Preventive diagnosis and maintenance system and method for offshore wind power equipment

Abstract

The invention discloses a preventive diagnosis and maintenance system and method for offshore wind power equipment, and relates to the technical field of offshore wind turbine generator maintenance, and the system comprises a data input module, a maintenance judgment module, an early warning maintenance module, an intelligent fault diagnosis module and an operation and maintenance management module. The data input module is used for inputting real-time state data of each component of the offshore wind power equipment, and the operation and maintenance management module controls operation and management of the whole preventive diagnosis and maintenance system. According to the invention, information from different monitoring means is fused by adopting a data fusion algorithm, richer equipment state features are extracted through fusion processing, the collected data are preprocessed in the data collection process to improve the accuracy and reliability of the data, and the data collection accuracy and reliability are improved by utilizing complementarity among different monitoring means. The accuracy and reliability of damage identification are improved, and the diagnosis and maintenance system can efficiently and accurately identify the damage position and the damage degree of the fan structure or equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of offshore wind turbine maintenance, and in particular to a preventive diagnosis and maintenance system and method for offshore wind power equipment. Background Art

[0002] The preventive diagnostic maintenance system for offshore wind power equipment is designed to ensure the stable operation of offshore wind power equipment, reduce failure rates and improve operation and maintenance efficiency through real-time monitoring, data analysis, fault diagnosis and predictive maintenance. The preventive diagnostic maintenance system for offshore wind power equipment uses information technology and Internet of Things technology to conduct real-time monitoring and data analysis of offshore wind farms. By installing various sensors and monitoring equipment, the system can collect operating status and structural safety data of key equipment such as wind turbines, substations, and transmission lines, and conduct in-depth analysis to identify potential faults and perform maintenance in advance.

[0003] The defects of the wind power equipment maintenance system in the prior art are:

[0004] 1. Patent document CN109376872B discloses an offshore wind turbine maintenance system. This maintenance system cannot integrate information from different monitoring methods and cannot extract richer equipment status characteristics. Uncertainties such as model accuracy, test noise during testing, and incomplete parameter identification will result in the system being unable to efficiently and accurately identify the damage location and extent of wind turbine equipment.

[0005] 2. Patent document CN218277151U discloses an operation and maintenance monitoring system for offshore wind farms. This operation and maintenance monitoring system cannot integrate information from different monitoring methods and cannot extract richer equipment status characteristics. Uncertainties such as model accuracy, test noise during experiments, and incomplete parameter identification will cause the system to be unable to efficiently and accurately identify the damage location and degree of wind power equipment.

[0006] 3. Patent document CN220979768U discloses a fault diagnosis system for offshore wind turbine blades. This fault diagnosis system cannot automatically identify the fault type and location of the equipment, and cannot perform timely repair and replacement before the equipment fails. This will lead to the occurrence and expansion of faults, reducing the accuracy and reliability of the system fault diagnosis.

[0007] 4. Patent document CN118462501A discloses a preventive maintenance and fault diagnosis system and method for offshore wind turbines. This fault diagnosis system cannot automatically identify the fault type and location of the equipment, and cannot perform timely repair and replacement before the equipment fails, which will lead to the occurrence and expansion of faults and reduce the accuracy and reliability of system fault diagnosis. Summary of the Invention

[0008] The object of the present invention is to provide a preventive diagnosis and maintenance system and method for offshore wind power equipment to solve the problems raised in the above background technology.

[0009] To achieve the above objectives, the present invention provides the following technical solutions: a preventive diagnostic maintenance system for offshore wind power equipment, comprising a data input module, a maintenance judgment module, an early warning maintenance module, and an operation and maintenance management module, wherein the data input module is used to input real-time status data of each component of the offshore wind power equipment;

[0010] The operation and maintenance management module controls the operation and management of the entire preventive diagnosis and maintenance system, including data collection, analysis, storage, and the formulation and execution of maintenance plans.

[0011] Preferably, the data input module includes a data acquisition unit, a data processing unit and a data fusion unit. The data acquisition unit collects real-time status data of vibration, temperature, pressure and current parameters of offshore wind power equipment. The data processing unit filters, denoises and analyzes the collected data to extract characteristic values ​​and trend information. The data processing unit is also used to store and manage data to ensure the integrity and traceability of the data. The data fusion unit fuses different monitoring information.

[0012] Preferably, the maintenance judgment module uses a mathematical model based on real-time status data to obtain the risk of each component, and determines whether there is a component whose risk exceeds the corresponding preventive maintenance threshold. The maintenance judgment module includes a fault diagnosis unit and a maintenance range acquisition unit. The fault diagnosis unit uses a machine learning algorithm to perform fault diagnosis based on the processed data to automatically identify the fault type and fault location of the equipment. The maintenance range acquisition unit determines the range of components that need maintenance in order to formulate a specific maintenance plan.

[0013] Preferably, the early warning maintenance module includes an early warning model unit, an early warning release unit, an intelligent fault diagnosis unit and a maintenance execution unit. The early warning model unit promptly detects potential problems before a fault occurs, providing operation and maintenance personnel with sufficient time for prevention and repair. When a potential fault is discovered, the early warning release unit promptly releases the fault type, fault location, severity and recommended maintenance measures to the operation and maintenance personnel. The intelligent fault diagnosis unit analyzes the operating data corresponding to each fault cause, extracts data features and automatically gives the percentage of each fault cause and the corresponding solution based on the operating data before and after the fault. The maintenance execution unit formulates a specific maintenance plan and performs maintenance work based on the early warning information and fault diagnosis results. The maintenance work includes replacing damaged parts, adjusting equipment parameters and cleaning and maintenance.

[0014] A preventive diagnostic maintenance method for offshore wind power equipment is applicable to a preventive diagnostic maintenance system for offshore wind power equipment, preferably comprising the following steps:

[0015] Step S1, status monitoring and data analysis;

[0016] Step S2: fault diagnosis and early warning;

[0017] Step S3: Maintenance plan formulation and implementation;

[0018] Step S4: Maintenance effect evaluation and optimization.

[0019] Preferably, the data input module is used to execute step S1, using sensors and monitoring equipment to collect status data of offshore wind power equipment in real time and process and analyze the data, extract characteristic values ​​and trends to evaluate the operating status of the equipment, and the data fusion unit fuses different monitoring information.

[0020] Preferably, the data fusion unit regards different sensor data as different events, calculates the probability distribution after fusion, and performs fusion processing on different monitoring information. The data fusion algorithm formula is as follows:

[0021]

[0022] in, Indicates that in the event Events under the conditions The probability of occurrence, Indicates that in the event Conditions under which events occur The probability of occurrence, and Represent events respectively and events Probability of occurrence.

[0023] Preferably, the maintenance judgment module is used to execute step S2, and the fault diagnosis unit uses a machine learning algorithm to perform fault diagnosis based on the data analysis results, and when a potential fault is found, early warning information is issued in time to remind the operation and maintenance personnel to handle it.

[0024] Preferably, the likelihood function is maximized to estimate the regression coefficient to achieve classification, and the machine learning algorithm formula is as follows:

[0025]

[0026] in, is the probability of the event occurring, is the independent variable, is the regression coefficient.

[0027] Preferably, the early warning maintenance module is used to execute step S3, formulate a specific maintenance plan based on the fault diagnosis results and early warning information, and perform maintenance work according to the plan, including replacing damaged parts and adjusting equipment parameters;

[0028] The maintenance effect evaluation and optimization steps are as follows: evaluate the effect of the maintenance work, including the operating status of the equipment and the maintenance cost, and optimize and improve the maintenance plan and method based on the evaluation results.

[0029] Compared with the prior art, the present invention has the following beneficial effects:

[0030] 1. The present invention fuses information from different monitoring methods by adopting a data fusion algorithm. The fusion process extracts richer equipment status features, providing more accurate information support for damage identification. It is suitable for data fusion scenarios of offshore wind power equipment with high uncertainty. The current damage diagnosis and prediction technology faces uncertainty when applied to offshore wind power systems, such as model accuracy, test noise during experiments, and incomplete parameter identification. During the data acquisition process, the collected data is filtered and denoised to reduce the interference of test noise, improve the accuracy and reliability of the data, and combine vibration monitoring, temperature monitoring, acoustic emission monitoring and other monitoring methods to obtain more comprehensive equipment status information. The complementarity between different monitoring methods is used to improve the accuracy and reliability of damage identification, so that the diagnosis and maintenance system can efficiently and accurately identify the damage location and degree of the wind turbine structure or equipment.

[0031] 2. The present invention uses a maintenance judgment module to perform intelligent analysis and diagnosis on the equipment status data. The intelligent diagnosis automatically identifies the fault type and fault location of the equipment, provides accurate guidance for maintenance, and formulates targeted preventive maintenance plans based on the equipment status data and intelligent diagnosis results. Preventive maintenance performs timely repairs and replacements before the equipment fails to avoid the occurrence and expansion of faults. The working environment of offshore wind power equipment is complex and changeable, and the requirements for monitoring and diagnostic technologies are high. The model is continuously optimized and trained, and more actual data and fault cases are used to improve the model to improve the accuracy and reliability of the system's fault diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 A diagram of the preventive diagnostic maintenance system of the present invention;

[0033] Figure 2 Schematic diagram of the system workflow of the present invention. DETAILED DESCRIPTION

[0034] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0035] In the description of the present invention, it should be noted that the terms "upper," "lower," "inner," "outer," "front end," "rear end," "both ends," "one end," "the other end," and the like, indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings and are intended solely to facilitate and simplify the description of the present invention. They are not intended to indicate or imply that the devices or components referred to must have, be constructed, or operate in a specific orientation, and therefore should not be construed as limiting the present invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0036] In the description of the present invention, it should be noted that, unless otherwise expressly specified or limited, the terms "installed," "provided with," "connected," etc., should be understood in a broad sense. For example, "connected" may refer to a fixed connection, a movable connection, a detachable connection, or an integral connection; it may refer to a mechanical connection or an electrical connection; it may refer to a direct connection or an indirect connection through an intermediate medium; it may refer to internal communication between two components. Those skilled in the art will be able to understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0037] Example 1, an embodiment provided by the present invention: a preventive diagnosis and maintenance system for offshore wind power equipment, comprising a data input module and an operation and maintenance management module;

[0038] The data input module is used to input the real-time status data of each component of the offshore wind power equipment. The data input module includes a data acquisition unit, a data processing unit and a data fusion unit. The data acquisition unit collects the real-time status data of the vibration, temperature, pressure and current parameters of the offshore wind power equipment. The data processing unit filters, denoises and analyzes the collected data to extract characteristic values ​​and trend information. The data processing unit is also used to store and manage data to ensure the integrity and traceability of the data. The data fusion unit fuses different monitoring information.

[0039] The operation and maintenance management module controls the operation and management of the entire preventive diagnostic maintenance system, including data collection, analysis, storage, and the formulation and execution of maintenance plans.

[0040] Example 2, an embodiment provided by the present invention: a preventive diagnosis and maintenance system for offshore wind power equipment, comprising a data input module, a maintenance judgment module and an operation and maintenance management module;

[0041] The data input module is used to input the real-time status data of each component of the offshore wind power equipment. The data input module includes a data acquisition unit, a data processing unit, and a data fusion unit. The data acquisition unit collects real-time status data of the vibration, temperature, pressure, and current parameters of the offshore wind power equipment. The data processing unit filters, removes noise, and analyzes the collected data to extract characteristic values ​​and trend information. The data processing unit is also used to store and manage data to ensure data integrity and traceability. The data fusion unit integrates different monitoring information;

[0042] The operation and maintenance management module controls the operation and management of the entire preventive diagnostic maintenance system, including data collection, analysis, storage, and the formulation and execution of maintenance plans;

[0043] The maintenance judgment module uses a mathematical model based on real-time status data to obtain the risk of each component and determines whether there are components whose risk exceeds the corresponding preventive maintenance threshold. The maintenance judgment module includes a fault diagnosis unit and a maintenance scope acquisition unit. The fault diagnosis unit uses a machine learning algorithm to perform fault diagnosis based on the processed data to automatically identify the fault type and fault location of the equipment. The maintenance scope acquisition unit determines the scope of components that need maintenance in order to formulate a specific maintenance plan.

[0044] Example 3, an embodiment provided by the present invention: a preventive diagnosis and maintenance system for offshore wind power equipment, comprising a data input module, a maintenance judgment module, an early warning maintenance module and an operation and maintenance management module;

[0045] The data input module is used to input the real-time status data of each component of the offshore wind power equipment. The data input module includes a data acquisition unit, a data processing unit, and a data fusion unit. The data acquisition unit collects real-time status data of the vibration, temperature, pressure, and current parameters of the offshore wind power equipment. The data processing unit filters, removes noise, and analyzes the collected data to extract characteristic values ​​and trend information. The data processing unit is also used to store and manage data to ensure data integrity and traceability. The data fusion unit integrates different monitoring information;

[0046] The operation and maintenance management module controls the operation and management of the entire preventive diagnostic maintenance system, including data collection, analysis, storage, and the formulation and execution of maintenance plans;

[0047] The maintenance judgment module uses a mathematical model based on real-time status data to determine the risk level of each component and to determine whether any component has a risk level exceeding the corresponding preventive maintenance threshold. The maintenance judgment module includes a fault diagnosis unit and a maintenance scope acquisition unit. The fault diagnosis unit uses a machine learning algorithm based on processed data to automatically identify the type and location of the equipment fault. The maintenance scope acquisition unit determines the range of components requiring maintenance in order to formulate a specific maintenance plan.

[0048] The early warning maintenance module includes an early warning model unit and an early warning release unit. The early warning model unit promptly detects potential problems before a fault occurs, providing operation and maintenance personnel with sufficient time to prevent and repair them. When a potential fault is discovered, the early warning release unit promptly releases the fault type, fault location, severity, and recommended maintenance measures to the operation and maintenance personnel.

[0049] Example 4, an embodiment provided by the present invention: a preventive diagnosis and maintenance system for offshore wind power equipment, comprising a data input module, a maintenance judgment module, an early warning maintenance module and an operation and maintenance management module;

[0050] The data input module is used to input the real-time status data of each component of the offshore wind power equipment. The data input module includes a data acquisition unit, a data processing unit, and a data fusion unit. The data acquisition unit collects real-time status data of the vibration, temperature, pressure, and current parameters of the offshore wind power equipment. The data processing unit filters, removes noise, and analyzes the collected data to extract characteristic values ​​and trend information. The data processing unit is also used to store and manage data to ensure data integrity and traceability. The data fusion unit integrates different monitoring information;

[0051] The operation and maintenance management module controls the operation and management of the entire preventive diagnostic maintenance system, including data collection, analysis, storage, and the formulation and execution of maintenance plans;

[0052] The maintenance judgment module uses a mathematical model based on real-time status data to determine the risk level of each component and to determine whether any component has a risk level exceeding the corresponding preventive maintenance threshold. The maintenance judgment module includes a fault diagnosis unit and a maintenance scope acquisition unit. The fault diagnosis unit uses a machine learning algorithm based on processed data to automatically identify the type and location of the equipment fault. The maintenance scope acquisition unit determines the range of components requiring maintenance in order to formulate a specific maintenance plan.

[0053] The early warning maintenance module includes an early warning model unit, an early warning release unit, an intelligent fault diagnosis unit and a maintenance execution unit. The early warning model unit promptly detects potential problems before a fault occurs, providing operation and maintenance personnel with sufficient time for prevention and repair. When a potential fault is discovered, the early warning release unit promptly releases the fault type, fault location, severity and recommended maintenance measures to the operation and maintenance personnel. The intelligent fault diagnosis unit analyzes the operating data corresponding to each fault cause, extracts data features and automatically gives the percentage of each fault cause and the corresponding solution based on the operating data before and after the fault. The maintenance execution unit formulates a specific maintenance plan and performs maintenance work based on the early warning information and fault diagnosis results. The maintenance work includes replacing damaged parts, adjusting equipment parameters and cleaning and maintenance.

[0054] Example 5, based on the above example, the present invention provides an example: a preventive diagnostic maintenance method for offshore wind power equipment, comprising the following steps:

[0055] Step S1, status monitoring and data analysis;

[0056] The data input module is used to execute step S1, using sensors and monitoring equipment to collect status data of offshore wind turbines in real time, process and analyze the data, extract characteristic values ​​and trends to evaluate the operating status of the equipment, and the data fusion unit fuses different monitoring information;

[0057] The data fusion unit regards different sensor data as different events, calculates the probability distribution after fusion, and performs fusion processing on different monitoring information. The data fusion algorithm formula is as follows:

[0058]

[0059] in, Indicates that in the event Conditions under which events occur The probability of occurrence, Indicates that in the event Conditions under which events occur The probability of occurrence, and Represent events respectively and events Probability of occurrence.

[0060] Example 6: Based on the above example, the present invention provides an example of a preventive diagnostic maintenance method for offshore wind power equipment, comprising the following steps:

[0061] Step S1, status monitoring and data analysis;

[0062] Step S2: Fault diagnosis and early warning.

[0063] The data input module is used to execute step S1, using sensors and monitoring equipment to collect status data of offshore wind turbines in real time, process and analyze the data, extract characteristic values ​​and trends to evaluate the operating status of the equipment, and the data fusion unit fuses different monitoring information;

[0064] The data fusion unit regards different sensor data as different events, calculates the probability distribution after fusion, and performs fusion processing on different monitoring information. The data fusion algorithm formula is as follows:

[0065]

[0066] in, Indicates that in the event Conditions under which events occur The probability of occurrence, Indicates that in the event Conditions under which events occur The probability of occurrence, and Represent events respectively and events Probability of occurrence;

[0067] The maintenance judgment module is used to execute step S2. The fault diagnosis unit uses a machine learning algorithm based on the data analysis results to perform fault diagnosis. When a potential fault is found, an early warning message is issued in a timely manner to remind the operation and maintenance personnel to handle it.

[0068] Maximize the likelihood function to estimate the regression coefficient to achieve classification. The machine learning algorithm formula is as follows:

[0069]

[0070] in, is the probability of the event occurring, is the independent variable, is the regression coefficient.

[0071] Example 7, based on the above example, the present invention provides an example: a preventive diagnostic maintenance method for offshore wind power equipment, comprising the following steps:

[0072] Step S1, status monitoring and data analysis;

[0073] Step S2: fault diagnosis and early warning;

[0074] Step S3: Maintenance plan formulation and implementation;

[0075] Step S4: Maintenance effect evaluation and optimization.

[0076] The data input module is used to execute step S1, using sensors and monitoring equipment to collect status data of offshore wind turbines in real time, process and analyze the data, extract characteristic values ​​and trends to evaluate the operating status of the equipment, and the data fusion unit fuses different monitoring information;

[0077] The data fusion unit regards different sensor data as different events, calculates the probability distribution after fusion, and performs fusion processing on different monitoring information. The data fusion algorithm formula is as follows:

[0078]

[0079] in, Indicates that in the event Conditions under which events occur The probability of occurrence, Indicates that in the event Conditions under which events occur The probability of occurrence, and Represent events respectively and events Probability of occurrence;

[0080] The maintenance judgment module is used to execute step S2. The fault diagnosis unit uses a machine learning algorithm based on the data analysis results to perform fault diagnosis. When a potential fault is found, an early warning message is issued in a timely manner to remind the operation and maintenance personnel to handle it.

[0081] Maximize the likelihood function to estimate the regression coefficient to achieve classification. The machine learning algorithm formula is as follows:

[0082]

[0083] in, is the probability of the event occurring, is the independent variable, is the regression coefficient.

[0084] The early warning maintenance module is used to execute step S3, formulate a specific maintenance plan based on the fault diagnosis results and early warning information, and perform maintenance work according to the plan, including replacing damaged parts and adjusting equipment parameters;

[0085] The steps for maintenance effect evaluation and optimization are as follows: Evaluate the effectiveness of maintenance work, including the operating status of the equipment and maintenance costs, and optimize and improve the maintenance plan and methods based on the evaluation results.

[0086] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the invention can be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims, not the foregoing description, and all variations within the meaning and range of equivalents of the claims are intended to be included therein. Any reference sign in a claim should not be construed as limiting the claim to which it relates.

Claims

1. A preventive diagnostic maintenance system for offshore wind power equipment, characterized by: It includes a data input module, a maintenance judgment module, an early warning maintenance module and an operation and maintenance management module. The data input module is used to input the real-time status data of each component of the offshore wind power equipment; The operation and maintenance management module controls the operation and management of the entire preventive diagnosis and maintenance system, including data collection, analysis, storage, and the formulation and execution of maintenance plans.

2. A preventive diagnostic maintenance system for offshore wind power equipment according to claim 1, characterized in that: The data input module includes a data acquisition unit, a data processing unit and a data fusion unit. The data acquisition unit collects real-time status data of vibration, temperature, pressure and current parameters of offshore wind power equipment. The data processing unit filters, denoises and analyzes the collected data to extract characteristic values ​​and trend information. The data processing unit is also used to store and manage data to ensure data integrity and traceability. The data fusion unit fuses different monitoring information.

3. The preventive diagnostic maintenance system for offshore wind power equipment according to claim 1, characterized in that: The maintenance judgment module uses a mathematical model based on real-time status data to obtain the risk of each component and determines whether there are components whose risk exceeds the corresponding preventive maintenance threshold. The maintenance judgment module includes a fault diagnosis unit and a maintenance scope acquisition unit. The fault diagnosis unit uses a machine learning algorithm to perform fault diagnosis based on processed data to automatically identify the fault type and fault location of the equipment. The maintenance scope acquisition unit determines the scope of components that need maintenance in order to formulate a specific maintenance plan.

4. The preventive diagnostic maintenance system for offshore wind power equipment according to claim 1, characterized in that: The early warning maintenance module includes an early warning model unit, an early warning release unit, an intelligent fault diagnosis unit and a maintenance execution unit. The early warning model unit promptly detects potential problems before a fault occurs, providing operation and maintenance personnel with sufficient time for prevention and repair. When a potential fault is discovered, the early warning release unit promptly releases the fault type, fault location, severity and recommended maintenance measures to the operation and maintenance personnel. The intelligent fault diagnosis unit analyzes the operating data corresponding to each fault cause, extracts data features and automatically gives the percentage of each fault cause and the corresponding solution based on the operating data before and after the fault. The maintenance execution unit formulates a specific maintenance plan and performs maintenance work based on the early warning information and fault diagnosis results. The maintenance work includes replacing damaged parts, adjusting equipment parameters and cleaning and maintenance.

5. A preventive diagnostic maintenance method for offshore wind power equipment, applicable to a preventive diagnostic maintenance system for offshore wind power equipment according to any one of claims 1 to 4, characterized in that: The steps include: Step S1, status monitoring and data analysis; Step S2: fault diagnosis and early warning; Step S3: Maintenance plan formulation and implementation; Step S4: Maintenance effect evaluation and optimization.

6. A preventive diagnostic maintenance method for offshore wind power equipment according to claim 5, characterized in that: The data input module is used to execute step S1, using sensors and monitoring equipment to collect status data of offshore wind power equipment in real time and process and analyze the data, extracting characteristic values ​​and trends to evaluate the operating status of the equipment, and the data fusion unit fuses different monitoring information.

7. A preventive diagnostic maintenance method for offshore wind power equipment according to claim 6, characterized in that: The data fusion unit regards different sensor data as different events, calculates the probability distribution after fusion, and performs fusion processing on different monitoring information. The data fusion algorithm formula is as follows: in, Indicates that in the event Conditions under which events occur The probability of occurrence, Indicates that in the event Conditions under which events occur The probability of occurrence, and Represent events respectively and events Probability of occurrence.

8. The preventive diagnostic maintenance method for offshore wind power equipment according to claim 5, characterized in that: The maintenance judgment module is used to execute step S2. The fault diagnosis unit uses a machine learning algorithm to perform fault diagnosis based on the data analysis results. When a potential fault is found, early warning information is issued in a timely manner to remind the operation and maintenance personnel to handle it.

9. A preventive diagnostic maintenance method for offshore wind power equipment according to claim 8, characterized in that: Maximizing the likelihood function to estimate the regression coefficient to achieve classification, the machine learning algorithm formula is as follows: in, is the probability of the event occurring, is the independent variable, is the regression coefficient.

10. The preventive diagnostic maintenance method for offshore wind power equipment according to claim 5, characterized in that: The early warning maintenance module is used to execute step S3, formulate a specific maintenance plan based on the fault diagnosis results and early warning information, and perform maintenance work according to the plan, including replacing damaged parts and adjusting equipment parameters; The maintenance effect evaluation and optimization steps are as follows: evaluate the effect of the maintenance work, including the operating status of the equipment and the maintenance cost, and optimize and improve the maintenance plan and method based on the evaluation results.

Images