Integrated management system and method for intelligent wind power plant

Abstract

The invention relates to the technical field of power plant management, and discloses an integrated management system and method of an intelligent wind power plant. Multi-source data of the wind power plant and operation data of inspection equipment are collected through an intelligent sensing layer and are transmitted to an edge computing layer through a network communication layer; and comprehensive perception of the states of the wind power plant and the ancillary facilities is realized. Furthermore, the edge calculation layer can timely discover the equipment abnormity of the wind power plant and predict the wind power output through the processing of an equipment health condition prediction model, a wind power prediction model and an energy consumption optimization model, reasonably plans the inspection work, improves the operation efficiency and equipment reliability of the power plant, reduces the operation and maintenance cost, and achieves the intelligent inspection.

Description

Technical Field

[0001] This invention relates to the field of power plant management technology, specifically to an integrated management system and method for intelligent wind power plants. Background Technology

[0002] With the increasing global demand for renewable energy, wind power, as a clean and sustainable energy source, has been widely applied and developed. The integrated management system of a smart wind farm is a key component of modern wind farm operation, aiming to achieve comprehensive monitoring and intelligent management of the wind farm and its ancillary facilities (such as booster stations) by integrating various advanced technologies.

[0003] However, traditional wind farm management systems typically rely on decentralized data acquisition systems and manual inspections, which have many limitations in terms of data processing efficiency, real-time performance, and ability to respond to emergencies. Summary of the Invention

[0004] In view of this, the present invention provides an integrated management system and method for intelligent wind farms, in order to solve the problems that traditional wind farm management systems usually rely on decentralized data acquisition systems and manual inspections, which result in many limitations in terms of data processing efficiency, real-time performance and ability to respond to emergencies.

[0005] In a first aspect, the present invention provides an integrated management system for an intelligent wind power plant, the system comprising: an intelligent sensing layer, a network communication layer, an edge computing layer, a container cloud platform, a PaaS layer, an application layer, and multiple inspection devices;

[0006] The intelligent sensing layer acquires multi-source datasets of the wind farm and operational datasets of multiple inspection devices, and sends these datasets to the edge computing layer via the network communication layer. The edge computing layer, based on the multi-source datasets, processes them using equipment health status prediction models and wind power prediction models to obtain abnormal operational datasets of the wind farm, and sends these abnormal operational datasets to the PaaS layer via a container cloud platform. The edge computing layer also processes the operational datasets using an energy consumption optimization model to obtain multiple operational status datasets of multiple inspection devices, and sends these multiple operational status datasets to the PaaS layer via a container cloud platform. The PaaS layer, upon receiving the abnormal operational datasets and multiple operational status datasets, controls the application layer to start and sends these datasets to the application layer. The application layer, based on the multiple operational status datasets, identifies multiple target inspection devices among the multiple inspection devices, and, based on the abnormal operational datasets, uses a preset intelligent inspection mechanism to control the multiple target inspection devices to perform intelligent inspections of the wind farm, obtaining the inspection results.

[0007] The integrated management system for intelligent wind farms provided by this invention collects multi-source data and inspection equipment operation data from the wind farm through an intelligent sensing layer, and transmits this data to the edge computing layer through a network communication layer, achieving comprehensive perception of the status of the wind farm and its ancillary facilities. Furthermore, the edge computing layer processes the multi-source data using equipment health status prediction models and wind power prediction models, enabling preliminary analysis of equipment health trends and wind power output, reducing the data transmission pressure on the backbone network. The processed abnormal operation dataset is then sent to the PaaS layer, achieving localized and rapid data processing, improving the real-time performance of anomaly detection, providing a precise analytical basis for subsequent application layer decisions, and reducing the risk of sudden equipment failures. Simultaneously, the edge computing layer processes the inspection equipment operation data through an energy consumption optimization model, obtaining an operation status dataset and transmitting it to the PaaS layer, achieving dynamic optimization of the inspection equipment's energy consumption. Furthermore, upon receiving abnormal data and operation status data, the PaaS layer initiates the application layer and transmits the data, ensuring the efficiency and flexibility of data processing and application startup. Finally, the application layer filters target inspection equipment based on operational status data and controls inspections through an intelligent inspection mechanism by combining abnormal data, achieving precise scheduling of inspection tasks. Therefore, by implementing this invention, through multi-source data acquisition and model processing, it is possible to promptly detect equipment anomalies in wind power farms and predict wind power output, rationally plan inspection work, improve the operating efficiency and equipment reliability of power farms, reduce operation and maintenance costs, and thus realize intelligent inspection.

[0008] In one alternative implementation, the intelligent sensing layer includes: a positioning terminal for acquiring multi-source datasets and running datasets via differential GPS technology.

[0009] The integrated management system for intelligent wind farms provided by this invention acquires data through positioning terminals using differential GPS technology introduced into the intelligent sensing layer. This enables high-precision positioning of key equipment and inspection equipment in the wind farm, providing accurate location information for equipment management, fault diagnosis, and inspection route planning. It enhances data accuracy and asset management transparency, and facilitates rapid response to emergencies.

[0010] In one alternative implementation, the application layer includes a security module connected to a camera on the positioning terminal for security monitoring of the wind farm.

[0011] The integrated management system for intelligent wind farms provided by this invention connects the security module of the application layer with the camera of the positioning terminal for security detection. It can monitor the surrounding situation of the wind farm in real time, promptly detect abnormal behaviors such as intrusion and boundary crossing, protect the safety of personnel and equipment in the wind farm, and reduce safety hazards.

[0012] In one optional implementation, the security module includes: a fire data acquisition unit, which is equipped with an alarm; the fire data acquisition unit is used to receive smoke data and temperature data from the wind power plant, and to use the smoke data and temperature data to assess the fire risk level of the wind power plant, and to control the alarm to be activated according to the assessment results.

[0013] The integrated management system for intelligent wind power plants provided by this invention can monitor smoke and temperature data in real time through the fire data acquisition unit in the security module. This enables real-time assessment of fire risks and timely alarms, allowing for early warnings in the early stages of a fire. This buys time for personnel evacuation and firefighting efforts, reduces losses caused by fires, and protects the property and lives of personnel at the wind power plant.

[0014] In one alternative implementation, the edge computing layer is also used to access the container cloud platform via SSL / TLS encrypted transmission mode according to preset access control policies and IP blacklist / whitelist filtering methods.

[0015] The integrated management system for intelligent wind farms provided by this invention effectively prevents illegal requests and unauthorized access by employing preset access control policies, IP blacklist / whitelist filtering, and SSL / TLS encrypted transmission mode at the edge computing layer. This ensures the security and confidentiality of data during transmission and processing, and prevents data leakage and malicious attacks.

[0016] In one alternative implementation, the container cloud platform includes a cloud-edge collaboration module, which comprises an edge node authorization unit, a database application unit, a containerized deployment unit, and an offline working mode unit.

[0017] The integrated management system for intelligent wind farms provided by this invention features a cloud-edge collaboration module on a container cloud platform. This module enables functions such as edge node authorization, database application, containerized deployment, and offline working mode, simplifying system management and maintenance processes, improving system flexibility and scalability, ensuring that the system can maintain basic functions even when the network is interrupted, and guaranteeing the normal operation of wind farm equipment.

[0018] In one optional implementation, the system is connected to the cloud; the system further includes: an interface layer, which integrates multiple industrial communication protocols, and includes an encryption module; the encryption module is used to acquire multiple wind farm data information from the wind farm, and encrypt the multiple wind farm data information before sending it to the cloud through multiple industrial communication protocols.

[0019] The integrated management system for intelligent wind power plants provided by this invention integrates multiple industrial communication protocols and encryption modules at the interface layer, enabling the system to communicate with various external devices and systems. At the same time, it ensures the security of data during transmission, enhances the openness and compatibility of the system, and meets the data exchange needs of large-scale distributed systems.

[0020] In one alternative implementation, the edge computing layer is also used to send abnormal operation datasets and multiple operation status datasets to the cloud.

[0021] The integrated management system for intelligent wind farms provided by this invention uses an edge computing layer to send abnormal operation datasets and multiple operation status datasets to the cloud, facilitating centralized analysis and long-term data storage. This provides data support for overall operation optimization, fault trend analysis, and predictive maintenance of the power plant, thereby improving the scientific nature of management decisions.

[0022] In one optional implementation, the application layer is further configured to control multiple inspection devices to perform intelligent inspections of the wind power plant based on a preset schedule and a preset intelligent inspection mechanism, thereby obtaining inspection results.

[0023] The integrated management system for intelligent wind power plants provided by this invention enables the application layer to control inspections based on a preset schedule, making intelligent inspections more flexible and efficient, improving the targeting and effectiveness of inspections, and thus enabling the timely detection of potential problems.

[0024] Secondly, the present invention provides an integrated management method for intelligent wind farms, used in the integrated management system of intelligent wind farms according to the first aspect or any corresponding embodiment thereof; the method includes:

[0025] The process involves acquiring multi-source datasets of the wind farm and operational datasets of multiple inspection devices; processing the multi-source datasets using equipment health status prediction models and wind power prediction models to obtain abnormal operational datasets of the wind farm; processing the operational datasets using energy consumption optimization models to obtain multiple operational status datasets of multiple inspection devices; identifying multiple target inspection devices from among the multiple inspection devices based on the multiple operational status datasets; and using a pre-set intelligent inspection mechanism to control the multiple target inspection devices to conduct intelligent inspections of the wind farm based on the abnormal operational datasets, thereby obtaining inspection results.

[0026] The integrated management method for intelligent wind farms provided by this invention can promptly detect equipment anomalies and predict wind power output through multi-source data acquisition and model processing, rationally plan inspection work, improve the operating efficiency and equipment reliability of the power farm, reduce operation and maintenance costs, and thus realize intelligent inspection. Attached Figure Description

[0027] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0028] Figure 1 This is a structural block diagram of an integrated management system for an intelligent wind farm according to an embodiment of the present invention;

[0029] Figure 2 This is a schematic diagram of the integrated management system for an intelligent wind power plant according to an embodiment of the present invention;

[0030] Figure 3 This is a flowchart illustrating the integrated management method for a smart wind farm according to an embodiment of the present invention;

[0031] Figure 4 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Detailed Implementation

[0032] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0033] This invention provides an integrated management system for intelligent wind farms. By introducing a multi-layered architecture design encompassing an intelligent sensing layer, network communication layer, edge computing layer, container cloud platform, PaaS layer, and application layer, it achieves fully automated management of the entire process from data acquisition to processing, analysis, and decision-making, thereby improving the operational efficiency and safety of wind farms. Simultaneously, through multi-source data acquisition and model processing, it can promptly detect equipment anomalies and predict wind power output, rationally plan inspection work, improve the operating efficiency and equipment reliability of the wind farm, reduce maintenance costs, and ultimately achieve intelligent inspection.

[0034] This embodiment provides an integrated management system for intelligent wind power farms, such as... Figure 1As shown, the integrated management system 1 of the intelligent wind power plant is connected to the cloud 2. Furthermore, the integrated management system 1 of the intelligent wind power plant includes: intelligent sensing layer 11, network communication layer 12, edge computing layer 13, container cloud platform 14, PaaS layer 15, application layer 16, multiple inspection devices 17, and interface layer 18.

[0035] Among them, the inspection equipment 17 can be a drone or a robot.

[0036] Furthermore, the container cloud platform 14 includes a cloud-edge collaboration module 141. Furthermore, the cloud-edge collaboration module 141 includes an edge node authorization unit, a database application unit, a containerized deployment unit, and an offline working mode unit.

[0037] Furthermore, the edge node authorization unit is implemented through a container management platform, allowing the cloud to add edge nodes to the edge cluster, thereby simplifying system management and operation and maintenance, and ensuring the standardization and convenience of edge node access; the database application unit selects a database solution suitable for localization needs, which can ensure data security and performance; the containerized deployment unit packages all applications into container images and runs them on the edge, making the applications easy to expand and maintain, and thus able to flexibly adapt to different operating needs and scenario changes in wind farms; the offline working mode unit can ensure that the system can still maintain basic functional operation in the event of network interruption, ensuring that the normal operation of field equipment is not affected by network conditions, and improving the stability and reliability of the system.

[0038] Furthermore, interface layer 18 defines standard API interfaces for interaction with other systems or platforms, ensuring the openness and interoperability of the system. At the same time, interface layer 18 integrates multiple industrial communication protocols.

[0039] Specifically, interface layer 18 supports multiple industrial communication protocols such as ModBus, OPC-UA, CAN, and Profibus, while container cloud platform 14 uses protocols such as HTTP and MQTT to transmit collected data to the cloud 2, supporting the data exchange needs of large-scale distributed systems. Extensive support for communication protocols allows the system to seamlessly connect to different types of hardware devices, enhancing compatibility and adaptability. Furthermore, an efficient protocol transmission mechanism ensures rapid data transmission and processing, meeting the needs of complex application scenarios.

[0040] Optionally, the intelligent sensing layer 11 is used to acquire multi-source datasets of the wind power plant and operational datasets of multiple inspection devices 17, and send the multi-source datasets and operational datasets to the edge computing layer 13 through the network communication layer 12.

[0041] The intelligent sensing layer 11 includes a positioning terminal 111. Furthermore, the positioning terminal 111 is installed in key locations, such as the base of a wind turbine tower or a substation, and supports communication and image viewing.

[0042] The multi-source dataset represents a collection of multi-source data from a wind farm and its ancillary facilities, which may include equipment operation data such as temperature, humidity, vibration, video stream, and acoustic signature, as well as meteorological data such as wind speed, wind direction, and humidity. The operation dataset is used to reflect the operating status of multiple inspection devices 17, and may include parameters such as the real-time power output, operating time, moving distance, and speed of the inspection devices.

[0043] Furthermore, the network communication layer 12 can achieve secure isolation between the internal network and the external network and efficient data transmission, and supports multiple communication protocols.

[0044] Specifically, the positioning terminal 111 can be used to achieve high-precision positioning of key equipment and inspection equipment in the wind power plant through differential GPS technology, thereby obtaining the corresponding multi-source dataset of the wind power plant and the operation dataset of multiple inspection equipment.

[0045] Differential GPS technology refers to a technology that improves positioning accuracy by providing error correction data in real time through a base station. Its core is to improve positioning accuracy from meter level to sub-meter or even centimeter level by eliminating common error sources (such as atmospheric delay, satellite clock error, etc.).

[0046] In some alternative implementations, the positioning terminal 111 can be installed at key locations in the wind farm (such as the base of the wind turbine tower, substation, etc.) and the positioning terminal 111 can be configured for multiple inspection devices 17 (drones, robots, etc.) to ensure comprehensive coverage of key equipment and inspection equipment.

[0047] Furthermore, the positioning terminal 111 can use differential GPS technology to correct errors by utilizing the difference in observation data between the base station (which needs to be deployed in advance at a known precise location) and the mobile station (positioning terminal 111), thereby achieving real-time positioning with centimeter-level accuracy and accurately obtaining the location information of key equipment and the real-time location and movement trajectory data of inspection equipment.

[0048] Furthermore, while providing high-precision positioning information, the positioning terminal 111 combines with other sensing devices in the wind farm (such as temperature sensors, humidity sensors, vibration sensors, cameras, and acoustic fingerprint collection devices) to integrate the positioning information with multi-source data such as temperature, humidity, equipment vibration data, video streams, and acoustic fingerprints, forming a multi-source dataset for the wind farm.

[0049] Furthermore, for multiple inspection devices 17, the positioning terminal 111 records in real time their position changes, moving speed, running time, energy consumption and other data during operation, which together constitute the operation dataset of the inspection devices.

[0050] Furthermore, the collected multi-source dataset and the inspection equipment operation dataset are sent to the edge computing layer 13 through the network communication layer 12.

[0051] By introducing differential GPS technology into the positioning terminal at the intelligent sensing layer, high-precision positioning of key equipment and inspection equipment in wind farms can be achieved. This provides accurate location information for equipment management, fault diagnosis, and inspection route planning, enhancing data accuracy and asset management transparency, and facilitating rapid response to emergencies.

[0052] Optionally, the edge computing layer 13 is used to obtain an abnormal operation dataset of the wind farm based on the multi-source dataset, processed by the equipment health status prediction model and the wind power prediction model, and to send the abnormal operation dataset to the PaaS layer 15 through the container cloud platform 14.

[0053] The equipment health status prediction model is obtained by training a Long Short-Term Memory (LSTM) network using historical operating data. It is used to predict the simulated health status of the equipment in the future. Its output formula is shown in the following relation (1):

[0054] H(t) = LSTM(D) past (1)

[0055] In the formula: H(t) represents the predicted health index; D past This indicates the past operating data of the equipment.

[0056] Equipment health status prediction models can predict potential health problems in equipment in advance, providing a basis for preventive maintenance and reducing the occurrence of unexpected equipment failures.

[0057] Furthermore, the wind power forecasting model is used to predict short-term wind power output based on meteorological forecast data using a random forest regression algorithm, thus assisting in grid dispatching decisions. The forecasting formula is shown in equation (2) below:

[0058] W = RF(M) (2)

[0059] In the formula: W represents the expected wind power output; M represents the set of meteorological parameters.

[0060] Wind power forecasting models can help wind farms more accurately grasp wind power output, optimize grid dispatch, and improve wind power utilization efficiency and overall operational benefits.

[0061] Specifically, by inputting multi-source datasets into the device health status prediction model, the device health index H(t) for a future period of time can be calculated.

[0062] Furthermore, the real-time health index can be compared with a preset health threshold. If H(t) is lower than the preset health threshold, it is determined that the equipment has potential faults or health hazards, and abnormal equipment information is generated.

[0063] Furthermore, by inputting multi-source datasets into the wind power prediction model, the theoretical wind power generation W in the short term can be predicted.

[0064] Furthermore, the predicted power generation W can be compared with the actual power generation data collected by the intelligent sensing layer in real time. If the deviation between the two exceeds the preset range (such as exceeding the normal fluctuation threshold), it is determined that there is an anomaly in the power generation, and power generation anomaly information is generated.

[0065] Furthermore, the equipment anomaly information and power generation anomaly information are integrated to form a corresponding abnormal operation dataset, and the abnormal operation dataset is sent to the PaaS layer 15 through the transmission mechanism of the container cloud platform 14.

[0066] In some optional implementations, the received multi-source datasets can be pre-processed such as cleaning, format conversion, and compression encoding before anomaly identification processing is performed using equipment health status prediction models and wind power prediction models.

[0067] In some alternative implementations, machine vision algorithms can be used to identify anomalies in images (such as cracks on the surface of wind turbine blades, loose or missing bolts, corrosion on the surface of towers, and risks of vegetation intrusion), and acoustic analysis technology can be used to determine changes in the state of mechanical components (such as abnormal noises from gearboxes, wear on generator bearings, and leaks in hydraulic systems) and ultimately generate corresponding abnormal operation datasets.

[0068] Optionally, the edge computing layer 13 is also used to obtain multiple operating status datasets of multiple inspection devices 17 based on the running dataset and processed by the energy consumption optimization model, and to send the multiple operating status datasets to the PaaS layer 15 through the container cloud platform 14.

[0069] Among them, the energy consumption optimization model represents a model that minimizes energy consumption through linear regression based on the relationship between power output P and time t, as shown in the following relationship (3):

[0070] E=P·t+λ (3)

[0071] In the formula: E represents total energy consumption; λ represents fixed energy consumption factor.

[0072] Furthermore, by using an energy consumption optimization model to analyze and optimize the energy consumption of wind farm inspection equipment, and by rationally planning the operating power and time of the equipment, unnecessary energy consumption can be reduced while meeting normal operating requirements, thereby improving energy utilization efficiency and reducing operating costs.

[0073] Specifically, by inputting the obtained operating dataset into the energy consumption optimization model, the total energy consumption of the inspection equipment 17 under the current operating state can be calculated.

[0074] Among them, the energy consumption optimization model can optimize the operating parameters of the equipment (such as adjusting the operating speed to balance power and time) by analyzing the relationship between power output and time in the running data and combining the requirements of the inspection task, so as to minimize the total energy consumption E under the premise of meeting the requirements of the inspection task.

[0075] Furthermore, after optimization by the energy consumption optimization model, the optimal operating parameters of each inspection device 17 can be output, which may include recommended power output, operating time, energy consumption expectation, equipment load status and other information, and integrated to form an operating status dataset for each inspection device 17.

[0076] Furthermore, the multiple operational status datasets of the multiple inspection devices 17 can be sent to the PaaS layer 15 via the container cloud platform 14.

[0077] Furthermore, during the transmission of abnormal operation datasets and multiple operation status datasets, the edge computing layer 13 can access the container cloud platform 14 through SSL / TLS encrypted transmission mode according to preset access control policies and IP blacklist / whitelist filtering methods.

[0078] Furthermore, the preset access control policy represents fine-grained permission management based on application layer 16. By defining the operation permissions of different roles, it ensures that only authorized users / systems can access sensitive data and prevents unauthorized operations.

[0079] Furthermore, the IP blacklist / whitelist filtering method represents a network layer-based access control mechanism that quickly intercepts requests from known illegal sources by pre-setting trusted (whitelist) and prohibited (blacklist) IP address ranges, thereby reducing the risk of malicious attacks.

[0080] Furthermore, SSL / TLS encrypted transmission mode represents an encryption protocol that ensures secure data transmission. Through authentication, data encryption, and integrity verification, it prevents data from being eavesdropped on, tampered with, or forged during transmission, ensuring the confidentiality and reliability of data interaction between the edge computing layer and the container cloud platform.

[0081] Specifically, when the edge computing layer 13 interacts with the container cloud platform 14, all access requests are intercepted first.

[0082] Furthermore, through a pre-defined IP blacklist / whitelist mechanism, the IP address of the request source is verified: only legitimate IP addresses in the whitelist are allowed to continue access, while requests initiated by IP addresses in the blacklist are directly rejected, thus filtering out illegal access attempts at the source.

[0083] Furthermore, for requests filtered by IP blacklists and whitelists, the edge computing layer 13 can further verify the legitimacy of the request based on preset access control policies (such as user role permissions, operation permission levels, etc.). For example, it can check whether the request initiator has the permission to access specific data or perform specific operations; only requests that pass permission verification can enter the data transmission stage.

[0084] Furthermore, after authorization verification, the edge computing layer 13 and the container cloud platform 14 negotiate to establish an SSL / TLS encrypted connection:

[0085] (1) Both parties exchange encryption certificates to verify the legitimacy of their identities;

[0086] (2) Negotiate and determine the encryption algorithm and session key to ensure that a high-strength encryption method is used during data transmission.

[0087] Furthermore, the edge computing layer 13 can send the transmitted data (such as abnormal operation datasets and multiple operation status datasets) to the container cloud platform 14 through the established SSL / TLS encrypted channel to ensure that the data is not stolen or tampered with during transmission.

[0088] Optionally, the edge computing layer 13 is also used to send abnormal operation datasets and multiple operation status datasets to the cloud 2.

[0089] Specifically, the edge computing layer 13 can automatically send the obtained abnormal operation dataset and multiple operation status datasets to the cloud 2 through network connection, so as to enable further centralized analysis and historical record storage, providing data support for subsequent global analysis, trend prediction, long-term operation and maintenance decisions, etc.

[0090] Optionally, the PaaS layer 15 is used to control the application layer 16 to start when it receives an abnormal running dataset and multiple running status datasets, and to send the abnormal running dataset and multiple running status datasets to the application layer 16.

[0091] Among them, PaaS layer 15 can provide developers with support for microservice architecture and service governance capabilities, including but not limited to CI / CD pipelines, DevOps practices, service mesh and other functions.

[0092] Specifically, when the PaaS layer 15 receives an abnormal operation dataset and multiple operation status datasets, it triggers a startup control operation on the application layer 16. This ensures that the application layer 16 is only started when there is an actual business need (such as needing to handle exceptions or schedule inspections), thus avoiding resource waste and ensuring timely response.

[0093] Furthermore, while controlling the start of the application layer 16, the PaaS layer 15 can also send the received abnormal operation dataset and multiple operation status datasets to the application layer 16 for intelligent inspection and scheduling, etc., realizing data-driven decision-making, forming a closed loop from data collection to decision execution, and improving the automation and accuracy of wind farm management.

[0094] Optionally, the application layer 16 is used to determine multiple target inspection devices among multiple inspection devices 17 based on multiple operating status datasets, and to control multiple target inspection devices to perform intelligent inspections of the wind power plant based on the abnormal operation dataset using a preset intelligent inspection mechanism, so as to obtain inspection results.

[0095] Specifically, based on the received multiple operational status datasets, the current energy consumption, remaining battery life, and operational efficiency of each inspection device can be analyzed, and the most suitable devices for performing inspection tasks (such as devices with low energy consumption, sufficient battery life, and in an idle state) can be selected and identified as multiple target inspection devices. By screening to avoid resource waste, it can be ensured that the inspection task is performed with the lowest energy consumption and the highest efficiency, which is in line with the goal of the energy consumption optimization model.

[0096] Furthermore, by combining the received abnormal operation dataset, the corresponding preset intelligent inspection mechanism can be invoked, including:

[0097] (1) Based on the inspection path planning algorithm (considering distance, speed and cost coefficients, and minimizing the total cost), plan the optimal inspection route for the target inspection equipment;

[0098] The inspection path planning function is shown in the following relation (4):

[0099] C=ɑd+βv (4)

[0100] In the formula: C represents the total cost; α represents the unit distance cost coefficient; d represents the distance; β represents the unit time cost coefficient; and v represents the speed.

[0101] (2) Develop targeted inspection tasks according to the priority of abnormal points (such as prioritizing the inspection of equipment with low health index and areas with large deviation in power generation).

[0102] Furthermore, the application layer 16 can send control commands to the designated target inspection equipment, driving it to perform inspections according to the planned route and tasks. Simultaneously, it receives data collected during the inspection process in real time (such as equipment status images and parameter readings), analyzes the data, and generates inspection results including abnormal locations, problem types, and handling suggestions.

[0103] Optionally, the application layer 16 is also used to control multiple inspection devices 17 to conduct intelligent inspections of the wind power plant based on a preset schedule and a preset intelligent inspection mechanism, and obtain inspection results.

[0104] Specifically, the application layer 16 can monitor preset triggering conditions in real time, and trigger intelligent inspection tasks when the system time reaches the preset inspection time node (such as a fixed time period every day or a specific date every week).

[0105] Furthermore, once the inspection task is activated, the application layer 16 can use a preset intelligent inspection mechanism to control multiple inspection devices 17 to conduct intelligent inspections of the wind power plant and obtain the corresponding inspection results. The specific process can be referred to the above-described process of inspection based on abnormal operation datasets and multiple operation status datasets, and will not be elaborated here.

[0106] Optionally, the application layer 16 includes a security module 161, which is connected to the camera of the positioning terminal 111 for security monitoring of the wind power plant.

[0107] Specifically, the security module 161 achieves detection through connection with the camera of the positioning terminal 111, thus possessing functions such as intrusion detection, boundary crossing detection, and perimeter protection. Simultaneously, combined with video analytics and physical barriers, it protects critical facilities from unauthorized intrusion. The security module effectively prevents illegal intrusion, ensuring the safety of personnel and property within the wind farm; through intelligent means, it reduces the need for manual monitoring and improves the level of security management.

[0108] In some alternative implementations, the security module 161 can receive video stream data of key areas of the wind farm (such as the area around the wind turbine, the booster station, the substation, etc.) collected by the camera of the positioning terminal 111 in real time through connection with the camera.

[0109] Furthermore, the security module 161 can utilize built-in video analysis technologies (such as machine vision algorithms) to process the received video stream in real time and identify anomalies in the footage, including:

[0110] (1) Intrusion detection: Identify unauthorized personnel, vehicles, etc. that enter the restricted area of ​​the wind farm;

[0111] (2) Boundary crossing detection: Detects whether any object or person crosses the preset safety boundary (such as a fence or warning zone);

[0112] (3) Perimeter protection: Continuous monitoring of the area surrounding the wind farm to ensure that external interference does not affect the operation of core facilities.

[0113] Furthermore, when the aforementioned security anomaly is detected, the security module 161 can trigger an alarm mechanism (such as sending an alarm signal to the system backend or triggering an audible and visual alarm), and simultaneously record the time, location, and video clip of the anomaly, providing a basis for subsequent security handling.

[0114] Furthermore, through the aforementioned real-time video analysis and intelligent recognition, all-weather, automated monitoring of wind farm safety has been achieved, reducing the cost and blind spots of manual patrols, decreasing the need for human monitoring, improving the timeliness of security response, and thus enhancing the level of safety management.

[0115] Optionally, the security module 161 includes a fire detection unit, and the fire detection unit is equipped with an alarm.

[0116] Furthermore, the fire data acquisition unit is used to receive smoke and temperature data from the wind farm, and to use the smoke and temperature data to assess the fire risk level of the wind farm, and to control the alarm to be activated based on the assessment results.

[0117] Specifically, the security module 161 can establish a connection with traditional smoke detectors, temperature sensors and other equipment in the wind farm, and receive smoke data (such as smoke concentration and diffusion range) and temperature data (such as ambient temperature and equipment surface temperature) transmitted by these devices in real time.

[0118] Furthermore, upon receiving smoke and temperature data from the wind farm, the fire data acquisition unit can invoke a built-in algorithm to analyze the received smoke and temperature data.

[0119] For example, the fire risk level (e.g., low, medium, or high risk) of a current area can be assessed by comparing real-time data with preset safety thresholds (e.g., normal ambient temperature range, smoke-free baseline). For instance, when the temperature exceeds a critical value and significant smoke is detected, it is classified as high risk.

[0120] Furthermore, based on the obtained fire risk level assessment results, the fire data acquisition unit can perform corresponding operations:

[0121] (1) If the risk is low or medium, only record the data and continue to monitor it;

[0122] (2) If a high risk is reached (e.g., the fire judgment conditions are met), the alarm in the fire acquisition unit is immediately triggered (e.g., an audible and visual alarm signal is issued), and fire alarm information is sent to the system backend at the same time.

[0123] Furthermore, while activating the alarm, the fire data acquisition unit can also link the system to activate emergency plans (such as issuing evacuation instructions through the broadcast system) to provide support for subsequent fire response and personnel evacuation.

[0124] Through the above process, real-time monitoring and graded response to fire hazards in wind power plants were achieved. At the same time, early warning and rapid alarms minimized the losses caused by fires and ensured the safety of personnel and equipment at wind power plants.

[0125] Optionally, the interface layer 18 includes an encryption module 181. Further, the encryption module 181 is used to acquire multiple wind farm data information of the wind farm, and encrypt the multiple wind farm data information and send it to the cloud 2 through multiple industrial communication protocols.

[0126] Specifically, the encryption module 181 can obtain data information from multiple wind farms.

[0127] Furthermore, after acquiring data from multiple wind farms, the encryption module 181 can use AES-256-bit encryption storage technology to encrypt the data from these multiple wind farms.

[0128] Furthermore, the TLS 1.3 protocol can be used to send the encrypted data information of multiple wind farms to the cloud 2, which protects the wind farm data information during transmission, provides high-strength security protection for wind farm data, prevents data from being stolen or tampered with during storage and transmission, and ensures information security and user privacy.

[0129] The integrated management system for intelligent wind farms provided in this embodiment collects multi-source data (temperature, humidity, vibration, etc.) and inspection equipment operation data from the wind farm through an intelligent sensing layer, and transmits this data to the edge computing layer through a network communication layer, achieving comprehensive perception of the wind farm and its auxiliary facilities. Furthermore, the edge computing layer processes the multi-source data using equipment health status prediction models and wind power prediction models, enabling preliminary analysis of equipment health trends and wind power output, reducing the data transmission pressure on the backbone network. The processed abnormal operation dataset is then sent to the PaaS layer, achieving localized and rapid data processing, improving the real-time performance of anomaly detection, providing a precise analytical basis for subsequent application layer decisions, and reducing the risk of sudden equipment failures. Simultaneously, the edge computing layer processes the inspection equipment operation data through an energy consumption optimization model, obtaining an operation status dataset and transmitting it to the PaaS layer, achieving dynamic optimization of the inspection equipment's energy consumption. Furthermore, upon receiving abnormal data and operation status data, the PaaS layer initiates the application layer and transmits the data, ensuring the efficiency and flexibility of data processing and application startup. Finally, the application layer filters target inspection equipment based on operational status data and controls inspections through an intelligent inspection mechanism by combining abnormal data, achieving precise scheduling of inspection tasks. Therefore, by implementing this invention, through multi-source data acquisition and model processing, it is possible to promptly detect equipment anomalies in wind power farms and predict wind power output, rationally plan inspection work, improve the operating efficiency and equipment reliability of power farms, reduce operation and maintenance costs, and thus realize intelligent inspection.

[0130] In one instance, such as Figure 2 As shown, an integrated management system for an intelligent wind farm is provided, comprising: an intelligent sensing layer for collecting multi-source data from the wind farm and its ancillary facilities, including but not limited to temperature, humidity, vibration, video streams, and acoustic signatures; a network communication layer for secure isolation and efficient data transmission between the internal and external networks, supporting multiple communication protocols; an edge computing layer equipped with high-performance computing nodes responsible for preliminary processing and analysis of the collected data, reducing the burden on the backbone network; a container cloud platform based on a cloud-native architecture, providing a containerized deployment environment to ensure rapid application iteration and elastic scaling; a PaaS layer for providing developers with support for microservice architecture and service governance capabilities, including but not limited to CI / CD pipelines, DevOps practices, and service mesh functions; an application layer containing functional modules such as task scheduling, anomaly detection, and data analysis, capable of triggering specific actions or alarms according to rules; and an interface layer defining standard API interfaces for interaction with other systems or platforms, ensuring the system's openness and interoperability.

[0131] Furthermore, through a multi-layered design, this architecture achieves fully automated management of the entire process from data acquisition to processing, analysis, and decision-making, improving the operational efficiency and safety of wind farms. Simultaneously, the adoption of advanced cloud computing technology and containerized deployment enhances the system's flexibility and scalability, while reducing maintenance costs.

[0132] Furthermore, the edge computing layer includes the following steps:

[0133] Step S1: Obtain real-time data from the intelligent perception layer;

[0134] Step S2: Use edge computing nodes to perform preliminary processing on the raw data, such as cleaning, format conversion, and compression encoding;

[0135] Step S3: All raw data and processed feature data are stored locally for at least one month, and important information can be retained for a long time through a rolling update mechanism;

[0136] Step S4: Use machine vision algorithms to identify anomalies in the image and use voiceprint analysis technology to determine changes in the state of mechanical parts;

[0137] Step S5: Automatically upload feature data to the cloud via network connection for further centralized analysis and historical record storage;

[0138] Step S6: Implement SSL / TLS encrypted transmission mode, configure IP blacklists and whitelists to filter illegal requests, and set strict access control policies to prevent unauthorized access;

[0139] Through the steps described above, the edge computing layer not only reduces the load on the backbone network but also ensures the real-time performance and accuracy of data. Furthermore, security measures ensure secure and reliable data transmission, protecting sensitive information from leakage.

[0140] Furthermore, the application layer includes an intelligent inspection mechanism used to control drones and robots to inspect the substation. This intelligent inspection mechanism includes: optimizing the inspection route using an inspection path planning algorithm, where the inspection path planning function is C = αd + βv, where d is the distance, v is the speed, and α and β represent the unit distance cost coefficient and unit time cost coefficient, respectively, aiming to minimize the total cost C. Drones and robots execute preventative maintenance plans according to a predetermined schedule or conditions triggered by the intelligent inspection mechanism, reducing the possibility of unexpected downtime. The mechanism also performs real-time analysis of the data obtained during the inspection process, quickly locates potential problem points, and generates reports for the maintenance team's reference.

[0141] Furthermore, the intelligent inspection mechanism reduces the need for manual intervention and improves inspection efficiency and accuracy. Optimized path planning reduces energy consumption and extends equipment lifespan. Real-time data analysis helps to identify and resolve problems promptly, ensuring the stable operation of the wind farm.

[0142] Furthermore, the edge computing layer includes an algorithm model library, which includes at least: (1) an equipment health status prediction model: using historical operating data to train a Long Short-Term Memory (LSTM) network to predict the simulated health status of equipment in the future. The model output formula is H(t) = LSTM(D past ), where D past (1) Represents the past operating data of the equipment, H(t) is the predicted health index; (2) Energy consumption optimization model: Considering the relationship between power output P and time t, the energy consumption is minimized by the mathematical method of linear regression, where the formula is E=P·t+λ, where λ is a fixed energy consumption factor, and E represents the total energy consumption; (3) Wind power prediction model: Based on meteorological forecast data, the random forest regression algorithm is used to predict the wind power output in the short term to assist the grid dispatch decision, where the prediction formula is W=RF(M), where M is the meteorological parameter set, and W is the expected wind power output;

[0143] Furthermore, the application of these models effectively improves the accuracy and predictability of equipment health management, optimizes energy consumption, and reduces unnecessary waste. Wind power forecasting models help power companies better plan dispatching, improving economic and social benefits.

[0144] Furthermore, the container cloud platform includes a cloud-edge collaboration module, which includes: edge node authorization: implemented through the container management platform, allowing cloud nodes to join the edge cluster with one click, simplifying management and operation; database applications: selecting database solutions suitable for localization needs to ensure data security and performance; containerized deployment: all applications are packaged into container images and run on the edge, making them easy to scale and maintain; offline working mode: even in the event of a network outage, the system can still maintain basic functional operation without affecting the normal operation of on-site equipment.

[0145] The cloud-edge collaboration module enhances interoperability between systems, simplifies management and maintenance processes, and improves system response speed and reliability. Especially in situations of network instability, the offline working mode ensures that critical business operations remain unaffected.

[0146] Furthermore, the intelligent sensing layer includes high-precision positioning terminals that support communication and image viewing. These terminals are installed in critical locations, such as the base of wind turbine towers and substations, and provide centimeter-level positioning services through differential GPS technology. The high-precision positioning terminals provide accurate location information, enhancing the transparency and efficiency of asset management. In particular, they can quickly locate fault points or dangerous areas during emergency response, improving processing speed.

[0147] Furthermore, the application layer includes a security module, which works with cameras in the intelligent perception layer to perform detection, thereby providing functions such as intrusion detection, boundary crossing detection, and perimeter protection. Combined with video analytics and physical barriers, it protects critical facilities from illegal intrusion. The security module effectively prevents illegal intrusion and ensures the safety of personnel and property within the wind farm. Through intelligent means, it reduces the need for manual monitoring and improves the level of security management.

[0148] Furthermore, the security module also includes a fire alarm acquisition module, which is equipped with an alarm. This module receives signals from traditional smoke detectors, heat sensors, and other devices, and uses a built-in algorithm to assess the fire risk level. Once a fire alarm signal is detected, the system immediately activates the emergency plan, notifies relevant personnel, and guides evacuation procedures via the broadcast system. By issuing alarms in the early stages of a fire, the fire alarm acquisition module buys valuable rescue time and minimizes losses. The comprehensive emergency plan ensures safe evacuation and reduces the harm caused by accidents.

[0149] Furthermore, the interface layer supports multiple industrial communication protocols such as ModBus, OPC-UA, CAN, and Profibus, while the container cloud platform uses protocols such as HTTP and MQTT to transmit collected data to the cloud, supporting the data exchange needs of large-scale distributed systems. Extensive support for communication protocols allows the system to seamlessly interface with different types of hardware devices, enhancing compatibility and adaptability. The efficient protocol transmission mechanism ensures rapid data transmission and processing, meeting the needs of complex application scenarios.

[0150] Furthermore, the interface layer integrates an encryption module, which includes AES-256-bit encryption storage technology and uses the TLS1.3 protocol to protect wind farm data during transmission. The encryption module provides strong security protection for wind farm data, preventing data from being stolen or tampered with during storage and transmission, thus ensuring information security and user privacy.

[0151] The integrated management system for intelligent wind farms provided in this example, through the introduction of an advanced multi-layered architecture design including edge computing layer, container cloud platform, PaaS layer, application layer and interface layer, achieves fully automated management of the entire process from data collection to processing, analysis and decision-making, thereby improving the operational efficiency and safety of wind farms.

[0152] According to an embodiment of the present invention, an integrated management method for a smart wind farm is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0153] This embodiment provides an integrated management method for intelligent wind farms, which can be used in the integrated management system 1 for intelligent wind farms provided in the above embodiments of the present invention. Figure 3 This is a flowchart of an integrated management method for a smart wind farm according to an embodiment of the present invention, such as... Figure 3 As shown, the process includes the following steps:

[0154] Step S301: Obtain the multi-source dataset of the wind power plant and the operation dataset of multiple inspection devices.

[0155] For the specific process, please refer to the functional description of the intelligent sensing layer 11 in the integrated management system 1 of the intelligent wind power plant in the above embodiments, which will not be repeated here.

[0156] Step S302: Based on the multi-source dataset, the abnormal operation dataset of the wind power plant is obtained after processing by the equipment health status prediction model and the wind power prediction model.

[0157] For the specific process, please refer to the functional description of the edge computing layer 13 in the integrated management system 1 of the intelligent wind power plant in the above embodiments, which will not be repeated here.

[0158] Step S303: Based on the running dataset, the energy consumption optimization model is used to process multiple running status datasets of multiple inspection devices to obtain multiple running status datasets.

[0159] For the specific process, please refer to the functional description of the edge computing layer 13 in the integrated management system 1 of the intelligent wind power plant in the above embodiments, which will not be repeated here.

[0160] Step S304: Based on multiple operating status datasets, identify multiple target inspection devices among multiple inspection devices.

[0161] For a detailed description of the process, please refer to the functional description of the PaaS layer 15 and application layer 16 in the integrated management system 1 for intelligent wind farms in the above embodiments, which will not be repeated here.

[0162] Step S305: Based on the abnormal operation dataset, use a preset intelligent inspection mechanism to control multiple target inspection devices to conduct intelligent inspections of the wind power plant and obtain inspection results.

[0163] For a detailed description of the process, please refer to the functional description of the PaaS layer 15 and application layer 16 in the integrated management system 1 for intelligent wind farms in the above embodiments, which will not be repeated here.

[0164] The integrated management method for intelligent wind farms provided in this embodiment can promptly detect equipment anomalies and predict wind power output through multi-source data acquisition and model processing, rationally plan inspection work, improve the operating efficiency and equipment reliability of the power farm, reduce operation and maintenance costs, and thus realize intelligent inspection.

[0165] This invention also provides a computer device for performing the above-described... Figure 3 The integrated management method for intelligent wind power plants is shown.

[0166] Please see Figure 4 , Figure 4 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention, such as... Figure 4 As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 4 Take a processor 10 as an example.

[0167] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0168] The memory 20 stores instructions executable by at least one processor 10 to cause at least one processor 10 to perform the method shown in the above embodiments.

[0169] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0170] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0171] The computer device also includes a communication interface 30 for communicating with other devices or communication networks.

[0172] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0173] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0174] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. An integrated management system for a smart wind farm, characterized in that, The system comprises an intelligent perception layer, a network communication layer, an edge computing layer, a container cloud platform, a PaaS layer, an application layer, and a plurality of inspection devices. The intelligent perception layer is configured to acquire a plurality of source data sets of a wind farm and a plurality of operation data sets of the plurality of inspection devices, and send the plurality of source data sets and the plurality of operation data sets to the edge computing layer through the network communication layer. The edge computing layer is configured to obtain abnormal operation data sets of the wind farm by processing the plurality of source data sets through a device health condition prediction model and a wind power prediction model, and send the abnormal operation data sets to the PaaS layer through the container cloud platform. The edge computing layer is further configured to obtain a plurality of operation state data sets of the plurality of inspection devices by processing the plurality of operation data sets through an energy consumption optimization model, and send the plurality of operation state data sets to the PaaS layer through the container cloud platform. The PaaS layer is configured to control the application layer to start when the abnormal operation data sets and the plurality of operation state data sets are received, and send the abnormal operation data sets and the plurality of operation state data sets to the application layer. The application layer is configured to determine a plurality of target inspection devices among the plurality of inspection devices based on the plurality of operation state data sets, and control the plurality of target inspection devices to perform intelligent inspection on the wind farm based on the abnormal operation data sets by using a preset intelligent inspection mechanism, to obtain an inspection result.

2. The system of claim 1, wherein, The intelligent perception layer comprises: A positioning terminal configured to acquire the plurality of source data sets and the plurality of operation data sets by using a differential GPS technology.

3. The system of claim 2, wherein, The application layer comprises: A security module connected with a camera of the positioning terminal, and configured to perform security detection on the wind farm.

4. The system of claim 3, wherein, The security module comprises a fire-fighting acquisition unit, and the fire-fighting acquisition unit is provided with an alarm. The fire-fighting acquisition unit is configured to receive smoke data and temperature data of the wind farm, and use the smoke data and the temperature data to evaluate a fire risk level of the wind farm, and control the alarm to start according to an evaluation result.

5. The system of claim 1, wherein The edge computing layer is further configured to access the container cloud platform through an SSL / TLS encryption transmission mode according to a preset access control strategy and an IP black and white list filtering method.

6. The system of claim 1, wherein, The container cloud platform comprises a cloud-edge collaboration module, and the cloud-edge collaboration module comprises an edge node authorization unit, a database application unit, a container deployment unit, and an offline working mode unit.

7. The system of claim 1, wherein, The system is connected with a cloud end, and further comprises an interface layer integrated with a plurality of industrial communication protocols, and the interface layer comprises an encryption module. The encryption module is configured to acquire a plurality of wind farm data information of the wind farm, and send the plurality of wind farm data information to the cloud end after encryption through the plurality of industrial communication protocols.

8. The system of claim 7, wherein The edge computing layer is also used to send the abnormal operation dataset and the multiple operation status datasets to the cloud.

9. The system according to claim 1, characterized in that, The application layer is also used to control the multiple inspection devices to conduct intelligent inspections of the wind power plant based on a preset schedule and using the preset intelligent inspection mechanism, so as to obtain inspection results.

10. An integrated management method of a smart wind farm, characterized by, An integrated management system for a smart wind farm according to any one of claims 1 to 9; the method comprising: Acquire multi-source datasets of wind power plants and operational datasets of multiple inspection devices; Based on the multi-source dataset, after processing by the equipment health status prediction model and the wind power prediction model, an abnormal operation dataset of the wind power plant is obtained. Based on the aforementioned operational dataset, and after processing by an energy consumption optimization model, multiple operational status datasets of the multiple inspection devices are obtained. Based on the multiple operational status datasets, multiple target inspection devices are determined from the multiple inspection devices; Based on the abnormal operation dataset, a preset intelligent inspection mechanism is used to control the multiple target inspection devices to conduct intelligent inspections of the wind power plant and obtain inspection results.

Images