Intelligent safety monitoring method, system and equipment for offshore wind plant and medium

Abstract

The invention discloses an intelligent safety monitoring method, system and device for an offshore wind plant and a medium, and relates to the technical field of safety monitoring, and the method comprises the steps: deploying a plurality of different monitoring modular units in the offshore wind plant, and building a safety monitoring model; monitoring data acquired by each monitoring modular unit is transmitted to a preset central control terminal to form an intelligent safety monitoring platform, and the monitoring modular units execute data acquisition based on a received remote configuration parameter instruction; the intelligent safety monitoring platform supports analysis and calculation processing of monitoring data and outputs a safety monitoring result; in the safety monitoring model, a plurality of key performance indexes are defined for the monitoring modular unit based on the project unit identifier and a preset monitoring standard demand, and if a certain key performance index exceeds a corresponding data change threshold, a safety early warning instruction is triggered; the offshore wind plant safety monitoring method is more intelligent and efficient, and the monitoring level of the offshore wind plant is improved.

Description

Technical Field

[0001] The present application relates to the field of safety monitoring technology, and in particular to an intelligent safety monitoring method, system, equipment and medium for offshore wind farms. Background Art

[0002] Offshore wind farms face many challenges due to their special marine environment. Wind turbines and supporting facilities (such as wind turbines and offshore booster stations) are exposed to high-salinity and high-humidity environments for a long time and are subject to complex load conditions, which makes the stress conditions of the foundation structure complex and changeable, thus affecting the safety and stability of the entire wind power facility. In order to ensure the safe and reliable operation of offshore wind farms, it is necessary to strengthen the real-time monitoring of projects such as uneven settlement and vibration status of wind power foundation structures during the construction and operation periods. Through effective safety monitoring, not only can potential safety hazards be discovered and handled in a timely manner, but the monitoring results can also be fed back to the design department to optimize subsequent engineering design, guide on-site construction, improve the quality of engineering construction, and ultimately ensure the long-term stable operation of wind farms.

[0003] At present, the safety monitoring of offshore wind farms mainly relies on static monitoring methods, that is, technicians are regularly dispatched to the site to perform manual measurements or use fixed sensors to collect data. However, conventional static data collection automation systems are difficult to meet the monitoring needs of the operating status of offshore wind turbines that are changing every moment. Real-time monitoring will generate a large amount of monitoring data, which puts higher requirements on the automation system and data processing. However, the existing static monitoring system is difficult to efficiently process such a large amount of data.

[0004] In summary, the traditional static monitoring method is unable to cope with the complex and changeable working environment of offshore wind farms, especially in terms of detection efficiency, intelligence and monitoring level. It is urgent to develop a more intelligent and efficient offshore wind farm safety monitoring method to meet the needs of modern offshore wind power development. Summary of the invention

[0005] In order to provide a more intelligent and efficient offshore wind farm safety monitoring method and improve the monitoring level of offshore wind farms, the present application provides an offshore wind farm intelligent safety monitoring method, system, equipment and medium.

[0006] In the first aspect, the invention objective of the present application is achieved by adopting the following technical solutions: An intelligent safety monitoring method for an offshore wind farm, comprising: Collect engineering project data, equipment information and environmental parameters of offshore wind farms, and establish a safety monitoring model with associated project unit identification; Deploy multiple monitoring modular units responsible for different monitoring tasks in an offshore wind farm, transmit the monitoring data collected by each monitoring modular unit to a preset central control terminal to form an intelligent safety monitoring platform, and the monitoring modular unit performs data collection operations based on the received remote configuration parameter instructions; the intelligent safety monitoring platform supports analyzing and calculating the monitoring data of each monitoring modular unit, and outputs corresponding safety monitoring results based on the received data query instructions; In the safety monitoring model, based on the project unit identifier and the preset monitoring standard requirements, define several key performance indicators for the monitoring modular unit, and associate corresponding data change thresholds with different key performance indicators of each monitoring modular unit. Based on the data change thresholds, perform data early warning judgment. If a certain key performance indicator exceeds the corresponding data change threshold, trigger a safety early warning instruction.

[0007] By adopting the above technical solutions, a safe monitoring method for an intelligent, automated and more efficient offshore wind farm project is provided. The present invention collects engineering project data, equipment information and environmental parameters, establishes a safety monitoring model associated with project unit identifiers, and deploys multiple monitoring modular units responsible for different monitoring tasks, realizing all-round and intelligent real-time safety monitoring of the offshore wind farm; specifically, by collecting basic data such as engineering project data, equipment information and environmental parameters of the offshore wind farm, a detailed safety monitoring model associated with project unit identifiers is constructed to ensure the consistency of all relevant data affecting safety monitoring. The multiple deployed monitoring modular units can cover multiple key components of equipment components such as multiple wind turbines and offshore booster stations at different construction locations in the construction of the offshore wind farm, and perform accurate data collection for different monitoring tasks (such as inclination, vibration, stress and strain, corrosion potential), which is beneficial to improving the extensiveness and pertinence of the safety monitoring scope and enhancing the safety monitoring effect; at the same time, during the monitoring construction process of the offshore wind farm, based on the changes in actual monitoring requirements and the requirements of industry monitoring standards, the present invention constructs an intelligent safety monitoring platform, which supports equipment management configuration and remote monitoring equipment management (for example, including the configuration and management of 4 types of data such as inclination monitoring, vibration monitoring, corrosion potential monitoring, stress and strain monitoring and all monitoring equipment in this project, and supports users to customize the configuration modification of the equipment). That is, the user can execute efficient remote configuration and management by inputting remote configuration parameter instructions at the control end of the intelligent safety monitoring platform to realize flexible and efficient on-site monitoring equipment management and maintenance, which is beneficial to improving the response speed and operation efficiency of the intelligent safety monitoring system; the intelligent safety monitoring platform also supports real-time analysis and calculation processing of the data of each monitoring modular unit, enabling managers to understand the operation status of the wind farm at any time, discover potential problems in time and take preventive measures; further, in the safety monitoring model, based on the project unit identifier and the preset monitoring standard requirements, several key performance indicators are defined for each monitoring modular unit, and corresponding data change thresholds are associated with these indicators. Through targeted and refined threshold monitoring, a clear evaluation standard is ensured for the status of each monitoring point of the offshore wind farm, improving the accuracy and reliability of early warning judgment. The entire intelligent safety monitoring system not only enhances the safety management level of the offshore wind farm, but also improves the overall operation and maintenance efficiency.

[0008] In a preferred example of the present application: The collection of engineering project data, equipment information and environmental parameters of the offshore wind farm, the deployment of multiple monitoring modular units responsible for different monitoring tasks in the offshore wind farm, and the establishment of a safety monitoring model associated with project unit identifiers specifically include: Perform data preprocessing on the engineering project data, equipment information and environmental parameters of the offshore wind farm to obtain the basic data of the target monitoring area after preprocessing; Based on the preprocessed basic data, several monitoring modular units are generated within the target monitoring area; According to the positions and types of the monitoring modular units, the positions of several monitoring points for each monitoring modular unit are determined; The monitoring modular units are associated with the corresponding project unit identifiers, and a complete safety monitoring model is constructed to guide the subsequent deployment and management of the monitoring modular units.

[0009] By adopting the above technical solutions, data preprocessing is carried out on the engineering project data, equipment information and environmental parameters, eliminating the noise and outliers in the original data, and ensuring the quality of the basic data for subsequent analysis and decision-making; by reasonably allocating the monitoring point positions of each monitoring modular unit, the comprehensiveness of the monitoring positions is improved to more accurately capture the state changes of each key part, optimizing the deployment of the monitoring modular units, and then by constructing a comprehensive and complete safety monitoring model to provide a unified data management and analysis framework, which is beneficial to enhancing the collaborative working ability between different monitoring modules of each monitoring modular unit, and further ensuring that each monitoring point can be configured according to the predetermined standards, improving the on-site operation efficiency.

[0010] In a preferred example of the present application: in the safety monitoring model, based on the project unit identifier and the preset monitoring standard requirements, several key performance indicators are defined for the monitoring modular unit, and corresponding data change thresholds are associated with different key performance indicators of each monitoring modular unit. Based on the data change thresholds, data early warning judgment is carried out. If a certain key performance indicator exceeds the corresponding data change threshold, a safety early warning instruction is triggered, including: Based on the project unit identifier and the preset monitoring standard requirements, several key performance indicators are defined for each monitoring modular unit. The several key performance indicators include settlement rate, vibration amplitude, inclination angle, stress-strain level, corrosion potential change rate; the several key performance indicators cover all potential safety risk points; Corresponding data change thresholds are associated with different key performance indicators of each monitoring modular unit; The intelligent safety monitoring platform receives and analyzes the monitoring data transmitted by each monitoring modular unit, and combines the corresponding data change thresholds to carry out real-time data early warning judgment. If a certain key performance indicator exceeds the corresponding data change threshold, a safety early warning instruction is triggered and sent to the designated user terminal; Among them, the data change thresholds include a first-level early warning threshold, a second-level threshold, and a third-level threshold. The safety early warning instruction generates corresponding first-level early warning signals, second-level early warning signals, and third-level early warning signals based on the actual early warning level of the data change threshold.

[0011] By adopting the above technical solution, a method of defining key performance indicators (KPIs) and setting up a multi-level early warning mechanism in a safety monitoring model is provided. Specifically, multiple key performance indicators (such as settlement rate, vibration amplitude, tilt angle, stress and strain, etc.) are defined for each monitoring modular unit to cover all potential safety risk points existing in an offshore wind farm, ensuring comprehensive monitoring of the health status of offshore wind power facilities; corresponding data change thresholds are associated with different key performance indicators of each monitoring modular unit, and a three-level early warning mechanism (level one, level two, level three) is implemented, which is beneficial to sending out early warning signals at the initial stage of problems, enabling relevant personnel to have sufficient time to take preventive measures and avoid small problems evolving into major accidents; improving the response efficiency of safety monitoring; the multi-level early warning mechanism notifies relevant personnel to take corresponding preventive or emergency response measures according to different levels of early warning signals (such as signals set in different colors like yellow, orange, red, etc.).

[0012] In a preferred example of the present application: the method further includes: taking each of the monitoring modular units as a basic unit and performing initial configuration according to a defined number of key performance indicators; After completing the initial configuration of the monitoring modular units, it further includes: Dividing the monitoring tasks of the monitoring modular units into multiple monitoring task segments according to project characteristic information and specific work content, obtaining multiple different monitoring task segments; Obtaining quality acceptance standard information corresponding to multiple different monitoring task segments, and associating corresponding standard quality thresholds based on the quality acceptance standard information; Obtaining the design product quality in each monitoring task segment, marking the task segments with design product quality lower than the corresponding standard quality threshold as unqualified, obtaining unqualified marked monitoring segments; analyzing the reasons for unqualified for the unqualified marked monitoring segments, obtaining the results of unqualified reason analysis; Based on the results of unqualified reason analysis, outputting improvement measure suggestions, where the improvement measure suggestions include adjusting monitoring parameters, optimizing sensor layout or strengthening the monitoring intensity at specific positions.

[0013] By adopting the above technical solutions, based on refined task management and optimization, it helps to more accurately track the status of each task segment; through quality control and standardization, it is beneficial to improve the standardized quality management level of each task segment and achieve quality standardization control and standardized management; further, by marking the task segments with the design product quality lower than the standard quality threshold as unqualified and analyzing the reasons for nonconformity, potential problems and their roots can be quickly identified; at the same time, based on the results of the analysis of the reasons for nonconformity, suggestions for improvement measures are output, such as adjusting monitoring parameters, optimizing sensor layout or strengthening the monitoring intensity at specific positions. The continuous improvement mechanism ensures that the system can continuously adapt to new requirements and technological progress, improving the monitoring efficiency and accuracy.

[0014] In a preferred example of the present application: in the safety monitoring model, a corresponding equipment maintenance strategy is associated with each of the monitoring modular units for equipment status maintenance; the method further includes: Obtain the actual operation time data and its maintenance progress arrangement of each monitoring modular unit to construct a health status change curve corresponding to each monitoring modular unit; According to the health status change curve, analyze the health status change trend of each monitoring modular unit to determine the influence scope of controllable maintenance factors and uncontrollable maintenance factors; Associate the influence scope of the uncontrollable factors with the environmental risk index interval, and combine historical working condition data analysis to conduct risk assessment of the uncontrollable factors to obtain a risk assessment result; Associate the risk assessment result with the corresponding project unit identifier and output warning adjustment information based on the risk assessment result; Dynamically adjust the equipment maintenance strategy of the monitoring modular unit according to the health status change trend and the risk assessment result.

[0015] By adopting the above technical solutions, the association and dynamic adjustment of the monitoring equipment and the equipment maintenance strategy are realized, so that the equipment status of the monitoring equipment is continuously and effectively maintained, which is beneficial to extending the service life of the equipment. Further, the present invention constructs a health status change curve for showing the change of the equipment over time, analyzes the health status change trend of each detection modular unit to determine the influence scope of controllable maintenance factors and uncontrollable maintenance factors, so as to obtain an accurate risk assessment result and improve the accuracy of safety monitoring risk identification. The present invention provides a dynamically adjustable equipment maintenance strategy to ensure that the maintenance activities always conform to the current actual equipment situation, maximizing the safety and reliability of the equipment.

[0016] In a preferred example of the present application: the method further includes: Obtain the historical operating condition data of each monitoring modular unit; based on the historical operating condition data, obtain the operating condition time data and the operating condition measurement data, and construct the operating state change curve of each monitoring modular unit according to the operating condition time data and the operating condition measurement data; Adopt a machine learning algorithm, based on the operating state change curve and the operating condition measurement data, to determine the instability probability data of each monitoring modular unit, where the instability probability data is used to characterize the probability of the monitoring modular unit having an abnormality under specific conditions; compare the instability probability data with a preset risk threshold, and if the instability probability data exceeds the preset risk threshold, trigger a risk warning signal.

[0017] By adopting the above technical solution, an accurate risk assessment method is provided, which can identify in advance the monitoring modular units that need to be focused on, guide the operation and maintenance team to conduct targeted inspections and maintenance, and avoid unnecessary resource waste; specifically, first obtain the historical operating condition data of each monitoring modular unit, and construct an operating state change curve based on the historical operating condition data to introduce a data-driven risk prediction mechanism, which not only improves the accuracy of risk assessment, but also can capture long-term trends and potential problems, enhancing the risk predictability of the system.

[0018] In a preferred example of the present application: the method further includes: Taking each monitoring modular unit as a basic unit, calculate the vulnerability data of the offshore wind power facility according to a preset vulnerability evaluation factor, specifically including: Divide the target monitoring area into average grids, and determine all the grids involved in a single monitoring modular unit; Assign values to each grid within a single monitoring modular unit according to the vulnerability evaluation factor to obtain the vulnerability grid score; extract the arithmetic mean of the vulnerability grid scores of all the grids involved in a single monitoring modular unit to calculate the discrimination score of the vulnerability evaluation factor of the single monitoring modular unit; Use the discrimination score of the vulnerability evaluation factor and the comprehensive index method to calculate the facility vulnerability data of each monitoring modular unit; and / or, Combine the instability probability data and the facility vulnerability data of each monitoring modular unit, and input them into a preset safety risk discrimination matrix to obtain the corresponding safety risk level data.

[0019] By adopting the above technical solutions, the calculation of vulnerability data for each monitoring modular unit is further extended, and it is combined with instability probability data for safety risk assessment; the vulnerability data of the facility is calculated according to the preset vulnerability evaluation factors (such as fan type, tower height, foundation structure form, etc.), ensuring a comprehensive assessment of all factors that may affect the safety of the facility and helping to identify potential vulnerable points; then, through refined grid division and grid replication calculations, in a scientific and quantitative way of vulnerability assessment, the vulnerability data of the facility for each monitoring modular unit is calculated, and the safety risk level data obtained by combining the instability probability data and the facility vulnerability data, with an integrated multi-dimensional data assessment method, significantly improves the accuracy of safety risk assessment and optimizes the safety risk management efficiency of the intelligent safety monitoring platform.

[0020] In the second aspect, the invention object of the present application is achieved by adopting the following technical solutions: An intelligent safety monitoring system for an offshore wind farm, which is used to execute an intelligent safety monitoring method for an offshore wind farm as described above. The system includes: A data collection module, which is used to collect engineering project data, equipment information and environmental parameters of the offshore wind farm, deploy multiple monitoring modular units responsible for different monitoring tasks in the offshore wind farm, and the monitoring modular units perform data acquisition operations based on the received remote configuration parameter instructions. An intelligent safety monitoring platform, which is used to establish a safety monitoring model associated with the project unit identifier, receive the monitoring data collected by each monitoring modular unit, and the intelligent safety monitoring platform supports the analysis and calculation processing of the monitoring data of each monitoring modular unit, and outputs the corresponding safety monitoring results based on the received data query instructions. In the safety monitoring model, based on the project unit identifier and the preset monitoring standard requirements, several key performance indicators are defined for the monitoring modular unit, and corresponding data change thresholds are associated with different key performance indicators of each monitoring modular unit. Based on the data change thresholds, data warning judgments are made. If a certain key performance indicator exceeds the corresponding data change threshold, a safety warning instruction is triggered.

[0021] In the third aspect, the invention object of the present application is achieved by adopting the following technical solutions: A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above intelligent safety monitoring method for an offshore wind farm are implemented.

[0022] In the fourth aspect, the invention object of the present application is achieved by adopting the following technical solutions: A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned intelligent safety monitoring method for an offshore wind farm are implemented.

[0023] In summary, the present application includes at least one of the following beneficial technical effects: 1. Provide an intelligent safety monitoring platform including data collection, monitoring model establishment, data transmission and processing platform construction, and definition of key performance indicators (KPIs) and early warning mechanisms, significantly improving the intelligence level and reliability of the intelligent safety monitoring system for offshore wind farms; 2. Through efforts in data-driven risk prediction, application of machine learning algorithms, real-time dynamic early warning, comprehensive coverage of risk factors, refined grid division and assignment, scientific quantification of vulnerability, integration of multi-dimensional data to improve evaluation accuracy, and optimization of safety risk management, etc., significantly enhance the reliability and intelligence level of the intelligent safety monitoring system for offshore wind farms Description of the Drawings

[0024] Figure 1 is a flowchart of an intelligent safety monitoring method for an offshore wind farm in an embodiment of the present application; Figure 2 is a system home page diagram of an application example of an intelligent safety monitoring platform in an intelligent safety monitoring method for an offshore wind farm in an embodiment of the present application; Figure 3 is an example diagram of a sensor data viewing page of the data collection function in an intelligent safety monitoring platform in an intelligent safety monitoring method for an offshore wind farm in an embodiment of the present application; Figure 4 is an example diagram of a data management page of the data collection function in an intelligent safety monitoring platform in an intelligent safety monitoring method for an offshore wind farm in an embodiment of the present application; Figure 5 is an example diagram of setting data change thresholds for the monitoring and alarm function in an intelligent safety monitoring platform in an intelligent safety monitoring method for an offshore wind farm in an embodiment of the present application; Figure 6 is an example diagram of the application of a three-level alarm mechanism for the monitoring and alarm function in an intelligent safety monitoring platform in an intelligent safety monitoring method for an offshore wind farm in an embodiment of the present application; Figure 7 is an example diagram of a setting page for the monitoring and alarm function in an intelligent safety monitoring platform in an intelligent safety monitoring method for an offshore wind farm in an embodiment of the present application. Detailed Embodiments

[0025] The following further describes the present application in detail with reference to the drawings.

[0026] In one embodiment, as Figure 1 shown, the present application discloses an intelligent safety monitoring method for an offshore wind farm, specifically including the following steps: S1: Collect the project engineering data, equipment information, and environmental parameters of the offshore wind farm. Deploy multiple monitoring modular units responsible for different monitoring tasks in the offshore wind farm, and establish a safety monitoring model associated with the project unit identifier.

[0027] In this embodiment, the project engineering data includes the engineering design documents, construction records, and completion data of the wind farm; the equipment information refers to the technical specifications, operating parameters, and maintenance records of key equipment such as wind turbines, offshore substations, and cables; the environmental parameters refer to natural environmental factors covering marine meteorological conditions (such as wind speed, wave height, and ocean current), hydrogeological characteristics, etc.; the monitoring modular unit refers to an intelligent sensor or monitoring device responsible for different monitoring tasks, such as vibration sensors, inclinometers, stress strain gauges, etc.; the project unit identifier is used to uniquely identify the identity code of the sensing equipment at each monitoring point in the offshore wind farm project, facilitating data management and tracking.

[0028] Specifically, the safety monitoring model is a three-dimensional visual BIM model established based on the offshore wind farm, which is associated with monitoring parameters such as project engineering data, equipment information, and environmental parameters; according to the project engineering data and equipment information, identify the positions crucial for safety, such as tower base, blade connection, cable joint, etc., select appropriate sensor types and technical solutions according to monitoring requirements, such as vibration sensors, inclinometers, stress strain gauges, corrosion potential sensors, etc., install monitoring modular units at the selected key positions, and perform initialization configuration to ensure that each unit can work properly and accurately collect data.

[0029] Furthermore, the present application will also provide stainless steel protective covers for inclinometers, accelerometers, steel plate stress gauges, etc. at the installation positions of the sensors on the basis of not affecting the monitoring function of the sensors for protection.

[0030] Specifically, step S1 further includes: S11: Perform data preprocessing on the project engineering data, equipment information, and environmental parameters of the offshore wind farm to obtain the basic data of the target monitoring area after preprocessing.

[0031] S12: Generate several monitoring modular units in the target monitoring area based on the preprocessed basic data.

[0032] Specifically, based on the engineering project data and equipment information, key positions and indicators that need to be monitored with emphasis are determined, such as tower barrel foundations, blade joints, cable joints, etc. According to the requirements of relevant monitoring standards, the distribution of monitoring points is reasonably planned to ensure that all key parts can be effectively monitored, improving the effectiveness and reliability of monitoring; appropriate sensor types and technical solutions are selected according to the monitoring requirements, such as vibration sensors, inclinometers, stress-strain gauges, corrosion potential sensors, etc.; the topological structure of the monitoring network is designed according to the target detection area to ensure smooth communication between each monitoring modular unit, covering the entire target monitoring area, and monitoring modular units are installed at the selected key positions and initialized to ensure that each unit can work properly and accurately collect data.

[0033] S13: Determine the positions of several monitoring points for each monitoring modular unit according to the position and type of the monitoring modular unit.

[0034] Specifically, confirm the specific position of each monitoring modular unit, and determine the applicable monitoring point positions according to the type of the monitoring modular unit. For example, vibration sensors are suitable for installation at positions prone to vibration; for complex structures or large equipment, the same type of monitoring modular unit may need to be arranged at multiple positions to comprehensively capture state changes.

[0035] For example, each monitoring modular unit is installed based on a pre-set installation process and calculates and analyzes based on a data processing method that meets the data processing requirement standards.

[0036] Example 1: The installation method of the dynamic strain gauge is base welding or glue fixation, and the sensor is fixed with screws. The calculation principle of the dynamic strain gauge includes: Due to the deformation (such as strain change) of the measured surface of the dynamic strain gauge, the relative movement of the two end fixing blocks is caused, resulting in the deformation of the internal elastic element. The high-performance strain gauge pasted on the elastic element senses it and is collected by a data acquisition instrument.

[0037] The sensitive element uses a low-creep and high-precision resistance strain gauge. After strict pasting technology and moisture-proof sealing technical measures, it finally forms a full-bridge output.

[0038] Calculation formula (1): ε=S×△U / U0(1) Where: ε is the strain value (με) of the measured point, U0 is the bridge supply voltage (V) of the sensor, △U is the output voltage (mV) of the sensor, and S is the sensitivity (με / mV / V) of the sensor.

[0039] Substitute the strain value ε into formula (2) to obtain the stress value σ of the measured point: σ=E×ε(2) Where: E is the elastic modulus of the material of the test piece, generally 206 GPa.

[0040] Example 2: The installation method of the static steel plate stress gauge is welding of the base or fixing with expansion bolts, and the sensor is fixed with screws. The calculation principle is as follows: The static steel plate stress gauge is applicable to the long-term strain monitoring of steel structures or concrete structures, including the surface strain measurement of concrete structures or steel structures such as bridges, tunnels, foundation pit supports, columns, steel sheet piles, etc. The static strain calculation formula is as follows: ε = G × C × (R1 - R0) Where: ε - calculated strain value, unit is με; G refers to the instrument standard coefficient, 3.7 με / word; C - average correction coefficient, given by the calibration table; R0 is the initial reading frequency modulus (unit: word); R1 refers to the current reading frequency modulus (unit: word); The strain gauge itself should also consider the influence brought by the change of environmental temperature due to different use environments. Therefore, temperature correction is required. For example, when the strain gauge is installed on a steel structure, the steel string of the sensor has the same temperature expansion coefficient as the steel structure, 12.2 με / °C, and usually no correction is required.

[0041] Stress = Strain * Elastic Modulus = Microstrain * 10^-6 * 206 * 1000 = Microstrain * 0.206 (MPa).

[0042] S14: Associate the monitoring modular unit with the corresponding project unit identifier, and construct a complete safety monitoring model to guide the subsequent deployment and management of the monitoring modular unit.

[0043] Specifically, establish an association between the project unit identifier and the corresponding monitoring points, equipment, and environmental parameters to form a complete data chain; design the logical structure of the safety monitoring model, clarify the relationship between each monitoring modular unit and the data flow direction, and integrate the data from different monitoring modular units onto a unified platform (i.e., the intelligent safety monitoring platform of the present application) to ensure the integrity and consistency of the data.

[0044] S2: Transmit the monitoring data collected by each monitoring modular unit to the preset central control terminal to form an intelligent safety monitoring platform. The monitoring modular unit performs data collection operations based on the received remote configuration parameter instructions; the intelligent safety monitoring platform supports the analysis and calculation processing of the monitoring data of each monitoring modular unit, and outputs the corresponding safety monitoring results based on the received data query instructions.

[0045] In this embodiment, the central control terminal refers to a data center or cloud server located on land, which is used to receive and process data from the monitoring modular unit; the remote configuration parameter instruction is an instruction sent by the monitoring personnel from the central control terminal to the monitoring modular unit, which is used to adjust the monitoring frequency, change the monitoring parameters, etc.; the intelligent security monitoring platform refers to a comprehensive information system that supports functions such as data storage, analysis, calculation processing, and user interface display. The intelligent security monitoring platform also supports the spatio-temporal distribution analysis of data: that is, the inspection and evaluation of the monitored quantity in time and space, mainly including the comparison and analysis of the current monitored quantity with the previous monitored quantity, historical monitored quantity, historical limit quantity, and surrounding similar or related monitored quantities in the same time period, to identify trend values and abnormal values, so as to discover doubts or abnormal values in the time and space distribution of the measured values. Spatio-temporal analysis is applicable to all monitored quantities.

[0046] As Figures 2 to 7 shown, it is an example diagram of an actual application platform of the intelligent security monitoring platform (in the figure, the intelligent security monitoring platform is named Guodian Investment V Security Monitoring System), Figures 3 - 7 which is a function page display diagram of the intelligent security monitoring platform. The function columns named in the intelligent security monitoring platform include a data acquisition function module, a data management function module, a compilation and calculation function module, a report generation function module, a monitoring and alarm function module, a measuring point management function module, a project management function module, a system management function module, and a personal center function module.

[0047] Specifically, the Guodian Investment V Security Monitoring System supports the following functions: (1) Support device management configuration, including the basic information configuration of 71 fans and the equipment information configuration management of 1 booster station, and support users to customize device configuration modification.

[0048] (2) Support monitoring device management, including the configuration and management of 4 types of data such as tilt monitoring, vibration monitoring, corrosion potential monitoring, and stress and strain monitoring, as well as all monitoring devices in this project, and support users to customize device configuration modification.

[0049] (3) Support the configuration and management of monitoring devices, design to realize remote control of monitoring devices and remote instruction sending based on methods such as http and RS485, and can set monitoring parameters of on-site data acquisition units, such as sampling frequency, communication interval, etc., and can also monitor the working status of on-site data acquisition units.

[0050] (4) Support the static monitoring data query function. Users can perform data screening and query through multiple conditions such as monitoring type, fan number, start time, etc., and can export the query results. (5) Support monitoring data query. Users can perform data screening and query through multiple conditions, encrypt the data export function, and can export the query results after entering the password.

[0051] (6) Support device control record query. The system administrator can query the remote control records of each device, including information such as the operator, operation time, and operation behavior.

[0052] (7) Support report record query. The system supports querying the operation records of various file reports, including information such as report browsing time, download time, and operating user.

[0053] (8) Support monitoring report management. According to the requirements of business management, manage the corresponding monitoring reports, such as daily reports, weekly reports, monthly reports, annual reports, etc.

[0054] (9) Integrate the monitoring system user guide file into the system in the form of a PDF file to facilitate the wind farm management personnel to master the monitoring system in a timely manner.

[0055] Specifically, each monitoring modular unit transmits the collected data to the central control terminal in real time through wired or wireless communication. After receiving the remote configuration parameter instruction sent by the central control terminal, the monitoring modular unit automatically adjusts its own working state. The central control terminal cleans, transforms, analyzes, and calculates the received data, extracts valuable information, and can also output the corresponding safety monitoring results, such as visual forms like reports and charts, according to the user's needs through data query instructions.

[0056] S3: In the safety monitoring model, based on the project unit identifier and the preset monitoring standard requirements, define a number of key performance indicators for the monitoring modular unit, and associate corresponding data change thresholds with different key performance indicators of each monitoring modular unit. Based on the data change thresholds, perform data early warning judgment. If a certain key performance indicator exceeds the corresponding data change threshold, trigger a safety early warning instruction.

[0057] In this embodiment, the key performance indicators (KPIs) are important parameters for measuring the health status of offshore wind power facilities, such as settlement rate, vibration amplitude, tilt angle, stress and strain level, corrosion potential change rate, etc.; the data change threshold refers to the preset upper and lower limits of the KPI, which are used to judge whether to trigger an early warning signal; the safety early warning instruction refers to the alarm information automatically generated by the intelligent safety monitoring platform and sent to the user terminals connected to relevant personnel when a certain KPI exceeds the preset threshold.

[0058] Specifically, step S3 further includes: S31: Based on the project unit identifier and the preset monitoring standard requirements, define a number of key performance indicators for each monitoring modular unit. The number of key performance indicators includes settlement rate, vibration amplitude, tilt angle, stress and strain level, corrosion potential change rate; the number of key performance indicators covers all potential safety risk points.

[0059] Specifically, a reasonable measurement range and unit are preset for each key performance indicator, and the selected key performance indicators are associated with the corresponding project unit identifiers, so that each detection point can accurately reflect the state change of its location.

[0060] S32: Associate corresponding data change thresholds with different key performance indicators of each monitoring modular unit.

[0061] Specifically, based on historical data and expert experience, reasonable upper and lower limit thresholds, including first-level, second-level, and third-level warning thresholds, are set for each KPI.

[0062] S33: The intelligent safety monitoring platform receives and analyzes the monitoring data transmitted by each monitoring modular unit, and makes real-time data warning judgments in combination with the corresponding data change thresholds. If a certain key performance indicator exceeds the corresponding data change threshold, a safety warning instruction is triggered and sent to the designated user terminal; Among them, the data change thresholds include first-level warning thresholds, second-level thresholds, and third-level thresholds. The safety warning instructions generate corresponding first-level warning signals, second-level warning signals, and third-level warning signals based on the actual warning levels of the data change thresholds.

[0063] In this embodiment, the first-level warning signal, the second-level warning signal, and the third-level warning signal are yellow, orange, or red warning signals respectively. Further, the network connection status and device status of each monitoring modular unit are also displayed in real time in the intelligent safety monitoring platform. For example, the device connection status is displayed in green, and red represents that the device is not connected; when a certain KPI exceeds the preset threshold, the system automatically generates a warning instruction of the corresponding level and sends it to the designated user terminal.

[0064] In one embodiment, an intelligent safety monitoring method for an offshore wind farm further includes: Taking each monitoring modular unit as a basic unit, perform initial configuration according to a defined number of key performance indicators; after completing the initial configuration of the monitoring modular unit, it further includes: S10: Divide the monitoring tasks of the monitoring modular unit into multiple monitoring task segments according to the project characteristic information and specific work content, and obtain multiple different monitoring task segments.

[0065] In this embodiment, a monitoring task segment refers to dividing the entire monitoring task into multiple independent work segments, each of which is responsible for a specific monitoring task or area; quality acceptance standard information refers to the quality acceptance standards set according to industry specifications, design requirements, and actual operation experience to ensure that the monitoring results are valuable for reference; the standard quality threshold is a specific quality standard set for each monitoring task segment to determine whether the monitoring data meets the expectations; a non-conformance mark refers to marking a design product in a monitoring task segment when its quality is lower than the corresponding standard quality threshold for subsequent processing.

[0066] Specifically, based on the engineering project data and equipment information, identify the key tasks and areas that need to be monitored with emphasis; for example, according to the requirements of the "Technical Regulations for the Construction Organization Design of Offshore Wind Farm Projects" NB / T31033-2019, and in accordance with the project characteristic information (such as geographical location, equipment type) and specific work content (such as regular inspections, specific parameter monitoring), divide the monitoring task into multiple independent work segments, assign a unique identifier to each monitoring task segment, and set start and end times and spatial ranges for each task segment.

[0067] S20: Obtain the quality acceptance standard information corresponding to multiple different monitoring task segments, and associate the corresponding standard quality thresholds based on the quality acceptance standard information.

[0068] In this embodiment, according to the provisions of the "Design Code for the Foundation Safety Monitoring of Wind Turbines in Wind Farm Projects" NB / T10920-2022, obtain the quality acceptance standard information corresponding to multiple different monitoring task segments, and set specific quality thresholds for each monitoring task segment and associate them according to the collected quality acceptance standard information.

[0069] S30: Obtain the quality of the design products in each monitoring task segment, mark the task segments in which the quality of the design products in the monitoring task segments is lower than the corresponding standard quality thresholds as non-conforming to obtain non-conforming marked monitoring segments; analyze the reasons for non-conformance for the non-conforming marked monitoring segments to obtain the results of the analysis of the reasons for non-conformance.

[0070] In this embodiment, each monitoring modular unit collects data at a predetermined frequency and transmits the monitoring data to the intelligent safety monitoring platform through a communication network; conduct in-depth analysis on the non-conforming marked monitoring segments to find out the reasons for quality problems, such as sensor failures, environmental impacts, construction errors, etc.

[0071] S40: Based on the results of the analysis of the reasons for non-conformance, output suggestions for improvement measures, and the improvement measures suggestions include adjusting monitoring parameters, optimizing sensor layout, or strengthening the monitoring intensity at specific positions.

[0072] In this embodiment, adjusting the monitoring parameters includes adjusting the monitoring frequency, monitoring parameters, and monitoring time; optimizing the sensor arrangement includes optimizing the installation position and quantity of sensors; strengthening the monitoring intensity at specific locations includes increasing the detection frequency or deploying more sensors at specific monitoring points with quality problems.

[0073] In one embodiment, in the safety monitoring model, a corresponding equipment maintenance strategy is associated with each monitoring modular unit for equipment status maintenance. An intelligent safety monitoring method for an offshore wind farm further includes: S111: Obtain the actual operation time data and its maintenance schedule of each monitoring modular unit to construct a health status change curve corresponding to each monitoring modular unit.

[0074] Specifically, the equipment maintenance strategy includes predictive maintenance and preventive maintenance; the health status change curve is used to reflect a chart or data sequence driven by the change in health status at different times; the actual operation time data includes start time, shutdown time, fault records, etc.; the maintenance schedule refers to the completed maintenance tasks and upcoming maintenance plans.

[0075] S112: Analyze the health status change trend of each monitoring modular unit according to the health status change curve, and determine the influence scope of controllable maintenance factors and uncontrollable maintenance factors.

[0076] Specifically, the controllable maintenance factors refer to factors that can be adjusted and controlled through human intervention, such as regular inspections, lubrication, component replacement, etc.; the uncontrollable maintenance factors refer to factors that cannot be directly controlled by humans, such as natural environmental conditions (wind speed, temperature, humidity), accidental events, etc.; using statistical analysis and machine learning algorithms, deeply analyze the health status change curve to identify the main factors affecting the equipment health status.

[0077] S113: Associate the influence scope of uncontrollable factors with the environmental risk index interval, and combine historical working condition data analysis to conduct risk assessment of uncontrollable factors to obtain a risk assessment result.

[0078] In this embodiment, the environmental risk index interval is the risk level range evaluated according to environmental conditions. Different risk index intervals are set according to environmental conditions (such as wind speed, temperature, humidity) to quantify the impact of uncontrollable factors on equipment; the risk assessment result is an assessment conclusion of the potential risk degree based on data analysis; for example, three environmental risk index intervals are set: low risk (0 - 2 levels), medium risk (3 - 5 levels), high risk (6 - 10 levels), corresponding to different combinations of wind speed, temperature, and humidity; associate the influence scope of enhanced summer sea breeze with the environmental risk index interval, and it is found that when the wind speed exceeds a certain threshold, the risk index enters the high - risk interval.

[0079] For example, the graph showing the variation of the vibration amplitude of a certain wind turbine over time in the past year shows several obvious fluctuations. Using a machine learning algorithm to analyze the above-mentioned health status change curve, the main factors affecting the health of the wind turbine are identified: for example, it is found that the vibration amplitude of a certain wind turbine increases significantly in a specific season. The analysis results show that the increase in the vibration amplitude of the wind turbine is mainly caused by two factors: one is the bearing wear found during regular inspections (controllable factor), and the other is the increase in mechanical stress caused by the enhanced sea breeze in summer (uncontrollable factor); at this time, the scope of influence is further determined: the analysis shows that the influence of bearing wear on the vibration amplitude is concentrated within a few weeks after each maintenance cycle, while the enhanced sea breeze persists throughout the summer; at this time, three environmental risk index intervals are set: low risk (0-2 levels), medium risk (3-5 levels), high risk (6-10 levels), corresponding to different combinations of wind speed, temperature, and humidity respectively. Associating the scope of influence of the enhanced sea breeze in summer with the environmental risk index interval, it is found that when the wind speed exceeds a certain threshold, the risk index enters the high-risk interval. Further, combining the historical data of the past few years, analyzing the specific impact of the enhanced sea breeze in summer on the health status of the wind turbine, and obtaining the risk assessment result: during the high-risk period, the vibration amplitude of the wind turbine increases significantly, which may lead to more frequent maintenance requirements and potential safety hazards.

[0080] S114: Associate the risk assessment result with the corresponding project unit identifier, and output warning adjustment information based on the risk assessment result.

[0081] In this embodiment, the warning adjustment information includes warning levels (such as yellow, orange, red) and specific recommended measures.

[0082] S115: Dynamically adjust the equipment maintenance strategy of the monitoring modular unit according to the health status change trend and the risk assessment result.

[0083] For example, the vibration amplitude of a certain wind turbine increases significantly during the high-risk period, and the maintenance frequency needs to be increased. The specified maintenance plan is to complete the bearing replacement of all high-risk wind turbines before the end of the next month. At the same time, the existing maintenance strategy is appropriately adjusted, such as increasing the maintenance frequency, optimizing the sensor layout, or strengthening the monitoring intensity at specific positions. For example, during the high-risk period, increase the sampling frequency of the wind turbine vibration sensor to capture abnormal situations more timely.

[0084] In one embodiment, an intelligent safety monitoring method for an offshore wind farm further includes: S100: Obtain the historical operating condition data of each monitoring modular unit; obtain the operating condition time data and operating condition measurement data based on the historical operating condition data, and construct the operating state change curve of each monitoring modular unit according to the operating condition time data and the operating condition measurement data.

[0085] In this embodiment, the historical operating condition data includes various status records during the operation of the equipment, such as temperature, pressure, vibration, stress, etc.; the operating condition time data records the operation of the monitoring equipment in different time periods, such as start time, stop time, maintenance time, etc.; the operating condition measurement data refers to the specific measurement values measured by the monitoring equipment, such as temperature readings, vibration amplitudes, stress and strain levels, etc.; the operating state change curve refers to a chart or data sequence that reflects the change trend of the operating state of the equipment in different time periods.

[0086] S200: Using a machine learning algorithm, based on the operating state change curve and the operating condition measurement data, determine the instability probability data of each monitoring modular unit. The instability probability data is used to characterize the probability of the monitoring modular unit being abnormal under specific conditions.

[0087] In this embodiment, the instability probability data characterizes the probability of the monitoring modular unit being abnormal under specific conditions; select a suitable machine learning algorithm according to the application scenario, such as random forest, support vector machine (SVM), neural network, etc.

[0088] S300: Compare the instability probability data with a preset risk threshold. If the instability probability data exceeds the preset risk threshold, trigger a risk warning signal.

[0089] In this embodiment, the risk threshold refers to a pre-set risk limit, which is used to judge whether to trigger a warning signal.

[0090] Take an application scenario as an example: Collect all the historical operating condition data of Fan A in the past year, including the start time, stop time, maintenance time of each time and the corresponding measurement values such as temperature, vibration amplitude, stress and strain level, etc.; then extract the key time point information (such as start time, stop time, maintenance time) to form the operating condition time data, and extract the specific measurement values (such as temperature, vibration amplitude, stress and strain level) to form the operating condition measurement data; draw the operating state change curve of Fan A to visually display its change trend over time. For example, draw a graph of the vibration amplitude changing with time, showing several obvious fluctuations; at this time, select the random forest algorithm because it performs excellently in dealing with complex non-linear relationships; use the historical data of the past year to train the random forest model so that it can identify the patterns between the normal state and the abnormal state and can predict possible future instability situations. Then use the trained random forest model to calculate the probability of Fan A being abnormal in the next week. The specific steps are as follows: Feature extraction: Extract features from the current data, such as average vibration amplitude, maximum vibration amplitude, temperature change rate, stress and strain level, etc.

[0091] Model prediction: The extracted features are input into a random forest model, and the model outputs a value between 0 and 1, representing the probability of abnormality occurring in Wind Turbine A within the next week. For example, if the model prediction result is 0.75, it means there is a 75% probability of abnormality occurring.

[0092] Furthermore, according to relevant industry standards and actual monitoring experience, a reasonable risk threshold is set for Wind Turbine A. For example, when the instability probability exceeds 0.6, a first-level warning signal is triggered; when it exceeds 0.65, a second-level warning signal is triggered; when it exceeds 0.7, a third-level warning signal is triggered.

[0093] In one embodiment, after step S300, an intelligent safety monitoring method for an offshore wind farm further includes: S101 takes each monitoring modular unit as a basic unit, and calculates the vulnerability data of the offshore wind power facilities according to the preset vulnerability evaluation factors, specifically including: S1011: The target monitoring area is evenly divided into grids, and all grids involved in a single monitoring modular unit are determined.

[0094] Specifically, according to the monitoring accuracy requirements, a suitable grid size (such as 10m×10m) is selected, and the entire target monitoring area is divided into uniform small units (grids) using a Geographic Information System (GIS) tool to ensure coverage of all key positions, determine all grids involved in each monitoring modular unit, and establish an association relationship.

[0095] S1012: Each grid within a single monitoring modular unit is assigned a value according to the vulnerability evaluation factor to obtain the vulnerability grid score.

[0096] Specifically, according to industry standards and actual operation experience, suitable vulnerability evaluation factors are selected, such as material strength, corrosion rate, stress level, etc.; specific assignment rules are formulated. For example, different score ranges (such as 0 - 5 points) are assigned according to different material strengths, and each grid is scored according to the assignment rules to obtain the vulnerability grid score. For example, a certain grid is assigned a higher corrosion rate score because it is in a high-corrosion environment. Through the assignment of vulnerability evaluation factors in the present invention, the scientific quantification of risks is achieved.

[0097] S1013: The arithmetic mean of the vulnerability grid scores of all grids involved in a single monitoring modular unit is extracted to calculate the discriminant score of the vulnerability evaluation factor of the single monitoring modular unit.

[0098] Specifically, the vulnerability evaluation factor is an index used to evaluate the degree of vulnerability of equipment or structures under specific conditions, such as material properties, environmental impacts, etc.; the vulnerability data refers to the comprehensive value reflecting the vulnerability of facilities calculated based on multiple evaluation factors; grid division refers to dividing the target monitoring area into several uniform small units (grids) for more refined analysis; the vulnerability grid score refers to the score obtained by assigning values to each grid according to the vulnerability evaluation factors; the vulnerability evaluation factor discrimination score refers to the comprehensive vulnerability score of a single monitoring modular unit calculated by the arithmetic mean.

[0099] Specifically, collect the vulnerability grid scores of all grids involved in a single monitoring modular unit, perform arithmetic averaging on all grid scores, and calculate the vulnerability evaluation factor discrimination score of a single monitoring modular unit; for example, the vulnerability evaluation factor discrimination score of a certain fan is 4.2. Through arithmetic averaging, the vulnerability conditions of all grids are comprehensively considered, avoiding the influence of local outliers.

[0100] S1014: Calculate the facility vulnerability data of each monitoring modular unit using the vulnerability evaluation factor discrimination score and the comprehensive index method.

[0101] Specifically, select a suitable comprehensive index method according to the application scenario, such as the Analytic Hierarchy Process (AHP), fuzzy comprehensive evaluation method, etc., and construct a weight system for each vulnerability evaluation factor to ensure that the importance of different factors is reflected. Use the vulnerability evaluation factor discrimination score and the weight system to calculate the facility vulnerability data of each monitoring modular unit through the comprehensive index method. For example, the facility vulnerability data of a certain fan is 85 points.

[0102] and / or S1015: Combine the instability probability data and the facility vulnerability data of each monitoring modular unit, input them into a preset safety risk discrimination matrix, and obtain the corresponding safety risk level data.

[0103] In this embodiment, first define a safety risk discrimination matrix, that is, set a two-dimensional matrix. The horizontal axis represents the instability probability data (such as between 0 and 1), and the vertical axis represents the facility vulnerability data (such as between 0 and 100 points). Each grid corresponds to a safety risk level (such as low, medium, high). Input the instability probability data and the facility vulnerability data of each monitoring modular unit into the safety risk discrimination matrix, find the corresponding grid, determine its safety risk level, and then send the determined safety risk level data to the central control terminal to notify the relevant responsible personnel to take appropriate preventive or emergency response measures; for example, a certain fan is judged as "high risk", and a corresponding level 3 warning signal is immediately triggered; further, different safety risk levels can be distinguished and prompted by different warning signals.

[0104] It should be understood that the sequence numbers of the steps in the above embodiments do not indicate the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0105] In one embodiment, an intelligent safety monitoring system for an offshore wind farm is provided, and the intelligent safety monitoring system for the offshore wind farm corresponds to an intelligent safety monitoring method for an offshore wind farm in the above embodiment.

[0106] An intelligent safety monitoring system for an offshore wind farm includes a data collection module and an intelligent safety monitoring platform. The detailed descriptions of each functional module are as follows: The data collection module is used to collect the engineering project data, equipment information and environmental parameters of the offshore wind farm. A plurality of monitoring modular units responsible for different monitoring tasks are deployed in the offshore wind farm, and the monitoring modular units execute data acquisition operations based on the received remote configuration parameter instructions. The intelligent safety monitoring platform is used to establish a safety monitoring model associated with the project unit identifier, receive the monitoring data collected by each monitoring modular unit, and the intelligent safety monitoring platform supports the analysis and calculation processing of the monitoring data of each monitoring modular unit, and outputs the corresponding safety monitoring results based on the received data query instructions. In the safety monitoring model, based on the project unit identifier and the preset monitoring standard requirements, several key performance indicators are defined for the monitoring modular unit, and corresponding data change thresholds are associated with different key performance indicators of each monitoring modular unit. Based on the data change thresholds, data warning judgment is performed. If a certain key performance indicator exceeds the corresponding data change threshold, a safety warning instruction is triggered.

[0107] For the specific limitations of an intelligent safety monitoring system for an offshore wind farm, reference can be made to the limitations of an intelligent safety monitoring method for an offshore wind farm in the above text, which will not be elaborated here; each module in the above intelligent safety monitoring system for an offshore wind farm can be implemented in whole or in part by software, hardware and their combinations; the above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so as to facilitate the processor to call and execute the operations corresponding to the above each module.

[0108] In one embodiment, a computer device is provided, which may be a server. The computer device includes a processor, a memory, a network interface, and a database connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store engineering project data, equipment information, environmental parameters, and so on. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, it implements a method for intelligent safety monitoring of an offshore wind farm.

[0109] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the method for intelligent safety monitoring of an offshore wind farm as described above.

[0110] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by the processor, it implements the steps of the method for intelligent safety monitoring of an offshore wind farm as described above.

[0111] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it may include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in the present application may include non-volatile and / or volatile memories. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or an external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0112] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0113] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. An intelligent safety monitoring method for an offshore wind farm, characterized in that: include: Collect engineering project data, equipment information and environmental parameters of offshore wind farms, deploy multiple monitoring modular units responsible for different monitoring tasks in offshore wind farms, and establish a safety monitoring model with associated project unit identification; Transmitting the monitoring data collected by each monitoring modular unit to a preset central control terminal to form an intelligent safety monitoring platform, wherein the monitoring modular unit performs data collection operations based on the received remote configuration parameter instructions; The intelligent safety monitoring platform supports analysis and calculation of monitoring data of each monitoring modular unit, and outputs corresponding safety monitoring results based on received data query instructions; In the safety monitoring model, based on the project unit identification and preset monitoring standard requirements, several key performance indicators are defined for the monitoring modular unit, and corresponding data change thresholds are associated with different key performance indicators of each monitoring modular unit. Data warning judgment is performed based on the data change thresholds. If a key performance indicator exceeds the corresponding data change threshold, a safety warning instruction is triggered.

2. The method for intelligent safety monitoring of offshore wind farms according to claim 1, characterized in that: The collection of engineering project data, equipment information and environmental parameters of the offshore wind farm, deployment of multiple monitoring modular units responsible for different monitoring tasks in the offshore wind farm, and establishment of a safety monitoring model associated with the project unit identification specifically include: Performing data preprocessing on the engineering project data, equipment information and environmental parameters of the offshore wind farm to obtain basic data of the preprocessed target monitoring area; Based on the preprocessed basic data, generating a plurality of monitoring modular units within the target monitoring area; Determining the locations of a plurality of monitoring points of each monitoring modular unit according to the location and type of the monitoring modular unit; The monitoring modular units are associated with corresponding project unit identifiers, and a complete safety monitoring model is constructed to guide the deployment and management of subsequent monitoring modular units.

3. The method for intelligent safety monitoring of offshore wind farms according to claim 1, characterized in that: In the safety monitoring model, based on the project unit identification and the preset monitoring standard requirements, several key performance indicators are defined for the monitoring modular unit, and different key performance indicators of each monitoring modular unit are associated with corresponding data change thresholds. Data early warning judgment is performed based on the data change thresholds. If a key performance indicator exceeds the corresponding data change threshold, a safety early warning instruction is triggered, including: Based on the project unit identification and preset monitoring standard requirements, several key performance indicators are defined for each monitoring modular unit, including sedimentation rate, vibration amplitude, tilt angle, stress strain level, corrosion potential change rate; several of the key performance indicators cover all potential safety risk points; Associating corresponding data change thresholds for different key performance indicators of each monitoring modular unit; The intelligent safety monitoring platform receives and analyzes the monitoring data transmitted by each monitoring modular unit, and performs real-time data warning judgment in combination with the corresponding data change threshold. If a key performance indicator exceeds the corresponding data change threshold, a safety warning instruction is triggered and sent to the designated user terminal; Among them, the data change threshold includes a first-level warning threshold, a second-level threshold, and a third-level threshold. The security warning instruction generates corresponding first-level warning signals, second-level warning signals, and third-level warning signals based on the actual warning level of the data change threshold.

4. The method for intelligent safety monitoring of an offshore wind farm according to claim 1, characterized in that: The method further comprises: taking each of the monitoring modular units as a basic unit, performing initial configuration according to a number of defined key performance indicators; After the initial configuration of the monitoring modular unit is completed, it also includes: Dividing the monitoring task of the monitoring modular unit into a plurality of monitoring task segments according to project characteristic information and specific work content, thereby obtaining a plurality of different monitoring task segments; Acquire quality acceptance standard information corresponding to a plurality of different monitoring task segments, and associate corresponding standard quality thresholds based on the quality acceptance standard information; Obtain the designed product quality in each monitoring task segment, mark the task segment whose designed product quality in the monitoring task segment is lower than the corresponding standard quality threshold as unqualified, and obtain the unqualified marked monitoring segment; analyze the unqualified causes of the unqualified marked monitoring segment to obtain the unqualified cause analysis results; Based on the analysis results of the reasons for non-conformity, improvement measures are suggested, including adjusting monitoring parameters, optimizing sensor layout or strengthening monitoring efforts at specific locations.

5. The method for intelligent safety monitoring of offshore wind farms according to claim 1, characterized in that: In the safety monitoring model, each monitoring modular unit is associated with a corresponding equipment maintenance strategy to perform equipment status maintenance; the method further includes: Obtaining the actual operating time data of each monitoring modular unit and its maintenance schedule to construct a health status change curve corresponding to each monitoring modular unit; According to the health status change curve, the health status change trend of each monitoring modular unit is analyzed to determine the influence range of controllable maintenance factors and uncontrollable maintenance factors; Associating the influence range of the uncontrollable factors with the environmental risk index range, and combining with historical operating condition data analysis to conduct risk assessment of the uncontrollable factors to obtain risk assessment results; Associating the risk assessment result with the corresponding project unit identifier, and outputting early warning adjustment information based on the risk assessment result; The equipment maintenance strategy of the monitoring modular unit is dynamically adjusted according to the health status change trend and risk assessment result.

6. The method for intelligent safety monitoring of offshore wind farms according to claim 1, characterized in that: The method also includes: Acquire historical operating condition data of each monitoring modular unit; acquire operating condition time data and operating condition measurement data based on the historical operating condition data, and construct an operating state change curve of each monitoring modular unit according to the operating condition time data and the operating condition measurement data; Using a machine learning algorithm, based on the operating state change curve and the working condition measurement data, determine the instability probability data of each monitoring modular unit, wherein the instability probability data is used to characterize the probability of abnormality of the monitoring modular unit under specific conditions; The instability probability data is compared with a preset risk threshold, and if the instability probability data exceeds the preset risk threshold, a risk warning signal is triggered.

7. The method for intelligent safety monitoring of offshore wind farms according to claim 6, characterized in that: The method further comprises: Taking each monitoring modular unit as the basic unit, the vulnerability data of offshore wind power facilities is calculated according to the preset vulnerability assessment factors, including: Divide the target monitoring area into average grids and determine all grids involved in a single monitoring modular unit; Assign a value to each grid in a single monitoring modular unit according to the vulnerability assessment factor to obtain the vulnerability grid score; The arithmetic mean of the vulnerability grid scores of all grids involved in a single monitoring modular unit is extracted to calculate the vulnerability assessment factor discrimination score of a single monitoring modular unit; The vulnerability data of the facility of each monitoring modular unit is calculated by using the vulnerability assessment factor discrimination score and the comprehensive index method; and / or, The instability probability data of each monitoring modular unit and the facility vulnerability data are combined and input into a preset safety risk judgment matrix to obtain corresponding safety risk level data.

8. An intelligent safety monitoring system for offshore wind farms, characterized in that: The system is used to execute an offshore wind farm intelligent safety monitoring method according to any one of claims 1 to 7, the system comprising: A data collection module is used to collect engineering project data, equipment information and environmental parameters of the offshore wind farm. A plurality of monitoring modular units responsible for different monitoring tasks are deployed in the offshore wind farm. The monitoring modular units perform data collection operations based on the received remote configuration parameter instructions; An intelligent safety monitoring platform, used to establish a safety monitoring model associated with the project unit identification, receive monitoring data collected by each monitoring modular unit, support analysis and calculation processing of the monitoring data of each monitoring modular unit, and output corresponding safety monitoring results based on the received data query instructions; In the safety monitoring model, based on the project unit identification and preset monitoring standard requirements, several key performance indicators are defined for the monitoring modular unit, and corresponding data change thresholds are associated with different key performance indicators of each monitoring modular unit. Data warning judgment is performed based on the data change thresholds. If a key performance indicator exceeds the corresponding data change threshold, a safety warning instruction is triggered.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the offshore wind farm intelligent safety monitoring method as claimed in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of an offshore wind farm intelligent safety monitoring method as claimed in any one of claims 1 to 7 are implemented.

Images