CN108228900B - Power equipment multispectral data center model building method based on hierarchical structure - Google Patents
Power equipment multispectral data center model building method based on hierarchical structure Download PDFInfo
- Publication number
- CN108228900B CN108228900B CN201810119273.6A CN201810119273A CN108228900B CN 108228900 B CN108228900 B CN 108228900B CN 201810119273 A CN201810119273 A CN 201810119273A CN 108228900 B CN108228900 B CN 108228900B
- Authority
- CN
- China
- Prior art keywords
- power equipment
- agent
- data center
- model
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/51—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
- G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/54—Interprogram communication
- G06F9/547—Remote procedure calls [RPC]; Web services
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B17/00—Systems involving the use of models or simulators of said systems
- G05B17/02—Systems involving the use of models or simulators of said systems electric
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2209/00—Indexing scheme relating to G06F9/00
- G06F2209/54—Indexing scheme relating to G06F9/54
- G06F2209/544—Remote
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2221/00—Indexing scheme relating to security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F2221/21—Indexing scheme relating to G06F21/00 and subgroups addressing additional information or applications relating to security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F2221/2141—Access rights, e.g. capability lists, access control lists, access tables, access matrices
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Data Mining & Analysis (AREA)
- Computer Hardware Design (AREA)
- Computer Security & Cryptography (AREA)
- Bioethics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method for establishing a multispectral data center model of power equipment based on a layered structure, which comprises the following steps: the method comprises the steps of analyzing based on a multispectral data structure of the power equipment, constructing a multispectral data center model of the power equipment, constructing an image recognition analysis model, analyzing the application relation of the image recognition analysis model to the multispectral data center model, constructing an information connection agent structure of the power equipment, independently modeling units in each model system by means of a computer, generating a hierarchical control unit, and connecting the hierarchical control unit according to an actual topological relation to form a network with a distributed structure, so that the multispectral data of the power equipment are automatically layered and calculated. The invention provides a self-adaptive adjustment layered structure technology, can adapt to the requirement of frequent change of image data of power equipment, and provides powerful support for further comprehensively analyzing power images and judging the running state of the power equipment.
Description
Technical Field
The invention relates to the technical field of power equipment data management and application, in particular to a power equipment multispectral data center model building method based on a hierarchical structure.
Background
At present, some transformer substations are provided with video monitoring systems, and the functions of monitoring field equipment, controlling the motion of a remote camera, recording digital videos and the like can be realized. However, only the monitoring function is not provided with the image recognition function, and the automatic recognition and analysis functions of the substation transformation equipment are lacked. Still rely on the personnel on duty to observe and the image of analysis collection to judge the running state of substation equipment, the system lacks the automatic identification and the analysis function to substation equipment image. The method is fundamentally not mature in research on analysis of transformer substation images with complex backgrounds and a method for judging operation faults of transformer equipment, improves image analysis capability practically, and is a problem which needs to be solved urgently.
The invention with the patent number of 201510412958.6 discloses a multispectral-based composite insulator detection method, which comprises the following steps: selecting detection equipment, and performing visible light detection, infrared detection and ultraviolet detection on the same composite insulator by using the detection equipment under the same operation condition to obtain a detection image of the composite insulator; comparing a partial discharge luminous point of the visible light image, a partial hot spot of the infrared image and a corona discharge point of the ultraviolet image; under the same operation condition, comparing visible light images, infrared images and ultraviolet images of different composite insulators of the same base tower on the same line; and establishing a multispectral detection database for each composite insulator, comparing the data according to the detected data in a certain period, and finding out the existing data difference. The invention organically combines three detection means of visible light, infrared and ultraviolet, has complementary advantages, is easy to carry out charged detection on the insulator, can find the defects of the composite insulator in time and is convenient to carry out large-area routing inspection.
The invention with the patent number of 201110419576.8 provides a composite insulator hyperspectral detection method, which comprises the following steps: 1) imaging the composite insulator by adopting a hyperspectral imager to obtain a hyperspectral image of the composite insulator; 2) preprocessing a hyperspectral image of the composite insulator, wherein the hyperspectral image comprises geometric correction and radiation correction so as to obtain more accurate spectral information; 3) and (4) processing and analyzing by using a professional analysis platform, determining the running state of the composite insulator, outputting/displaying a judgment result, and judging whether the composite insulator needs to be replaced. The hyperspectral detection method for the composite insulator can be used for carrying out non-contact detection on the composite insulator without climbing a tower by workers; the time required by field operation is short, when the hyperspectral imager is used for acquiring data, the information of a plurality of composite insulators can be acquired at the same time, the plurality of composite insulators can be conveniently processed and analyzed at the later stage, the purpose of batch detection is achieved, and the requirement of state detection of the composite insulators in China is met.
However, in practical application, some problems existing in the current online monitoring of the power transformation equipment can be fundamentally solved through multispectral detection analysis and identification technologies such as visible light, infrared, ultraviolet and the like: the operation parameters of important equipment need to be monitored in real time, the requirement on real-time performance is difficult to meet by adopting manual inspection, and the responsibility, working attitude and mental condition of an inspector seriously influence the detection result; the operation state of many high-voltage equipment is difficult to be converted into electric signals, and diagnosis is easily influenced by strong electromagnetic field interference in the signal conversion and transmission processes; the detection of the equipment by using infrared is still in a simple application level of temperature record, is not associated with the equipment state, and historical data is difficult to store and retrieve; in addition, it is difficult for human eyes to distinguish gradation changes of fine images, and it is difficult to objectively determine the degree of surface defects of the power transformation device. Therefore, the application of the multispectral image analysis and recognition technology and the establishment of the model can promote the intellectualization and the automation of the online monitoring system, improve the working efficiency of the transformer substation workers, obtain higher economic benefit and have greater practical value and application prospect.
Disclosure of Invention
The invention aims to provide a method for establishing a multispectral data center model of power equipment based on a layered structure, provides a layered structure technology capable of being adjusted in a self-adaptive mode, can meet the requirement of frequent change of image data of the power equipment, and provides powerful support for further comprehensively analyzing power images and judging the running state of the power equipment.
In order to achieve the purpose, the invention adopts the technical scheme that: the method for establishing the multispectral data center model of the power equipment based on the layered structure comprises the following steps:
1) analyzing based on a multispectral data structure of the power equipment, wherein the multispectral data structure comprises analysis of a data center service framework and analysis of an image recognition analysis algorithm;
2) according to the analysis of a data center service framework, a multispectral data center model of the power equipment is constructed, and the multispectral data center model comprises an application layer, a scheduling layer, a service layer and a data layer which are connected with one another and carry out data transmission;
3) according to the analysis of the image recognition analysis algorithm, an image recognition analysis model is constructed, and the image recognition analysis model comprises image information acquisition and preprocessing, image feature extraction and reconstruction, and image judgment and recognition;
4) analyzing the application relation of the image recognition analysis model to the multispectral data center model, and constructing an information connection agent structure of the power equipment;
5) the method comprises the steps of calling a multispectral data center model of the electric power equipment, an image recognition analysis algorithm and an information connection agent structure of the electric power equipment, independently modeling units in each model system by means of a computer, generating a hierarchical control unit, and connecting the hierarchical control unit and the hierarchical control unit according to an actual topological relation to form a network of a distributed structure, so that automatic layering and operation of multispectral data of the electric power equipment are achieved.
Further, the power equipment information connection agent structure comprises a business agent and an application agent, wherein the business agent comprises a control agent, a distributed agent and a user agent, and the application agent comprises a data service agent and a visualization module.
Furthermore, the hierarchical control unit is of a multilayer nested structure and comprises a central agent unit, a simulation process unit, a simulation time sequence hierarchical control unit, an object agent unit, a state monitoring unit and an external interface unit which are connected in sequence.
Further, the external interface unit includes an EMS external database for acquiring initialization data, and the external interface unit is respectively interconnected with the simulation process unit, the simulation sequential hierarchical control unit, the object proxy unit, and the state monitoring unit in a bidirectional manner through a high performance message bus.
Furthermore, the data layer is a physical layer of the power equipment, spectrum information of the power equipment is acquired through the visualization module, the measuring equipment and the equipment agent, and image data results of the power equipment are inquired or image data transmitted from the service layer are stored.
Furthermore, the scheduling layer is an information security layer, and is used as a firewall of the whole system to not only authenticate the identity of the request at the rear end of the system, but also complete the encryption protection work in service forwarding.
Further, the business layer is composed of a plurality of subsystems and services suitable for the market, can call internal services and other external services, exchanges information with other agents, and collects and sends control signals from the business agent and the application agent.
Further, the application layer enables a user to directly face a computer terminal user and a mobile terminal application and accesses the power equipment state through application software or a mobile equipment APP program.
The invention has the beneficial effects that:
the invention provides a key technology related to multispectral detection analysis and identification of the operation state of power transformation equipment, establishes a multispectral data center model of the operation state of the power transformation equipment, and constructs a technical framework of a distributed power grid equipment image data processing center, wherein the technical framework comprises the contents of acquisition of images of multisource sensors, analysis and processing of image data, interaction and construction of a mobile terminal, and the like, the multisource images and the related information of power equipment are acquired through various sensors and other modes, the detection and analysis of power facility data are carried out, the data processing center constructs a data center storage framework, and a plurality of bottlenecks in the aspect of storage are further improved through a file system, a calculation framework and a database. And finally, realizing the technical interconnection between the data processing center and the mobile terminal by building a technical framework of the data processing center, thereby realizing the interconnection and intercommunication between the detection platform and the expert platform, and finally further guiding the field operation by utilizing the mobile terminal platform. The project can solve the problems of how to establish a multispectral data center model and efficiently utilize image data in multispectral image analysis of the power transformation equipment, provides a data base for fault detection and diagnosis of the power transformation equipment, exerts the advantages of the mobile terminal, ensures safe and reliable operation of the power grid equipment, has higher theoretical and practical significance, has very strong effectiveness and practicability, and is worthy of wide popularization and use.
Drawings
Fig. 1 is an architectural diagram of a multi-spectral data center model of a power device of the present invention.
FIG. 2 is a structural relationship diagram of an image recognition analysis model according to the present invention.
Fig. 3 is a schematic diagram of the composition structure of the hierarchical control unit of the present invention.
Fig. 4 is a composition relationship diagram of the power device information connection agent structure of the present invention.
Detailed Description
Examples
As shown in fig. 1 to 4, the method for establishing the multispectral data center model of the power equipment based on the hierarchical structure includes the following steps: 1) analyzing based on a multispectral data structure of the power equipment, wherein the multispectral data structure comprises analysis of a data center service framework and analysis of an image recognition analysis algorithm; 2) according to the analysis of a data center service framework, a multispectral data center model of the power equipment is constructed, and the multispectral data center model comprises an application layer, a scheduling layer, a service layer and a data layer which are connected with one another and carry out data transmission; 3) according to the analysis of the image recognition analysis algorithm, an image recognition analysis model is constructed, and the image recognition analysis model comprises image information acquisition and preprocessing, image feature extraction and reconstruction, and image judgment and recognition; 4) analyzing the application relation of the image recognition analysis model to the multispectral data center model, and constructing an information connection agent structure of the power equipment; 5) the method comprises the steps of calling a multispectral data center model of the electric power equipment, an image recognition analysis algorithm and an information connection agent structure of the electric power equipment, independently modeling units in each model system by means of a computer, generating a hierarchical control unit, and connecting the hierarchical control unit and the hierarchical control unit according to an actual topological relation to form a network of a distributed structure, so that automatic layering and operation of multispectral data of the electric power equipment are achieved.
When the multispectral data center model is applied specifically, the multispectral data center model of the power equipment is mainly divided into four layers, namely 1) an application layer, namely the multispectral data center model is directly applied to a computer terminal user and a mobile terminal; 2) scheduling layers, such as firewalls and the like; 3) a service layer; 4) and (6) a data layer. In the application layer, the user accesses the target device state using application software or a mobile device APP program. The request enters the service layer through the scheduling layer, and the firewall serving as the whole system not only performs identity verification on the request at the rear end of the system, but also completes service forwarding work. The system service layer is composed of a plurality of subsystems and services suitable for markets, and can call internal services and other external services. And finally, the data storage layer is responsible for inquiring the image data result of the power equipment or storing the image data transmitted from the service layer.
The image identification analysis model of the power grid equipment in the invention is as shown in figure 2: acquiring and preprocessing image information, extracting and reconstructing image characteristics, judging and identifying images, and comprehensively considering the color characteristics, texture characteristics, shapes (contour characteristics) and scale space information of equipment in the equipment characteristic extraction; the characteristic of typical equipment in computer vision based on geometric features is researched, the experience of successful application of image processing and recognition technology in other fields is used for reference, the algorithm of image processing and pattern recognition is applied to the recognition of the electric power equipment, a target can be found in the graph through a certain algorithm, the coordinate position of the target is determined, the type of the electric power equipment is recognized, the prerequisite condition for further comprehensively analyzing the electric power image is provided, and the foundation for judging the operation state of the electric power equipment is provided.
And reconstructing the equipment image according to the characteristics of the power grid equipment image, so that the quality of the obtained equipment image is improved. The image enhancement technology highlights the information of the interested area in the power grid equipment image aiming at the preprocessing process in the image analysis and identification, and transforms the original power grid equipment image into an image more suitable for human-computer identification. The commonly used image enhancement processing method of the equipment is researched: gray level transformation, histogram modification, image sharpening, noise removal, geometric distortion correction, frequency domain filtering, color enhancement and the like; the image enhancement algorithm based on the spatial domain and the image enhancement algorithm based on the transform domain are researched, and the image enhancement algorithm which is targeted and suitable for various application occasions is applied to the processing of the equipment images.
Aiming at the image reconstruction method based on sparse representation in the current image reconstruction field, an equipment image quality enhancement method based on compressed sensing theory and sparse representation is researched. The power grid equipment image generally has rich textures, the image reconstruction method based on sparse representation has a good effect on restoring the textures and other details of a natural image, and the performance is more excellent on the premise that no obvious noise influence and a fuzzy kernel are known. In addition, the number of dictionary atoms constructed by the sparse representation method is small, the efficiency is high, and a space is reserved for further designing an algorithm which is more complex and has a better image reconstruction effect.
The method is used for researching a high-level semantic feature extraction model based on deep learning, and constructing a depth network mapping model which is iterated layer by layer and abstracted layer by layer from the bottom visual features of the image to the high-level semantic features, aiming at reducing the semantic gap, obtaining the semantic features of the image and providing a good foundation for large-scale automatic image annotation
Aiming at the equipment image recognition based on deep learning, the most fundamental problem, namely more powerful characteristics, is researched and solved, and the recognition accuracy can be greatly improved by using a better network training model. And (4) directly predicting the possible equipment target at each position by using the global characteristics, and continuously performing iterative regression adjustment to obtain a final identification result. The research defines a regression mode, a network and a model, and the original recognition result is regressed again and then recognized, so that the effect is improved.
The method is based on the analysis of a layering technology, the technology is an information processing technology, a plurality of agents complete a certain target through cooperation, and the agents can interact information and behaviors with the environment where the agents are located. In the method, the agent unit corresponds to a distribution network subarea with a distributed mode. The hierarchy is a high-level existing form thereof, and the agent units are combined through a certain rule to realize the high-level interaction function of the group. In the method, "layering" is embodied in that: according to the proposed algorithm rule, the power equipment region is divided on an effective 'space' scale, and regional agents are formed by agent groups in the region. The method is technically characterized in that information and behavior interaction is performed between regional agents and between the regional agents and upper-layer system agents. The core value of the method is the functions of self-learning, self-coordination, self-management and self-execution of the agent group, and the agent group essentially has the capabilities of parallel processing and batch processing.
The power equipment information connection agent structure comprises a business agent and an application agent, wherein the business agent comprises a control agent, a distributed agent and a user agent, and the application agent comprises a data service agent and a visualization module. The system consists of four agents, namely a control agent, a distributed agent, a user agent and an application agent, wherein the application agent comprises a data service agent and a visualization module. In this system, each agent has its own target and responsibility. The function of the control agent includes monitoring for incidents. When a fault occurs, the control agent sends a signal to form isolation. The distributed agent is responsible for storing relevant distribution information and may also monitor distributed power and connection status. The distributed information includes the number of devices, type, power rating, utilization, etc. The user agent serves as a channel for the intelligent microgrid to provide users with knowledge of relevant information. The user agent provides the client with real-time information of the entities of the intelligent system. The user agent may also monitor the channels of important and non-important information, and finally, the application agent is responsible for storing system information, log information, and information sharing between agents, and the application agent also serves as a data access and user display module for each agent, as shown in fig. 4.
In the conventional model control, the modeling agent is a fixed unit which is initially set, and cannot be adjusted adaptively to the change of a scene. The agents designed by the invention are not fixed and invariable, and self-adaptive adjustment, namely 'nesting', can be carried out among the agents along with the change of scenes. The 'nesting' is a specific realization method of a 'layered' information model related to the invention, firstly, the identification and search of the vulnerability key path of the distribution network system are carried out, the basic agent unit is determined, then, the operation rule is formed according to the distributed structure access information and the key factors of the distributed access point and the equipment, and the 'merging' operation is carried out on the agent unit for a plurality of times, namely, the 'nesting'.
The layered mode of the invention comprises two aspects, one is the functional layering of a multispectral data center, namely function transmission from top to bottom, wherein the data layer is a physical layer of the power equipment, the spectral information of the power equipment is acquired through a visualization module, a measuring device and an equipment agent, and the image data result of the power equipment is inquired or the image data transmitted from a service layer is stored. The scheduling layer is an information security layer and is used as a firewall of the whole system to authenticate the identity of a request at the rear end of the system and complete encryption protection work in service forwarding. The business layer is composed of a plurality of subsystems and services suitable for the market, can call internal services and other external services, exchanges information with other agents, and collects and sends control signals from the business agent and the application agent. The application layer enables a user to directly face computer terminal users and mobile terminal applications, and accesses the power equipment state through application software or mobile equipment APP programs.
On the other hand, by simulating the control relationship and applying the concept of global coordination, the hierarchical control unit is hierarchical in network, namely, the hierarchical control unit is a multilayer nested structure and comprises a central agent unit, a simulation process unit, a simulation time sequence hierarchical control unit, an object agent unit, a state monitoring unit and an external interface unit which are connected in sequence.
The external interface unit comprises an EMS external database used for acquiring initialization data, and is respectively in bidirectional interconnection with the simulation process unit, the simulation time sequence hierarchical control unit, the object agent unit and the state monitoring unit through a high-performance message bus.
The hierarchical control unit of the invention is to form a plurality of central coordination agent units with cascade relations by a computing unit, which is responsible for simulating the control relation among multi-level networks, and a plurality of object agents in the interior of the hierarchical control unit respectively and collectively form an image recognition analysis algorithm taking 'distributed ordered access and network fluctuation minimum' as a 'global coordination target', after given input parameters and constraint conditions, the distributed node ordered access in the interior of the network and the energy balance process in the interior of the network are simulated, a network relation diagram is shown in figure 3, each part is independent relatively to the outside, and any external expansion can be carried out by the central agent unit, a multi-level multi-region network model divided by different types and regions of electric power equipment is generated, the cooperative management among the upper level, the lower level and the region is realized in different levels and different regions, and the upper level, the lower level and the horizontal level are only connected by the central agent unit, do not interfere with the internal operation.
In practical application, the hierarchical control unit is a multi-layer nested structure, and the structure of each level is similar. Taking a first level as an example, as shown in fig. 3, the system mainly includes a central agent unit, a simulation process, a simulation timing control, an object agent unit, a state monitoring unit, an external interface, and the like, and the structures and specific functions of each part are as follows:
the central agent is responsible for coordinating the simulation process between the upper level and the lower level and the sub-areas and coordinating the inside of the level as a whole. Each central agency is only responsible for the local level or the local area, and each upper level network or lower level network is responsible for independent central agencies. The central agent is responsible for calling a background simulation calculation program to analyze and calculate the internal state of the network at the current level and broadcasting the calculation result to all object agents governed by the central agent;
in the simulation process, as the simulation network is of a multi-level structure, in order to realize the parallelization calculation of the regions, each sub-region is divided into a simulation calculation process, so that the multi-region parallel calculation is realized. In addition, when the local region coordination strategy cannot be converged, cross-region overall coordination tasks are carried out through a central agent on the upper layer; the simulation scenario refers to the global state of a simulation network formed by current information of the central agent and the object agent under a certain time section.
The simulation time sequence control is to time sequence all simulation processes in all levels and sub-regions, and to perform simulation calculation of continuous time sections in an event triggering mode, wherein the calculation processes in each region are relatively independent, so that the central agency needs to pay special attention to the synchronization of events in the sub-regions on the time sequence. According to the definition of the simulation control loop of the central agency, such as state monitoring, simulation analysis, overall planning and task execution, the complete function of the central agency is defined as shown in the following diagram: and the central agent continuously updates the current network state according to the time stamp, broadcasts the result to the self network and acquires the state information of the agent of the object to which the central agent belongs through port monitoring. The central agency needs the support of the global coordination strategy and calculates the applicable coordination strategy under the current constraint condition. When the result of the calculation coordination strategy is not converged, the fact that self-coordination cannot be achieved in the network is indicated, and the network can be applied to the upper level. Similarly, the central proxy responds to requests sent by the lower level network.
The object agent unit is an object managed by the central unit, is the most basic construction module of the simulation network, contains a plurality of object agent instances in each area, is used for describing and constructing the basic attributes of the simulation object model, and is provided with a knowledge method base and a rule logic algorithm for autonomously responding to the state change of the object agent unit.
The central agent or the object agent is a computing unit, and the simulation network is formed by the computing units. In the software system, if the resources administered by the computing unit specifically point to a specific simulation model of a certain type, the external appearance of the computing unit is represented as an object agent, and if the resources administered by the computing unit also comprise other computing units, the external appearance of the computing unit is represented as a central agent. The autonomous induction of the simulation network is an autonomous management mechanism for the computing unit to manage the resources managed by the computing unit, and is used for replacing the original management work needing manual work. In addition, initialization data is acquired through an EMS external database, and the distributed file system provides file data of the topology model of each area.
The distributed cooperative modeling method under the architecture of the hierarchical control unit is to independently package a lower control unit, only pay attention to internal definition and an excitation response strategy to a main hierarchical control unit, has limited data and resources, and does not interfere or influence an external network structure and other targets. The main hierarchical control unit does not take the task of calculating the internal process of each node any more, only needs to formulate an excitation signal according to an overall control target to require response to the excitation signal, verifies a feedback result, and hides the internal analysis, adjustment and optimization process of the lower control unit. And the main manager of the practical application system does not want to pay more attention to the internal process of each subordinate, and only evaluates whether the system achieves the overall operation target, so the mode greatly reduces the burden of the central task.
While the invention has been described in terms of what are presently considered to be the preferred embodiments, and not of limitation, those skilled in the art will recognize that many alternative embodiments may be implemented using the concepts of the present invention. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (7)
1. The method for establishing the multispectral data center model of the power equipment based on the layered structure is characterized by comprising the following steps of:
analyzing based on a multispectral data structure of the power equipment, wherein the multispectral data structure comprises analysis of a data center service framework and analysis of an image recognition analysis algorithm;
according to the analysis of a data center service framework, a multispectral data center model of the power equipment is constructed, and the multispectral data center model comprises an application layer, a scheduling layer, a service layer and a data layer which are connected with one another and carry out data transmission;
according to the analysis of the image recognition analysis algorithm, an image recognition analysis model is constructed, and the image recognition analysis model comprises image information acquisition and preprocessing, image feature extraction and reconstruction, and image judgment and recognition;
analyzing the application relation of the image recognition analysis model to the multispectral data center model, and constructing an information connection agent structure of the power equipment; the power equipment information connection agent structure comprises a business agent and an application agent, wherein the business agent comprises a control agent, a distributed agent and a user agent, and the application agent comprises a data service agent and a visualization module;
the method comprises the steps of calling a multispectral data center model of the electric power equipment, an image recognition analysis algorithm and an information connection agent structure of the electric power equipment, independently modeling units in each model system by means of a computer, generating a hierarchical control unit, and connecting the hierarchical control unit and the hierarchical control unit according to an actual topological relation to form a network of a distributed structure, so that automatic layering and operation of multispectral data of the electric power equipment are achieved.
2. The method for building the multi-spectral data center model of the power equipment based on the layered structure according to claim 1, wherein: the hierarchical control unit is of a multilayer nested structure and comprises a central agent unit, a simulation process unit, a simulation time sequence hierarchical control unit, an object agent unit, a state monitoring unit and an external interface unit which are connected in sequence.
3. The method for building the multi-spectral data center model of the power equipment based on the layered structure according to claim 2, wherein: the external interface unit comprises an EMS external database used for acquiring initialization data, and the external interface unit is respectively in bidirectional interconnection with the simulation process unit, the simulation time sequence hierarchical control unit, the object agent unit and the state monitoring unit through a high-performance message bus.
4. The method for building the multi-spectral data center model of the power equipment based on the layered structure according to claim 1, wherein: the data layer is a physical layer of the power equipment, spectrum information of the power equipment is acquired through the visualization module, the measuring equipment and the equipment agent, and image data results of the power equipment are inquired or image data transmitted from the service layer are stored.
5. The method for building the multi-spectral data center model of the power equipment based on the layered structure according to claim 1, wherein: the scheduling layer is an information security layer and is used as a firewall of the whole system to authenticate the identity of a request at the rear end of the system and complete encryption protection work in service forwarding.
6. The method for building the multi-spectral data center model of the power equipment based on the layered structure according to claim 1, wherein: the business layer is composed of a plurality of subsystems and services adapted to the market, calls internal services, calls other external services, exchanges information with other agents, and collects and sends control signals from the business agents and the application agents.
7. The method for building the multi-spectral data center model of the power equipment based on the layered structure according to claim 1, wherein: the application layer enables a user to directly face computer terminal users and mobile terminal applications, and accesses the power equipment state through application software or mobile equipment APP programs.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810119273.6A CN108228900B (en) | 2018-02-06 | 2018-02-06 | Power equipment multispectral data center model building method based on hierarchical structure |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810119273.6A CN108228900B (en) | 2018-02-06 | 2018-02-06 | Power equipment multispectral data center model building method based on hierarchical structure |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108228900A CN108228900A (en) | 2018-06-29 |
| CN108228900B true CN108228900B (en) | 2021-12-24 |
Family
ID=62669732
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810119273.6A Active CN108228900B (en) | 2018-02-06 | 2018-02-06 | Power equipment multispectral data center model building method based on hierarchical structure |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108228900B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109272232A (en) * | 2018-09-21 | 2019-01-25 | 国家电网有限公司 | Visualized data management method based on substation's fining inspection business |
| CN109546684B (en) * | 2018-12-18 | 2024-04-02 | 辽宁恒顺新能源科技有限公司 | Micro-grid power supply system |
| CN113222211B (en) * | 2021-03-31 | 2023-12-12 | 中国科学技术大学先进技术研究院 | Method and system for predicting pollutant emission factors of multi-region diesel vehicle |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102968620A (en) * | 2012-11-16 | 2013-03-13 | 华中科技大学 | Scene recognition method based on layered Gaussian hybrid model |
| CN103218796A (en) * | 2013-05-14 | 2013-07-24 | 中国科学院自动化研究所 | Fusion method of full color-multispectral remote sensing images |
| CN104573654A (en) * | 2015-01-08 | 2015-04-29 | 中国林业科学研究院资源信息研究所 | Mangrove extraction method based on hierarchical decision tree |
| CN107248149A (en) * | 2017-05-31 | 2017-10-13 | 浙江国遥地理信息技术有限公司 | Methods on Multi-Sensors RS Image fusion method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6654634B2 (en) * | 2014-12-03 | 2020-02-26 | ベンタナ メディカル システムズ， インコーポレイテッド | Methods, systems and devices for quantitatively analyzing heterogeneous biomarker distributions |
-
2018
- 2018-02-06 CN CN201810119273.6A patent/CN108228900B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102968620A (en) * | 2012-11-16 | 2013-03-13 | 华中科技大学 | Scene recognition method based on layered Gaussian hybrid model |
| CN103218796A (en) * | 2013-05-14 | 2013-07-24 | 中国科学院自动化研究所 | Fusion method of full color-multispectral remote sensing images |
| CN104573654A (en) * | 2015-01-08 | 2015-04-29 | 中国林业科学研究院资源信息研究所 | Mangrove extraction method based on hierarchical decision tree |
| CN107248149A (en) * | 2017-05-31 | 2017-10-13 | 浙江国遥地理信息技术有限公司 | Methods on Multi-Sensors RS Image fusion method |
Non-Patent Citations (2)
| Title |
|---|
| "Optimal coinfection control of competitive epidemics in multi-layer networks";Ximing Chen et al.;《IEEE Conference on Decision and Control》;20150212;第6209-6214页 * |
| "应用多光谱图像融合的电力设备故障点检测方法";宋文洋;《万方数据知识服务平台》;20141013;第1-64页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108228900A (en) | 2018-06-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Huang et al. | An edge computing framework for real-time monitoring in smart grid | |
| CN106584450B (en) | A kind of Intelligent Mobile Robot centralized monitoring system and method | |
| CN108985531A (en) | A kind of multimode isomery electric power big data convergence analysis management system and method | |
| CN117240887B (en) | Wisdom thing networking energy management platform system | |
| CN108228900B (en) | Power equipment multispectral data center model building method based on hierarchical structure | |
| CN106532951A (en) | Transformer substation monitoring system | |
| CN104113596A (en) | Cloud monitoring system and method for private cloud | |
| Shoukat et al. | Smart home for enhanced healthcare: exploring human machine interface oriented digital twin model | |
| CN105069025A (en) | Intelligent aggregation visualization and management and control system for big data | |
| CN110851228B (en) | Complex event visualization arrangement processing system and method | |
| CN111208384A (en) | Smart power grid management system | |
| CN115908046A (en) | Visual power distribution system based on airport terminal building BIM | |
| CN110942287A (en) | Architecture of building brain | |
| CN115511656A (en) | Demand planning auxiliary decision system based on mining power grid data value | |
| CN113239759A (en) | Power grid operation field violation identification method | |
| Wang et al. | Research on intelligent monitoring and maintenance technology of substation based on digital twin | |
| CN114968981A (en) | Big data platform system based on power grid data and data processing method thereof | |
| Ju et al. | The use of edge computing-based internet of things big data in the design of power intelligent management and control platform | |
| CN117390590B (en) | CIM model-based data management method and system | |
| CN114722565A (en) | Meta-universe digital twin system | |
| WO2019104952A1 (en) | Scene intelligent analysis system and method based on metropolitan area level internet of things perceptual data | |
| CN116912774A (en) | Infrared image target identification method, electronic device and storage medium of power transmission and transformation equipment based on edge calculation | |
| CN110096042A (en) | Artificial swamp monitors methods of exhibiting and system on-line | |
| Long et al. | 6G comprehensive intelligence: network operations and optimization based on Large Language Models | |
| CN107291766A (en) | Laterally specialty fusion, longitudinal province ground power network panoramic information display systems for running through of county |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |