multi-dimensional interactive display scenes based on the graphically driven association structure; S4. Establish a real-time graphics response mechanism based on multi-dimensional interactive display scenarios; S5. Establish a multi-time-period state evolution sequence based on the graphical response mechanism; S6. Anomaly identification based on state evolution sequence.

2. The power monitoring system based on a visual intelligent platform according to claim 1, characterized in that, In step S1, the multi-source power state parameter correlation model selects voltage. Current ,frequency Active power reactive power Bus load rate Transformer load rate Based on these state parameters, establish the corresponding state matrix: 。 3. The power monitoring system based on a visual intelligent platform according to claim 1, characterized in that, In step S2, a logical topology graph is constructed based on the state parameter matrix using a node-edge model. Each node corresponds to an electrical component entity, and each edge represents the electrical connection relationship between devices. State parameters are mapped to a set of graphical node attributes. The node state attribute set is defined as follows: ； Node attributes are transformed into graphical visual features by the rendering engine, constructing a "state-graphics" mapping chain.

4. The power monitoring system based on a visual intelligent platform according to claim 1, characterized in that, In step S3, a state mapping tensor is constructed based on the node state attribute set: ； in, Represents the cross product of vectors. , is the state association tensor, representing the associated response structure between state parameters; Elements of this tensor Indicates the first The and the first The interaction strength between parameters.

5. A power monitoring system based on a visual intelligent platform according to claim 4, characterized in that, Step S3 includes a graphics attribute combination mapping function model, defining the graphics attribute mapping function. Used to extract key combined features from tensors and map them to different graph dimensions: Node size : This characterizes the overall load level of the equipment, namely the busbar and transformer load; Node outline : Voltage and current coupling characteristics; Node texture frequency : Frequency variation and power response intensity; Edge transparency : Sensitivity to changes in current and reactive power; Edge color gradient : The difference between the proportion of active and reactive power, i.e., the dominance of power type; in It is a constant term to prevent the denominator from being zero.

6. A power monitoring system based on a visual intelligent platform according to claim 4, characterized in that, The implementation of step S3 includes the following process: Obtain the state vector It originates from the node state attribute set in step S2; Constructing tensors ; Use mapping functions Extract key combined features; Will Corresponding to the properties of the graphics component; Construct the set of graphical attributes for each node in the visualization scene: .

7. A power monitoring system based on a visual intelligent platform according to claim 1, characterized in that, In step S4, the real-time graphics response mechanism adopts a graphics response function model, which includes the construction of response difference tensors: ； in, Representing element-level nonlinear difference operators: 。 8. A power monitoring system based on a visual intelligent platform according to claim 7, characterized in that, In the model construction of the graphical response function in step S4, for each graphical attribute Its update is based on the following decision function: ； in: Graphical attributes Should an update be triggered? Graphical attribute correlation difference extraction function; : Threshold for graphical attribute response; Each Mapping function in step S3 It has an associated structure: Graphic size The response difference function is Corresponding mapping function ; Graphic outline The response difference function is Corresponding mapping function ; Graphics texture frequency The response difference function is Corresponding mapping function ; Graphic edge transparency The response difference function is Corresponding mapping function ; Gradient of graphic edge colors The response difference function is Corresponding mapping function .

9. A power monitoring system based on a visual intelligent platform according to claim 7, characterized in that, In step S4, the response function model of the real-time graphics response mechanism is: ； :time The synthesized status output of the device's graphical response; : No. Differential response functions corresponding to each graphical attribute; : The response difference tensor derived from the difference calculation between steps S3 and S4; : No. Structural thresholds for graphical attribute response functions; The combined weight parameters of each response attribute are configured statically.

10. A power monitoring system based on a visual intelligent platform according to claim 1, characterized in that, In step S5, state sequences from different historical periods are constructed to form a set of graphical evolution trajectories. The state parameter matrix is ​​aggregated by time index to form a state temporal tensor, thereby describing the structural state in the time dimension. 。

Images