Intelligent monitoring system of wind power blade

Abstract

The invention discloses an intelligent monitoring system of a wind power blade, and relates to the technical field of wind power generation, the intelligent monitoring system of the wind power blade comprises a first sensing assembly, a second sensing assembly, a server and a reference adjustment module; each wind power blade is correspondingly provided with a first sensing assembly and a second sensing assembly; the first sensing assembly monitors motion data of the wind power blade; the second sensing assembly monitors health state data of the wind power blade; an exercise data reference interval and a health data reference interval are pre-stored in the server; when the server judges that the motion data does not fall into the motion data reference interval or the health state data does not fall into the health data reference interval, the server is used for outputting alarm information; and the benchmark adjusting module is used for generating a corresponding correction value according to the health state data and adjusting the motion data reference interval by using the correction value. According to the invention, multi-dimensional monitoring and automatic alarm of the operation state and the health state of the wind power blade are realized, and the motion data reference can be automatically adjusted.

Description

Technical Field

[0001] The present invention relates to the technical field of wind power generation, and in particular to an intelligent monitoring system for wind turbine blades. Background Art

[0002] As a key component of clean energy, wind power has experienced a remarkable technological evolution. Initially, wind power originated from traditional windmills, used for simple mechanical energy conversion. With the growing demand for renewable energy in the late 20th century, technology gradually shifted to large-scale power generation based on wind turbines. In the 1980s, early wind turbines employed shorter towers and smaller blades, resulting in limited power generation efficiency. Since the 21st century, technological advances have driven blade innovation: blade lengths have continued to increase, from tens of meters in the early days to hundreds of meters today; blade materials have been optimized, such as using lightweight composite materials to enhance strength and durability; and tower heights have been increased to capture high-altitude wind energy resources. Simultaneously, wind power applications have expanded from onshore to offshore. However, during this development, wind turbine blades, as key core components of wind turbines, face significant challenges due to their operational performance, directly determining power generation efficiency and equipment lifespan, exposure to complex and variable natural conditions such as wind and sand, lightning, and ultraviolet rays.

[0003] Currently, monitoring solutions for wind turbine blades primarily rely on a combination of traditional methods and some modern technologies. Traditionally, manual inspections are the mainstream method, requiring operators to regularly climb towers or use lifting equipment for close-up visual inspections. For example, after a wind turbine is shut down, they can use a telescope to observe blade surface damage, or utilize monitoring equipment to detect surface damage such as cracks, erosion, or deformation.

[0004] However, traditional wind turbine blade monitoring methods have significant limitations in monitoring dimensions. For manual inspection methods, since the wind turbine generator set needs to be shut down for inspection, it is difficult for operation and maintenance personnel to observe the movement data of the wind turbine blades during the inspection process; and after the wind turbine generator set is repaired and restarted, although the movement status of the wind turbine blades can be detected, it is difficult to detect the health status of the wind turbine blades at the same time.

[0005] Therefore, a new type of intelligent monitoring system for wind turbine blades is urgently needed to solve the problem that the current monitoring method for wind turbine blades has a single monitoring dimension and is difficult to monitor the movement state and health state of the wind turbine blades at the same time. Summary of the Invention

[0006] The main purpose of the present invention is to propose an intelligent monitoring system for wind turbine blades, aiming to solve the problem that the current monitoring method for wind turbine blades has a single monitoring dimension and is difficult to monitor the motion state and health state of the wind turbine blades at the same time.

[0007] To achieve the above-mentioned purpose, the intelligent monitoring system for wind turbine blades proposed in the present invention is applied to a wind turbine generator set, which includes multiple wind turbine blades. The intelligent monitoring system for wind turbine blades includes a first sensor component, a second sensor component, a server and a benchmark adjustment module; each wind turbine blade is correspondingly provided with at least one first sensor component and at least one second sensor component; the first sensor component is used to monitor the motion data of the wind turbine blade; the second sensor component is used to monitor the health status data of the wind turbine blade; the server pre-stores a motion data reference interval and a health data reference interval, and the server is communicated with the first sensor component and the second sensor component respectively; when the server determines that the motion data does not fall into the motion data reference interval or the health status data does not fall into the health data reference interval, the server is used to output an alarm message; the benchmark adjustment module is communicated with the server; the benchmark adjustment module is used to generate a corresponding correction value according to the health status data, and use the correction value to adjust the motion data reference interval.

[0008] In one embodiment, the motion data reference interval includes at least a rotation parameter; when the server determines that the rotation parameter remains zero within a preset time period, the server is configured to output motion abnormality alarm information.

[0009] In one embodiment, the intelligent monitoring system for wind turbine blades also includes a third sensor component, which is arranged on the fuselage or wind turbine blades of the wind turbine generator set, and the server is communicatively connected to the third sensor component; the third sensor component is used to monitor wind field data around the wind turbine generator set; the server also pre-stores a wind field data reference interval; when the server determines that the wind field data does not fall within the wind field data reference interval, the server is also used to output wind field alarm information.

[0010] In one embodiment, the motion data includes at least the blade rotation speed, and the wind field data includes at least the incoming wind speed; the server also pre-stores a mapping relationship between the incoming wind speed and the expected blade rotation speed range; when the server determines that the mapping relationship between the incoming wind speed and the expected blade rotation speed range is not satisfied, the server is also used to output motion abnormality alarm information.

[0011] In one embodiment, the server is further configured to store motion data, health status data, and wind farm data to form historical data; the server is further configured to analyze patterns in the historical data and predict future operating states of wind turbine blades.

[0012] In one embodiment, the health status data includes at least the strain and vibration of the wind turbine blade; the second sensing component includes at least a strain monitoring sensor and a vibration monitoring sensor, and the strain monitoring sensor and the vibration monitoring sensor are both communicatively connected to the server; the strain monitoring sensor is used to monitor the strain of the wind turbine blade; and the vibration monitoring sensor is used to monitor the vibration of the wind turbine blade.

[0013] In one embodiment, the health status data also includes at least the surface cracks and corrosion status of the wind turbine blades; the second sensing component also includes at least a crack monitoring module and a corrosion monitoring module, and the crack monitoring module and the corrosion monitoring module are both communicatively connected to the server; the crack monitoring module is used to transmit ultrasonic signals to penetrate the wind turbine blades and receive reflected signals of the ultrasonic signals; the corrosion monitoring module is used to detect infrared images of the wind turbine blades; the server is also used to process reflected signals of the ultrasonic signals to determine the crack conditions of the wind turbine blades; the server is also used to process infrared images of the wind turbine blades to determine the corrosion status of the wind turbine blades.

[0014] In one embodiment, the crack monitoring module and / or corrosion monitoring module is also used to capture visible light images of the wind turbine blades; the server is also used to process the visible light images of the wind turbine blades based on a deep learning algorithm to identify the surface crack conditions and corrosion status of the wind turbine blades.

[0015] In one embodiment, the first sensor component, the second sensor component, the server, and the benchmark adjustment module are all electrically connected to the wind turbine generator set; and / or, the intelligent monitoring system for wind turbine blades also includes a photovoltaic power generation module, and the first sensor component, the second sensor component, the server, and the benchmark adjustment module are all electrically connected to the photovoltaic power generation module; and / or, the intelligent monitoring system for wind turbine blades also includes a power supply station, and the first sensor component, the second sensor component, the server, and the benchmark adjustment module are all electrically connected to the power supply station.

[0016] In one embodiment, the intelligent monitoring system for wind turbine blades further includes a terminal device, which is communicatively connected to the server; the server is further configured to send an alarm message to the terminal device after outputting the alarm message; and the terminal device is configured to receive and display the alarm message.

[0017] The technical solution of the present invention achieves multi-dimensional simultaneous monitoring and comprehensive processing of the operating status and health status of the wind turbine blades and automatic alarms by independently setting a first sensor component and a second sensor component on each wind turbine blade, and using a server to communicate with them respectively, so as to timely obtain abnormal movement and health conditions of the wind turbine blades and improve the reliability and safety of the wind turbine generator set; then, the reference adjustment module is used to adjust the reference interval of the motion data according to the health status of the wind turbine blades, so that the server can make more accurate judgments on the motion data of the wind turbine blades. Specifically, the motion data of the wind turbine blades is monitored in real time by the first sensor component. The motion data may include data such as the rotation speed and yaw angle of the wind turbine blades, so as to accurately capture the dynamic behavior abnormalities of the blades during operation, such as abnormal rotation speed, etc., which helps to discover potential operational fault problems at an early stage; at the same time, the health status data is monitored by the second sensor component. The health status data may include cracks, strain conditions, corrosion conditions, etc. of the wind turbine blades, which can provide early warning of internal damage or degradation trends of the blades and avoid structural failure caused by sudden faults. Furthermore, the server automatically collects and processes multi-dimensional data, including motion data and health status data, through a communication connection, thereby simultaneously monitoring the motion and health status of the wind turbine blades. The server uses an algorithm to perform a comprehensive diagnosis of the multi-dimensional data, instantly outputting an alarm message when the motion data or health status data does not fall within the motion data reference interval, allowing maintenance personnel to promptly inspect and repair the wind turbine blades. This improves the timeliness and comprehensiveness of monitoring and alarms, and helps ensure the structural safety and continued normal operation of the wind turbine blades. Furthermore, since changes in the health status of wind turbine blades may also change the corresponding dynamic characteristics of the wind turbine blades, a baseline adjustment module is provided and communicated with the server. The baseline adjustment module generates corresponding correction values ​​based on the real-time measured health status data, and uses the correction values ​​to adjust the motion data reference interval. This allows the server to promptly update the motion data reference interval and obtain a motion data judgment benchmark that is more consistent with the current health status of the wind turbine blades. The server then performs motion status judgment based on the updated motion data reference interval, resulting in a more accurate judgment of the wind turbine blade's motion status. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary operation and maintenance personnel in this field, other drawings can be obtained based on the structures shown in these drawings without paying any creative work.

[0019] Figure 1A schematic structural diagram of an embodiment of an intelligent monitoring system for wind turbine blades provided by the present invention;

[0020] Figure 2 A schematic diagram of the module composition of an embodiment of an intelligent monitoring system for wind turbine blades provided by the present invention;

[0021] Figure 3 This is a schematic diagram of another module composition of an embodiment of the intelligent monitoring system for wind turbine blades provided by the present invention.

[0022] Description of Figure Numbers:

[0023] 1. Intelligent monitoring system for wind turbine blades; 11. First sensor component; 12. Second sensor component; 13. Server; 14. Third sensor component;

[0024] 2. Wind turbine generator set; 21. Wind turbine blades.

[0025] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0026] 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 operation and maintenance personnel in this field without making any creative efforts are within the scope of protection of the present invention.

[0027] It should be noted that if the embodiments of the present invention involve directional indications (such as up, down, left, right, front, back, etc.), the directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture. If the specific posture changes, the directional indications will also change accordingly.

[0028] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present invention, the descriptions of "first", "second", etc. are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features limited to "first" and "second" may explicitly or implicitly include at least one of such features. In addition, if "and / or" or "and / or" appears in the full text, its meaning includes three parallel solutions. Taking "A and / or B" as an example, it includes solution A, solution B, or solutions that satisfy both A and B. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the fact that ordinary operation and maintenance personnel in this field can implement it. When the combination of technical solutions is mutually contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0029] As a key component of clean energy, wind power has experienced a remarkable technological evolution. Initially, wind power originated from traditional windmills, used for simple mechanical energy conversion. With the growing demand for renewable energy in the late 20th century, technology gradually shifted to large-scale power generation based on wind turbines. In the 1980s, early wind turbines employed shorter towers and smaller blades, resulting in limited power generation efficiency. Since the 21st century, technological advances have driven blade innovation: blade lengths have continued to increase, from tens of meters in the early days to hundreds of meters today; blade materials have been optimized, such as using lightweight composite materials to enhance strength and durability; and tower heights have been increased to capture high-altitude wind energy resources. Simultaneously, wind power applications have expanded from onshore to offshore. However, during this development, wind turbine blades, as key core components of wind turbines, face significant challenges due to their operational performance, directly determining power generation efficiency and equipment lifespan, exposure to complex and variable natural conditions such as wind and sand, lightning, and ultraviolet rays.

[0030] Currently, monitoring solutions for wind turbine blades primarily rely on a combination of traditional methods and some modern technologies. Traditionally, manual inspections are the mainstream method, requiring operators to regularly climb towers or use lifting equipment for close-up visual inspections. For example, after a wind turbine is shut down, they can use a telescope to observe blade surface damage, or utilize monitoring equipment to detect surface damage such as cracks, erosion, or deformation.

[0031] However, traditional wind turbine blade monitoring methods have significant limitations in monitoring dimensions. For manual inspection methods, since the wind turbine generator set needs to be shut down for inspection, it is difficult for operation and maintenance personnel to observe the movement data of the wind turbine blades during the inspection process; and after the wind turbine generator set is repaired and restarted, although the movement status of the wind turbine blades can be detected, it is difficult to detect the health status of the wind turbine blades at the same time.

[0032] Therefore, a new type of intelligent monitoring system for wind turbine blades is urgently needed to solve the problem that the current monitoring method for wind turbine blades has a single monitoring dimension and is difficult to monitor the movement state and health state of the wind turbine blades at the same time.

[0033] In order to solve the above problems, the present invention proposes an intelligent monitoring system for wind turbine blades.

[0034] See also Figure 1 and Figure 2 In one embodiment of the present invention, the intelligent monitoring system 1 for wind turbine blades is applied to a wind turbine generator set 2, which includes a plurality of wind turbine blades 21. The intelligent monitoring system 1 for wind turbine blades includes a first sensor component 11, a second sensor component 12, a server 13, and a reference adjustment module. Each wind turbine blade 21 is correspondingly provided with at least one first sensor component 11 and at least one second sensor component 12. The first sensor component 11 is used to monitor motion data of the wind turbine blade 21; the second sensor component 12 is used to monitor health status data of the wind turbine blade 21. The server 13 pre-stores a motion data reference interval and a health data reference interval, and is communicatively connected to the first sensor component 11 and the second sensor component 12, respectively. When the server 13 determines that the motion data does not fall within the motion data reference interval or the health status data does not fall within the health data reference interval, the server 13 is configured to output an alarm message. The reference adjustment module is communicatively connected to the server 13. The reference adjustment module is configured to generate a corresponding correction value based on the health status data and adjust the motion data reference interval using the correction value.

[0035] The technical solution of the present invention achieves multi-dimensional simultaneous monitoring and comprehensive processing of the operating status and health status of the wind turbine blade 21 by independently providing a first sensor component 11 and a second sensor component 12 on each wind turbine blade 21, and communicating with them via a server 13. This allows for automatic alarms and timely notification of abnormal motion and health conditions of the wind turbine blade 21, thereby improving the reliability and safety of the wind turbine generator 2. Furthermore, a reference adjustment module is used to adjust the reference interval of motion data according to the health status of the wind turbine blade 21, thereby enabling the server 13 to more accurately determine the motion data of the wind turbine blade 21. Specifically, the first sensor component 11 monitors the motion data of the wind turbine blade 21 in real time. The motion data may include data such as the rotation speed and yaw angle of the wind turbine blade 21, thereby accurately capturing abnormal dynamic behavior of the blade during operation, such as abnormal rotation speed, and facilitating the early detection of potential operational faults. Simultaneously, the second sensor component 12 monitors health status data. The health status data may include cracks, strain, corrosion, etc. of the wind turbine blade 21, providing early warning of internal damage or degradation trends in the blade, thereby avoiding structural failure caused by sudden faults. In addition, the server 13 automatically collects and processes multi-dimensional data such as motion data and health status data through communication connections, thereby achieving the effect of simultaneously monitoring the motion status and health status of the wind turbine blade 21; the server 13 performs comprehensive diagnosis on the multi-dimensional data through algorithms, so that when the motion data does not fall into the motion data reference interval or the health status data does not fall into the health data reference interval, an alarm message is immediately output so that the operation and maintenance personnel can promptly inspect and process the wind turbine blade 21, which improves the timeliness and comprehensiveness of the monitoring alarm and helps to ensure the structural safety and continued normal operation of the wind turbine blade 21. In addition, since the corresponding dynamic characteristics of the wind turbine blade 21 may also change when the health status of the wind turbine blade 21 changes, a benchmark adjustment module is provided and the benchmark adjustment module is communicated with the server 13, so that the benchmark adjustment module is used to generate a corresponding correction value based on the real-time measured health status data, and the motion data reference interval is adjusted using the correction value, so that the server 13 can update the motion data reference interval in time and have a motion data judgment benchmark that is more in line with the current health status of the wind turbine blade 21, and perform motion status judgment based on the updated motion data reference interval, so that the judgment result of the motion status of the wind turbine blade 21 is more accurate.

[0036] In general, the present invention independently sets a first sensor component 11 and a second sensor component 12 on each wind turbine blade 21 to monitor the motion data and health status data of the wind turbine blade 21 respectively, thereby expanding the monitoring dimension and realizing more comprehensive fault detection; and through the server 13, the motion data and health status data are processed, and an alarm message is output when any data of the motion data and health status data is abnormal, thereby realizing multi-dimensional simultaneous monitoring and processing of the operating status and health status of the wind turbine blade 21 and automatic alarm, optimizing the preventive maintenance strategy of the wind turbine generator set 2, so as to timely know the abnormal motion and health conditions of the wind turbine blade 21, and improve the reliability and safety of the wind turbine generator set 2, and reduce the safety risks and production losses caused by blade failures.

[0037] Because each blade is equipped with an independent first sensor assembly 11 and second sensor assembly 12, server 13 can accurately locate problematic wind turbine blades 21 and the type of abnormality, facilitating timely and targeted maintenance by operations and maintenance personnel, thereby reducing unnecessary downtime and repair costs. Specifically, each first sensor assembly 11 and each second sensor assembly 12 can store a unique identifier, such as a unique serial number, and the corresponding data transmitted by them is accompanied by this serial number. Server 13 stores the serial number information corresponding to each sensor assembly, thereby accurately locating wind turbine blades 21 based on the serial number included in the data.

[0038] Among them, the server 13 can realize the identification of abnormal data in the motion data and health status data by adopting threshold comparison, pattern recognition and other methods. Exemplarily, the server 13 can store the motion data abnormal threshold and the health status data abnormal threshold. By comparing the real-time motion data with the motion data abnormal threshold and the health status data with the health status data abnormal threshold, it can be known whether the motion data and health status data are normal. In addition, the server 13 can also store a pattern recognition algorithm, such as a support vector machine based on supervised learning, a neural network algorithm, or a clustering algorithm based on unsupervised learning, such as the K-Means clustering algorithm, etc. The basic principle is to extract features from the motion data and health status data, so as to grasp the corresponding feature patterns and identify abnormal motion data and abnormal health status data. The above methods all enable the server 13 to realize the identification of abnormal data in the motion data and health status data. Of course, other methods can also be used, which will not be repeated here.

[0039] As an optional implementation, the benchmark adjustment module can pre-store a mapping table between health data and correction values, obtain corresponding correction values ​​based on different health data, and add / subtract the correction values ​​from the corresponding motion data reference interval. For example, when the corrosion state-related parameters or surface crack-related parameters in the health data of the wind turbine blade 21 are high, this will affect the aerodynamic characteristics of the wind turbine blade 21, thereby changing motion data standards such as rotational speed. Therefore, in this case, the benchmark adjustment module queries the mapping table between health data and correction values ​​based on the corrosion state-related parameters or surface crack-related parameters in the health data, obtains the corresponding correction values ​​for the motion data, and adds or subtracts the correction values ​​to the endpoints of the motion data reference interval, i.e., the maximum and minimum values, thereby adjusting the motion data reference interval. As another optional implementation, a relevant data set can be created based on historical health data and historical motion data, and a relevant model can be trained using a machine learning method. The trained model can then be loaded into the benchmark adjustment module, allowing the benchmark adjustment module to obtain the corresponding motion data prediction interval based on the health data, and then use the motion data prediction interval as the correction value to correct the motion data reference interval.

[0040] In addition, as an optional embodiment, the first sensing assembly 11 may include a speed sensor, an acceleration sensor, etc., to measure corresponding motion data such as the speed and acceleration of the wind turbine blade 21. The second sensing assembly 12 may include a strain monitoring sensor, a vibration monitoring sensor, a crack monitoring sensor, a corrosion monitoring sensor, etc., to measure health status data such as strain, vibration, crack status, and corrosion degree.

[0041] In addition, as an optional implementation, the server 13 can be set in the cabin of the wind turbine generator set 2. The server 13 can also be set in a dedicated machine room, operation and maintenance center, etc., which will not be repeated here.

[0042] See also Figure 1 and Figure 2 In an embodiment of the present invention, the motion data reference interval includes at least a rotation parameter; when the server 13 determines that the rotation parameter remains zero within a preset time period, the server 13 is configured to output motion abnormality alarm information.

[0043] In this embodiment, the server 13 is used to output motion abnormality alarm information by monitoring the rotation parameters of the motion data to be zero for a preset period of time. This mechanism can accurately identify blade stagnation faults and achieve rapid response through automatic alarms, thereby effectively improving the operational reliability and maintenance efficiency of the wind turbine blades 21. Specifically, because the rotation parameters continuously collected by the first sensor component 11 include the rotation speed information of the wind turbine blades 21, the server 13 determines in real time whether the blades are abnormally stagnant by setting a preset time threshold, thereby avoiding the subjectivity and lag of traditional manual inspections, ensuring that potential stagnation problems caused by jamming, mechanical failure, or environmental obstacles are captured in the first time, and an alarm information is output immediately. This process significantly shortens the fault detection cycle through automated logical processing, prevents the expansion of structural fatigue or component damage caused by long-term blade stagnation, and reduces the risk of false alarms and missed alarms.

[0044] Among them, the preset time can be set according to factors such as the wind conditions of the actual location of the wind farm. Under normal circumstances, the preset time can be set to 10 minutes. For areas with excellent wind conditions, the preset time can be shortened accordingly, such as setting the preset time to 5 minutes, so that early detection and alarm can be carried out in a shorter time, so that operation and maintenance personnel can carry out maintenance; and for areas with relatively general wind conditions, the preset time can be increased accordingly, such as setting the preset time to 20 minutes, which will not be repeated here.

[0045] See also Figure 1 and Figure 3 In an embodiment of the present invention, the intelligent monitoring system 1 for wind turbine blades further includes a third sensor component 14, which is disposed on the fuselage of the wind turbine generator set 2 or the wind turbine blade 21. The server 13 is communicatively connected to the third sensor component 14; the third sensor component 14 is configured to monitor wind field data around the wind turbine generator set 2; the server 13 also pre-stores a wind field data reference interval; and when the server 13 determines that the wind field data does not fall within the wind field data reference interval, the server 13 is further configured to output wind field alarm information.

[0046] In this embodiment, by adding a third sensor component 14 that is in communication with the server 13 and setting it on the fuselage of the wind turbine 2 or the wind turbine blades 21, active monitoring of the operating environment of the wind turbine 2 is achieved, greatly improving the system's perception and early warning capabilities of changes in the wind field environment. Specifically, the third sensor component 14 collects key wind field data around the wind turbine 2 in real time, such as wind speed, wind direction, turbulence intensity, or gust frequency. Since the server 13 pre-stores a wind field data reference interval, the server 13 can determine whether the wind field data is abnormal by comparing and analyzing it with the wind field data reference interval, thereby determining whether there are any wind field abnormalities such as sudden strong wind changes exceeding the safety threshold, continuous strong turbulence, or abnormal wind direction changes. Once the server 13 detects the existence of a wind field abnormality, it can immediately output wind field alarm information. This solution not only helps to identify in advance the direct threats that severe wind conditions may pose to the equipment itself, but also provides key environmental background information for explaining the blade movement or health anomalies detected by the first and second sensor components 12 in the above embodiment (such as the abnormal vibration caused by high wind speed, the microcracks in the blade material that may be induced by strong gusts, etc.), and realizes the complete fault chain tracing from external environmental inducements to the blade body status response. In addition, the coordinated mechanism of wind farm alarm and blade abnormality alarm allows operation and maintenance personnel to quickly distinguish whether the root cause of the fault is caused by a problem with the blade itself or a sudden change in external wind conditions, so as to formulate targeted maintenance strategies, avoid unnecessary blade disassembly and maintenance, and promptly initiate active defense measures such as shutdown protection under extreme wind farm conditions, thereby minimizing the operating risks of wind turbine generator set 2 and extending the life of key equipment.

[0047] As an optional implementation, the third sensing component 14 may include sensors such as anemometers and wind vanes, so as to monitor the corresponding wind field data.

[0048] In an embodiment of the present invention, the motion data includes at least the blade rotation speed, and the wind field data includes at least the incoming wind speed; the server 13 also pre-stores a mapping relationship between the incoming wind speed and the expected blade rotation speed range; when the server 13 determines that the mapping relationship between the incoming wind speed and the expected blade rotation speed range is not satisfied, the server 13 is also used to output motion abnormality alarm information.

[0049] In this embodiment, server 13 utilizes a pre-stored mapping between incoming wind speed and the expected blade speed range for diagnosis, significantly improving the accuracy and refinement of motion anomaly alerts. Specifically, after obtaining incoming wind speed information from wind farm data and the actual speed of wind turbine blades 21 from motion data, server 13 searches for the expected normal speed range for wind turbine blades 21 at that specific wind speed. By comparing these data, server 13 can accurately identify speed anomalies that deviate from normal patterns. For example, if the actual speed is persistently below the expected range, this may indicate problems such as icing or increased mechanical resistance on the wind turbine blades 21. If the actual speed is persistently above the expected range, it may indicate a transmission system failure. Compared to solutions that simply monitor the absolute value of the speed for abnormalities, the associated diagnosis method in this solution, based on the mapping between incoming wind speed and the expected blade speed range, can more sensitively detect potential faults caused by a mismatch between the actual operating status of wind turbine generator set 2 and the wind energy input, avoiding misjudgments or omissions caused by ignoring environmental factors. The resulting motion anomaly warning not only alerts maintenance personnel to blade anomalies but also pinpoints the relationship between the anomaly and wind input, greatly facilitating rapid locating of the root cause. This further improves the accuracy and efficiency of maintenance work, reducing unnecessary inspection costs and downtime losses.

[0050] In an embodiment of the present invention, the server 13 is further used to store motion data, health status data and wind farm data to form historical data; the server 13 is further used to analyze patterns in the historical data and predict the future operating status of the wind turbine blades 21 .

[0051] In this embodiment, server 13 forms a historical database by storing motion data from the first sensor assembly 11, health data from the second sensor assembly 12, and wind field data from the third sensor assembly 14. Based on this historical data, it analyzes the regularity of this data to predict the future operating state of the wind turbine blade 21, significantly enhancing the monitoring system's proactive maintenance capabilities. Specifically, server 13 continuously accumulates multi-dimensional operational, status, and environmental data, establishing a comprehensive historical data record. By analyzing the evolution trends, correlation patterns, and statistical regularities of this historical data, server 13 can identify slow degradation processes or potential risks that are difficult to capture through real-time monitoring. This enables the intelligent monitoring system to go beyond the limitations of real-time alerts and predict the potential future risk of blade performance degradation, component lifespan exhaustion, or failure under specific wind conditions. For example, it can predict structural fatigue by analyzing the growth trend of vibration amplitude over time, or predict the risk of material crack growth by combining historical strain data at specific wind speeds. This predictive capability provides reliable decision support for operations and maintenance personnel, enabling them to proactively plan preventive maintenance based on the predicted results and intervene before potential problems develop into actual failures. This effectively avoids unexpected shutdowns and emergency repairs caused by sudden serious failures, ensures the continuous and stable operation of the wind turbine generator set 2 to the greatest extent, extends the service life of the wind turbine blades 21, and significantly reduces the subsequent high maintenance costs and power generation losses.

[0052] See also Figure 1 and Figure 3 In an embodiment of the present invention, the health status data includes at least the strain and vibration of the wind turbine blade 21; the second sensing component 12 includes at least a strain monitoring sensor and a vibration monitoring sensor, and both the strain monitoring sensor and the vibration monitoring sensor are communicatively connected to the server 13; the strain monitoring sensor is used to monitor the strain of the wind turbine blade 21; and the vibration monitoring sensor is used to monitor the vibration of the wind turbine blade 21.

[0053] In this embodiment, the second sensing assembly 12 accurately collects strain and vibration data from the wind turbine blade 21 by providing strain monitoring sensors and vibration monitoring sensors, respectively. Together, these sensors form the core monitoring dimension for blade health, significantly enhancing the ability to early identify structural risks and operational anomalies. Specifically, strain monitoring sensors are directly attached to the surface of key blade areas or embedded within the material to continuously monitor subtle deformations of the blade when subjected to wind pressure loads, centrifugal forces, or impacts during operation. The strain data obtained can be used to infer the instantaneous wind pressure loads, structural stress distribution, and long-term fatigue accumulation experienced by the blade. A persistent abnormal increase in strain or a sudden change in strain under specific load patterns may indicate significant safety hazards such as interlayer failure, debonding at adhesive bonds, or structural buckling of beams. Furthermore, vibration monitoring sensors capture the dynamic response characteristics of the blade during operation in real time, including changes in vibration frequency, amplitude, and mode. Abnormal vibration signals are often a direct response to blade natural frequency shifts, internal damage expansion (such as cracks and delamination), or external damage and collisions. This dual monitoring mechanism provides a synergistic understanding of the static bearing capacity and dynamic response characteristics of the blade structure, enabling the system to cross-validate potential damage at both the microscopic deformation and macroscopic motion levels. For example, when abnormal vibration characteristics in a specific area coincide with abnormally high strain measured in that area, it is highly certain that there is a risk of structural damage in that area. By integrating strain and force analysis of wind turbine blades 21, this solution significantly improves the reliability of diagnostic conclusions and the accuracy of fault location, providing maintenance personnel with more targeted early warning information, allowing timely intervention before the blade structure is substantially threatened, thereby avoiding catastrophic failures.

[0054] See also Figure 1 and Figure 3 In an embodiment of the present invention, the health status data also includes at least surface cracks and corrosion status of the wind turbine blade 21; the second sensor component 12 also includes at least a crack monitoring module and a corrosion monitoring module, and both the crack monitoring module and the corrosion monitoring module are communicatively connected to the server 13; the crack monitoring module is used to transmit an ultrasonic signal to penetrate the wind turbine blade 21 and receive a reflected signal of the ultrasonic signal; the corrosion monitoring module is used to detect an infrared image of the wind turbine blade 21; the server 13 is also used to process the reflected signal of the ultrasonic signal to determine the crack condition of the wind turbine blade 21; the server 13 is also used to process the infrared image of the wind turbine blade 21 to determine the corrosion status of the wind turbine blade 21.

[0055] In this embodiment, the collaborative configuration of the crack monitoring module and the corrosion monitoring module enables three-dimensional nondestructive testing of surface and internal defects in wind turbine blades 21, significantly enhancing the intelligent monitoring system's early warning capabilities for hidden damage. Specifically, the crack monitoring module transmits ultrasonic signals in a directionally directed manner toward the wind turbine blade 21 and receives the reflected signals. This module leverages the characteristics of the reflected waves generated by the ultrasonic waves propagating through the material and encountering discontinuous interfaces such as cracks to obtain structural information. The server 13 analyzes the intensity, propagation time, and spectral characteristics of the reflected signals to accurately identify the initiation location, propagation depth, and morphological characteristics of microcracks within the blade, thereby overcoming the limitations of visual inspection and capturing early-stage internal defects. Simultaneously, the corrosion monitoring module collects infrared thermal imaging data from the blade surface and, based on the principle of localized temperature anomalies caused by changes in thermal conductivity due to corrosion, generates a visual corrosion distribution map. The server 13 analyzes the areas of abnormal temperature gradients in the infrared image to quantitatively assess the extent and severity of surface corrosion. By combining ultrasonic and infrared detection methods, this solution simultaneously covers two core damage modes: hidden internal cracks and external surface corrosion. For example, when an ultrasonic signal detects a tiny interlayer crack in a certain area, simultaneous analysis of the infrared image at that location to determine whether there is an abnormal temperature change zone can help distinguish the damage attributes, such as whether it is a crack or corrosion-induced material degradation. This multimodal data processing mechanism can significantly improve the accuracy of complex damage identification, providing the operation and maintenance team with a scientific basis for assessing the remaining life of the structure, allowing them to accurately formulate targeted repair plans and effectively avoid structural fracture or catastrophic failure caused by minor damage degradation.

[0056] In an embodiment of the present invention, the crack monitoring module and / or the corrosion monitoring module are also used to capture visible light images of the wind turbine blades 21; the server 13 is also used to process the visible light images of the wind turbine blades 21 based on a deep learning algorithm to identify the surface crack conditions and corrosion status of the wind turbine blades 21.

[0057] In this embodiment, the crack monitoring module and corrosion monitoring module, by adding visible light image acquisition capabilities and combining them with deep learning algorithms for intelligent analysis, achieve multi-dimensional and precise identification of crack and corrosion characteristics on the surface of wind turbine blades 21. Specifically, the modules use high-definition cameras to capture visible light images of the blade surface, capturing microscopic visual information such as crack morphology, rust spots, and coating delamination. Server 13 processes the visible light images based on pre-trained deep learning algorithms (such as convolutional neural networks). The algorithms automatically identify visual features such as edge anomalies, color distortion, or texture discontinuities in the images, efficiently extracting subtle damage patterns that are difficult for the human eye to detect. Because ultrasound is insensitive to open-surface microcracks and infrared is prone to missing superficial corrosion without thermal characteristics, visible light imaging directly captures the physical state of the blade surface and can intuitively capture millimeter-level crack orientation or pitting corrosion. Therefore, this technology significantly overcomes the shortcomings of relying solely on ultrasound or infrared detection. Furthermore, this solution leverages the accuracy and efficiency of deep learning in image recognition to quickly locate defect areas and quantify damage size from massive amounts of image data.

[0058] In addition, by performing multi-source comparison between the visible light analysis results and the ultrasonic reflection signals and infrared temperature field data, the server 13 can construct a comprehensive damage map and cross-verify the false detection results of a single method, such as distinguishing between real cracks and stain shadows, thereby further improving the accuracy of identifying surface defects of the wind turbine blades 21 and greatly reducing the need for manual re-inspection, so that the operation and maintenance team can formulate efficient maintenance plans based on the quantitative damage reports automatically generated by the system, significantly shortening the downtime and maintenance cycle and reducing maintenance costs.

[0059] In an embodiment of the present invention, the first sensor component 11, the second sensor component 12, the server 13, and the benchmark adjustment module are all electrically connected to the wind turbine generator set 2; and / or, the intelligent monitoring system 1 for wind turbine blades also includes a photovoltaic power generation module, and the first sensor component 11, the second sensor component 12, the server 13, and the benchmark adjustment module are all electrically connected to the photovoltaic power generation module; and / or, the intelligent monitoring system 1 for wind turbine blades also includes a power supply station, and the first sensor component 11, the second sensor component 12, the server 13, and the benchmark adjustment module are all electrically connected to the power supply station.

[0060] In this embodiment, the intelligent monitoring system ensures the continuous and stable operation of all key components by providing three flexible and reliable power supply methods: wind power supply, photovoltaic supply, and power station supply, significantly improving the system's deployment adaptability and operation and maintenance reliability in the complex environment of wind turbine generator set 2. Specifically, the first solution fully utilizes the power resources of wind turbine generator set 2 by directly electrically connecting the first sensor component 11, the second sensor component 12, the server 13, and the benchmark adjustment module to the wind turbine generator set 2. This enables the first sensor component 11, the second sensor component 12, the server 13, and the benchmark adjustment module to obtain power supply, especially ensuring the high-frequency collection and real-time processing capabilities of blade operation data in continuous rainy or nighttime environments. The second solution achieves independent power supply by adding a photovoltaic power generation module, enabling the entire monitoring system to operate independently with green energy. The third solution, by connecting to a power supply station, can provide high-stability, strong anti-interference industrial-grade power guarantee for high-power consumption equipment such as server 13, minimizing data processing interruptions or equipment damage caused by voltage fluctuations. These three power supply methods can operate independently or complement each other. For example, the photovoltaic power generation module prioritizes power supply when there is sufficient sunlight and automatically and seamlessly switches to the backup power supply when there is insufficient sunlight. This reduces the risk of system failure caused by power problems, extends the maintenance-free operation cycle of sensor equipment in harsh environments, and lays a solid energy foundation for all-weather intelligent monitoring.

[0061] See also Figure 3 In an embodiment of the present invention, the intelligent monitoring system 1 for wind turbine blades further includes a terminal device, which is communicatively connected to the server 13; the server 13 is further configured to send an alarm message to the terminal device after outputting the alarm message; and the terminal device is configured to receive and display the alarm message.

[0062] In this embodiment, the server 13 achieves real-time closed-loop transmission of alarm information from generation to transmission to the operation and maintenance personnel terminal through a communication connection with the terminal device, significantly improving the timeliness of the response to the wind turbine blade 21 fault and the initiative of the operation and maintenance decision-making. Specifically, after detecting an abnormal motion alarm, an abnormal health status alarm, or a wind farm alarm, the server 13 immediately sends the corresponding alarm information to the terminal device through the communication network; the terminal device is responsible for receiving and displaying it, so that the operation and maintenance personnel can obtain accurate fault location and diagnosis conclusions in the first time, regardless of whether they are on-site, in the control center, or in a remote office, reducing the alarm delay from hours to seconds; especially when the monitoring system captures major safety hazards such as the risk of blade breakage, the second-level alarm can ensure that the emergency shutdown command is issued very quickly, effectively avoiding catastrophic equipment damage and safety accidents.

[0063] Among them, the terminal equipment can intuitively display alarm contents such as abnormality type, location, severity level, and related data details such as crack size and over-limit speed value, so that operation and maintenance personnel can obtain detailed alarm information in a timely manner.

[0064] The above description is merely an exemplary embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structural transformation made by utilizing the contents of the present invention's description and drawings under the technical concept of the present invention, or directly / indirectly applied in other related technical fields, is included in the patent protection scope of the present invention.

Claims

1. An intelligent monitoring system for wind turbine blades, characterized in that: Applied to a wind turbine generator set, the wind turbine generator set includes a plurality of wind turbine blades, and the intelligent monitoring system of the wind turbine blades includes a first sensor component, a second sensor component, a server and a reference adjustment module; Each of the wind turbine blades is correspondingly provided with at least one of the first sensor components and at least one of the second sensor components; The first sensing component is used to monitor the motion data of the wind turbine blade; the second sensing component is used to monitor the health status data of the wind turbine blade; The server pre-stores a motion data reference interval and a health data reference interval, and is communicatively connected to the first sensor component and the second sensor component respectively; when the server determines that the motion data does not fall within the motion data reference interval or the health status data does not fall within the health data reference interval, the server is configured to output an alarm message; The benchmark adjustment module is in communication with the server; the benchmark adjustment module is used to generate a corresponding correction value according to the health status data, and use the correction value to adjust the motion data reference interval.

2. The intelligent monitoring system for wind turbine blades according to claim 1, characterized in that: The motion data reference interval includes at least a rotation parameter; when the server determines that the rotation parameter remains zero within a preset time period, the server is configured to output motion abnormality alarm information.

3. The intelligent monitoring system for wind turbine blades according to claim 1, characterized in that: The intelligent monitoring system for wind turbine blades further includes a third sensor component, which is arranged on the fuselage of the wind turbine generator set or the wind turbine blade, and the server is communicatively connected to the third sensor component; The third sensor component is used to monitor wind field data around the wind turbine generator set; The server also pre-stores a reference interval of wind farm data; When the server determines that the wind farm data does not fall within the wind farm data reference interval, the server is further configured to output wind farm alarm information.

4. The intelligent monitoring system for wind turbine blades according to claim 3, characterized in that: The motion data includes at least the blade rotation speed, and the wind field data includes at least the incoming wind speed; The server also pre-stores a mapping relationship between the incoming wind speed and the expected rotation speed range of the blades; When the server determines that the incoming wind speed and the expected rotational speed range of the blade do not satisfy the mapping relationship, the server is further configured to output motion abnormality alarm information.

5. The intelligent monitoring system for wind turbine blades according to claim 4, characterized in that: The server is further configured to store the motion data, the health status data, and the wind farm data to form historical data; The server is further configured to analyze the patterns of the historical data and predict the future operating status of the wind turbine blades.

6. The intelligent monitoring system for wind turbine blades according to claim 1, characterized in that: The health status data includes at least strain and vibration of the wind turbine blade; The second sensing component includes at least a strain monitoring sensor and a vibration monitoring sensor, both of which are communicatively connected to the server; the strain monitoring sensor is used to monitor the strain of the wind turbine blade; and the vibration monitoring sensor is used to monitor the vibration of the wind turbine blade.

7. The intelligent monitoring system for wind turbine blades according to claim 1 or 6, characterized in that: The health status data also includes at least surface cracks and corrosion status of the wind turbine blades; The second sensing component further comprises at least a crack monitoring module and a corrosion monitoring module, and both the crack monitoring module and the corrosion monitoring module are communicatively connected to the server; The crack monitoring module is used to transmit ultrasonic signals to penetrate the wind turbine blades and receive reflected signals of the ultrasonic signals; The corrosion monitoring module is used to detect infrared images of wind turbine blades; The server is further configured to process the reflected signal of the ultrasonic signal to determine the crack condition of the wind turbine blade; the server is further configured to process the infrared image of the wind turbine blade to determine the corrosion condition of the wind turbine blade.

8. The intelligent monitoring system for wind turbine blades according to claim 7, characterized in that: The crack monitoring module and / or the corrosion monitoring module are further used to capture visible light images of the wind turbine blades; The server is also used to process the visible light image of the wind turbine blade based on a deep learning algorithm to identify surface cracks and corrosion conditions of the wind turbine blade.

9. The intelligent monitoring system for wind turbine blades according to any one of claims 1 to 6, characterized in that: The first sensor component, the second sensor component, the server, and the reference adjustment module are all electrically connected to the wind turbine generator set; And / or, the intelligent monitoring system for wind turbine blades further comprises a photovoltaic power generation module, and the first sensor component, the second sensor component, the server, and the reference adjustment module are all electrically connected to the photovoltaic power generation module; And / or, the intelligent monitoring system for wind turbine blades further includes a power supply station, and the first sensor component, the second sensor component, the server, and the reference adjustment module are all electrically connected to the power supply station.

10. The intelligent monitoring system for wind turbine blades according to any one of claims 1 to 6, characterized in that: The intelligent monitoring system for wind turbine blades further includes a terminal device, which is communicatively connected to the server; The server is further configured to send the alarm information to the terminal device after outputting the alarm information; The terminal device is used to receive and display the alarm information.

Images