Excitation system intelligent monitoring operation and maintenance method, system and device based on cloud platform and storage medium

Abstract

The invention discloses an excitation system intelligent monitoring operation and maintenance method, system and device based on a cloud platform, and a storage medium, and relates to the technical field of generator excitation, and the method comprises the steps: building an artificial intelligence model based on real-time operation state information received by the cloud platform; performing data analysis according to the artificial intelligence model and the real-time operation state information, generating a state evaluation result and formulating operation and maintenance measures; and performing decoupling monitoring and computing resource management on each component of the excitation system through the Docker container. The method has the advantages that high-reliability monitoring operation and maintenance are achieved, intelligent specialized monitoring, state evaluation and operation and maintenance guidance of the multiple excitation systems are achieved, timeliness and reliability of monitoring operation and maintenance of the excitation systems are improved, the digital level and the operation level of a power plant are improved, and safe and stable operation of a power grid is guaranteed.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of generator excitation technology, in particular to an intelligent monitoring and operation method, system and equipment of an excitation system based on a cloud platform and a storage medium. BACKGROUND

[0002] With the increasing proportion of new energy power generation, synchronous generators, especially large-capacity synchronous generator sets, are the core components of new power system operation, and their voltage control capability and high inertia are crucial to the stable operation of large power grids. The excitation system is the core component of the synchronous generator and is the key to the voltage source function of the synchronous generator. At the same time, the excitation system can also provide transient voltage support and provide stable power grid under fault conditions. Therefore, the safe and stable operation level of the excitation system is directly related to the operation level of the generator set, and improving the monitoring and operation level of the excitation system to realize the long-term reliable operation of the excitation system has great practical and economic significance.

[0003] The excitation system needs to be analyzed and processed in time to ensure system stability under long-term uninterrupted operation in harsh electromagnetic environments. There are multiple excitation systems in current large power plants, and their operation and maintenance mainly rely on on-site personnel and experience, which is not timely. On the other hand, the excitation system has strong professionalism, involving multiple disciplines such as motors, power electronics, and microcomputer control. Current fault analysis often requires manufacturer personnel to assist in on-site solutions, limiting the improvement of operation and maintenance level. Therefore, real-time high-level intelligent operation state monitoring and maintenance of the excitation system is necessary.

[0004] To solve the above problems, cloud platform technology is a reliable solution. The outstanding advantages of cloud platform are massive computing and storage resources and convenient information interaction and analysis capabilities. The introduction of cloud platform can support the storage and application analysis of multiple excitation system operation monitoring data, and can design and integrate an excitation system intelligent monitoring and operation system with better integration and stronger professionalism based on the cloud platform. Through the cloud platform, long-term massive operation data of multiple excitation systems are collected in real time, and professional comprehensive analysis of the operation data is performed on the cloud platform to realize real-time and efficient interaction of the excitation system, manufacturers and operators, and improve the monitoring and operation level of the excitation system. SUMMARY

[0005] In view of the above problems, the present application is proposed.

[0006] Therefore, the technical problem solved by the present application is that the existing excitation system intelligent monitoring and operation method has poor fault analysis timeliness, delayed operation and maintenance response, poor comprehensive capture of device state, and how to establish a unified analysis platform.

[0007] To solve the above technical problems, the application provides the following technical scheme: a cloud platform-based intelligent monitoring and operation and maintenance method for an excitation system, comprising: constructing an artificial intelligence model based on real-time operation state information received by the cloud platform; performing data analysis according to the artificial intelligence model and the real-time operation state information, generating a state evaluation result and formulating an operation and maintenance measure; decoupling monitoring and computing resource management of each component of the excitation system through a Docker container; the computing resource management comprises dynamically establishing a container instance on each server of the cloud platform based on a load balancing principle, and outputting a resource evaluation value of each server by monitoring the proportion of the usage of the memory, the hard disk and the CPU of the server.

[0008] As a preferred scheme of the cloud platform-based intelligent monitoring and operation and maintenance method for the excitation system, the operation state information comprises device state information and related alarms, faults and fault recording; the device state information comprises excitation transformer monitoring data, excitation regulator monitoring data, rectifier power cabinet monitoring data and de-excitation circuit monitoring data; the faults comprise power supply voltage state, PT disconnection, thyristor synchronous voltage phase sequence and generator terminal voltage phase sequence state, AC sampling state, thyristor trigger pulse number and quantity state, double-machine communication fault, hardware and software watchdog detection fault; and the fault recording is recording for the fault of the electrical primary system.

[0009] As a preferred scheme of the cloud platform-based intelligent monitoring and operation and maintenance method for the excitation system, the construction of the artificial intelligence model comprises: selecting related historical data to construct an artificial intelligence model training sample based on the operation state information received by the cloud platform, selecting multi-source information of electricity, temperature and state information as input information of an artificial intelligence algorithm, constructing an artificial intelligence model by training each parameter of the state evaluation artificial intelligence model and uploading the parameters to the cloud platform.

[0010] As a preferred scheme of the cloud platform-based intelligent monitoring and operation and maintenance method for the excitation system, the generation of the state evaluation result comprises: comprehensively analyzing multi-source data by using the trained artificial intelligence model according to real-time monitoring data uploaded by the excitation system and received by the cloud platform, evaluating the operation state of each part, identifying abnormal state or potential fault, and automatically formulating an operation and maintenance measure based on the generated state evaluation result.

[0011] As a preferred scheme of the cloud platform-based intelligent monitoring and operation and maintenance method for the excitation system, the formulation of the operation and maintenance measure comprises: automatically generating a maintenance work instruction according to the state evaluation result, combining a debugging instruction provided by an excitation manufacturer and the experience of on-site operation and maintenance personnel to pre-write, connecting the maintenance task to a production management system, and automatically updating the device state and optimizing the monitoring strategy by the management system.

[0012] As a preferred scheme of the cloud platform-based excitation system intelligent monitoring operation and maintenance method, the decoupling monitoring and computing resource management comprises: monitoring and operation and maintenance related analysis and calculation of the excitation system are performed by creating container instances, container images and digital operation and maintenance guidance images are established for each component of the excitation system, and multiple servers in the cloud platform take load balancing as a scheduling target, preferentially establish container instances on servers with rich computing and storage resources, perform excitation system monitoring operation and maintenance analysis tasks, form a sequence of a server set according to the order from small to large of resource utilization, and update in real time according to the set and the state information sent by each server, and the server with a low resource evaluation value is scheduled and used first.

[0013] As a preferred scheme of the cloud platform-based excitation system intelligent monitoring operation and maintenance method, the container image and the digital operation and maintenance guidance image comprise: the container image comprises excitation transformer, excitation regulator, rectifier power cabinet and de-excitation circuit monitoring and operation and maintenance images, the digital operation and maintenance guidance image monitors and maintains the excitation system by taking the container as a carrier, and the container instance is created and released according to actual monitoring requirements.

[0014] Another object of the present application is to provide a cloud platform-based excitation system intelligent monitoring operation and maintenance system, which can generate state evaluation results and develop operation and maintenance measures by analyzing data according to an artificial intelligence model and collected data, and solve the problem of operation and maintenance response delay in the current excitation system intelligent monitoring operation and maintenance technology.

[0015] As a preferred scheme of the cloud platform-based excitation system intelligent monitoring operation and maintenance system, the system comprises an online monitoring module, a state evaluation module, a container management module and a resource scheduling module; the online monitoring module is used for directly uploading the collected information of each excitation system to the cloud end, the cloud end performs online real-time monitoring on the operation state of each excitation system, and normalizes the monitoring data, and the excitation system number and unit parameter information are also uploaded to the cloud end; the state evaluation module is used for receiving real-time monitoring data from the online monitoring module, including electrical parameters, temperatures and state information of the excitation transformer, the excitation regulator, the rectifier power cabinet and the de-excitation circuit, comprehensively analyzing the multi-source data by using a pre-trained artificial intelligence model, outputting the operation state evaluation result of each component of the excitation system, comparing the evaluation result with historical data, and forming a device state trend analysis report; the container management module is used for monitoring and operation and maintenance related analysis and calculation of the excitation system by creating a container instance, dynamically creating a container instance according to the number of excitation devices accessed to the system, automatically releasing the related container resources when the excitation system exits the monitoring, maintaining the mapping relationship between the container instance and the physical server in real time, and independently operating each monitoring unit; the resource scheduling module is used for monitoring the memory usage percentage, the hard disk usage percentage and the CPU usage percentage of each server in real time, outputting the resource evaluation value of each server according to a preset algorithm, establishing a server resource priority queue according to the order from small to large of the resource evaluation value, preferentially scheduling the servers with low resource evaluation value, regularly updating the server state information and re-outputting the evaluation value, and dynamically adjusting the container deployment scheme.

[0016] A computer device comprises a memory and a processor, the memory stores a computer program, and the processor executes the computer program to implement the steps of the cloud platform-based excitation system intelligent monitoring operation and maintenance method.

[0017] A computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the cloud platform-based excitation system intelligent monitoring operation and maintenance method.

[0018] The application has the beneficial effects that the intelligent monitoring and operation method of the excitation system based on the cloud platform is aimed at the complexity and professionalism of the multi-excitation system monitoring, collects the multi-excitation system monitoring information through the cloud platform, interacts with the monitoring artificial intelligence model of the excitation manufacturer, completes the system state evaluation and operation guidance in the cloud platform, combines the excitation system operation state, the operation and maintenance demand of the power plant and the professionalism of the manufacturer, realizes the high-reliability monitoring and operation, realizes the decoupling monitoring and calculation resource management of each component of the excitation system through the Docker container, realizes the intelligent and professional monitoring, state evaluation and operation guidance of the multi-excitation system, improves the timeliness and reliability of the excitation system monitoring and operation, improves the digital level and operation level of the power plant, and ensures the safe and stable operation of the power grid. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the application, and for those skilled in the art, other drawings can be obtained without creative labor based on these drawings.

[0020] Figure 1 The overall flowchart of the intelligent monitoring and operation method of the excitation system based on the cloud platform provided for the first embodiment of the application. DETAILED DESCRIPTION

[0021] In order to make the above-mentioned purposes, features and advantages of the application more apparent and easy to understand, the specific embodiments of the application will be described in detail below with reference to the drawings of the specification. Obviously, the described embodiments are only a part of the embodiments of the application, rather than all the embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor should belong to the protection scope of the application.

[0022] Embodiment 1, refer to Figure 1 For an embodiment of the application, an intelligent monitoring and operation method of an excitation system based on a cloud platform is provided, comprising:

[0023] S1: constructing an artificial intelligence model based on real-time operation state information received by the cloud platform.

[0024] Further, the operation state information includes device state information and related alarms, faults and fault recording.

[0025] The device state information includes excitation transformer monitoring data, excitation regulator monitoring data, rectifier power cabinet monitoring data and de-excitation circuit monitoring data.

[0026] The faults include power supply voltage state, PT disconnection, thyristor synchronization voltage phase sequence and generator terminal voltage phase sequence state, AC sampling state, thyristor trigger pulse number and quantity state, double-machine communication fault, hardware and software watchdog detection fault.

[0027] The fault recording is recording for the electrical primary system fault.

[0028] The device state information includes trigger angle, high / low voltage side three-phase voltage / current, three-phase winding temperature, three-phase core temperature, transformer temperature, excitation chamber temperature, each rectifier power cabinet output voltage, bridge arm current, excitation current, thyristor junction temperature, trigger angle, AC side three-phase voltage / current, voltage closed loop, current closed loop and reactive power closed loop control flag, each control closed loop given reference value, control loop output, de-excitation branch current, de-excitation resistance current sharing coefficient, de-excitation switch action number, crosslinker action number, fault includes power supply voltage too low, too high, or disappears; PT disconnection; thyristor synchronization voltage phase sequence and generator terminal voltage phase sequence error; AC sampling error; thyristor trigger pulse number and quantity error; double-machine communication fault; hardware and software watchdog detection fault, fault recording includes excitation voltage, excitation current, stator voltage, stator current mutation, i.e. recording.

[0029] It should be noted that the online monitoring function of the excitation system intelligent monitoring operation and maintenance system cloud platform directly uploads the collected information of each excitation system to the cloud, the cloud performs online real-time monitoring on the operation state of each excitation system, and normalizes the monitoring data, and at the same time, the excitation system number and corresponding unit parameter information are also uploaded to the cloud.

[0030] The state monitoring information uploaded by the excitation system includes: excitation transformer monitoring data, excitation regulator monitoring data, rectifier power cabinet monitoring data, de-excitation circuit monitoring data, wherein the excitation transformer monitoring data includes high / low voltage side three-phase voltage / current, three-phase winding temperature, three-phase core temperature, transformer temperature, excitation chamber temperature, the excitation regulator monitoring data mainly includes the analog quantity signals such as stator / rotor voltage and excitation current collected by each channel of the excitation regulator, on-grid switch and de-excitation switch position, magnetizing and demagnetizing, switching and other switch quantity signals, voltage, current, active power, reactive power, trigger angle and other excitation regulator calculation quantities, at the same time, alarm information, fault information, operation log, fault recording and the like are sent to the cloud platform at regular intervals, the rectifier power cabinet monitoring data mainly includes rectifier bridge arm current, output voltage, excitation current, trigger angle, thyristor temperature, pulse, rectifier cabinet temperature, resistance-capacitance absorption temperature, and the de-excitation circuit monitoring data mainly includes de-excitation branch current, de-excitation resistance current sharing coefficient, de-excitation switch action number, crosslinker action number, and fast-fuse state.

[0031] It should be noted that the construction of the artificial intelligence model comprises selecting relevant historical data to construct an artificial intelligence model training sample based on the operating state information received by the cloud platform, selecting multi-source information of electrical, temperature, and state information as input information of the artificial intelligence algorithm, constructing the artificial intelligence model by training the parameters of the artificial intelligence model, and uploading the parameters to the cloud platform.

[0032] It should be noted that the cloud platform transmits device state information and related alarm, fault, and fault recording information to the manufacturer at regular intervals, the manufacturer processes the excitation system information, selects normal and fault related historical data to establish an artificial intelligence model training sample, selects multi-source information of electrical, temperature, and state information as input information of the artificial intelligence algorithm, completes the establishment of the artificial intelligence model by training the parameters of the artificial intelligence model, and uploads the established artificial intelligence model and its parameters to the cloud platform.

[0033] It should be noted that the real-time acquisition of multi-source state data and fault recording information, combined with the artificial intelligence model, realizes real-time evaluation of the operating state of the device and fault early warning, solves the problems of data isolation and lagging fault diagnosis in traditional monitoring, and significantly improves the early identification ability and operation and maintenance efficiency of the excitation system fault through data normalization processing and cloud collaborative analysis.

[0034] S2: Perform data analysis according to the artificial intelligence model and real-time operating state information, generate a state evaluation result, and develop operation and maintenance measures.

[0035] Further, generating a state evaluation result comprises using the trained artificial intelligence model to comprehensively analyze multi-source data based on real-time monitoring data uploaded by the excitation system received by the cloud platform, evaluating the operating state of each part, identifying abnormal states or potential faults, and automatically developing operation and maintenance measures based on the generated state evaluation result.

[0036] It should be noted that the state of the excitation transformer, the rectification power cabinet, the excitation regulator and the de-excitation circuit is evaluated according to the training of the artificial intelligence model and the real-time acquisition of data, the state evaluation artificial intelligence model is trained through the artificial intelligence algorithm and the acquisition of data, and a corresponding state evaluation container image is made. The inputs of the excitation transformer evaluation artificial intelligence model include the firing angle, the high / low voltage side three-phase voltage / current, the three-phase winding temperature, the three-phase core temperature, the transformer temperature, the excitation chamber temperature, etc. The inputs of the rectification power cabinet evaluation artificial intelligence model include the output voltage of each rectification power cabinet, the bridge arm current, the excitation current, the thyristor junction temperature, the trigger angle, the three-phase voltage / current on the AC side, etc. The inputs of the excitation regulator evaluation artificial intelligence model include the flag bit of the voltage closed loop, the current closed loop and the reactive power closed loop control, the given reference value of each control closed loop, the control loop output, etc. The inputs of the de-excitation circuit evaluation artificial intelligence model include the de-excitation branch current, the de-excitation resistor current sharing coefficient, the de-excitation switch action frequency, and the cross-connector action frequency.

[0037] It should also be noted that the development of operation and maintenance measures includes automatically generating maintenance operation instruction books according to the state evaluation results, combining the debugging instruction books provided by the excitation manufacturers and the experience of the on-site operation and maintenance personnel to pre-write, connecting the maintenance tasks to the production management system, and the management system automatically updating the device state and optimizing the monitoring strategy.

[0038] It should also be noted that on the basis of the state evaluation of the excitation system and the reverse state, the control of the operation and maintenance process is realized by automatically publishing the maintenance operation instruction book. The maintenance operation instruction book is pre-written in combination with the debugging instruction book provided by the excitation manufacturer and the experience of the on-site operation and maintenance personnel. After the completion of the maintenance operation, it is connected to the production management system, which is convenient for whole-process control.

[0039] It should also be noted that through the comprehensive analysis of the multi-source real-time data of the excitation system by the artificial intelligence model, the precise evaluation and abnormal detection of the device running state are realized, the operation and maintenance measures are automatically generated, the problem of traditional operation and maintenance relying on manual experience and lagging response is solved, the maintenance process is optimized, the fault handling efficiency is improved, the device failure rate is reduced, the service life is prolonged, and the stable operation of the power system is ensured.

[0040] S3: Decoupling monitoring and computing resource management of each component of the excitation system through a Docker container.

[0041] Further, the decoupling of monitoring and computing resource management includes creating container instances for excitation system monitoring and operation and maintenance related analysis, establishing container images and digital operation and maintenance guidance images for each component of the excitation system, and the multiple servers in the cloud platform prioritize establishing container instances on servers with more abundant computing and storage resources for excitation system monitoring and operation and maintenance analysis tasks. According to the order from small to large of resource utilization, a sequence of server sets is formed, and the state information of the sets and each server is updated in real time. The server with the lowest resource evaluation value is scheduled first.

[0042] It should be noted that the container image and the digital operation and maintenance guidance image include the container image containing the excitation transformer, the excitation regulator, the rectifier power cabinet and the de-excitation circuit monitoring and operation image, and the digital operation and maintenance guidance image monitors and maintains the excitation system with the container as the carrier. According to the actual monitoring requirements, the container instances are created and released.

[0043] It should also be noted that the monitoring and operation and maintenance related analysis of the excitation system is performed by creating container instances, and corresponding container images are established for each component of the excitation system, including the excitation transformer, the excitation regulator, the rectifier power cabinet and the de-excitation circuit monitoring and operation image. At the same time, digital operation and maintenance guidance images for the operation and maintenance of each part are established. The excitation system is monitored and maintained with the container as the carrier, and the container instances are created and released according to the actual monitoring requirements. When a new excitation system to be monitored needs to be added, the cloud platform dynamically creates a container instance through the Docker container image. When the excitation system exits the monitoring system, the corresponding container is released.

[0044] The multiple servers in the cloud platform prioritize establishing container instances on servers with more abundant computing and storage resources for excitation system monitoring and operation and maintenance analysis tasks. The cloud platform computing analysis task scheduling module sorts the available servers according to the resource conditions based on the monitoring of the running state of the cloud servers. Considering that the excitation system monitoring and operation and maintenance requires a large amount of server memory, hard disk and CPU, these three aspects are used as the basis for server resource evaluation, represented as:

[0045]

[0046] where S i is the resource evaluation value of the i-th server, S im is the memory of the i-th server, S ih is the hard disk of the i-th server, S ic is the CPU usage percentage of the i-th server, S immax is the maximum value of the memory of the i-th server, S ihmax is the maximum value of the hard disk of the i-th server, and Sicmax The maximum value of the CPU usage percentage of the i-th server.

[0047] According to the order of the resource usage from small to large, a sequence of the server set is formed, and the set is updated in real time according to the state information uploaded by each server, and the server with a low resource evaluation value is scheduled to be used first.

[0048] It should be noted that the excitation system is modularly decoupled and monitored through the Docker container, the intelligent allocation and load balancing of the computing resources are combined with the dynamic resource scheduling algorithm, the problems of low resource utilization and poor expansibility of the traditional centralized monitoring system are solved, the monitoring efficiency and operation flexibility are improved through the container deployment and elastic scaling, the hardware cost is reduced, and the system scalability is enhanced.

[0049] Embodiment 2 is an embodiment of the present application, which provides an excitation system intelligent monitoring and operation system based on a cloud platform, comprising an online monitoring module, a state evaluation module, a container management module and a resource scheduling module.

[0050] The online monitoring module is used for directly uploading the collection information of each excitation system to the cloud, the cloud performs online real-time monitoring on the running state of each excitation system, and normalizes the monitoring data, and uploads the excitation system number and unit parameter information to the cloud.

[0051] The state evaluation module is used for receiving real-time monitoring data from the online monitoring module, including electrical parameters, temperatures and state information of the excitation transformer, the excitation regulator, the rectifier power cabinet and the de-excitation circuit, comprehensively analyzing the multi-source data by using a pre-trained artificial intelligence model, outputting the running state evaluation result of each component of the excitation system, comparing the evaluation result with historical data, and forming a device state trend analysis report.

[0052] The container management module is used for monitoring and operation related analysis and calculation of the excitation system by creating a container instance, dynamically creating a container instance according to the number of excitation devices accessed to the system, automatically releasing related container resources when the excitation system exits the monitoring, maintaining the mapping relationship between the container instance and the physical server in real time, and independently running each monitoring unit.

[0053] The resource scheduling module is used for monitoring the memory usage percentage, the hard disk usage percentage and the CPU usage percentage of each server in real time, outputting the resource evaluation value of each server according to a preset algorithm, establishing a server resource priority queue according to the order of the resource evaluation value from small to large, and scheduling the server with a low resource evaluation value to be used first, updating the server state information regularly and outputting the evaluation value again, and dynamically adjusting the container deployment scheme.

[0054] If the functions are implemented in software, the functions can be stored in or implemented as one or more instructions or code on a computer-readable medium. Computer-readable media include both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage medium can be any available medium that can be accessed by a computer. By way of example, and not limitation, such computer-readable media can comprise RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. Also, any connection is properly termed a computer-readable medium. For example, if the software is transmitted from a website, server, or other remote source using a coaxial cable, fiber optic cable, or twisted pair, then the coaxial cable, fiber optic cable, or twisted pair are included in the definition of medium. Disk and disc, as used herein, include compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), and Blu-Ray® disc where disks usually reproduce data magnetically, while discs reproduce data optically with lasers. Combinations of the above should also be included within the scope of computer-readable media.

[0055] In other words, like a human driver of a vehicle, the autonomous vehicle 100 can be programmed to follow traffic laws and rules of the road, and to make decisions based on its programming and the information it receives from its sensors and other sources. The autonomous vehicle 100 can also be programmed to make decisions based on its programming and the information it receives from its sensors and other sources, even if those decisions are not in accordance with traffic laws and rules of the road. For example, the autonomous vehicle 100 can be programmed to avoid a collision with another vehicle, even if doing so would violate a traffic law or rule of the road.

[0056] In other words, like a human driver of a vehicle, the autonomous vehicle 100 can be programmed to follow traffic laws and rules of the road, and to make decisions based on its programming and the information it receives from its sensors and other sources. The autonomous vehicle 100 can also be programmed to make decisions based on its programming and the information it receives from its sensors and other sources, even if those decisions are not in accordance with traffic laws and rules of the road. For example, the autonomous vehicle 100 can be programmed to avoid a collision with another vehicle, even if doing so would violate a traffic law or rule of the road.

[0057] It should be understood that portions of the present application can be implemented in hardware, software, firmware, or combinations thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, implementation can be with any or a combination of the following technologies, which are all well known in the art: a discrete logic circuit having logic gates for implementing logic functions upon an application of data signals, an application specific integrated circuit having appropriate combinational logic gates, a programmable gate array (PGA), a field programmable gate array (FPGA), etc. It should be understood that the above-described embodiments are merely given as examples of the technical solution of the present application and are not to be interpreted in a limiting manner, and that for persons skilled in the art, modifications or equivalent replacements can be made to the technical solution of the present application without departing from the spirit and scope of the present application, and all such modifications or equivalent replacements shall be encompassed in the scope of the claims of the present application.

Claims

1. A cloud platform-based excitation system intelligent monitoring operation and maintenance method, characterized in that, The application relates to a cloud platform-based real-time operation state information receiving artificial intelligence model construction method. According to the artificial intelligence model and the real-time operation state information, data analysis is performed, a state evaluation result is generated, and operation and maintenance measures are formulated. Docker containers are used for decoupling monitoring and calculation resource management of components of an excitation system. The calculation resource management comprises dynamically establishing container instances on servers of the cloud platform based on a load balancing principle, and outputting resource evaluation values of the servers by monitoring the memory, hard disk and CPU usage proportion of the servers. The operation state information comprises, 2.The cloud platform-based excitation system intelligent monitoring operation and maintenance method of claim 1, wherein: device state information and related alarms, faults and fault recording; the device state information comprises excitation transformer monitoring data, excitation regulator monitoring data, rectifier power cabinet monitoring data and de-excitation circuit monitoring data; the faults comprise power supply voltage state, PT disconnection, thyristor synchronous voltage phase sequence and generator terminal voltage phase sequence state, AC sampling state, thyristor trigger pulse number and quantity state, double-machine communication fault, hardware and software watchdog detection fault; the fault recording is recording for faults of an electrical primary system. The artificial intelligence model construction comprises, 3.The cloud platform-based excitation system intelligent monitoring operation and maintenance method of claim 1 or 2, characterized in that: based on the operation state information received by the cloud platform, selecting related historical data to construct an artificial intelligence model training sample, selecting multi-source information of electricity, temperature and state information as input information of an artificial intelligence algorithm, constructing an artificial intelligence model by training parameters of a state evaluation artificial intelligence model and uploading the parameters to the cloud platform. The state evaluation result generation comprises, 4.The cloud platform-based excitation system intelligent monitoring operation and maintenance method of claim 1, wherein: based on real-time monitoring data uploaded by the excitation system received by the cloud platform, comprehensively analyzing multi-source data by using the trained artificial intelligence model, evaluating the operation state of each part, identifying abnormal states or potential faults, and automatically formulating operation and maintenance measures based on the generated state evaluation result. The operation and maintenance measure formulation comprises, 5. The cloud platform-based excitation system intelligent monitoring operation and maintenance method of claim 4, wherein: generating a maintenance work instruction automatically according to the state evaluation result, combining a debugging instruction provided by an excitation manufacturer and experience of on-site operation and maintenance personnel to pre-write, connecting the maintenance task to a production management system, and automatically updating the device state and optimizing the monitoring strategy by the management system. The decoupling monitoring and calculation resource management comprises, 6.The cloud platform-based excitation system intelligent monitoring operation and maintenance method of claim 1, wherein: monitoring and operation and maintenance related analysis calculation of the excitation system are performed by creating container instances, container images and digital operation and maintenance guidance images are established for each component of the excitation system, a plurality of servers in the cloud platform are preferentially used to establish container instances on servers rich in calculation and storage resources for excitation system monitoring and operation and maintenance analysis tasks, a sequence of a server set is formed according to the order from small to large of resource usage, and the server set is updated in real time according to the set and state information uploaded by each server, and the server with a low resource evaluation value is scheduled and used first. The container image and the digital operation and maintenance guidance image comprise, 7. The cloud platform-based excitation system intelligent monitoring operation and maintenance method of claim 6, wherein: the container image comprises excitation transformer, excitation regulator, rectifier power cabinet and de-excitation circuit monitoring and operation images, the digital operation and maintenance guidance image monitors and operates the excitation system by taking the container as a carrier, and the container instance is created and released according to actual monitoring requirements. ​ 8. A cloud platform-based intelligent monitoring and operation system for an excitation system, which adopts a cloud platform-based intelligent monitoring and operation method for an excitation system according to any one of claims 1 to 9. Comprise online monitoring module, state evaluation module, container management module, resource scheduling module; The online monitoring module is used for directly sending the collection information of each excitation system to the cloud end, the cloud end carries out online real-time monitoring on the operation state of each excitation system, and the monitoring data is normalized, and the excitation system number and unit parameter information are also uploaded to the cloud end; The state evaluation module is used for receiving real-time monitoring data from the online monitoring module, including electrical parameters, temperature and state information of excitation transformer, excitation regulator, rectifier power cabinet and de-excitation circuit, using a pre-trained artificial intelligence model to comprehensively analyze multi-source data, outputting the operation state evaluation result of each component of the excitation system, comparing the evaluation result with historical data, and forming a device state trend analysis report; The container management module is used for monitoring and operation related analysis and calculation of excitation system by creating container instance, dynamically creating container instance according to the number of excitation equipment accessed to the system, automatically releasing related container resources when the excitation system exits monitoring, maintaining the mapping relationship between container instance and physical server in real time, and each monitoring unit independently running; The resource scheduling module is used for real-time monitoring of the memory usage percentage, hard disk usage percentage and CPU usage percentage of each server, outputting the resource evaluation value of each server according to the preset algorithm, establishing a server resource priority queue according to the order from small to large of the resource evaluation value, and the server with low resource evaluation value is preferentially scheduled to be used, the server state information is updated regularly and the evaluation value is output again, and the container deployment scheme is dynamically adjusted. 9.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-8 when the computer program is executed by the processor. The processor executes the computer program to realize the steps of the cloud platform-based excitation system intelligent monitoring and operation method in any one of claims 1 to 7.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to realize the steps of the cloud platform-based excitation system intelligent monitoring and operation method in any one of claims 1 to 7.

Images