CN117974071A

CN117974071A - Electric power system intelligent management method and device based on multidimensional analysis

Info

Publication number: CN117974071A
Application number: CN202410370559.7A
Authority: CN
Inventors: 黄烈江; 夏明明; 沈狄龙; 吕渭; 冯伟烽; 胡晨烽; 来国海
Original assignee: Hangzhou Electric Power Equipment Manufacturing Co ltd Xiaoshan Xin Mei Complete Set Of Electrical Manufacturing Branch; Hangzhou Xinmei Electrical Equipment Manufacturing Co ltd
Current assignee: Hangzhou Electric Power Equipment Manufacturing Co ltd Xiaoshan Xin Mei Complete Set Of Electrical Manufacturing Branch; Hangzhou Xinmei Electrical Equipment Manufacturing Co ltd
Priority date: 2024-03-29
Filing date: 2024-03-29
Publication date: 2024-05-03

Abstract

The application provides an intelligent management method and device for an electric power system based on multidimensional analysis, wherein the method comprises the following steps: acquiring equipment information, operation information, environmental information of the environment where the equipment is located and historical fault conditions of a plurality of electrical equipment in an electric power system, wherein the operation information comprises a first operation temperature, equipment images and equipment deformation parameters; determining equipment stability parameters of each electrical equipment based on the equipment information of the plurality of electrical equipment and historical fault conditions; determining a fault prediction parameter of each electrical device based on the operation information of the plurality of electrical devices and the environmental information of the environment, wherein the fault prediction parameter comprises a plurality of candidate faults and risk values of each candidate fault, and the risk values are used for representing the possibility of occurrence of the corresponding candidate faults; a target electrical device is determined from the plurality of electrical devices based on the device stability parameters and the fault prediction parameters of each of the electrical devices.

Description

Electric power system intelligent management method and device based on multidimensional analysis

Technical Field

The application relates to the technical field of computers, in particular to an intelligent management method and device for an electric power system based on multidimensional analysis.

Background

In order to ensure the power supply quality, in the process of supplying power by using the power system, the electrical equipment in the power system is usually required to be managed and maintained manually so as to ensure the normal operation of the electrical equipment, thereby improving the power supply quality.

In the related art, a technician typically periodically maintains and manages electrical equipment in an electrical power system on a shift schedule. However, in this manner, technicians have no purpose, resulting in poor efficiency and effectiveness in managing and maintaining the power system, and thus, a more intelligent method for managing the power system is needed.

Disclosure of Invention

The embodiment of the application provides a power system intelligent management method and device based on multidimensional analysis, which can improve the efficiency and effect of maintaining a power system, and the technical scheme is as follows:

In one aspect, a method for intelligent management of a power system based on multidimensional analysis is provided, the method comprising:

Acquiring equipment information, operation information, environmental information of the environment where the equipment is located and historical fault conditions of a plurality of pieces of electrical equipment in an electric power system, wherein the operation information comprises a first operation temperature, equipment images and equipment deformation parameters, and the first operation temperature is the temperature measured by a contact sensor;

Determining equipment stability parameters of the electrical equipment based on the equipment information of the plurality of electrical equipment and the historical fault conditions, wherein the equipment stability parameters are used for representing the stability of the corresponding electrical equipment;

Determining a fault prediction parameter of each electrical device based on the operation information of the plurality of electrical devices and the environmental information of the environment, wherein the fault prediction parameter comprises a plurality of candidate faults and risk values of each candidate fault, and the risk values are used for representing the possibility of occurrence of the corresponding candidate faults;

And determining a target electrical device from the plurality of electrical devices based on the device stability parameter and the fault prediction parameter of each electrical device, wherein the target electrical device is the electrical device needing maintenance.

In one aspect, there is provided a power system intelligent management device based on multidimensional analysis, the device comprising:

The information acquisition module is used for acquiring equipment information, operation information, environmental information of the environment where the equipment is located and historical fault conditions of a plurality of pieces of electrical equipment in the power system, wherein the operation information comprises a first operation temperature, equipment images and equipment deformation parameters, and the first operation temperature is the temperature measured by the contact sensor;

A first parameter determining module, configured to determine, based on device information of the plurality of electrical devices and historical fault conditions, a device stability parameter of each electrical device, where the device stability parameter is used to represent stability of a corresponding electrical device;

A second parameter determining module, configured to determine, based on operation information of the plurality of electrical devices and environmental information of an environment in which the electrical devices are located, a fault prediction parameter of each of the electrical devices, where the fault prediction parameter includes a plurality of candidate faults and a risk value of each of the candidate faults, where the risk value is used to represent a likelihood of occurrence of a corresponding candidate fault;

And the equipment determining module is used for determining target electrical equipment from the plurality of electrical equipment based on equipment stability parameters and fault prediction parameters of the electrical equipment, wherein the target electrical equipment is the electrical equipment which needs maintenance.

In one possible implementation manner, the device information includes a device type, device structure information and device connection information, and the first parameter determining module is configured to determine, based on the device type and the device structure information of each of the electrical devices, a first device reliability parameter of each of the electrical devices, where the first device reliability parameter is used to represent individual reliability of the corresponding electrical device, and the device structure information is used to represent a structural framework adopted by the corresponding electrical device; determining a second equipment reliability parameter of each electrical equipment based on the first equipment reliability parameter of each electrical equipment and equipment connection information, wherein the second equipment reliability parameter is used for representing group reliability of an electrical equipment group where the corresponding electrical equipment is located, the equipment connection information is used for indicating other electrical equipment connected with the corresponding electrical equipment, and the equipment connection information is used for determining the electrical equipment group where the electrical equipment is located; and determining the equipment stability parameters of the electrical equipment based on the first equipment reliability parameters, the second equipment reliability parameters and the historical fault conditions of the electrical equipment.

In a possible implementation manner, the historical fault condition includes a historical fault time, a historical fault type and a fault elimination duration, and the first parameter determining module is configured to fuse a first device reliability parameter and a second device reliability parameter of each electrical device by adopting the following formula to obtain a comprehensive device reliability parameter of each electrical device;

Wherein/> For the first reliability parameter,/>For the second reliability parameter,/>For integrating device reliability parameters,/>、/>/>Is a constant;

determining fault risk parameters of the electrical equipment based on the historical fault time, the historical fault type, the fault elimination duration and the accumulated working duration of the electrical equipment; and determining the equipment stability parameters of the electrical equipment based on the comprehensive equipment reliability parameters and the fault risk parameters.

In a possible implementation manner, the second parameter determining module is configured to determine an own fault risk parameter of each electrical device based on operation information of each electrical device; determining environmental fault risk parameters of the electrical equipment based on environmental information of the environments of the electrical equipment; and carrying out fault prediction by adopting the self fault risk parameters and the environment fault risk parameters of the electric equipment to obtain a plurality of candidate faults of the electric equipment and risk values of the candidate faults.

In one possible implementation, the device images include a grayscale device image, an infrared device image, and a visible light device image, and the second parameter determining module is configured to determine a second operating temperature of each of the electrical devices based on the grayscale device image, the infrared device image, and the visible light device image of each of the electrical devices; fusing the first operating temperature and the second operating temperature of each electrical device to obtain a third operating temperature of each electrical device; and determining the self fault risk parameter of each electrical device based on the third operating temperature and the device deformation parameter of each electrical device.

In one possible implementation manner, the second parameter determining module is configured to input a gray scale device image, an infrared device image and a visible light device image of each electrical device into a temperature prediction model, and perform feature extraction on the gray scale device image, the infrared device image and the visible light device image through the temperature prediction model to obtain a gray scale image feature, an infrared image feature and a visible light image feature; mapping the gray image features, the infrared image features and the visible light image features to obtain second operation temperatures of a plurality of positions on each electrical device; and determining an average value of the first operating temperature and the second operating temperature of a plurality of positions on each electrical device as a third operating temperature of the plurality of positions on each electrical device.

In one possible implementation manner, the second parameter determining module is configured to generate, for any one of the plurality of electrical devices, a temperature distribution parameter of the electrical device based on third operating temperatures of a plurality of locations on the electrical device, where the temperature distribution parameter is used to reflect a temperature distribution situation of the corresponding electrical device; and determining the self fault risk parameter of the electrical equipment based on the temperature distribution parameter and the equipment deformation parameter of the electrical equipment.

In a possible implementation manner, the second parameter determining module is configured to perform weighted fusion on the self-fault risk parameters and the environmental fault risk parameters of each electrical device to obtain fused fault risk parameters of each electrical device; inputting the fusion fault risk parameters of each electrical device into a risk value prediction model, and extracting features of the fusion fault risk parameters of each electrical device through the risk value prediction model to obtain fault risk features of each electrical device; performing full connection and normalization on fault risk characteristics of each electrical device, and outputting probability sets of each electrical device, wherein each probability set comprises a plurality of probabilities, and one probability corresponds to one reference fault; and determining a plurality of candidate faults from a plurality of reference faults based on probability sets of the electrical equipment, and determining the probability corresponding to the candidate faults in the probability sets as a risk value of the candidate faults.

In one possible implementation manner, the device determining module is configured to determine a maintenance parameter of each electrical device, based on a device stability parameter and a fault prediction parameter of each electrical device, where the maintenance parameter is used to represent a maintenance necessity level of the corresponding electrical device; and determining an electrical device with the maintenance parameter being greater than or equal to a maintenance parameter threshold value in the plurality of electrical devices as a target electrical device.

In one aspect, an electronic device is provided that includes one or more processors and one or more memories having at least one computer program stored therein, the computer program loaded and executed by the one or more processors to implement the multi-dimensional analysis-based power system intelligent management method.

In one aspect, a computer readable storage medium is provided, in which at least one computer program is stored, the computer program being loaded and executed by a processor to implement the multi-dimensional analysis-based power system intelligent management method.

In one aspect, a computer program product or a computer program is provided, the computer program product or the computer program comprising a program code, the program code being stored in a computer readable storage medium, a processor of an electronic device reading the program code from the computer readable storage medium, the processor executing the program code, causing the electronic device to perform the above-described power system intelligent management method based on multi-dimensional analysis.

By the technical scheme provided by the embodiment of the application, equipment information, operation information, environmental information of the environment where the equipment is located and historical fault conditions of a plurality of electrical equipment in the power system can be obtained, namely, data related to the electrical equipment are obtained, the operation information comprises a first operation temperature, equipment images and equipment deformation parameters, and the first operation temperature is the temperature measured by the contact sensor. Based on the device information of the plurality of electrical devices and the historical fault conditions, device stability parameters of the respective electrical devices are determined, the device stability parameters being indicative of stability of the corresponding electrical devices. Based on the operation information of the plurality of electrical devices and the environmental information of the environment, determining the fault prediction parameters of the electrical devices, wherein the fault prediction parameters can reflect potential faults and fault risks of the corresponding electrical devices. And determining target electrical equipment, namely the electrical equipment which needs to be maintained, from the plurality of electrical equipment based on the equipment stability parameters and the fault prediction parameters of each electrical equipment, so that the equipment maintenance target is defined for technicians, and the efficiency and the effect of the electrical equipment maintenance are improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic diagram of an implementation environment of a power system intelligent management method based on multidimensional analysis according to an embodiment of the present application;

FIG. 2 is a flowchart of a method for intelligent management of an electric power system based on multidimensional analysis according to an embodiment of the present application;

FIG. 3 is a flowchart of another intelligent management method for a power system based on multidimensional analysis according to an embodiment of the present application;

Fig. 4 is a schematic structural diagram of an intelligent management device for an electric power system based on multidimensional analysis according to an embodiment of the present application;

fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments can be embodied in many forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. The same reference numerals in the drawings denote the same or similar structures, and thus detailed descriptions thereof will be omitted.

The terms "a," "an," "the," and "said" are used to indicate the presence of one or more elements/components/etc.; the terms "comprising" and "having" are intended to be inclusive and mean that there may be additional elements/components/etc. in addition to the listed elements/components/etc.

In order to describe the technical solution provided by the embodiments of the present application, the nouns related to the embodiments of the present application are described below.

An electric power system: the power generation system is integrated with secondary facilities such as power generation, power supply (power transmission, power transformation and power distribution), power utilization facilities, regulation control and relay protection and safety automatic devices, metering devices, dispatching automation, power communication and the like which are required for guaranteeing the normal operation of the power utilization facilities.

An electrical device: in a power system, devices such as a generator, a transformer, a power line, and a circuit breaker are collectively referred to.

Machine learning (MACHINE LEARNING, ML) is a multi-domain interdisciplinary, involving multiple disciplines such as probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory, and the like. It is specially studied how a computer simulates or implements the learning behavior of a human to acquire new knowledge or skills, reorganizing existing knowledge sub-models to continuously improve its own performance. Machine learning is the core of artificial intelligence, a fundamental approach to letting computers have intelligence, which is applied throughout various areas of artificial intelligence. Machine learning and deep learning typically include techniques such as artificial neural networks, belief networks, reinforcement learning, transfer learning, induction learning, teaching learning, and the like.

Normalization: and the number sequences with different value ranges are mapped to the (0, 1) interval, so that the data processing is facilitated. In some cases, the normalized value may be directly implemented as a probability.

The following describes an implementation environment of an embodiment of the present application.

Fig. 1 is a schematic diagram of an implementation environment of a power system intelligent management method based on multidimensional analysis according to an embodiment of the present application, referring to fig. 1, the implementation environment may include a terminal 110 and a server 140.

Terminal 110 is connected to server 140 via a wireless network or a wired network. Alternatively, the terminal 110 is a notebook computer, a desktop computer, or the like, but is not limited thereto. The terminal 110 is a terminal used by a monitoring center of the power system, the terminal 110 is connected with a plurality of sensors in the power system, the data collected by the sensors can be obtained, and the sensors are used for collecting data related to electrical equipment in the power system. The terminal 110 has installed thereon an application program supporting the determination of the electrical device.

The server 140 is an independent physical server, or a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, a distribution network (Content Delivery Network, CDN), basic cloud computing services such as big data and artificial intelligence platforms, and the like.

In the embodiment of the present application, the technical solution provided in the embodiment of the present application may be implemented by a server or a terminal as an execution body, or the technical method provided in the present application may be implemented by interaction between the terminal and the server, which is not limited in the embodiment of the present application.

After the implementation environment of the embodiment of the present application is described, the application scenario of the embodiment of the present application is described below. The technical scheme provided by the embodiment of the application can be applied to the scene of monitoring the electric power system, and after the technical scheme provided by the embodiment of the application is adopted, the terminal or the server can acquire the equipment information, the operation information, the environmental information of the environment where the plurality of electric equipment are positioned and the historical fault condition of the electric power system, namely the data related to the electric equipment are acquired, wherein the operation information comprises a first operation temperature, an equipment image and equipment deformation parameters, and the first operation temperature is the temperature measured by the contact sensor. The terminal or the server determines, based on the device information of the plurality of electrical devices and the historical fault conditions, a device stability parameter of each electrical device, the device stability parameter being capable of representing the stability of the corresponding electrical device. The terminal or the server determines a fault prediction parameter of each electrical device based on the operation information of the plurality of electrical devices and the environmental information of the environment where the plurality of electrical devices are located, wherein the fault prediction parameter can reflect potential faults and fault risks of the corresponding electrical devices. The terminal or the server determines the target electrical equipment from the plurality of electrical equipment based on equipment stability parameters and fault prediction parameters of each electrical equipment, wherein the target electrical equipment is the electrical equipment which needs to be maintained, the equipment maintenance target is defined for technicians, and the efficiency and the effect of the electrical equipment maintenance are improved.

After the application scenario of the embodiment of the application is introduced, the power system intelligent management method based on multidimensional analysis provided by the embodiment of the application is described below. Fig. 2 is a flowchart of a power system intelligent management method based on multidimensional analysis according to an embodiment of the present application, referring to fig. 2, taking an execution subject as a server as an example, the method includes the following steps.

The power system is a power system which needs to be monitored, and the power system is selected by technicians according to requirements. The plurality of electrical devices are components that make up the electrical power system. The device information of the electrical device is used to represent an attribute of the electrical device, that is, a parameter of the corresponding electrical device that is not normally changed in the electrical power system. The operation information of the electrical equipment is used to indicate the operation of the electrical equipment. The historical fault condition is used to represent a condition in which the electrical device has historically failed. A touch sensor refers to a sensor that requires contact with a measurement potential to measure temperature.

Wherein the device stability parameter of the electrical device is used to represent the stability of the corresponding electrical device, in some embodiments the device stability parameter is positively correlated with the stability, i.e. the higher the device stability parameter, the higher the stability; the lower the device stability parameter, the lower the stability.

The environment information is used for representing the environment condition of the environment where the electrical equipment is located. The candidate fault refers to a fault that may occur to the electrical device, and the risk value of the candidate fault is used to indicate the possibility of occurrence of the corresponding candidate fault, in other words, the higher the risk value, the higher the possibility of occurrence of the corresponding candidate fault; the lower the risk value, the lower the likelihood of occurrence of the corresponding candidate fault.

The multidimensional analysis in the application is to analyze equipment information, operation information, environmental information of the environment where the electrical equipment is located and historical fault conditions, so as to finally determine the target electrical equipment to be maintained.

The steps 201 to 204 are a simple introduction of the method for intelligent management of a power system based on multi-dimensional analysis according to the embodiment of the present application, and the method for intelligent management of a power system based on multi-dimensional analysis according to the embodiment of the present application will be described more clearly with reference to fig. 3, taking an execution subject as a server as an example, and includes the following steps.

The power system is a power system which needs to be monitored, and the power system is selected by technicians according to requirements. The plurality of electrical devices are components that make up the electrical power system. The device information of the electrical device is used to represent an attribute of the electrical device, that is, a parameter of the corresponding electrical device that is not normally changed in the electrical power system. The operation information of the electrical equipment is used to indicate the operation of the electrical equipment. The historical fault condition is used to represent a condition in which the electrical device has historically failed. A touch sensor refers to a sensor that requires contact with a measurement potential to measure temperature. The device deformation parameter is used to indicate the degree of deformation of the electrical device, for example, for a cable, the device deformation parameter is used to indicate the degree of bending and expansion of the cable, which is typically related to the temperature of the cable. It should be noted that, in the embodiment of the present application, the plurality of electrical devices in the electrical power system may not be all the electrical devices in the electrical power system, and the plurality of electrical devices are electrical devices selected by a technician according to actual situations and requirements.

In one possible implementation, a server obtains device identifications of a plurality of electrical devices in a power system. The server obtains device information, operation information, environmental information of the environment in which the plurality of electrical devices are located, and historical fault conditions from a device database based on device identifications of the respective electrical devices.

Wherein, the equipment database stores the relevant information of a plurality of electric equipment in the power system. In the case of equipment information, operating information, environmental information of the environment in which the equipment is located, and historical fault conditions, the equipment information and the historical fault conditions are uploaded into the equipment database by a technician, and the operating information and the environmental information are measured by sensors installed on the electrical equipment. In some embodiments, the power system is divided into a plurality of subsystems, each subsystem includes a part of electrical devices in the plurality of electrical devices, each subsystem corresponds to a system maintenance terminal, and the system maintenance terminal can acquire device information, operation information, environmental information of an environment where the electrical device is located and historical fault conditions of the electrical device in the corresponding subsystem, and upload the device information, the operation information, the environmental information of the environment where the electrical device is located and the historical fault conditions to the device database. In some embodiments, the above-described subsystem is also referred to as an electrical equipment group.

In the embodiment, the equipment information, the operation information, the environmental information of the environment where the equipment is located and the historical fault condition of the electrical equipment can be obtained by inquiring the equipment identification of the electrical equipment in the equipment database, so that the efficiency of information acquisition is high.

It should be noted that, because the operation amount of the power system intelligent management method based on the multi-dimensional analysis provided by the embodiment of the application is large, more operation resources and time are required to be consumed, the power system intelligent management method based on the multi-dimensional analysis is periodically executed or triggered and executed by technicians in the process of actually adopting the power system intelligent management method based on the multi-dimensional analysis provided by the embodiment of the application.

The manner in which the operation information of the electrical device is measured will be described below.

In some embodiments, for a first operating temperature in the operating information, the first operating temperature is measured by a touch sensor mounted on the electrical device, the touch sensor being referred to as a touch temperature sensor. In the embodiment of the present application, the first operating temperature of the electrical device refers to a first operating temperature of a plurality of positions on the electrical device, that is, a plurality of contact temperature sensors are installed on the electrical device, and the installation positions of the plurality of contact temperature sensors on the electrical device are set by a technician according to actual situations. Without the intelligent management method for the electric power system based on the multidimensional analysis provided by the embodiment of the application, the first operating temperature can be adopted to realize simple monitoring of the electric equipment.

In some embodiments, for the device image in the operation information, an image acquisition device is installed around the electrical device, through which the device image of the electrical device can be acquired. In the embodiment of the application, the equipment images comprise gray equipment images, infrared equipment images and visible light equipment images, wherein the gray equipment images and the visible light equipment images are acquired through a visible light image acquisition device, and the infrared equipment images are acquired through an infrared image acquisition device.

In some embodiments, for the device deformation parameters in the operation information, a deformation sensor is mounted on the electrical device, and the deformation sensor can be used to measure the device deformation parameters of the electrical device. In some embodiments, a plurality of deformation sensors are installed on the electrical equipment, so that deformation parameters of a plurality of positions on the electrical equipment are measured, and the deformation parameters of the plurality of positions are fused to obtain equipment deformation parameters of the electrical equipment. For example, the deformation parameters of the plurality of positions are weighted and summed to obtain the deformation parameters of the equipment of the electrical equipment, and weights of the plurality of positions in the weighted and summed are set by a technician according to actual conditions, which is not limited by the embodiment of the application.

The manner of measuring the environmental information of the environment in which the electrical apparatus is located is described below.

In some embodiments, the environmental information includes an ambient temperature, an ambient humidity, and an ambient weather type, wherein the ambient temperature and the ambient humidity are measured by a temperature sensor and a humidity sensor, respectively, and the ambient weather type is queried in a weather database based on a location of the electrical device.

Wherein the device stability parameter of the electrical device is used to indicate the stability of the corresponding electrical device, in some embodiments the device stability parameter is positively correlated with the stability, i.e. the higher the device stability parameter, the higher the stability. The lower the device stability parameter, the lower the stability.

In one possible implementation, the device information includes device type, device configuration information, and device connection information. The server determines a first device reliability parameter of each electrical device based on a device type of each electrical device and device configuration information, the first device reliability parameter being used to represent individual reliability of the corresponding electrical device, the device configuration information being used to represent a configuration framework employed by the corresponding electrical device. The server determines a second device reliability parameter of each electrical device based on the first device reliability parameter of each electrical device and device connection information, wherein the second device reliability parameter is used for representing group reliability of an electrical device group where a corresponding electrical device is located, the device connection information is used for indicating other electrical devices connected with the corresponding electrical device, and the device connection information is used for determining the electrical device group where the electrical device is located. The server determines device stability parameters for each of the electrical devices based on the first device reliability parameters, the second device reliability parameters, and the historical fault conditions for each of the electrical devices.

Wherein the first device reliability parameter is used to represent an individual reliability of the corresponding electrical device, the individual reliability representing a reliability of the electrical device when operating alone. The structural framework adopted by the electrical equipment is used for reflecting the basic structure of the electrical equipment, and the basic structure can reflect the technical route adopted by the electrical equipment to a certain extent, so that the individual reliability of the electrical equipment is reflected. In some embodiments, the first device reliability parameter is positively correlated with the individual reliability, i.e., the higher the first device reliability parameter, the higher the individual reliability; the lower the first device reliability parameter, the lower the individual reliability. The device connection information is used to reflect the device connection condition of the electrical device, that is, other electrical devices connected to the electrical device. In the embodiment of the application, the device connection information includes direct connection information and indirect connection information, the direct connection information is used for reflecting other electrical devices directly connected with the electrical device, and the indirect connection information is used for reflecting other electrical devices indirectly connected with the electrical device. The second equipment reliability parameter is used for indicating group reliability of the electric equipment group where the corresponding electric equipment is located, and the group reliability indicates reliability when the electric equipment and other electric equipment in the electric equipment group operate together. In some embodiments, the second device reliability parameter is positively correlated with the group reliability, i.e., the higher the second device reliability parameter, the higher the group reliability; the lower the second device reliability parameter, the lower the population reliability. The historical fault condition is used to reflect a fault that has occurred when the electrical device is operating, and of course, if one electrical device has not failed, the historical fault condition may be empty.

In this embodiment, the first device reliability parameter and the second device reliability parameter of the electrical device are determined by using the device information, and the device stability parameter is determined by using the first device reliability parameter, the second device reliability parameter and the historical fault condition, so that the accuracy of the device stability parameter is high.

In order to more clearly describe the above embodiments, the above embodiments will be described below in sections.

The first portion, the server, determines a first device reliability parameter for each electrical device based on the device type and device configuration information for each electrical device.

In one possible implementation manner, for any one of a plurality of electrical devices, the server queries based on the device type and the device structure information of the electrical device, and obtains a failure rate corresponding to the device type and the device structure information. The server determines the failure rate as a first device reliability parameter for the electrical device.

The query may be performed in an equipment database, where failure rates corresponding to combinations of different equipment types and equipment structure information are stored.

In this embodiment, the first device reliability parameter of the electrical device can be obtained by querying the device type and the device structure information of the electrical device, which is efficient.

The second portion, the server, determines a second device reliability parameter for each electrical device based on the first device reliability parameter and the device connection information for each electrical device.

In one possible implementation, the server generates a device graph network for each electrical device based on the first device reliability parameter and the device connection information for each electrical device, the device graph network including a plurality of device nodes representing other electrical devices connected directly or indirectly to the corresponding electrical device, the device nodes being characterized by the first device reliability parameter for the corresponding other electrical device. And the server carries out graph convolution on the equipment graph network of each piece of electric equipment to obtain second equipment reliability parameters of each piece of electric equipment.

In this embodiment, the first device reliability parameter and the device connection information of each electrical device are used to generate the device map network of each electrical device, and the second device reliability parameter is obtained based on the device map network, so that accuracy is high.

For example, for any one of a plurality of electrical devices, the server determines a plurality of other electrical devices directly and indirectly connected to the electrical device based on device connection information of the electrical device. The server generates a device node corresponding to the electrical device and device nodes corresponding to the plurality of other electrical devices. And the server adds connection lines between equipment nodes corresponding to the electrical equipment and equipment nodes corresponding to the plurality of other electrical equipment based on the equipment connection information of the electrical equipment to form an equipment graph network of the electrical equipment. And the server carries out graph convolution on the equipment graph network of the electrical equipment to obtain the second equipment reliability parameter of the electrical equipment.

The third portion, the server, determines device stability parameters for each of the electrical devices based on the first device reliability parameters, the second device reliability parameters, and the historical fault conditions for each of the electrical devices.

In one possible implementation manner, the historical fault condition includes a historical fault time, a historical fault type and a fault elimination duration, and the server uses the following formula (1) to fuse the first device reliability parameter and the second device reliability parameter of each electrical device to obtain the comprehensive device reliability parameter of each electrical device. The server determines fault risk parameters of each electrical device based on the historical fault time, the historical fault type, the fault elimination duration and the accumulated working duration of each electrical device. The server determines equipment stability parameters of each electrical equipment based on the comprehensive equipment reliability parameters and the fault risk parameters;

（1）

Wherein, For the first reliability parameter,/>For the second reliability parameter,/>For integrating device reliability parameters,/>、/>/>Is constant. /(I)、/>/>The setting and adjustment are performed by the skilled person according to the actual situation, and the embodiment of the present application is not limited thereto.

In order to more clearly describe the above embodiments, a method of determining the failure risk parameter and the equipment stability parameter in the above embodiments will be described below in two parts, respectively.

The first part and the server determine fault risk parameters of the electric equipment based on the historical fault time, the historical fault type, the fault elimination duration and the accumulated working duration of the electric equipment.

In one possible implementation manner, the server inputs the historical fault time, the historical fault type, the fault elimination duration and the accumulated working duration of each electrical device into a risk parameter prediction model, and the risk parameter prediction model is used for extracting features of the historical fault time, the historical fault type, the fault elimination duration and the accumulated working duration of each electrical device to obtain fault risk features of each electrical device. And the server carries out full connection and normalization on the fault risk characteristics of each electrical device through a risk parameter prediction model to obtain the fault risk parameters of each electrical device.

The second portion, the server, determines device stability parameters for each electrical device based on the integrated device reliability parameters and the fault risk parameters.

In one possible implementation, the server fuses the integrated device reliability parameter and the fault risk parameter to obtain the device stability parameter of each electrical device.

For example, for any one of a plurality of electrical devices, the server fuses the integrated device reliability parameter of the electrical device and the fault risk parameter by the following formula (2) to obtain a device stability parameter of the electrical device;

（2）

Wherein, For integrating device reliability parameters,/>Is a fault risk parameter,/>/>Is constant. In some embodiments,/>/>The setting and adjustment are performed by the skilled person according to the actual situation, and the embodiment of the present application is not limited thereto.

303. The server determines own fault risk parameters of the respective electrical devices based on the operation information of the respective electrical devices.

The device images comprise gray device images, infrared device images and visible light device images, and the gray device images are obtained by gray processing the visible light device images.

In one possible embodiment, the server determines the second operating temperature of each electrical device based on the grayscale device image, the infrared device image, and the visible light device image of each electrical device. And the server fuses the first operation temperature and the second operation temperature of each electrical device to obtain a third operation temperature of each electrical device. The server determines own fault risk parameters for each electrical device based on the third operating temperature and the device deformation parameters for each electrical device.

In this embodiment, the device image is used to determine a second operating temperature of the electrical device. And fusing the first operating temperature and the second operating temperature of the electrical equipment to obtain a third operating temperature of the electrical equipment. And obtaining the self fault risk parameter of the electrical equipment based on the third operation temperature of the electrical equipment and the equipment deformation parameter.

The first portion, the server, determines a second operating temperature for each of the electrical devices based on the grayscale device image, the infrared device image, and the visible light device image for each of the electrical devices.

In one possible implementation, the server inputs the grayscale device image, the infrared device image, and the visible light device image of each electrical device into a temperature prediction model, and performs feature extraction on the grayscale device image, the infrared device image, and the visible light device image through the temperature prediction model to obtain grayscale image features, infrared image features, and visible light image features. The server maps the gray image feature, the infrared image feature and the visible light image feature through the temperature prediction model to obtain second operation temperatures of a plurality of positions on each electric device.

The temperature prediction model belongs to an image recognition model, and can determine the temperature according to images. The second operating temperature is also referred to as the non-contact operating temperature.

In the embodiment, the temperature prediction model predicts the gray scale device image, the infrared device image and the visible light device image of the electrical device, so that the second operation temperature of the electrical device is obtained, and the accuracy is high.

For example, for any one of a plurality of electrical devices, the server inputs a grayscale device image, an infrared device image, and a visible light device image of the electrical device into the temperature prediction model. And the server convolves the gray scale device image, the infrared device image and the visible light device image at least once through the temperature prediction model to obtain gray scale image features, infrared image features and visible light image features. And the server performs full-connection normalization on the gray level image features, the infrared image features and the visible light image features through the temperature prediction model to obtain a first prediction temperature corresponding to the gray level equipment image, a second prediction temperature corresponding to the infrared equipment image and a third prediction temperature corresponding to the visible light equipment image. And the server performs weighted summation on the first predicted temperature, the second predicted temperature and the third predicted temperature to obtain a second running temperature of the electrical equipment.

Wherein the first predicted temperature of the electrical device is a first predicted temperature of a plurality of locations on the electrical device; the second predicted temperature of the electrical device refers to the second predicted temperature of the plurality of locations on the electrical device; the third predicted temperature of the electrical device refers to the third predicted temperature of the plurality of locations on the electrical device. Accordingly, the second operating temperature of the electrical device refers to the second operating temperature of the plurality of locations on the electrical device. The weights for performing weighted summation on the first predicted temperature, the second predicted temperature and the third predicted temperature are weights of a gray scale device image, an infrared device image and a visible light device image, and the weights are set by a technician according to actual conditions, which is not limited in the embodiment of the present application. For any one of a plurality of locations on the electrical device, a second operating temperature for the location is a weighted sum of a first predicted temperature for the location, the second predicted temperature, and the third predicted temperature.

And the second part and the server fuse the first operation temperature and the second operation temperature of each electrical device to obtain a third operation temperature of each electrical device.

The first operating temperature of the electrical equipment refers to the first operating temperature of a plurality of positions on the electrical equipment, and the second operating temperature refers to the second operating temperature of a plurality of positions on the electrical equipment.

In one possible embodiment, the server determines an average of the first operating temperature and the second operating temperature for the plurality of locations on each electrical device as a third operating temperature for the plurality of locations on each electrical device.

The third portion, the server, determines self-failure risk parameters for each of the electrical devices based on the third operating temperature and the device deformation parameters for each of the electrical devices.

In one possible embodiment, for any one of the plurality of electrical devices, the server generates a temperature distribution parameter for the electrical device based on a third operating temperature for a plurality of locations on the electrical device, the temperature distribution parameter being used to reflect a temperature distribution of the corresponding electrical device. The server determines a self-failure risk parameter of the electrical device based on the temperature distribution parameter and the device deformation parameter of the electrical device.

Wherein the temperature distribution parameter comprises a third operating temperature at a plurality of locations on the electrical device, and wherein a correspondence between the locations and the third operating temperature is substantially recorded.

In order to more clearly describe the above embodiment, a method for determining the self-failure risk parameter of the electrical device based on the temperature distribution parameter and the device deformation parameter of the electrical device in the above embodiment will be described below.

In some embodiments, the server inputs the temperature distribution parameters and the deformation parameters of the electrical equipment into a self-fault risk prediction model, and performs feature extraction on the temperature distribution parameters and the deformation parameters of the equipment through the self-fault risk prediction model to obtain self-fault risk features. And the server maps the self-fault risk characteristics through the self-fault risk prediction model and outputs self-fault risk parameters of the electrical equipment.

For example, the server inputs the temperature distribution parameters and the deformation parameters of the electrical equipment into a self-fault risk prediction model, and the self-fault risk prediction model encodes the temperature distribution parameters and the deformation parameters of the equipment based on an attention mechanism to obtain self-fault risk characteristics. And the server carries out full connection and normalization on the self-fault risk characteristics through the self-fault risk prediction model, and outputs self-fault risk parameters of the electrical equipment.

The environment information is used for representing the environment condition of the environment where the electrical equipment is located. The environmental information includes an ambient temperature, an ambient humidity, and an ambient weather type.

In one possible implementation, the server determines an ambient temperature interval in which the ambient temperature is located in the ambient information and an ambient humidity interval in which the ambient humidity is located. And the server queries based on the environmental temperature interval, the environmental humidity interval and the environmental weather type to obtain the environmental fault risk parameters of each electrical device.

The corresponding relation among the environmental temperature interval, the environmental humidity interval, the environmental weather type and the environmental fault risk parameter is set by a technician according to actual conditions, and the embodiment of the application is not limited to the above.

The candidate fault refers to a fault that may occur in the electrical apparatus, and the risk value of the candidate fault is used to indicate the possibility of occurrence of the corresponding candidate fault, in other words, the higher the risk value, the higher the possibility of occurrence of the corresponding candidate fault. The lower the risk value, the lower the likelihood of occurrence of the corresponding candidate fault. The risk values of a plurality of candidate faults of one electrical apparatus are collectively referred to as fault prediction parameters of the electrical apparatus.

In one possible implementation manner, the server performs weighted fusion on the self-fault risk parameters and the environment fault risk parameters of each electrical device to obtain fusion fault risk parameters of each electrical device. The server inputs the fusion fault risk parameters of each electrical device into a risk value prediction model, and the fusion fault risk parameters of each electrical device are extracted through the risk value prediction model to obtain the fault risk characteristics of each electrical device. The server carries out full connection and normalization on fault risk characteristics of each electrical device through the risk value prediction model, and outputs a probability set of each electrical device, wherein the probability set comprises a plurality of probabilities, and one probability corresponds to one reference fault. The server determines a plurality of candidate faults from a plurality of reference faults based on probability sets of the electric devices, and determines probabilities corresponding to the candidate faults in the probability sets as risk values of the candidate faults.

The multiple reference faults are a set of faults possibly generated by the electrical equipment, the multiple reference faults corresponding to the electrical equipment of different types are not identical, the multiple reference faults corresponding to the electrical equipment are set by a technician according to actual conditions, and the embodiment of the application is not limited to the above.

In order to more clearly describe the above embodiment, a method in which the server determines a plurality of candidate faults from a plurality of reference faults based on a probability set of each electrical device and determines a probability corresponding to the candidate fault in the probability set as a risk value of the candidate fault will be described below.

In some embodiments, for any one of a plurality of electrical devices, the server determines, based on a set of probabilities for the electrical device, a plurality of candidate faults from a plurality of reference faults corresponding to the electrical device, the candidate faults being reference candidate faults having probabilities greater than or equal to a probability threshold. And the server determines the probability corresponding to each candidate fault in the probability set as the risk value of each candidate fault. The probability threshold is set by a technician according to actual situations, which is not limited by the embodiment of the application.

In one possible embodiment, the server determines maintenance parameters of the respective electrical devices based on the device stability parameters and the failure prediction parameters of the respective electrical devices, the maintenance parameters being indicative of the maintenance necessity level of the corresponding electrical devices. The server determines an electrical device of the plurality of electrical devices having a maintenance parameter greater than or equal to a maintenance parameter threshold as a target electrical device.

The maintenance parameter threshold is set by a technician according to actual situations, which is not limited in the embodiment of the present application.

For example, for any one of the plurality of electrical devices, the server fuses the device stability parameter and the failure prediction parameter of the electrical device to obtain the reference maintenance parameter of the electrical device through the following formula (3). The server inputs the reference maintenance parameters of the electrical equipment into a maintenance parameter prediction model, and outputs the maintenance parameters of the electrical equipment through the maintenance parameter prediction model. The server determines an electrical device of the plurality of electrical devices, the maintenance parameter of which is greater than or equal to the maintenance parameter threshold, as a target electrical device;

（3）

Wherein, For reference maintenance parameters,/>For the equipment stability parameter,/>For the failure prediction parameters,/>、/>And is constant. In some embodiments,/>、/>/> The setting and adjustment are performed by the skilled person according to the actual situation, and the embodiment of the present application is not limited thereto.

Any combination of the above optional solutions may be adopted to form an optional embodiment of the present application, which is not described herein.

Fig. 4 is a schematic structural diagram of an intelligent management device for an electric power system based on multidimensional analysis according to an embodiment of the present application, referring to fig. 4, the device includes: an information acquisition module 401, a first parameter determination module 402, a second parameter determination module 403, and a device determination module 404.

The information acquisition module 401 is configured to acquire device information, operation information, environmental information of an environment where a plurality of electrical devices in the electrical power system are located, and historical fault conditions, where the operation information includes a first operation temperature, a device image, and a device deformation parameter, and the first operation temperature is a temperature measured by a contact sensor.

A first parameter determining module 402, configured to determine, based on the device information of the plurality of electrical devices and the historical fault conditions, a device stability parameter of each electrical device, where the device stability parameter is used to represent stability of a corresponding electrical device.

A second parameter determining module 403, configured to determine, based on the operation information of the plurality of electrical devices and the environmental information of the environment, a fault prediction parameter of each electrical device, where the fault prediction parameter includes a plurality of candidate faults and a risk value of each candidate fault, where the risk value is used to indicate a likelihood of occurrence of a corresponding candidate fault.

The device determining module 404 is configured to determine a target electrical device from the plurality of electrical devices based on the device stability parameter and the failure prediction parameter of each electrical device, where the target electrical device is an electrical device that needs maintenance.

In one possible implementation, the device information includes a device type, device configuration information, and device connection information, and the first parameter determining module 402 is configured to determine, based on the device type and the device configuration information of each electrical device, a first device reliability parameter of each electrical device, where the first device reliability parameter is used to represent an individual reliability of the corresponding electrical device, and the device configuration information is used to represent a structural framework adopted by the corresponding electrical device. And determining a second equipment reliability parameter of each electric equipment based on the first equipment reliability parameter of each electric equipment and equipment connection information, wherein the second equipment reliability parameter is used for representing group reliability of the electric equipment group where the corresponding electric equipment is located, the equipment connection information is used for indicating other electric equipment connected with the corresponding electric equipment, and the equipment connection information is used for determining the electric equipment group where the electric equipment is located. The device stability parameters for each electrical device are determined based on the first device reliability parameter, the second device reliability parameter, and the historical fault condition for each electrical device.

In one possible implementation manner, the historical fault condition includes a historical fault time, a historical fault type and a fault elimination duration, and the first parameter determining module 402 is configured to fuse the first device reliability parameter and the second device reliability parameter of each electrical device by adopting the following formula to obtain a comprehensive device reliability parameter of each electrical device;

Wherein/> For the first reliability parameter,/>For the second reliability parameter,/>For integrating device reliability parameters,/>、/>/>Is constant.

And determining fault risk parameters of each electrical device based on the historical fault time, the historical fault type, the fault elimination duration and the accumulated working duration of each electrical device. And determining the equipment stability parameters of the electric equipment based on the comprehensive equipment reliability parameters and the fault risk parameters.

In a possible embodiment, the second parameter determining module 403 is configured to determine an own fault risk parameter of each electrical device based on the operation information of each electrical device. And determining the environmental fault risk parameters of the electrical equipment based on the environmental information of the environment in which the electrical equipment is located. And carrying out fault prediction by adopting the self fault risk parameters and the environment fault risk parameters of each electrical device to obtain a plurality of candidate faults of each electrical device and risk values of each candidate fault.

In a possible implementation, the device images include a grayscale device image, an infrared device image, and a visible light device image, and the second parameter determining module 403 is configured to determine the second operating temperature of each electrical device based on the grayscale device image, the infrared device image, and the visible light device image of each electrical device. And fusing the first operating temperature and the second operating temperature of each electrical device to obtain a third operating temperature of each electrical device. And determining the self fault risk parameter of each electrical device based on the third operating temperature of each electrical device and the device deformation parameter.

In a possible implementation manner, the second parameter determining module 403 is configured to input the gray scale device image, the infrared device image, and the visible light device image of each electrical device into a temperature prediction model, and perform feature extraction on the gray scale device image, the infrared device image, and the visible light device image through the temperature prediction model to obtain a gray scale image feature, an infrared image feature, and a visible light image feature. And mapping the gray image features, the infrared image features and the visible light image features to obtain second operating temperatures of a plurality of positions on each electrical device. An average of the first operating temperature and the second operating temperature at the plurality of locations on each of the electrical devices is determined as a third operating temperature at the plurality of locations on each of the electrical devices.

In a possible implementation manner, the second parameter determining module 403 is configured to generate, for any one of the plurality of electrical devices, a temperature distribution parameter of the electrical device based on third operating temperatures of a plurality of locations on the electrical device, where the temperature distribution parameter is used to reflect a temperature distribution situation of the corresponding electrical device. And determining the self fault risk parameter of the electrical equipment based on the temperature distribution parameter and the equipment deformation parameter of the electrical equipment.

In a possible implementation manner, the second parameter determining module 403 is configured to perform weighted fusion on the self-fault risk parameter and the environmental fault risk parameter of each electrical device, so as to obtain a fused fault risk parameter of each electrical device. And inputting the fusion fault risk parameters of each electrical device into a risk value prediction model, and extracting features of the fusion fault risk parameters of each electrical device through the risk value prediction model to obtain fault risk features of each electrical device. The fault risk characteristics of the electrical devices are fully connected and normalized, and a probability set of the electrical devices is output, wherein the probability set comprises a plurality of probabilities, and one probability corresponds to one reference fault. And determining a plurality of candidate faults from the plurality of reference faults based on the probability set of each electrical device, and determining the probability corresponding to the candidate faults in the probability set as a risk value of the candidate faults.

In one possible implementation, the device determining module 404 is configured to determine a maintenance parameter of each electrical device based on the device stability parameter and the fault prediction parameter of each electrical device, where the maintenance parameter is used to indicate a maintenance necessity level of the corresponding electrical device. And determining an electrical device of the plurality of electrical devices, the maintenance parameter of which is greater than or equal to the maintenance parameter threshold value, as a target electrical device.

It should be noted that: the intelligent management device for a power system based on multidimensional analysis provided in the above embodiment is only exemplified by the division of the above functional modules when determining an electrical device, and in practical application, the above functional allocation may be performed by different functional modules according to needs, i.e., the internal structure of the electronic device is divided into different functional modules, so as to complete all or part of the functions described above. In addition, the embodiment of the intelligent power system management device based on multidimensional analysis and the embodiment of the intelligent power system management method based on multidimensional analysis provided in the above embodiments belong to the same concept, and detailed implementation processes of the intelligent power system management device are shown in the method embodiments, which are not repeated here.

Fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application, where the electronic device 500 may have a relatively large difference due to different configurations or performances, and may include one or more processors (Central Processing Units, CPUs) 501 and one or more memories 502, where the one or more memories 502 store at least one computer program, and the at least one computer program is loaded and executed by the one or more processors 501 to implement the methods provided in the foregoing method embodiments. Of course, the electronic device 500 may also have components such as a wired or wireless network interface, a keyboard, and an input/output interface, so as to perform input/output, and the electronic device 500 may also include other components for implementing the functions of the device, which are not described herein.

In an exemplary embodiment, a computer readable storage medium, e.g. a memory comprising a computer program executable by a processor for performing the power system intelligent management method based on multi-dimensional analysis in the above embodiment is also provided. For example, the computer readable storage medium may be Read-Only Memory (ROM), random-access Memory (Random Access Memory, RAM), compact disc Read-Only Memory (CD-ROM), magnetic tape, floppy disk, optical data storage device, and the like.

In an exemplary embodiment, a computer program product or a computer program is also provided, which comprises a program code, which is stored in a computer readable storage medium, from which the processor of the electronic device reads, and which is executed by the processor, such that the electronic device performs the above-described power system intelligent management method based on multi-dimensional analysis.

In some embodiments, a computer program according to an embodiment of the present application may be deployed to be executed on one electronic device, or on a plurality of electronic devices located at one site, or on a plurality of electronic devices distributed at a plurality of sites and interconnected by a communication network, where the plurality of electronic devices distributed at the plurality of sites and interconnected by the communication network may constitute a blockchain system.

It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program for instructing relevant hardware, where the program may be stored in a computer readable storage medium, and the above storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.

The foregoing description of the preferred embodiments of the present application is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements falling within the spirit and principles of the present application.

Claims

1. An intelligent management method of an electric power system based on multidimensional analysis is characterized by comprising the following steps:

2. The method of claim 1, wherein the device information includes device type, device configuration information, and device connection information, and wherein the determining device stability parameters for each of the electrical devices based on the device information and historical fault conditions for the plurality of electrical devices comprises:

Determining a first equipment reliability parameter of each electrical equipment based on equipment type and equipment structure information of each electrical equipment, wherein the first equipment reliability parameter is used for representing individual reliability of the corresponding electrical equipment, and the equipment structure information is used for representing a structural framework adopted by the corresponding electrical equipment;

Determining a second equipment reliability parameter of each electrical equipment based on the first equipment reliability parameter of each electrical equipment and equipment connection information, wherein the second equipment reliability parameter is used for representing group reliability of an electrical equipment group where the corresponding electrical equipment is located, the equipment connection information is used for indicating other electrical equipment connected with the corresponding electrical equipment, and the equipment connection information is used for determining the electrical equipment group where the electrical equipment is located;

And determining the equipment stability parameters of the electrical equipment based on the first equipment reliability parameters, the second equipment reliability parameters and the historical fault conditions of the electrical equipment.

3. The method of claim 2, wherein the historical fault conditions include a historical fault time, a historical fault type, and a fault elimination duration, wherein the determining the device stability parameter for each of the electrical devices based on the first device reliability parameter, the second device reliability parameter, and the historical fault conditions for each of the electrical devices comprises:

Fusing the first equipment reliability parameters and the second equipment reliability parameters of the electrical equipment by adopting the following formula to obtain comprehensive equipment reliability parameters of the electrical equipment;

Determining fault risk parameters of the electrical equipment based on the historical fault time, the historical fault type, the fault elimination duration and the accumulated working duration of the electrical equipment;

and determining the equipment stability parameters of the electrical equipment based on the comprehensive equipment reliability parameters and the fault risk parameters.

4. The method of claim 1, wherein determining the fault prediction parameter for each of the electrical devices based on the operational information of the plurality of electrical devices and the environmental information of the environment comprises:

Determining self-fault risk parameters of each electrical device based on the operation information of each electrical device;

Determining environmental fault risk parameters of the electrical equipment based on environmental information of the environments of the electrical equipment;

and carrying out fault prediction by adopting the self fault risk parameters and the environment fault risk parameters of the electric equipment to obtain a plurality of candidate faults of the electric equipment and risk values of the candidate faults.

5. The method of claim 4, wherein the device images include gray scale device images, infrared device images, and visible light device images, and wherein determining the self-failure risk parameters for each of the electrical devices based on the operational information for each of the electrical devices comprises:

determining a second operating temperature of each of the electrical devices based on the gray scale device image, the infrared device image, and the visible light device image of each of the electrical devices;

fusing the first operating temperature and the second operating temperature of each electrical device to obtain a third operating temperature of each electrical device;

and determining the self fault risk parameter of each electrical device based on the third operating temperature and the device deformation parameter of each electrical device.

6. The method of claim 5, wherein determining the second operating temperature of each of the electrical devices based on the grayscale device image, the infrared device image, and the visible light device image of each of the electrical devices comprises:

Inputting a gray scale device image, an infrared device image and a visible light device image of each electrical device into a temperature prediction model, and extracting features of the gray scale device image, the infrared device image and the visible light device image through the temperature prediction model to obtain gray scale image features, infrared image features and visible light image features; mapping the gray image features, the infrared image features and the visible light image features to obtain second operation temperatures of a plurality of positions on each electrical device;

The fusing the first operation temperature and the second operation temperature of each electrical device to obtain a third operation temperature of each electrical device, including:

And determining an average value of the first operating temperature and the second operating temperature of a plurality of positions on each electrical device as a third operating temperature of the plurality of positions on each electrical device.

7. The method of claim 6, wherein said determining an own risk of failure parameter for each of said electrical devices based on a third operating temperature and a device deformation parameter for each of said electrical devices comprises:

Generating temperature distribution parameters of any one of the plurality of electrical devices based on third operating temperatures of a plurality of positions on the electrical device, wherein the temperature distribution parameters are used for reflecting temperature distribution conditions of corresponding electrical devices;

and determining the self fault risk parameter of the electrical equipment based on the temperature distribution parameter and the equipment deformation parameter of the electrical equipment.

8. The method according to claim 4, wherein said predicting the fault using the self fault risk parameter and the environmental fault risk parameter of each of the electrical devices to obtain a plurality of candidate faults of each of the electrical devices and risk values of each of the candidate faults comprises:

weighting and fusing the self fault risk parameters and the environment fault risk parameters of the electrical equipment to obtain fused fault risk parameters of the electrical equipment;

Inputting the fusion fault risk parameters of each electrical device into a risk value prediction model, and extracting features of the fusion fault risk parameters of each electrical device through the risk value prediction model to obtain fault risk features of each electrical device; performing full connection and normalization on fault risk characteristics of each electrical device, and outputting probability sets of each electrical device, wherein each probability set comprises a plurality of probabilities, and one probability corresponds to one reference fault;

And determining a plurality of candidate faults from a plurality of reference faults based on probability sets of the electrical equipment, and determining the probability corresponding to the candidate faults in the probability sets as a risk value of the candidate faults.

9. The method of claim 1, wherein the determining a target electrical device from the plurality of electrical devices based on the device stability parameters and the fault prediction parameters of each of the electrical devices comprises:

Determining maintenance parameters of the electrical equipment based on equipment stability parameters and fault prediction parameters of the electrical equipment, wherein the maintenance parameters are used for representing the maintenance necessary degree of the corresponding electrical equipment;

And determining an electrical device with the maintenance parameter being greater than or equal to a maintenance parameter threshold value in the plurality of electrical devices as a target electrical device.

10. An intelligent management device for an electric power system based on multidimensional analysis, the device comprising: