A safety evaluation optimization method, system, equipment and medium for offshore wind power

Abstract

The present application relates to the technical field of offshore wind power, and in particular to a safety evaluation optimization method, system, equipment and medium for offshore wind power. The present application divides the wind farm into different safety management partitions according to the wind farm division information, and evaluates the safety risk level of each partition to generate a safety risk distribution map of the entire wind farm; then the operation control parameters of the wind turbine are obtained according to the risk level of the partition, and the operation control instructions are triggered; at the same time, the operation status of each partition is monitored in real time, the risk change trend is predicted, and parameter adjustment information is generated to trigger the corresponding parameter adjustment instructions; the present invention adopts a differentiated control strategy for the safety risks of different partitions of the offshore wind farm, improves the effectiveness of safety evaluation and optimization control, and at the same time monitors the operation status of the partition in real time and predicts the risk change trend, dynamically adjusts the operation control parameters of the wind turbine, and promptly responds to changes in the external environment and its own state, so as to improve the adaptability and flexibility of the wind farm operation.

Description

Technical Field

[0001] The present application relates to the technical field of offshore wind power, and in particular to a method, system, equipment and medium for optimizing safety evaluation of offshore wind power. Background Art

[0002] The marine environment where offshore wind farms are located is complex and changeable, and wind turbines face many safety risks and uncertainties during operation. How to ensure the safe and efficient operation of offshore wind farms has become a key issue that needs to be urgently addressed.

[0003] At present, the safety evaluation and optimization control of offshore wind farms mainly rely on the status monitoring system of wind turbines and the preset operation control strategy. By real-time monitoring of key parameters such as vibration, temperature, and speed of wind turbines, and judging the safety status of wind turbines according to pre-set thresholds, fault warning and protection control of wind turbines can be achieved. At the same time, the operation control parameters of wind turbines are usually pre-set according to factors such as wind resource conditions and grid connection requirements, and remain relatively fixed during the operation of wind turbines. It is difficult to adjust the operating status of wind turbines in time according to the dynamic changes of external environmental conditions. This situation needs to be further improved. Summary of the invention

[0004] In order to solve the problem that the existing wind turbine operating status is difficult to adjust in time according to the dynamic changes of external environmental conditions, the present application provides a safety evaluation optimization method, system, equipment and medium for offshore wind power, adopting the following technical solutions: In the first aspect, the present application provides a safety evaluation optimization method for offshore wind power, comprising the following steps:

[0005] Obtain wind farm division information, and divide the offshore wind farm into different safety management zones according to the wind farm division information; obtain abnormal state change trends and safety state change trends of each safety management zone, determine the safety risk level of each safety management zone according to the abnormal state change trends and safety state change trends, and generate a safety risk distribution map of the offshore wind farm;

[0006] According to the safety risk distribution map, the operation control parameters of the fans in each safety management zone are obtained, and the operation control instructions are triggered according to the operation control parameters;

[0007] Obtaining real-time monitoring data of each security management zone, and predicting the risk change trend in the future based on the real-time monitoring data;

[0008] Obtain parameter adjustment information based on risk change trend prediction results;

[0009] A parameter adjustment instruction is triggered according to the parameter adjustment information.

[0010] By adopting the above technical scheme, the present application first divides the wind farm into different safety management zones according to the wind farm division information, and evaluates the safety risk level of each zone respectively, and generates a safety risk distribution map of the entire wind farm; then, the operation control parameters of the wind turbine are obtained differentially according to the risk level of the zone, and the corresponding operation control instructions are dynamically triggered; at the same time, the operation status of each zone is monitored in real time, the risk change trend in the future period is predicted, and parameter adjustment information is generated accordingly to trigger the corresponding parameter adjustment instructions; the present invention can adopt differentiated evaluation and control strategies according to the safety risk characteristics of different zones of the offshore wind farm, improve the accuracy and effectiveness of safety evaluation and optimization control, and at the same time, by real-time monitoring of the operation status of the zone and predicting the risk change trend, the operation control parameters of the wind turbine can be dynamically adjusted so that it can respond to changes in the external environment and its own state in a timely manner, thereby improving the adaptability and flexibility of the wind farm operation.

[0011] Optionally, obtaining wind farm division information, and dividing the offshore wind farm into different safety management zones according to the wind farm division information, specifically includes the following steps:

[0012] According to the wind farm division information, obtaining geographical location information, sea condition characteristic parameters and power device layout information of the offshore wind farm;

[0013] Divide the offshore wind farm into a number of non-overlapping functional areas according to the geographical location information and the layout information of the power devices, each functional area comprising wind turbines and power devices that are geographically close and closely connected to each other;

[0014] Calculating the sea condition risk level of the target functional area according to the sea condition characteristic parameters of the target functional area, wherein the target functional area is any one of the functional areas;

[0015] The sea condition risk level of the target functional area is combined with the functional attribute corresponding to the target functional area to obtain the safety management partition identification of the target functional area.

[0016] By adopting the above technical solution, the present application first divides the offshore wind farm into several non-overlapping functional areas according to the geographical location information and power equipment layout information of the wind farm, and then calculates the corresponding sea condition risk level for each functional area according to its sea condition characteristic parameters, and combines the sea condition risk level with the functional attributes of the functional area to obtain the safety management zoning identification of the functional area; in this way, the zoning results are made more comprehensive and accurate, providing a basis for subsequent differentiated management and control.

[0017] Optionally, obtaining the abnormal state change trend and the safety state change trend of each safety management zone, determining the safety risk level of each safety management zone according to the abnormal state change trend and the safety state change trend, and generating the safety risk distribution map of the offshore wind farm specifically includes the following steps:

[0018] Acquire historical monitoring data of the target safety management partition, the historical monitoring data including wind turbine operating status parameters, power equipment operating parameters and sea environment parameters; perform sliding window division on the historical data of each monitoring parameter to obtain parameter samples within a plurality of time windows, the target safety management partition being any one of the safety management partitions;

[0019] Perform anomaly detection on parameter samples in the current time window, count the number and proportion of abnormal samples, generate an abnormal state quantity of the current time window, calculate the change rate between the abnormal state quantity of the current time window and the abnormal state quantity of the previous time window, and obtain the abnormal state change trend;

[0020] Perform security status assessment on the preset parameter samples in the current time window, weightedly integrate the security indicators of various preset parameter samples, obtain the comprehensive security status score of the current time window, calculate the change rate between the comprehensive security status score of the current time window and the score of the previous time window, and obtain the security status change trend;

[0021] Acquire the functional attributes corresponding to the target security management partition, and determine the importance weight coefficient of the target security management partition according to the functional attributes corresponding to the target security management partition;

[0022] Input the abnormal state quantity, abnormal state change trend, comprehensive safety state score, safety state change trend, and importance weight coefficient into a pre-established safety risk assessment model to obtain the safety risk level of the target safety management zone;

[0023] Based on the safety risk levels of the various safety management zones, a safety risk distribution map of the offshore wind farm is generated.

[0024] By adopting the above technical scheme, since the abnormal state and safety state of each safety management zone of an offshore wind farm are dynamically changing, the present application divides the historical monitoring data of each zone by means of a sliding window, and evaluates the abnormal state and safety state in each time window, and then calculates the rate of change between adjacent time windows to obtain the dynamic change trend of the abnormal state and safety state, and then combines the importance weight of the zone, calculates the safety risk level of each zone through a pre-established safety risk assessment model, and finally generates a safety risk distribution map of the entire wind farm, thereby constructing a complete set of safety risk assessment models, and dynamically reflects the evolution law of the abnormal state and safety state of each zone, making the risk assessment results more accurate and timely.

[0025] Optionally, according to the safety risk distribution map, the operation control parameters of the fans in each safety management zone are obtained, and the operation control instructions are triggered according to the operation control parameters, which specifically includes the following steps:

[0026] According to the security risk distribution map, identifying risk zones with preset security risk level thresholds;

[0027] Acquire historical operation control parameters of the wind turbines in the risk zone, and predict the safety risk probabilities corresponding to different operation control parameters according to the safety risk levels and historical operation control parameters corresponding to the risk zones;

[0028] According to the comparison result of the safety risk probability and the preset probability threshold, a target operation control parameter for reducing the safety risk level of the risk zone is obtained;

[0029] According to the target operation control parameter, an operation control instruction corresponding to each wind turbine in the risk zone is triggered.

[0030] By adopting the above-mentioned technical scheme, the present application first identifies the risk zone whose safety risk level exceeds the preset threshold according to the safety risk distribution map, then obtains the historical operation control parameters of the wind turbine in the risk zone, and combines the safety risk level of the zone to predict the probability of safety risk under different operation control parameter settings, then compares the predicted safety risk probability with the preset probability threshold, and selects the operation control parameter with the risk probability lower than the threshold as the target operation control parameter for reducing the risk, and finally, according to the target operation control parameter, sends corresponding operation control instructions to each wind turbine in the risk zone to adjust its operating status to reduce the overall safety risk level of the area, and realizes the quantitative optimization of the operation control parameters by predicting the risk probability of different parameters, avoiding empirical subjective parameter adjustment, improving the scientificity and reliability of parameter adjustment, and having fast response speed and good execution effect, which greatly improves the timeliness and accuracy of risk management.

[0031] Optionally, triggering a parameter adjustment instruction according to the parameter adjustment information specifically includes the following steps:

[0032] According to the parameter adjustment information, obtaining the adjustment time point and the operation control parameters after adjustment of the fan;

[0033] Comparing the adjusted operation control parameter with a preset safety threshold, and if the adjusted operation control parameter does not exceed the preset safety threshold range, triggering a parameter adjustment instruction according to the adjustment time point;

[0034] If the adjusted operating control parameter exceeds the preset safety threshold range, a parameter adjustment secondary optimization instruction is triggered;

[0035] According to the parameter adjustment secondary optimization instruction, secondary adjustment parameter information is obtained, and according to the secondary adjustment parameter information, the parameter adjustment instruction is triggered.

[0036] By adopting the above-mentioned technical scheme, before triggering the parameter adjustment instruction, the present application first compares the adjusted operation control parameters with the preset safety threshold value. If the parameters do not exceed the safety range, the adjustment instruction is directly triggered. If the parameters exceed the safety range, the parameter secondary optimization process is started to correct the adjustment parameters to ensure that the safety constraints are met before triggering the adjustment instruction, thereby achieving safe and controllable parameter adjustment, ensuring the safety and feasibility of the adjustment instructions, and improving the success rate and reliability of the parameter adjustment. At the same time, through the setting and control of the time point, the parameter adjustment instruction is accurately triggered and executed, avoiding the risks caused by inappropriate adjustment timing.

[0037] Optionally, according to the parameter adjustment secondary optimization instruction, obtaining secondary adjustment parameter information, and according to the secondary adjustment parameter information, triggering the parameter adjustment instruction specifically includes the following steps:

[0038] According to the parameter adjustment secondary optimization instruction, a risk attenuation factor α of the wind turbine corresponding to the adjusted operation control parameter exceeding the preset safety threshold range is obtained, wherein 0<α<1;

[0039] Acquire the current operating state and environmental information of the wind turbine, and calculate the adjustment coefficient β of the risk attenuation factor according to the current operating state and environmental information;

[0040] According to the risk attenuation factor and the adjustment coefficient, the secondary adjusted operation control parameter P is calculated. adj =P base +α*β*(P opt -P base ), where P base is the reference operating control parameter of the fan, P optAdjusted operating control parameters that exceed preset safety thresholds;

[0041] Determine whether the operating control parameters after the secondary adjustment still exceed the preset safety threshold range, if not, trigger the parameter adjustment instruction;

[0042] If so, the risk attenuation factor α is decreased according to the preset step size until the secondary adjusted operation control parameter does not exceed the preset safety threshold range.

[0043] By adopting the above-mentioned technical scheme, this application introduces a risk attenuation factor to quantify the adjustment range of the over-limit parameters, and at the same time calculates the adjustment coefficient in combination with the current operating status and environmental information of the wind turbine, adaptively corrects the risk attenuation factor, and then calculates the secondary adjusted operating control parameters through the risk attenuation model, and ensures that they meet the safety threshold requirements through iterative checks, and finally triggers more optimized parameter adjustment instructions to achieve dynamic optimization of the adjustment parameters, which has better applicability and robustness.

[0044] In a second aspect, the present application provides a safety evaluation and optimization system for offshore wind power, comprising:

[0045] A safety management partition division module is used to obtain wind farm division information and divide the offshore wind farm into different safety management partitions according to the wind farm division information;

[0046] A risk distribution map generating module is used to obtain the abnormal state change trend and the safety state change trend of each safety management zone, determine the safety risk level of each safety management zone according to the abnormal state change trend and the safety state change trend, and generate the safety risk distribution map of the offshore wind farm;

[0047] An operation control instruction triggering module is used to obtain the operation control parameters of the fans in each safety management zone according to the safety risk distribution map, and trigger the operation control instruction according to the operation control parameters;

[0048] The risk change trend prediction module is used to obtain the real-time monitoring data of each security management zone and predict the risk change trend in the future based on the real-time monitoring data;

[0049] The parameter adjustment information acquisition module is used to obtain parameter adjustment information based on the risk change trend prediction results;

[0050] The parameter adjustment instruction triggering module is used to trigger the parameter adjustment instruction according to the parameter adjustment information.

[0051] Optionally, the security management partition division module includes:

[0052] An information acquisition unit, used to acquire geographical location information, sea condition characteristic parameters and power device layout information of the offshore wind farm according to the wind farm division information;

[0053] A region division unit, used to divide the offshore wind farm into a number of non-overlapping functional areas according to the geographical location information and the layout information of the power devices, each functional area contains wind turbines and power devices that are close in geographical location and closely connected in electricity; a level calculation unit, used to calculate the sea condition risk level of the target functional area according to the sea condition characteristic parameters of the target functional area, the target functional area being any one of the functional areas;

[0054] The partition identification unit is used to combine the sea condition risk level of the target functional area with the functional attribute corresponding to the target functional area to obtain the safety management partition identification of the target functional area.

[0055] In a third aspect, the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned offshore wind power safety assessment optimization method when executing the computer program.

[0056] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above-mentioned offshore wind power safety assessment optimization method are implemented.

[0057] In summary, the present application includes at least one of the following beneficial technical effects:

[0058] 1. The present application first divides the wind farm into different safety management zones according to the wind farm division information, and evaluates the safety risk level of each zone respectively, and generates a safety risk distribution map of the entire wind farm; then, the operation control parameters of the wind turbine are obtained according to the risk level of the zone, and the operation control instructions are triggered; at the same time, the operation status of each zone is monitored in real time, the risk change trend is predicted, and parameter adjustment information is generated to trigger the corresponding parameter adjustment instructions; the present invention can adopt differentiated control strategies according to the safety risk characteristics of different zones of the offshore wind farm, improve the accuracy and effectiveness of safety evaluation and optimization control, and at the same time, by real-time monitoring of the operation status of the zone and predicting the risk change trend, dynamically adjust the operation control parameters of the wind turbine, and promptly respond to changes in the external environment and its own state, thereby improving the adaptability and flexibility of wind farm operation;

[0059] 2. This application first divides the offshore wind farm into several non-overlapping functional areas based on the geographical location information and power device layout information of the wind farm, and then calculates the corresponding sea condition risk level for each functional area based on its sea condition characteristic parameters, and combines the sea condition risk level with the functional attributes of the functional area to obtain the safety management zoning identification of the functional area; in this way, the zoning results are more comprehensive and accurate, providing a basis for subsequent differentiated management and control;

[0060] 3. Since the abnormal status and safety status of each safety management zone of an offshore wind farm change dynamically, this application divides the historical monitoring data of each zone by means of a sliding window, and evaluates the abnormal status and safety status in each time window, and then calculates the rate of change between adjacent time windows to obtain the dynamic change trend of the abnormal status and safety status. Combined with the importance weight of the zone, the safety risk level of each zone is calculated through a pre-established safety risk assessment model, and finally a safety risk distribution map of the entire wind farm is generated, thereby constructing a complete set of safety risk assessment models, and dynamically reflecting the evolution of the abnormal status and safety status of each zone, making the risk assessment results more accurate and timely. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 It is a flow chart of a safety evaluation optimization method for offshore wind power according to an embodiment of the present application;

[0062] Figure 2 It is a flow chart of step S100 in a safety evaluation optimization method for offshore wind power according to an embodiment of the present application;

[0063] Figure 3 It is a flowchart of step S200 in a safety evaluation optimization method for offshore wind power according to an embodiment of the present application;

[0064] Figure 4 It is a flowchart of step S300 in a safety evaluation optimization method for offshore wind power according to an embodiment of the present application;

[0065] Figure 5 It is a flowchart of step S600 in a safety evaluation optimization method for offshore wind power according to an embodiment of the present application;

[0066] Figure 6 It is a flowchart of step S640 in a safety evaluation optimization method for offshore wind power according to an embodiment of the present application;

[0067] Figure 7 This is a module schematic diagram of a safety evaluation and optimization system for offshore wind power in an embodiment of the present application;

[0068] Figure 8It is a diagram of the internal structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0069] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification and appended claims of the present application, the singular expressions "one", "a kind of", "said", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations comprising one or more listed items.

[0070] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0071] The embodiments of the present application are further described in detail below in conjunction with the drawings in the specification.

[0072] In the first aspect, the present application provides a safety evaluation optimization method for offshore wind power, referring to Figure 1 , including the following steps: S100, obtaining wind farm division information, and dividing the offshore wind farm into different safety management zones according to the wind farm division information.

[0073] In this embodiment, the acquired wind farm division information includes but is not limited to: geographical location information of the wind farm, wind turbine distribution information, cable topology information, etc. Based on this information, the wind farm can be divided into several safety management partitions, each of which contains a certain number of wind turbines and related equipment.

[0074] Specifically, when dividing the safety management zones, various factors can be comprehensively considered, such as the geographical distribution of wind turbines, electrical connection topology, wind environment characteristics, etc., and clustering algorithms, network partitioning algorithms, etc. can be used to divide the wind farm into several relatively independent zones with certain management significance. For example, the zones can be divided according to the geographical areas where the wind turbines are located, with each zone being a safety management zone; the zones can also be divided according to the electrical topology of the wind turbines, with wind turbines with close electrical connections being divided into the same zone; the zones can also be divided in combination with wind condition characteristics, with areas with similar wind conditions being divided into the same zone.

[0075] S200, obtaining abnormal state change trends and safety state change trends of each safety management zone, determining the safety risk level of each safety management zone according to the abnormal state change trends and safety state change trends, and generating a safety risk distribution map of the offshore wind farm.

[0076] In this embodiment, the abnormal state change trend and the safety state change trend can be obtained by analyzing the historical monitoring data of the fans and equipment in each partition. The abnormal state change trend reflects the changes in the frequency and severity of abnormal events in the partition, and the safety state change trend reflects the changes in the overall safety level of the partition.

[0077] Specifically, statistical analysis, machine learning and other methods are used to mine and model the historical monitoring data of each partition to identify the changing patterns and laws of abnormal status and safety status. For example, the number and level of abnormal alarms in each partition can be statistically analyzed to determine whether the frequency and severity of abnormalities show an upward or downward trend; trend prediction can be performed on safety indicators such as vibration and temperature of the fan to determine the possible changing trend of the safety status in the future; and the abnormal status and safety status of each partition can be graded and compared through machine learning algorithms such as clustering and classification to obtain the relative risk level differences between partitions. Finally, according to the risk level of each partition, an intuitive safety risk distribution map is generated to provide a decision-making basis for risk management.

[0078] S300. According to the safety risk distribution map, the operation control parameters of the fans in each safety management zone are obtained, and the operation control instructions are triggered according to the operation control parameters.

[0079] In this embodiment, the operation control parameters include the start and stop state of the wind turbine, the power limit value, the pitch angle, the yaw angle, etc. The adjustment of these parameters can affect the power generation performance and safety performance of the wind turbine. According to the safety risk distribution map, corresponding operation control strategies and parameter settings can be formulated for different risk levels of partitions.

[0080] Specifically, for partitions with higher safety risk levels, more stringent and conservative operation control measures are taken, such as reducing power limit values, increasing pitch angles, etc., in order to sacrifice certain power generation benefits in exchange for higher safety margins; for partitions with lower safety risk levels, control parameter restrictions are appropriately relaxed, such as increasing power limit values, reducing pitch angles, etc., to maximize power generation performance while ensuring safety. Specific parameter settings can be determined through simulation analysis, expert experience, etc. The triggering of operation control instructions can be automatically issued through the centralized monitoring system of the wind farm, or it can be manually executed by the on-duty staff.

[0081] S400. Acquire real-time monitoring data of each security management partition, and predict the risk change trend in the future based on the real-time monitoring data.

[0082] In this embodiment, the real-time monitoring data includes SCADA operation data of the wind turbine, CMS status monitoring data, meteorological environment monitoring data, etc. These data reflect the real-time operation status and external environmental conditions of each partition of the wind farm. By analyzing and predicting the real-time data, the risk change trend can be grasped in time, providing a basis for dynamic optimization control.

[0083] Specifically, a risk prediction model is established using machine learning algorithms, such as support vector machines, random forests, neural networks, etc., and real-time monitoring data of each partition is input to predict the changing trend of risk levels in the future, such as the next 24 hours. The model is trained using historical monitoring data and corresponding risk level label data. Through the rolling input of real-time data and model reasoning, continuous risk change trend prediction results can be obtained, providing real-time basis for control optimization. At the same time, the risk prediction model can regularly use new monitoring data and risk labels to update and fine-tune the model to ensure prediction accuracy and adaptability.

[0084] S500. Obtain parameter adjustment information according to the risk change trend prediction result.

[0085] In this embodiment, the parameter adjustment information includes the control parameter adjustment direction, adjustment range, adjustment time point, etc. of the fans in each partition, which is generated according to the risk change trend prediction results, in order to respond to possible risk changes through parameter adjustment, and achieve active prevention and dynamic optimization.

[0086] Specifically, the parameter adjustment direction and amplitude of each wind turbine are determined based on the deviation between the risk change trend prediction result and the current control parameters. For example, if it is predicted that the risk level may increase significantly in the future and the current power limit is high, the power limit of the corresponding wind turbine needs to be lowered. The adjustment amplitude can be determined by referring to the difference between the predicted risk level and the current risk level, the adjustment experience in similar situations in the past, and other factors. For example, a comparison table can be pre-set based on the adjustment experience in similar situations in the past. In addition, according to the operating conditions and environmental conditions of the wind turbine, the time point of parameter adjustment should be reasonably arranged to avoid other risks caused by inappropriate adjustment timing. The parameter adjustment information finally generated can be used to guide the issuance of subsequent adjustment instructions.

[0087] S600: triggering a parameter adjustment instruction according to the parameter adjustment information.

[0088] In this embodiment, the manner of triggering the parameter adjustment instruction includes automatically issuing the control instruction, manually confirming and issuing the control instruction, and the like.

[0089] In one embodiment, referring to Figure 2In step S100, wind farm division information is obtained, and the offshore wind farm is divided into different safety management zones according to the wind farm division information, which specifically includes the following steps:

[0090] S110. According to the wind farm division information, obtain the geographical location information, sea condition characteristic parameters and power device layout information of the offshore wind farm.

[0091] In this embodiment, the geographical location information includes the longitude and latitude coordinates of the wind farm, the distance from the coastline, the water depth distribution, etc., which can be obtained from the design documents of the wind farm, marine surveying and mapping data and other sources; the sea condition characteristic parameters include the average wind speed, wind direction distribution, wave height, tide level, etc., which are obtained through on-site measurement, historical observation data analysis and other methods; the power device layout information includes the coordinate position of the wind turbine, the location of the substation, the laying path of the submarine cable, etc., which can be extracted from the electrical design drawings of the wind farm.

[0092] Specifically, the geographical location, sea conditions and layout of power devices of the wind farm are digitally processed and visualized using tools such as GIS geographic information system and CAD design software. For example, the longitude and latitude coordinate information of the wind farm is imported into the GIS system to generate a schematic diagram of the geographical location of the wind farm; the coordinate location information of power devices such as wind turbines and substations is extracted from the CAD drawings to generate an electrical layout diagram of the wind farm; the collected sea condition characteristic parameters are associated with the corresponding geographical location to generate a thermal map of the sea condition distribution of the wind farm.

[0093] S120. Divide the offshore wind farm into a number of non-overlapping functional areas according to the geographical location information and the layout information of the power devices, each functional area including wind turbines and power devices that are close in geographical location and closely connected in electricity.

[0094] In this embodiment, the division of functional areas comprehensively considers the two dimensions of geographical location and electrical topology. Wind turbines and power devices with close geographical locations usually have similar sea conditions and working environments, and are suitable for unified management in the same functional area; wind turbines and power devices with close electrical connections usually have stronger electrical coupling and correlation, and are also suitable for unified management in the same functional area. The wind turbines and power devices within the functional area are relatively compact, while different functional areas are relatively independent and have clear boundaries.

[0095] Specifically, a graph-based network partitioning algorithm is used to abstract the wind farm into a weighted undirected graph, with wind turbines and substations as nodes of the graph, and the geographical distance and electrical connection between nodes as the edge weights of the graph. The graph is divided into several subgraphs that are tight inside and loose outside, and each subgraph corresponds to a functional area. During the partitioning process, the number and size of the functional areas are set according to actual needs. The functional areas obtained by the partitioning are marked with different colors or numbers to generate a functional area division schematic diagram of the wind farm.

[0096] S130. Calculate the sea condition risk level of the target functional area according to the sea condition characteristic parameters of the target functional area, where the target functional area is any one of the functional areas.

[0097] Specifically, multiple sea condition characteristic parameters are quantified into a comprehensive sea condition risk index. For example, fuzzy membership evaluation is performed on each sea condition characteristic parameter to obtain their corresponding risk membership vectors; then, weighted summation is performed on each risk membership vector to obtain a comprehensive sea condition risk membership vector; finally, the sea condition risk level of the functional area is determined based on the maximum membership principle.

[0098] S140: Combine the sea condition risk level of the target functional area with the functional attribute corresponding to the target functional area to obtain a safety management zone identification of the target functional area.

[0099] In one embodiment, referring to Figure 3 In step S200, the abnormal state change trend and the safety state change trend of each safety management zone are obtained, and the safety risk level of each safety management zone is determined according to the abnormal state change trend and the safety state change trend, and a safety risk distribution map of the offshore wind farm is generated, which specifically includes the following steps:

[0100] S210, obtaining historical monitoring data of the target safety management partition, the historical monitoring data including wind turbine operating status parameters, power equipment operating parameters and sea environment parameters; performing sliding window division on the historical data of each monitoring parameter to obtain parameter samples within several time windows.

[0101] The target security management partition is any one of the security management partitions.

[0102] In this embodiment, historical monitoring data can be obtained from multiple data sources such as the SCADA system, CMS system, and meteorological monitoring system of the wind farm, and the time span can be set according to data quality and analysis requirements, such as the past year, the past three months, etc. Wind turbine operating status parameters include generator speed, pitch angle, yaw angle, etc., reflecting the force and motion state of the wind turbine; power equipment operating parameters include transformer temperature, cable current, circuit breaker operation times, etc., reflecting the health level and aging degree of power equipment; sea condition parameters may include wind speed, wind direction, wave height, current speed, etc., reflecting the severity of the offshore operating environment.

[0103] Specifically, each start-up and shutdown cycle is used as a sliding window. The sliding step size of the window can be consistent with the window length, or it can be smaller than the window length to form a partial overlap. The overlap degree is set according to the continuity of the time series characteristics and the amount of data. For each time window, the statistical characteristics of each monitoring parameter can be extracted, such as mean, variance, maximum value, minimum value, etc., and the frequency domain characteristics can also be extracted, such as spectrum energy, bandwidth, etc., and the time domain characteristics can also be extracted, such as rise time, peak time, etc. The extracted features are used as sample data for subsequent anomaly detection and safety assessment.

[0104] S220, perform anomaly detection on parameter samples in the current time window, count the number and proportion of abnormal samples, generate an abnormal state quantity of the current time window, calculate the change rate between the abnormal state quantity of the current time window and the abnormal state quantity of the previous time window, and obtain the abnormal state change trend.

[0105] In this embodiment. Anomaly detection can be performed based on different criteria such as parameter thresholds, statistical distribution, and time series patterns. The threshold method sets the upper and lower limits of the normal range based on expert experience or historical data analysis, and samples beyond the range are judged as abnormal; the statistical distribution method assumes that the parameters obey a certain probability distribution, and samples that deviate far from the distribution center are judged as abnormal; the time series pattern method is to establish a time series prediction model for parameters through methods such as autoregression and periodic analysis, and samples with large deviations from the predicted values ​​are judged as abnormal. The abnormal state quantity can be measured by the ratio of the number of abnormal samples to the total number of samples, reflecting the overall level of abnormal occurrence in the current time window. The abnormal state change trend can be measured by the difference between the abnormal state quantities of the previous and next windows divided by the abnormal state quantity of the previous window, reflecting the dynamic change trend of the abnormal occurrence level. Positive values ​​indicate an upward trend, negative values ​​indicate a downward trend, and the larger the absolute value, the more drastic the change.

[0106] Specifically, different anomaly detection methods are used for different types of monitoring parameters. For example, for parameters that are strongly constrained by physical laws, methods based on thresholds or statistical distribution can be used; for parameters with large fluctuations, methods based on time series patterns can be used. For the same type of parameters, multiple anomaly detection methods can be tried, and the best method can be compared and selected through cross-validation and other methods. The abnormal samples of each parameter detected can be summarized to calculate the abnormal state quantity and change trend. When calculating the abnormal state change trend, the upper and lower limits of the change rate can be set, and an early warning can be issued when the change rate exceeds the upper or lower limit by a large amount. The specific threshold setting can be determined based on historical abnormal situations and risk tolerance.

[0107] S230. Perform a security status assessment on the preset parameter samples in the current time window, weightedly integrate the security indicators of each preset parameter sample to obtain a comprehensive security status score for the current time window, calculate the rate of change between the comprehensive security status score of the current time window and the score of the previous time window, and obtain a security status change trend.

[0108] In this embodiment, the preset parameters are a group of key parameters that have a greater impact on the safety state, including generator temperature, blade vibration acceleration, and tower inclination angle, selected based on the experience of wind turbine and power equipment operation and maintenance. A quantitative safety index is designed for each preset parameter according to its correlation with the safety state, such as the more the generator temperature deviates from the rated temperature, the lower the safety index; the greater the blade vibration acceleration amplitude, the lower the safety index; the more the tower inclination angle deviates from the vertical direction, the lower the safety index.

[0109] S240: Acquire functional attributes corresponding to the target security management partition, and determine the importance weight coefficient of the target security management partition according to the functional attributes corresponding to the target security management partition.

[0110] In this embodiment, the functional attributes reflect the role and status of the target safety management zone in the entire wind farm, such as the proportion of power generation, grid support role, geographical location, etc. Different functional attributes have different impacts on the safety production and economic benefits of the wind farm, so different weights need to be assigned when assessing safety risks. The importance weight coefficient can be represented by a value between 0 and 1. The larger the value, the higher the importance of the zone, and the greater the weight in the subsequent risk assessment.

[0111] S250, input the abnormal state quantity, abnormal state change trend, comprehensive safety state score, safety state change trend, and importance weight coefficient into a pre-established safety risk assessment model to obtain the safety risk level of the target safety management partition.

[0112] Specifically, each input indicator is first normalized to eliminate differences in dimensions and numerical ranges, and then input into the model. The normalized indicator value is multiplied by the corresponding weight coefficient and then added together to obtain a comprehensive risk assessment value. The assessment value is compared with the preset level threshold to determine the current risk level.

[0113] S260. Generate a safety risk distribution map of the offshore wind farm based on the safety risk level of each safety management zone.

[0114] In one embodiment, referring to Figure 4 In step S300, according to the safety risk distribution map, the operation control parameters of the fans in each safety management zone are obtained, and the operation control instructions are triggered according to the operation control parameters, which specifically includes the following steps: S310, according to the safety risk distribution map, identify the risk zone with the preset level threshold of the safety risk level operation.

[0115] In this embodiment, the preset level threshold is a risk level limit set according to the safety management requirements and risk tolerance of the wind farm. Through manual recognition or image processing algorithms, areas above the preset level threshold are extracted from the safety risk distribution map as risk zones for key management and control.

[0116] S320, obtaining historical operation control parameters of the wind turbines in the risk zone, and predicting the safety risk probabilities corresponding to different operation control parameters according to the safety risk levels corresponding to the risk zones and the historical operation control parameters.

[0117] In this embodiment, the historical operation control parameters refer to the actual control instructions and corresponding execution parameters of the wind turbine in the past period of time, such as power setting value, pitch angle instruction, yaw angle instruction, etc. The safety risk probability refers to the probability of a wind turbine failure or accident under certain operation control parameters. By associating and analyzing the risk level and the operation control parameters, and using machine learning algorithms to establish a mapping model from parameters to risk probabilities, the safety effect of control decisions can be quantitatively evaluated.

[0118] S330. According to the comparison result between the safety risk probability and the preset probability threshold, a target operation control parameter for reducing the safety risk level of the risk zone is obtained.

[0119] In this embodiment, the preset probability threshold is the highest acceptable risk probability set according to the safety management requirements and structural characteristics of the risk zone, such as 5%. The safety risk probability prediction result is compared with the preset probability threshold to find the operation control parameter that can reduce the risk probability to below the threshold as the target parameter to guide the actual operation control process.

[0120] Specifically, a grid search algorithm is used to find a parameter combination with a safety risk probability lower than a preset threshold and the smallest control parameter adjustment range as the target parameter. During the search process, an upper limit of the adjustment range is set, such as the maximum power change percentage, the maximum pitch angle change degree, etc., to avoid excessive adjustments from causing impacts on the unit. The lower limit of power generation efficiency can also be set, such as the minimum wind energy utilization coefficient, the minimum power generation, etc., to ensure that the adjusted power generation efficiency is not too low. In addition, considering the coordination between different wind turbines, constraints such as power balance between wind turbines and minimum wake effect can be added when searching for target parameters, so that multiple wind turbines can be controlled collaboratively, which not only reduces local risks but also takes into account global benefits.

[0121] S340. Triggering operation control instructions corresponding to each wind turbine in the risk zone according to the target operation control parameters.

[0122] In one embodiment, referring to Figure 5 In step S600, a parameter adjustment instruction is triggered according to the parameter adjustment information, which specifically includes the following steps:

[0123] S610. Obtain the adjustment time point and the adjusted operation control parameters of the fan according to the parameter adjustment information.

[0124] S620: Compare the adjusted operation control parameter with the preset safety threshold. If the adjusted operation control parameter does not exceed the preset safety threshold, trigger a parameter adjustment instruction according to the adjustment time point.

[0125] The preset safety threshold in this embodiment is a preset limit value during adjustment. By comparing the adjusted operation control parameter with the corresponding safety threshold, the feasibility and safety of the parameter adjustment scheme can be judged. If the parameter is within the limit, it means that the adjustment scheme is safe and feasible, and the system can directly trigger the adjustment instruction. If the parameter exceeds the limit, it means that the adjustment scheme has safety hazards and needs to be further optimized.

[0126] S630: If the adjusted operating control parameter exceeds the preset safety threshold range, a parameter adjustment secondary optimization instruction is triggered.

[0127] S640. According to the parameter adjustment secondary optimization instruction, obtain secondary adjustment parameter information, and trigger the parameter adjustment instruction according to the secondary adjustment parameter information.

[0128] In one embodiment, referring to Figure 6 In step S640, according to the parameter adjustment secondary optimization instruction, secondary adjustment parameter information is obtained, and according to the secondary adjustment parameter information, the parameter adjustment instruction is triggered, which specifically includes the following steps:

[0129] S641. According to the parameter adjustment secondary optimization instruction, a risk attenuation factor of the wind turbine corresponding to the adjusted operating control parameter exceeding a preset safety threshold range is obtained.

[0130] In which, the risk attenuation factor is assumed to be α, 0<α<1.

[0131] S642. Obtain the current operating status and environmental information of the wind turbine, and calculate the adjustment coefficient of the risk attenuation factor according to the current operating status and environmental information.

[0132] Here, the adjustment coefficient is β.

[0133] S643. Calculate the operation control parameters after secondary adjustment based on the risk attenuation factor and the adjustment coefficient.

[0134] Specifically, the operating control parameter P after secondary adjustment is adj =P base +α*β*(P opt -P base ), where P base is the reference operating control parameter of the fan, P opt Adjusted operating control parameters that exceed the preset safety threshold range.

[0135] S644: Determine whether the operating control parameter after the second adjustment still exceeds the preset safety threshold range; if not, trigger a parameter adjustment instruction.

[0136] S645. If yes, the risk attenuation factor is decreased according to the preset step size until the operation control parameter after the second adjustment does not exceed the preset safety threshold range.

[0137] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0138] In the second aspect, the present application provides a safety evaluation and optimization system for offshore wind power. The safety evaluation and optimization system for offshore wind power of the present application is described below in combination with the above-mentioned safety evaluation and optimization method for offshore wind power.

[0139] Reference Figure 7 , a safety evaluation and optimization system for offshore wind power, comprising:

[0140] A safety management zoning division module is used to obtain wind farm division information and divide the offshore wind farm into different safety management zones according to the wind farm division information;

[0141] A risk distribution map generation module is used to obtain the abnormal state change trend and the safety state change trend of each safety management zone, determine the safety risk level of each safety management zone according to the abnormal state change trend and the safety state change trend, and generate a safety risk distribution map of the offshore wind farm;

[0142] An operation control instruction triggering module is used to obtain the operation control parameters of the fans in each safety management zone according to the safety risk distribution map, and trigger the operation control instructions according to the operation control parameters;

[0143] The risk change trend prediction module is used to obtain the real-time monitoring data of each security management zone and predict the risk change trend in the future based on the real-time monitoring data;

[0144] The parameter adjustment information acquisition module is used to obtain parameter adjustment information based on the risk change trend prediction results;

[0145] The parameter adjustment instruction triggering module is used to trigger the parameter adjustment instruction according to the parameter adjustment information.

[0146] In one embodiment, the security management partitioning module includes:

[0147] An information acquisition unit, used to acquire geographical location information, sea condition characteristic parameters and power device layout information of the offshore wind farm according to the wind farm division information;

[0148] A region division unit is used to divide the offshore wind farm into a number of non-overlapping functional areas according to the geographical location information and the layout information of the power devices, each functional area contains wind turbines and power devices that are close in geographical location and closely connected in electricity;

[0149] A level calculation unit, used to calculate the sea condition risk level of the target functional area according to the sea condition characteristic parameters of the target functional area, where the target functional area is any one of the functional areas;

[0150] The partition identification unit is used to combine the sea condition risk level of the target functional area with the functional attributes corresponding to the target functional area to obtain the safety management partition identification of the target functional area.

[0151] In one embodiment, the risk distribution map generation module includes:

[0152] The parameter sample acquisition unit is used to obtain the historical monitoring data of the target safety management partition, the historical monitoring data includes wind turbine operating status parameters, power equipment operating parameters and sea environment parameters; the historical data of each monitoring parameter is divided into sliding windows to obtain parameter samples within a number of time windows, and the target safety management partition is any one of the safety management partitions;

[0153] The abnormal state change trend acquisition unit is used to perform abnormality detection on the parameter samples in the current time window, count the number and proportion of abnormal samples, generate the abnormal state quantity of the current time window, calculate the change rate between the abnormal state quantity of the current time window and the abnormal state quantity of the previous time window, and obtain the abnormal state change trend;

[0154] A security status change trend acquisition unit is used to evaluate the security status of the preset parameter samples in the current time window, weightedly integrate the security indicators of various preset parameter samples, obtain the comprehensive security status score of the current time window, calculate the change rate between the comprehensive security status score of the current time window and the score of the previous time window, and obtain the security status change trend; an importance weight coefficient acquisition unit is used to obtain the functional attributes corresponding to the target security management partition, and determine the importance weight coefficient of the target security management partition according to the functional attributes corresponding to the target security management partition;

[0155] A security risk level acquisition unit is used to input the abnormal state quantity, abnormal state change trend, comprehensive security state score, security state change trend, and importance weight coefficient into a pre-established security risk assessment model to obtain the security risk level of the target security management zone;

[0156] The safety risk distribution map generating unit is used to generate a safety risk distribution map of the offshore wind farm based on the safety risk level of each safety management zone.

[0157] In one embodiment, the operation control instruction trigger module includes:

[0158] A risk zone identification unit, used to identify risk zones with preset level thresholds for security risk level operations according to the security risk distribution map;

[0159] The risk probability prediction unit is used to obtain the historical operation control parameters of the wind turbine in the risk zone, and predict the safety risk probability corresponding to different operation control parameters according to the safety risk level and historical operation control parameters corresponding to the risk zone;

[0160] An operation control parameter acquisition unit, used to obtain a target operation control parameter for reducing the safety risk level of the risk zone according to a comparison result between the safety risk probability and a preset probability threshold;

[0161] The operation control instruction triggering unit is used to trigger the operation control instructions corresponding to each wind turbine in the risk zone according to the target operation control parameters.

[0162] In one embodiment, the parameter adjustment instruction triggering module includes:

[0163] A parameter adjustment acquisition unit is used to acquire the adjustment time point and the adjusted operation control parameter of the fan according to the parameter adjustment information; a parameter adjustment instruction first trigger unit is used to compare the adjusted operation control parameter with a preset safety threshold, and if the adjusted operation control parameter does not exceed the preset safety threshold range, the parameter adjustment instruction is triggered according to the adjustment time point;

[0164] A secondary optimization instruction triggering unit is used to trigger a parameter adjustment secondary optimization instruction if the adjusted operation control parameter exceeds a preset safety threshold range;

[0165] The parameter adjustment instruction second trigger unit is used to obtain secondary adjustment parameter information according to the parameter adjustment secondary optimization instruction, and trigger the parameter adjustment instruction according to the secondary adjustment parameter information.

[0166] In one embodiment, the parameter adjustment instruction second trigger unit includes:

[0167] A risk attenuation factor acquisition subunit is used to adjust the secondary optimization instruction according to the parameter, and acquire the risk attenuation factor α of the wind turbine corresponding to the adjusted operation control parameter exceeding the preset safety threshold range, wherein 0<α<1;

[0168] The adjustment coefficient acquisition subunit is used to obtain the current operating state and environmental information of the wind turbine, and calculate the adjustment coefficient β of the risk attenuation factor according to the current operating state and environmental information;

[0169] The operation control parameter calculation subunit is used to calculate the secondary adjusted operation control parameter P according to the risk attenuation factor and the adjustment coefficient. adj =P base +α*β*(P opt -P base ), where P base is the reference operating control parameter of the fan, P opt Adjusted operating control parameters that exceed preset safety thresholds;

[0170] The risk attenuation factor adjustment subunit is used to determine whether the operation control parameter after the secondary adjustment still exceeds the preset safety threshold range. If not, a parameter adjustment instruction is triggered;

[0171] The parameter adjustment instruction triggers the subunit, which is used to, if yes, reduce the risk attenuation factor α according to a preset step size until the operation control parameter after the secondary adjustment does not exceed the preset safety threshold range.

[0172] In one embodiment, the present application provides an electronic device, which may be a server, and its internal structure diagram may be as follows: Figure 8As shown. The electronic device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic 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 electronic device is used to store data. The network interface of the electronic device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a safety evaluation optimization method for offshore wind power is implemented.

[0173] Those skilled in the art will understand that Figure 8 The structure shown in the figure is merely a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the electronic device to which the scheme of the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0174] In one embodiment, an electronic device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0175] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the above-mentioned computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0176] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, any equivalent changes made according to the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A safety evaluation optimization method for offshore wind power, characterized in that: The steps include: Acquire wind farm division information, and divide the offshore wind farm into different safety management zones according to the wind farm division information; Obtaining abnormal state change trends and safety state change trends of each safety management zone, determining the safety risk level of each safety management zone according to the abnormal state change trends and safety state change trends, and generating a safety risk distribution map of the offshore wind farm; According to the safety risk distribution map, the operation control parameters of the fans in each safety management zone are obtained, and the operation control instructions are triggered according to the operation control parameters; Obtaining real-time monitoring data of each security management zone, and predicting the risk change trend in the future based on the real-time monitoring data; According to the risk change trend prediction results, parameter adjustment information is obtained, wherein the parameter adjustment information includes the control parameter adjustment direction, adjustment amplitude and adjustment time point of the fans in each partition. Specifically, according to the deviation between the risk change trend prediction results and the current control parameters, the parameter adjustment direction and amplitude of the fans in each partition are determined; according to the operating conditions and environmental conditions of the fans, the adjustment time point of the fans in each partition is determined; triggering a parameter adjustment instruction according to the parameter adjustment information; The abnormal state change trend and the safety state change trend of each safety management zone are obtained, and the safety risk level of each safety management zone is determined according to the abnormal state change trend and the safety state change trend, and the safety risk distribution map of the offshore wind farm is generated, which specifically includes the following steps: Acquire historical monitoring data of the target safety management partition, the historical monitoring data including wind turbine operating status parameters, power equipment operating parameters and sea environment parameters; perform sliding window division on the historical data of each monitoring parameter to obtain parameter samples within a plurality of time windows, the target safety management partition being any one of the safety management partitions; Perform anomaly detection on parameter samples in the current time window, count the number and proportion of abnormal samples, generate an abnormal state quantity of the current time window, calculate the change rate between the abnormal state quantity of the current time window and the abnormal state quantity of the previous time window, and obtain the abnormal state change trend; Perform security status assessment on the preset parameter samples in the current time window, weightedly integrate the security indicators of various preset parameter samples, obtain the comprehensive security status score of the current time window, calculate the change rate between the comprehensive security status score of the current time window and the score of the previous time window, and obtain the security status change trend; Acquire the functional attributes corresponding to the target security management partition, and determine the importance weight coefficient of the target security management partition according to the functional attributes corresponding to the target security management partition; Input the abnormal state quantity, abnormal state change trend, comprehensive safety state score, safety state change trend, and importance weight coefficient into a pre-established safety risk assessment model to obtain the safety risk level of the target safety management zone; Based on the safety risk levels of the various safety management zones, a safety risk distribution map of the offshore wind farm is generated.

2. The safety evaluation optimization method for offshore wind power according to claim 1 is characterized in that: Obtaining wind farm division information, and dividing the offshore wind farm into different safety management zones according to the wind farm division information, specifically includes the following steps: According to the wind farm division information, obtaining geographical location information, sea condition characteristic parameters and power device layout information of the offshore wind farm; Divide the offshore wind farm into a number of non-overlapping functional areas according to the geographical location information and the layout information of the power devices, each functional area comprising wind turbines and power devices that are geographically close and closely connected to each other; Calculating the sea condition risk level of the target functional area according to the sea condition characteristic parameters of the target functional area, wherein the target functional area is any one of the functional areas; The sea condition risk level of the target functional area is combined with the functional attribute corresponding to the target functional area to obtain the safety management partition identification of the target functional area.

3. The offshore wind power safety evaluation optimization method according to claim 1, characterized in that: According to the safety risk distribution map, the operation control parameters of the fans in each safety management zone are obtained, and the operation control instructions are triggered according to the operation control parameters, which specifically includes the following steps: According to the security risk distribution map, identifying risk zones with preset security risk level thresholds; Acquire historical operation control parameters of the wind turbines in the risk zone, and predict the safety risk probabilities corresponding to different operation control parameters according to the safety risk levels and historical operation control parameters corresponding to the risk zones; According to the comparison result of the safety risk probability and the preset probability threshold, a target operation control parameter for reducing the safety risk level of the risk zone is obtained; According to the target operation control parameter, an operation control instruction corresponding to each wind turbine in the risk zone is triggered.

4. The safety evaluation optimization method for offshore wind power according to claim 1, characterized in that: According to the parameter adjustment information, triggering a parameter adjustment instruction specifically includes the following steps: According to the parameter adjustment information, obtaining the adjustment time point and the operation control parameters after adjustment of the fan; Comparing the adjusted operation control parameter with a preset safety threshold, and if the adjusted operation control parameter does not exceed the preset safety threshold range, triggering a parameter adjustment instruction according to the adjustment time point; If the adjusted operating control parameter exceeds the preset safety threshold range, a parameter adjustment secondary optimization instruction is triggered; According to the parameter adjustment secondary optimization instruction, secondary adjustment parameter information is obtained, and according to the secondary adjustment parameter information, the parameter adjustment instruction is triggered.

5. The offshore wind power safety evaluation optimization method according to claim 4 is characterized in that: According to the parameter adjustment secondary optimization instruction, obtaining secondary adjustment parameter information, and according to the secondary adjustment parameter information, triggering the parameter adjustment instruction specifically includes the following steps: According to the parameter adjustment secondary optimization instruction, a risk attenuation factor α of the wind turbine corresponding to the adjusted operation control parameter exceeding the preset safety threshold range is obtained, wherein 0<α<1; Acquire the current operating state and environmental information of the wind turbine, and calculate the adjustment coefficient β of the risk attenuation factor according to the current operating state and environmental information; According to the risk attenuation factor and the adjustment coefficient, the secondary adjusted operation control parameter P is calculated. adj =P base +α*β*(P opt -P base ), where P base is the reference operating control parameter of the fan, P opt Adjusted operating control parameters that exceed preset safety thresholds; Determine whether the operating control parameters after the secondary adjustment still exceed the preset safety threshold range, if not, trigger the parameter adjustment instruction; If so, the risk attenuation factor α is decreased according to the preset step size until the secondary adjusted operation control parameter does not exceed the preset safety threshold range.

6. A safety evaluation and optimization system for offshore wind power, characterized in that: include: A safety management partition division module is used to obtain wind farm division information and divide the offshore wind farm into different safety management partitions according to the wind farm division information; A risk distribution map generating module is used to obtain the abnormal state change trend and the safety state change trend of each safety management zone, determine the safety risk level of each safety management zone according to the abnormal state change trend and the safety state change trend, and generate the safety risk distribution map of the offshore wind farm; An operation control instruction triggering module is used to obtain the operation control parameters of the fans in each safety management zone according to the safety risk distribution map, and trigger the operation control instruction according to the operation control parameters; The risk change trend prediction module is used to obtain the real-time monitoring data of each security management zone and predict the risk change trend in the future based on the real-time monitoring data; The parameter adjustment information acquisition module is used to acquire parameter adjustment information according to the risk change trend prediction result, wherein the parameter adjustment information includes the control parameter adjustment direction, adjustment amplitude and adjustment time point of the fans in each partition. Specifically, according to the deviation between the risk change trend prediction result and the current control parameter, the parameter adjustment direction and amplitude of the fans in each partition are determined; according to the operating conditions and environmental conditions of the fans, the adjustment time point of the fans in each partition is determined; A parameter adjustment instruction triggering module, used for triggering a parameter adjustment instruction according to the parameter adjustment information; Among them, the risk distribution map generation module includes: The parameter sample acquisition unit is used to obtain the historical monitoring data of the target safety management partition, the historical monitoring data includes wind turbine operating status parameters, power equipment operating parameters and sea environment parameters; the historical data of each monitoring parameter is divided into sliding windows to obtain parameter samples within a number of time windows, and the target safety management partition is any one of the safety management partitions; The abnormal state change trend acquisition unit is used to perform abnormality detection on the parameter samples in the current time window, count the number and proportion of abnormal samples, generate the abnormal state quantity of the current time window, calculate the change rate between the abnormal state quantity of the current time window and the abnormal state quantity of the previous time window, and obtain the abnormal state change trend; The security status change trend acquisition unit is used to evaluate the security status of the preset parameter samples in the current time window, weightedly integrate the security indicators of the preset parameter samples, obtain the comprehensive security status score of the current time window, calculate the change rate between the comprehensive security status score of the current time window and the score of the previous time window, and obtain the security status change trend; An importance weight coefficient acquisition unit is used to acquire the functional attributes corresponding to the target security management partition, and determine the importance weight coefficient of the target security management partition according to the functional attributes corresponding to the target security management partition; A security risk level acquisition unit is used to input the abnormal state quantity, abnormal state change trend, comprehensive security state score, security state change trend, and importance weight coefficient into a pre-established security risk assessment model to obtain the security risk level of the target security management zone; The safety risk distribution map generating unit is used to generate a safety risk distribution map of the offshore wind farm based on the safety risk level of each safety management zone.

7. The offshore wind power safety evaluation and optimization system according to claim 6, characterized in that: The security management partitioning module includes: An information acquisition unit, used to acquire geographical location information, sea condition characteristic parameters and power device layout information of the offshore wind farm according to the wind farm division information; A region division unit, for dividing the offshore wind farm into a plurality of non-overlapping functional areas according to the geographical location information and the layout information of the power devices, each functional area comprising wind turbines and power devices that are geographically close and closely connected in terms of electricity; a level calculation unit, used to calculate the sea condition risk level of the target functional area according to the sea condition characteristic parameters of the target functional area, wherein the target functional area is any one of the functional areas; The partition identification unit is used to combine the sea condition risk level of the target functional area with the functional attribute corresponding to the target functional area to obtain the safety management partition identification of the target functional area.

8. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the offshore wind power safety evaluation optimization method described in any one of claims 1 to 5 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the offshore wind power safety assessment optimization method described in any one of claims 1-5 are implemented.

Images