Offshore wind power safety monitoring information dynamic management system

Abstract

The invention discloses an offshore wind power safety monitoring information dynamic management system, which relates to the field of offshore wind power safety monitoring and comprises a data processing unit, an information service unit and a management prediction unit. According to the system, data cleaning, integration and fusion can be realized through the data cleaning module, the data integration module and the data fusion module in the data processing module, and various data can be fused and unified after processing, so that the data processing difficulty is reduced, the workload of the whole system is reduced, and the data processing efficiency is improved. The abnormal data is identified through the identification early warning module, the corresponding early warning information can be triggered according to the abnormal data exceeding the threshold value after identification, when the abnormal data is processed, the identification efficiency of the abnormal data is high, the error is small, the precision is high, and the stability of offshore wind power safety monitoring can be improved; the change rule of the monitoring data in the normal monitoring period can be correctly reflected, and the accuracy of curve prediction is improved.

Description

Technical Field

[0001] The present invention relates to the field of offshore wind power safety monitoring, and in particular to an offshore wind power safety monitoring information dynamic management system. Background Art

[0002] Offshore wind power safety monitoring is an important part of ensuring the stable operation of offshore wind farms and extending the service life of equipment. Currently, the safety monitoring of supporting structures in offshore wind farms mainly includes the observation of data such as uneven settlement, soil pressure, stress and strain, and tilt vibration.

[0003] Traditional methods solve the problem of being unable to provide early warning of submarine cable faults by using resistance curve construction modules and fault warning modules. However, the data obtained by wind power monitoring equipment contains diverse types of information, and it is difficult to integrate and unify the multiple data, which increases the difficulty and workload of data processing and reduces the efficiency of system use. Summary of the Invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is: how to transfer the solid temperature from the grid to the grid points while minimizing the deviation.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a dynamic management system for offshore wind power safety monitoring information, which includes the following steps:

[0007] Data processing unit, information service unit and management and prediction unit;

[0008] The data processing unit collects and processes the usage data of various safety monitoring devices to build a basic database;

[0009] The information service unit uses the basic database to provide users with information query and data retrieval services;

[0010] The management and prediction unit manages the monitoring equipment and quickly predicts the safety of offshore wind power;

[0011] The data processing unit includes a data acquisition module, a data processing module and a database construction module;

[0012] The data acquisition module collects operating data of multiple sensors and devices, including vibration frequency, tilt angle, temperature and humidity, and uneven settlement;

[0013] The data processing module cleans, integrates and fuses the collected data, and fuses and unifies multi-source data;

[0014] The database construction module categorizes the data processed in the data processing module and constructs a basic database for security monitoring according to the categories.

[0015] As a preferred solution of the offshore wind power safety monitoring information dynamic management system described in the present invention, wherein: the data processing module includes a data cleaning module, a data integration module and a data fusion module;

[0016] The data cleaning module mines and analyzes the data, and performs filtering and cleaning on the analyzed data;

[0017] The data integration module quickly integrates the data cleaned in the data cleaning module;

[0018] The data fusion module quickly fuses the cleaned and integrated data;

[0019] In the data cleaning module, the filtering and cleaning of data also includes:

[0020] Perform dynamic gain control on multi-source data, extract data fusion related features, and obtain the process distribution feature subset of the cleaning process;

[0021] Through data clustering processing and deep learning of cluster centers, data redundancy filtering is achieved.

[0022] As a preferred solution of the offshore wind power safety monitoring information dynamic management system described in the present invention, wherein: the information service unit includes a data query module, an information retrieval module and an information synchronization module;

[0023] The data query module performs dynamic and static queries on the monitoring data, inputs query conditions to filter the information, and obtains the corresponding monitoring data;

[0024] The information retrieval module retrieves relevant information of the query data from the data query module, sorts the relevant information by time priority, and generates a search report;

[0025] The information synchronization module receives external modified data and synchronizes the modified data to the local database.

[0026] As a preferred solution of the offshore wind power safety monitoring information dynamic management system described in the present invention, wherein: the management and prediction unit includes an identification and warning module, an equipment management module, a parameter adjustment module and a curve prediction module;

[0027] The identification and warning module is used to identify abnormal data in the database samples, and after checking the abnormal data, trigger the system warning and locate the abnormal device;

[0028] The device management module is used to centrally manage various devices and sensors currently under security monitoring, and to control the use and interruption of the devices and sensors.

[0029] As a preferred solution of the offshore wind power safety monitoring information dynamic management system described in the present invention, the parameter adjustment module is used to adjust the usage parameters of each device, including usage time, tilt angle, operating frequency and warning threshold;

[0030] The curve prediction module is used to randomly collect five groups of monitoring data to construct a monitoring data change curve in the wind farm, calculate the change rate of the corresponding monitoring data according to the change curve, and construct a prediction curve according to the change rate.

[0031] As a preferred solution of the offshore wind power safety monitoring information dynamic management system described in the present invention, wherein: in the data cleaning module, the filtering and cleaning processing of the data also includes:

[0032] Perform dynamic gain control on multi-source data, extract data fusion related features, and obtain the process distribution feature subset of the cleaning process;

[0033] Through data clustering processing and deep learning of cluster centers, data redundancy filtering is achieved;

[0034] The extraction of data fusion related feature quantities is performed through fuzzy C-means clustering, and the data feature parameter extraction expression is obtained as follows:

[0035]

[0036] Among them, βδ is the statistical analysis data around the node, F is the fuzzy C-means cluster, p i is the maximum number of hops, α i is a pre-set threshold, α j is the threshold corresponding to different values ​​of j.

[0037] As a preferred solution of the offshore wind power safety monitoring information dynamic management system described in the present invention, when the data fusion module fuses the data, it also includes:

[0038] Map the data feature nonlinear vector space to the phenomenon separable space to obtain the optimal classification hyperplane. Based on the obtained optimal hyperplane, group the multi-source heterogeneous data. Different groups correspond to different sensors. Establish a data fusion model. The expression of the fusion model is:

[0039]

[0040] Among them, l i ,l j is the optimal solution for data i and j, is the mean of the optimal solutions of i and j, e is the number of sensors, λ is the generalization parameter, s is the actual value of the data, is a constraint condition;

[0041] Determine the optimal solution for the data of the current model, establish a decision function for the data, and assist in solving the model based on the decision function;

[0042] Solve the function and complete the fusion. The expression of the solution process is:

[0043]

[0044] Among them, f(x) is the decision function, is the data mean set label of sensor e, l e is the optimal solution label for the data, δ is the bias term, y i , y are the acquired data feature vectors as input vector and feature vector set respectively.

[0045] As a preferred solution of the offshore wind power safety monitoring information dynamic management system described in the present invention, the identification and early warning module further includes, when identifying abnormal data,

[0046] Establish a data set, determine the radius of the area that defines the density and the minimum number of points contained in the area when defining the core point, denoted as c and d respectively;

[0047] Randomly select a data from the data set, record it as object a, determine whether a is a core point, if a is a core point, find all data points that are density-reachable from a to form a data cluster;

[0048] If a is an edge point, select another data point as the object point as the core point, find all data points that are density-reachable from the core point, and form a data cluster until all points are processed;

[0049] Output the overall processing results, establish a trigger data set, and compare the data in the trigger data set with the trigger threshold one by one. When the data type is the same as the threshold and higher than the threshold, the system warning is triggered.

[0050] Beneficial effects of the present invention: The present invention can realize data cleaning, integration and fusion through the data cleaning module, data integration module and data fusion module in the data processing module. After processing, multiple data can be integrated and unified, thereby reducing the difficulty of data processing and reducing the workload of the entire system. The abnormal data is identified by the identification and early warning module. After identification, the corresponding early warning information can be triggered according to the abnormal data exceeding the threshold. When processing the abnormal data, the recognition efficiency of the abnormal data is high, the error is small, and the accuracy is high, which can improve the stability of offshore wind power safety monitoring; the management effect of the monitoring information is good, and the prediction analysis curve is constructed according to the historical data. The data collection frequency is high, which can reduce the interference of abnormal values ​​on the remaining data, and can correctly reflect the change law of the monitoring data during the normal monitoring period, thereby providing data support for the subsequent prediction curve and improving the accuracy of the curve prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0052] Figure 1 This is a framework diagram of a dynamic management system for offshore wind power safety monitoring information provided by the first embodiment of the present invention.

[0053] Figure 2 This is a system diagram of a data processing module of a dynamic management system for offshore wind power safety monitoring information provided by the second embodiment of the present invention.

[0054] Figure 3 This is a system diagram of an information service unit of an offshore wind power safety monitoring information dynamic management system provided by the second embodiment of the present invention.

[0055] Among them: 1. Data processing unit; 11. Data acquisition module; 12. Data processing module; 121. Data cleaning module; 122. Data integration module; 123. Data fusion module; 13. Database construction module; 2. Information service unit; 21. Data query module; 22. Information retrieval module; 23. Information synchronization module; 3. Management and prediction unit; 31. Identification and warning module; 32. Equipment management module; 33. Parameter adjustment module; 34. Curve prediction module. DETAILED DESCRIPTION

[0056] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0057] Example 1, with reference to Figures 1 to 3 In one embodiment of the present invention, a dynamic management system for offshore wind power safety monitoring information is provided, comprising:

[0058] Data processing unit 1, information service unit 2, and management and prediction unit 3; data processing unit 1 is used to collect and process usage data of various safety monitoring equipment and build a basic database; information service unit 2 is used to provide users with information query and data retrieval services using the basic database; management and prediction unit 3 is used to manage monitoring equipment and quickly predict offshore wind power safety;

[0059] The data processing unit 1 includes a data acquisition module 11, a data processing module 12 and a database construction module 13; the data acquisition module 11 is used to collect working data of multiple sensors and equipment, including vibration frequency, tilt angle, temperature and humidity, and uneven settlement;

[0060] The data processing module 12 is used to clean, integrate and fuse the collected data, and to fuse and unify multiple data; the data processing module 12 includes a data cleaning module 121, a data integration module 122 and a data fusion module 123; the data cleaning module 121 is used to mine and analyze the data, and to filter and clean the analyzed data; the data integration module 122 is used to quickly integrate the cleaned data in the data cleaning module 121.

[0061] In the data cleaning module 121, the filtering and cleaning of data also includes the following:

[0062] A1. Dynamically control the gain of multi-source data, extract data fusion-related features, and obtain the process distribution feature subset of the cleaning process;

[0063] A2. Through data clustering processing and deep learning of cluster centers, data redundancy filtering is achieved.

[0064] In extracting data fusion related features, the data feature parameter extraction expression is obtained through fuzzy C-means clustering:

[0065]

[0066] Among them, β is the statistical analysis data around the node, F is the fuzzy C-means cluster, p i is the maximum number of hops, α i is a pre-set threshold, α j is the threshold corresponding to different values ​​of j.

[0067] The data fusion module 123 is used to quickly fuse the cleaned and integrated data. When the data fusion module 123 fuses the data, the following contents are also included:

[0068] Step 1: Build a fusion model: Map the data feature nonlinear vector space to the phenomenon separable space to obtain the optimal classification hyperplane. Based on the obtained optimal hyperplane, group the multi-source heterogeneous data. Different groups correspond to different sensors. Build a data fusion model. The expression of the fusion model is as follows:

[0069]

[0070] Where l i ,l j is the optimal solution for data i and j, is the mean of the optimal solutions of i and j, e is the number of sensors, λ is the generalization parameter, s is the actual value of the data, is a constraint condition;

[0071] Step 2: Determine the optimal solution: Determine the optimal solution for the data of the current model, establish a decision function for the data, and assist in solving the model based on the decision function;

[0072] Step 3: Solve the function and complete the fusion: The expression of the solution process is as follows:

[0073]

[0074] Where f(x) is the decision function, is the data mean set label of sensor e, l e is the label of the optimal solution of the data, and δ is the bias term.

[0075] The database construction module 13 is used to classify the data processed by the data processing module 12 and construct a basic database for security monitoring according to the categories.

[0076] It should be further explained that:

[0077] By using dynamic gain control of the data to achieve preliminary processing before feature extraction of multi-source data, it assists in subsequent feature T-shirts. Through fuzzy C-means clustering, it can improve the extraction effect of data feature parameters and facilitate the subsequent initial cleaning and integration of data.

[0078] By constructing fusion models and constraints, unified data processing can be achieved, and multi-source data can be normalized into the same type. By determining the optimal solution, the establishment of subsequent decision functions can be assisted, and the decision function can assist in solving the subsequent fusion model. According to the solution results and the realization of fusion processing of data, the processed data can be classified according to the categories of different devices or sensors through the database construction module 13, so that the data corresponds to the device, and then a basic database is established to centrally store the processed and classified data, which provides a data basis for subsequent management of the equipment and adjustment of parameters.

[0079] The information service unit 2 includes a data query module 21, an information retrieval module 22 and an information synchronization module 23;

[0080] The data query module 21 is used to perform dynamic and static queries on monitoring data, input query conditions to filter information, and obtain corresponding monitoring data;

[0081] The information retrieval module 22 is used to retrieve the relevant information of the query data in the data query module 21, sort the relevant information by time priority, and generate a search report;

[0082] The information synchronization module 23 is used to receive external modified data and synchronize the modified data to the local database.

[0083] The management and prediction unit 3 includes an identification and warning module 31, an equipment management module 32, a parameter adjustment module 33 and a curve prediction module 34;

[0084] The identification and warning module 31 is used to identify abnormal data in the database samples, and after checking the abnormal data, trigger the system warning and locate the abnormal device;

[0085] The identification and warning module 31 also includes the following when identifying abnormal data:

[0086] Step 1: Create a data set and determine the radius of the area that defines the density and the minimum number of points contained in the area that defines the core points, denoted as c and d respectively;

[0087] Step 2: Randomly select a data point from the data set, record it as object a, and determine whether a is a core point. If a is a core point, find all data points that are density-reachable from a to form a data cluster.

[0088] Step 3: If a is an edge point, select another data point as the object point as the core point, find all data points that are densely reachable from the core point, and form a data cluster until all points are processed;

[0089] Step 4: Output the overall processing results, establish a trigger data set, and compare the data in the trigger data set with the trigger threshold one by one. When the data type is the same as the threshold and higher than the threshold, the system warning is triggered.

[0090] The device management module 32 is used to centrally manage various devices and sensors currently under security monitoring, and to control the use and interruption of the devices and sensors.

[0091] The parameter adjustment module 33 is used to adjust the usage parameters of each device, including usage time, tilt angle, operating frequency and warning threshold;

[0092] The curve prediction module 34 is used to randomly collect five groups of monitoring data to construct a monitoring data change curve in the wind farm, calculate the change rate of the corresponding monitoring data according to the change curve, and construct a prediction curve according to the change rate.

[0093] In this embodiment, the data query module 21 and the information retrieval module 22 facilitate data query and information retrieval, and facilitate the rapid acquisition of monitoring data. Based on the generated retrieval report, the operating status of the current monitoring equipment and sensors can be obtained, and the establishment of subsequent work logs can be assisted. The information synchronization module 23 can achieve rapid information synchronization, thereby reducing the loss of data after information update and ensuring data integrity, thereby better serving the control terminal and staff and reducing safety hazards when using the equipment.

[0094] At the same time, the judgment of object points can quickly distinguish whether the object points are core points or non-core points. Random selection can reduce the randomness of core point selection. Through multiple selection and processing, full coverage of the internal data of the data set can be achieved, thereby improving the processing effect of the internal data of the data set, improving the accuracy of subsequent anomaly identification, and facilitating the rapid assessment of offshore wind power safety and fault judgment.

[0095] In the present invention, data acquisition module 11 is used to realize data acquisition of multiple safety monitoring devices and sensors, data processing module 12 is used to process the data collected in data acquisition module 11, clean, integrate and fuse the data to unify the data, and the processed data is used as the basic data of the database to assist in the construction of subsequent databases, the working data of the current device or sensor can be quickly queried through the information service unit 2, and the relevant information of the data can be retrieved through the information retrieval module 22, so as to assist the staff in judging the working status of the current device and sensor and manually calibrating the same, and the calibrated information can be synchronized through the information synchronization module 23, and the synchronized data is stored in the local database to avoid data loss, and the data of the local database can be transmitted to the management prediction unit 3 through the information service unit 2;

[0096] After acquiring data through the identification and early warning module 31, the abnormal data in the data set is quickly identified and judged. When abnormal data is identified and exceeds a predetermined threshold, the system alarm is triggered and the abnormal equipment is quickly located, informing the control terminal and the staff that there are safety hazards when the offshore wind farm is currently in use. Positioning facilitates the staff to repair the equipment. The equipment management module 32 can be used to shut down the corresponding equipment to reduce equipment damage. The parameter adjustment module 33 can be used to adjust the parameters of the sensors and equipment so that the equipment and sensors adapt to changes in the current offshore environment. The prediction curve of the curve prediction module 34 can assist in judging the safe operation range of the offshore wind farm within the predetermined time, so that the control terminal can take corresponding adjustment measures in time to ensure the safe use of the offshore wind farm.

[0097] Example 2 is an embodiment of the present invention.

[0098] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0099] The logic and / or steps represented in a block diagram or otherwise described herein, for example, may be considered as an ordered list of executable instructions for implementing the logical functions, and may be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" may be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0100] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0101] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0102] Example 3: In this example, in order to verify the beneficial effects of the present invention, economic benefit calculation and simulation experiments were conducted to scientifically demonstrate the effectiveness of the present invention. This example conducted experiments on the existing traditional method and the method of this example.

[0103] In order to verify the beneficial effects of the present invention, scientific demonstration was carried out through economic benefit calculation and simulation experiments. The existing traditional method and the method of the present invention were tested for different test dimensions. The experiments and relevant data were recorded in Table 1, among which the traditional method was recorded as the comparison method. The present invention realizes the monitoring of offshore wind power safety through the resistance curve construction module and the fault warning module.

[0104] Table 1: Experimental data record table

[0105] Test Dimensions Comparison Method Method of the present invention Data processing time (hours) 8 3 Data fusion accuracy (%) 70 90 Abnormal data identification time (seconds) 15 5 Abnormal data misjudgment rate (%) 10 3 Number of failures of offshore wind power safety monitoring systems (per month) 5 2 Monitoring information management cost (yuan / month) 8000 5000 Data collection frequency (times / minute) 10 30 Deviation rate between predicted curve and actual data (%) 18 8 Economic benefit improvement ratio (%) 10 25

[0106] Compared with traditional data processing methods, the method of the present invention takes less time, has a higher data fusion accuracy, shortens the time for identifying abnormal data, significantly reduces the misjudgment rate of abnormal data, reduces the number of failures, reduces the cost of monitoring information management, increases the proportion of economic efficiency, and reduces the deviation rate between the predicted curve and the actual data.

[0107] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A dynamic management system for offshore wind power safety monitoring information, characterized in that: include: Data processing unit (1), information service unit (2) and management prediction unit (3); The data processing unit (1) collects and processes usage data of various safety monitoring devices to build a basic database; The information service unit (2) provides information query and data retrieval services for users using a basic database; The management and prediction unit (3) manages the monitoring equipment and quickly predicts the safety of offshore wind power; The data processing unit (1) comprises a data acquisition module (11), a data processing module (12) and a database construction module (13); The data acquisition module (11) collects operating data of multiple sensors and devices, including vibration frequency, tilt angle, temperature and humidity, and uneven settlement; The data processing module (12) cleans, integrates and fuses the collected data, and fuses and unifies multi-source data; The database construction module (13) classifies the data processed in the data processing module (12) and constructs a basic database for security monitoring according to the categories.

2. The offshore wind power safety monitoring information dynamic management system according to claim 1, characterized in that: The data processing module (12) includes a data cleaning module (121), a data integration module (122) and a data fusion module (123); The data cleaning module (121) mines and analyzes the data, and performs filtering and cleaning on the analyzed data; The data integration module (122) quickly integrates the data cleaned in the data cleaning module (121); The data fusion module (123) quickly fuses the cleaned and integrated data; In the data cleaning module (121), the filtering and cleaning of data also includes: Perform dynamic gain control on multi-source data, extract data fusion related features, and obtain the process distribution feature subset of the cleaning process; Through data clustering processing and deep learning of cluster centers, data redundancy filtering is achieved.

3. The offshore wind power safety monitoring information dynamic management system according to claim 1, characterized in that: The information service unit (2) includes a data query module (21), an information retrieval module (22) and an information synchronization module (23); The data query module (21) performs dynamic and static queries on the monitoring data, inputs query conditions to filter the information, and obtains the corresponding monitoring data; The information retrieval module (22) retrieves relevant information of the query data in the data query module (21), sorts the relevant information by time priority, and generates a retrieval report; The information synchronization module (23) receives external modified data and synchronizes the modified data into a local database.

4. The offshore wind power safety monitoring information dynamic management system according to claim 1, characterized in that: The management prediction unit (3) includes an identification and warning module (31), an equipment management module (32), a parameter adjustment module (33) and a curve prediction module (34); The identification and warning module (31) is used to identify abnormal data in the database sample, and after checking the abnormal data, trigger a system warning and locate the abnormal device; The device management module (32) is used to centrally manage various devices and sensors currently under security monitoring, and to control the use and interruption of the devices and sensors.

5. The offshore wind power safety monitoring information dynamic management system according to claim 4, characterized in that: The parameter adjustment module (33) is used to adjust the use parameters of each device, including use time, tilt angle, operating frequency and warning threshold; The curve prediction module (34) is used to randomly collect five groups of monitoring data to construct a monitoring data change curve in the wind field, calculate the change rate of the corresponding monitoring data according to the change curve, and construct a prediction curve according to the change rate.

6. The offshore wind power safety monitoring information dynamic management system according to claim 2, characterized in that: In the data cleaning module (121), the filtering and cleaning of data also includes: Perform dynamic gain control on multi-source data, extract data fusion related features, and obtain the process distribution feature subset of the cleaning process; Through data clustering processing and deep learning of cluster centers, data redundancy filtering is achieved; The extraction of data fusion related feature quantities is performed through fuzzy C-means clustering, and the data feature parameter extraction expression is obtained as follows: Among them, βδ is the statistical analysis data around the node, F is the fuzzy C-means cluster, p i is the maximum number of hops, α i is a pre-set threshold, α j is the threshold corresponding to different values ​​of j.

7. The offshore wind power safety monitoring information dynamic management system according to claim 2, characterized in that: When the data fusion module (123) fuses the data, it also includes: Map the data feature nonlinear vector space to the phenomenon separable space to obtain the optimal classification hyperplane. Based on the obtained optimal hyperplane, group the multi-source heterogeneous data. Different groups correspond to different sensors. Establish a data fusion model. The expression of the fusion model is: Among them, l i ,l j is the optimal solution for data i and j, is the mean of the optimal solutions of i and j, e is the number of sensors, λ is the generalization parameter, s is the actual value of the data, is a constraint condition; Determine the optimal solution for the data of the current model, establish a decision function for the data, and assist in solving the model based on the decision function; Solve the function and complete the fusion. The expression of the solution process is: Among them, f(x) is the decision function, is the data mean set label of sensor e, l e is the optimal solution label for the data, δ is the bias term, y i , y are the acquired data feature vectors as input vector and feature vector set respectively.

8. The offshore wind power safety monitoring information dynamic management system according to claim 4, characterized in that: The identification and early warning module (31) further includes, when identifying abnormal data, Establish a data set, determine the radius of the area that defines the density and the minimum number of points contained in the area when defining the core point, denoted as c and d respectively; Randomly select a data from the data set, record it as object a, determine whether a is a core point, if a is a core point, find all data points that are density-reachable from a to form a data cluster; If a is an edge point, select another data point as the object point as the core point, find all data points that are density-reachable from the core point, and form a data cluster until all points are processed; Output the overall processing results, establish a trigger data set, and compare the data in the trigger data set with the trigger threshold one by one. When the data type is the same as the threshold and higher than the threshold, the system warning is triggered.

Images