Offshore wind turbine generator blade state monitoring method and device and storage medium

Abstract

The invention relates to the technical field of offshore wind turbine generators, in particular to an offshore wind turbine generator blade state monitoring method, device and equipment and a computer storage medium. According to the method for monitoring the state of the blade of the offshore wind turbine generator, multiple advanced sensors are reasonably arranged in different coatings of the blade, key data such as corrosion, stress and coating conditions are collected in real time, the health state of the blade is accurately evaluated by means of data preprocessing, feature extraction and an intelligent evaluation algorithm, and potential faults are early warned in advance. The service life of the blade is effectively prolonged, the maintenance cost is reduced, the operation efficiency and reliability of a wind turbine generator are improved, scientific decision support is provided for offshore wind power operation and maintenance, economic benefits of a wind power plant and stable energy supply are guaranteed, and the method has important significance in promoting technical progress and sustainable development of the offshore wind power industry.

Description

Technical Field

[0001] The present invention relates to the technical field of offshore wind turbines, and in particular to a method, device, equipment and computer storage medium for monitoring the status of blades of offshore wind turbines. Background Art

[0002] Traditional offshore wind turbine blade condition monitoring technology has the following problems: the anti-corrosion effect is difficult to monitor in real time, and the corrosion location cannot be accurately predicted; the blade stress state is difficult to accurately assess, which can easily lead to structural fatigue damage; there is a lack of real-time feedback on coating wear, and timely repairs are not possible. Summary of the invention

[0003] Therefore, the technical problem to be solved by the present invention is to overcome the problem of inaccurate status monitoring of blades of offshore wind turbines in the prior art.

[0004] In order to solve the above technical problems, the present invention provides a method for monitoring the blade status of an offshore wind turbine, comprising:

[0005] Using the bottom layer sensor arranged on the bottom layer coating on the surface of the blade, the first corrosion state data of the blade surface, the thickness data of the anti-corrosion bottom layer on the blade surface and the adhesion state data between the bottom layer on the blade surface and the substrate are monitored in real time;

[0006] Using a middle layer sensor disposed on the middle layer coating on the blade surface, real-time monitoring is performed on the first stress state data on the blade surface, the second corrosion state data on the blade surface, the second stress state data on the blade surface, the first temperature data and the first humidity data on the blade surface;

[0007] Using an upper layer sensor disposed on the upper layer coating on the blade surface, the wear state data of the blade surface coating and the second temperature data and the second humidity data of the blade surface are monitored in real time;

[0008] Preprocess and extract features of the monitored data, and evaluate the corrosion status, stress status and coating status of the blade surface;

[0009] Generate early warning signals based on the evaluation results.

[0010] Preferably, the use of a bottom layer sensor disposed on the bottom layer coating on the blade surface to monitor in real time the first corrosion state data on the blade surface, the thickness data of the anti-corrosion bottom layer on the blade surface, and the adhesion state data between the bottom layer on the blade surface and the substrate comprises:

[0011] Using multiple multifunctional corrosion sensors evenly distributed in the bottom coating on the blade surface, according to electrochemical technology, real-time monitoring of the electrochemical characteristic change data in the bottom coating on the blade surface is performed to obtain the first corrosion state data on the blade surface;

[0012] Using multiple anti-corrosion bottom layer thickness sensors installed at key locations under the bottom layer coating on the blade surface, the non-contact measurement technology is used to collect the thickness data of the bottom layer coating on the blade surface in real time to obtain the thickness data of the anti-corrosion bottom layer on the blade surface;

[0013] By using multiple bottom layer adhesion sensors installed at key positions where the bottom layer on the blade surface and the blade substrate are combined, the adhesion state data between the bottom layer on the blade surface and the blade substrate are monitored in real time based on the resistance strain principle or the acoustic principle.

[0014] Preferably, the use of a middle layer sensor disposed on the middle layer coating on the blade surface to monitor in real time the first stress state data on the blade surface, the second corrosion state data on the blade surface, the second stress state data on the blade surface, and the first temperature data and the first humidity data on the blade surface comprises:

[0015] Using a plurality of adaptive stress sensors disposed in a middle layer coating on the surface of the blade and located in a first preset area, the first stress state data on the surface of the blade is monitored in real time according to the resistance strain principle;

[0016] Using a plurality of corrosion sensors disposed in the middle layer coating on the blade surface and located in the second preset area, the corrosion products and corrosion rate on the blade surface are detected in real time according to electrochemical or optical principles to obtain second corrosion state data on the blade surface;

[0017] Using a plurality of stress sensors disposed in the middle layer coating on the blade surface and located in the third preset area, the second stress state data on the blade surface is monitored in real time according to the principle of fiber grating or piezoelectric ceramics;

[0018] A plurality of environmental temperature and humidity sensors arranged in the middle coating layer on the surface of the blade are used to monitor the first temperature data and the first humidity data on the surface of the blade in real time.

[0019] Preferably, the use of an upper layer sensor disposed on the upper layer coating on the blade surface to monitor the wear state data of the blade surface coating and the second temperature data and the second humidity data of the blade surface in real time comprises:

[0020] Using a plurality of optical sensors disposed in the upper coating on the surface of the blade and located in the fourth preset area, the glossiness and color changes of the upper coating on the surface of the blade are monitored in real time according to the principles of optical reflection, scattering and absorption, so as to obtain the wear state data of the coating on the surface of the blade;

[0021] The second temperature data and the second humidity data of the blade surface are monitored in real time by using a plurality of environmental temperature and humidity sensors arranged in the upper coating layer on the blade surface.

[0022] Preferably, the preprocessing and feature extraction of the monitored data includes:

[0023] De-noising, filtering and correction of the monitored data;

[0024] The preprocessed data is subjected to time domain feature extraction, frequency domain feature extraction and wavelet transform feature extraction.

[0025] Preferably, the blade surface corrosion state assessment, blade surface stress state assessment and blade surface coating state assessment include:

[0026] Based on the pre-processed first corrosion state data and the second corrosion state data of the blade surface, and in combination with the extracted characteristic data, according to the corrosion state assessment model, the corrosion state level of the blade is predicted;

[0027] Based on the preprocessed first stress state data and the second stress state data of the blade surface, according to the stress-strain relationship model, combined with the blade structure model and load conditions, the stress distribution is predicted, and the stress concentration area is predicted according to the extracted characteristic data;

[0028] Based on the wear state data of the blade surface coating after pretreatment, the wear area, peeling area and aging degree of the coating are predicted according to the coating state evaluation model.

[0029] Preferably, generating a warning signal according to the evaluation result includes:

[0030] Set warning thresholds for corrosion, stress, and coating status based on blade design parameters, operating experience, and historical data;

[0031] When the status evaluation result of the blade exceeds the corresponding warning threshold, a warning signal is generated.

[0032] The present invention also provides a device for monitoring the blade status of an offshore wind turbine, comprising:

[0033] The blade surface bottom layer monitoring module is used to monitor the first corrosion state data of the blade surface, the thickness data of the anti-corrosion bottom layer on the blade surface, and the adhesion state data between the bottom layer on the blade surface and the substrate in real time by using the bottom layer sensor arranged on the bottom layer coating on the blade surface;

[0034] The blade surface middle layer monitoring module is used to monitor the first stress state data of the blade surface, the second corrosion state data of the blade surface, the second stress state data of the blade surface, the first temperature data and the first humidity data of the blade surface in real time by using the middle layer sensor arranged on the middle layer coating of the blade surface;

[0035] The upper layer monitoring module on the blade surface is used to monitor the wear state data of the blade surface coating and the second temperature data and the second humidity data of the blade surface in real time by using the upper layer sensor arranged on the upper layer coating on the blade surface;

[0036] The blade surface condition assessment module is used to pre-process and extract features from the monitored data, and to assess the blade surface corrosion condition, blade surface stress condition, and blade surface coating condition;

[0037] The early warning module is used to generate early warning signals according to the evaluation results.

[0038] The present invention also provides an offshore wind turbine blade status monitoring device, comprising:

[0039] Memory for storing computer programs;

[0040] The processor is used to implement the above-mentioned steps of the offshore wind turbine blade status monitoring method when executing the computer program.

[0041] The present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned method for monitoring the condition of blades of an offshore wind turbine are implemented.

[0042] The above technical solution of the present invention has the following advantages compared with the prior art:

[0043] The offshore wind turbine blade condition monitoring method described in the present invention collects key data such as corrosion, stress, and coating condition in real time by rationally arranging multiple advanced sensors in different coatings of the blades, and accurately evaluates the health status of the blades with the help of data preprocessing, feature extraction, and intelligent evaluation algorithms, and warns of potential faults in advance. This not only effectively prolongs the service life of the blades, reduces maintenance costs, and improves the operating efficiency and reliability of wind turbines, but also provides scientific decision-making support for offshore wind power operation and maintenance, ensures the economic benefits of wind farms and stable energy supply, and is of great significance to promoting technological progress and sustainable development in the offshore wind power industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to make the content of the present invention more clearly understood, the present invention is further described in detail below according to specific embodiments of the present invention in conjunction with the accompanying drawings, wherein:

[0045] Figure 1 It is a flow chart of an implementation method of an offshore wind turbine blade status monitoring method provided by the present invention;

[0046] Figure 2 is a schematic diagram of the sensor location;

[0047] Figure 3 It is a schematic diagram of data collection and preprocessing;

[0048] Figure numerals: 1-100 - blade body; 1-101 - leading edge or trailing edge of the blade; 1-102 - root or connection part of the blade; 1-103 - specific area of ​​the blade; 1-104 - tip or tip part of the blade. DETAILED DESCRIPTION

[0049] The core of the present invention is to provide a method, device, equipment and computer storage medium for monitoring the status of offshore wind turbine blades, which effectively improves the accuracy of offshore wind turbine blade status monitoring.

[0050] In order to enable those skilled in the art to better understand the scheme of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific implementation methods. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than 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 work are within the scope of protection of the present invention.

[0051] Please refer to Figure 1 , Figure 1 This is a flow chart of an implementation method of an offshore wind turbine blade status monitoring method provided by the present invention; the specific operation steps are as follows:

[0052] S101: using a bottom layer sensor disposed on the bottom layer coating on the surface of the blade, real-time monitoring of first corrosion state data on the blade surface, thickness data of the anti-corrosion bottom layer on the blade surface, and adhesion state data between the bottom layer on the blade surface and the substrate;

[0053] S102: using a middle layer sensor disposed on the middle layer coating on the blade surface, real-time monitoring of first stress state data on the blade surface, second corrosion state data on the blade surface, second stress state data on the blade surface, first temperature data and first humidity data on the blade surface;

[0054] S103: using an upper layer sensor disposed on the upper layer coating on the blade surface to monitor in real time the wear state data of the blade surface coating and the second temperature data and the second humidity data of the blade surface;

[0055] S104: preprocessing and feature extraction of the monitored data, and evaluating the corrosion state of the blade surface, the stress state of the blade surface, and the coating state of the blade surface;

[0056] S105: Generate a warning signal based on the evaluation results.

[0057] Based on the above embodiments, this embodiment describes step S101 in detail:

[0058] Generally, the bottom-level sensors include the following two types of sensors:

[0059] Anti-corrosion base thickness sensor: Installed under the base coating, monitors the thickness of the anti-corrosion base in real time. Challenge: The base in the offshore environment is susceptible to corrosion, which may affect the performance of the sensor. Solution: Select sensors made of corrosion-resistant materials and conduct regular inspections and maintenance.

[0060] Substrate Adhesion Sensor: Used to detect the adhesion between the substrate and the blade substrate. Challenge: The adhesion between the substrate and the substrate is susceptible to seawater corrosion and mechanical stress. Solution: Use high-adhesion sensors and ensure that the anti-corrosion coating construction process meets standards to ensure good adhesion performance.

[0061] Using multiple multifunctional corrosion sensors evenly distributed in the bottom coating on the blade surface, based on electrochemical technology, real-time monitoring of the electrochemical characteristics of the bottom coating on the blade surface, such as changes in conductivity or electrode potential, to obtain the first corrosion state data of the blade surface:

[0062] The working principle of multifunctional corrosion sensors usually involves electrochemical technology. A multifunctional corrosion sensor is embedded in the underlying coating on the surface of the blade, which forms an electrochemical cell between the sensor, the blade surface and the coating. When corrosion begins to occur, the corrosion products in the coating change the electrochemical properties, such as conductivity or electrode potential, resulting in changes in current. Data transmission process: Multifunctional sensors are usually equipped with data transmission modules, which can transmit the collected data to a data acquisition unit or a cloud server via wired or wireless means. In the case of corrosion protection of offshore wind turbine blades, since the blades are located in an offshore environment far away from land, wireless transmission technology such as wireless sensor networks (WSN) or Internet of Things (IoT) technology is usually selected.

[0063] The data transmission process is as follows:

[0064] Data collection: The multifunctional sensor monitors the corrosion degree of the blade surface in real time and collects relevant data. Data collection can be completed through the data processing unit inside the sensor.

[0065] Data Coding: The collected data may be analog or digital signals and need to be encoded and formatted for transmission and storage.

[0066] Wireless transmission: The sensor transmits the encoded data to the data acquisition unit or central controller through the built-in wireless module, such as Bluetooth, Wi-Fi, or other wireless communication technologies.

[0067] Data reception and processing: The data acquisition unit or central controller receives data from multiple sensors and integrates and processes them. Data processing may involve data decoding, correction, and outlier detection.

[0068] Data storage and analysis: The processed data is stored in a database or cloud server for subsequent data analysis and monitoring. Data analysis may use machine learning algorithms or other intelligent algorithms to predict the location and extent of corrosion and implement intelligent early warning.

[0069] Through the above working principles and data transmission process, the multifunctional sensor can provide real-time monitoring and intelligent prediction functions for the corrosion protection of offshore wind turbine blades, helping to ensure the safe operation of the blades and extend the life of the blades.

[0070] Using multiple anti-corrosion bottom layer thickness sensors installed at key locations under the bottom layer coating on the blade surface (such as the leading edge, trailing edge and other corrosion-prone areas of the blade), based on non-contact measurement technology (such as the principle of ultrasonic thickness measurement, regularly sending ultrasonic signals and receiving reflected signals, and calculating the coating thickness based on the propagation time of the signal), the bottom layer coating thickness data of the blade surface is collected in real time to obtain the anti-corrosion bottom layer thickness data on the blade surface:

[0071] ·Using multiple bottom layer adhesion sensors installed at the key position where the bottom layer on the blade surface is combined with the blade substrate, according to the resistance strain principle or acoustic principle, when the adhesion between the bottom layer and the substrate changes, the resistance value or sound wave propagation characteristics sensed by the sensor will change accordingly, thereby real-time monitoring of the adhesion state data between the bottom layer on the blade surface and the blade substrate.

[0072] Based on the above embodiments, this embodiment describes step S102 in detail:

[0073] Generally, the following three types of sensors can be added to the middle layer, and the adaptive sensor is one of them, which can be used as a combination in the present invention.

[0074] Corrosion sensor: monitors the degree of corrosion on the blade surface. Challenge: Seawater is severely corrosive and may cause sensor failure. Solution: Use corrosion-resistant materials to manufacture sensors and take protective measures, such as coating with special anti-corrosion layers.

[0075] Stress sensor: monitors the stress on the blade surface. Challenge: affected by wind, waves and temperature changes, blade stress is complex and changeable. Solution: select high-performance stress sensors suitable for complex environments and place them on the blades to minimize external influences.

[0076] Environmental temperature and humidity sensor: Continuously monitor the temperature and humidity of the blade surface. Challenge: The temperature and humidity of the offshore environment fluctuate greatly. Solution: Choose a sensor that can adapt to a wide range of temperature and humidity, and add a protective cover to reduce external influences.

[0077] ·Use multiple adaptive stress sensors arranged in the middle coating layer on the blade surface, located in the first preset area (along the main beam of the blade and the area with greater stress), made of special materials according to the resistance strain principle. When the blade surface is subjected to stress, the stress sensor senses the effect of the stress, causing the resistance value of the material to change accordingly, and monitors the first stress state data of the blade surface in real time;

[0078] The adaptive stress sensor is a sensor that can dynamically sense the stress state of the blade surface. It can monitor the stress condition of the blade surface in real time and perform stress assessment and early warning through intelligent algorithms. In the application of offshore wind turbine blade corrosion protection, the adaptive stress sensor helps to accurately assess the stress condition of the blade and prevent structural fatigue and damage.

[0079] Working principle: The working principle of the adaptive stress sensor is based on the resistance strain principle. The adaptive stress sensor is embedded in the middle coating on the surface of the blade. The sensor is made of a special material whose resistance value changes when it is subjected to external stress. When the blade surface is subjected to stress, the stress sensor senses the effect of the stress, causing the resistance value of the material to change accordingly.

[0080] Data transmission process: Adaptive stress sensors are usually equipped with data transmission modules, which can transmit the collected data to the data acquisition unit or cloud server via wired or wireless means. In the case of offshore wind turbine blade corrosion protection, since the blades are located in an offshore environment far away from land, wireless transmission technology such as wireless sensor network (WSN) or Internet of Things (IoT) technology is usually selected.

[0081] The data transmission process is as follows:

[0082] Data collection: The adaptive stress sensor monitors the stress condition of the blade surface in real time and collects relevant data. Data collection can be completed through the data processing unit inside the sensor.

[0083] Data Coding: The collected data may be analog or digital signals and need to be encoded and formatted for transmission and storage.

[0084] Wireless transmission: The sensor transmits the encoded data to the data acquisition unit or central controller through the built-in wireless module, such as Bluetooth, Wi-Fi, or other wireless communication technologies.

[0085] Data reception and processing: The data acquisition unit or central controller receives data from multiple sensors and integrates and processes them. Data processing may involve data decoding, correction, and outlier detection.

[0086] Data storage and analysis: The processed data is stored in a database or cloud server for subsequent data analysis and monitoring. Data analysis may use machine learning algorithms or other intelligent algorithms for stress assessment and prediction, as well as intelligent early warning.

[0087] Through the above working principles and data transmission process, the adaptive stress sensor can provide real-time monitoring and intelligent early warning functions for the corrosion protection of offshore wind turbine blades, helping to ensure the structural integrity of the blades and avoid stress accumulation and damage.

[0088] Utilizing multiple corrosion sensors disposed in the middle coating layer on the blade surface and located in a second preset area (appropriate position in the middle coating layer), based on electrochemical or optical principles, the corrosion products and corrosion rate on the blade surface are detected in real time to obtain the second corrosion state data on the blade surface;

[0089] Using multiple stress sensors arranged in the middle coating layer on the blade surface and located in the third preset area (such as the blade root, near the pitch bearing, etc.), based on the fiber grating or piezoelectric ceramic principle, it is possible to accurately sense the stress changes caused by wind load, gravity, inertial force, etc. on the blade during operation, and monitor the second stress state data on the blade surface in real time;

[0090] Multiple environmental temperature and humidity sensors are used to monitor the first temperature data and the first humidity data of the blade surface in real time at multiple positions (such as the leading edge, trailing edge, and tip of the blade) in the middle layer coating on the blade surface. The sensors use semiconductor temperature and humidity sensing elements and can sense the temperature and humidity changes on the blade surface in real time.

[0091] Based on the above embodiments, this embodiment describes step S103 in detail:

[0092] Generally, optical sensors can be considered as upper sensors, and ambient temperature and humidity sensors can also be added:

[0093] Optical sensors: monitor the gloss and color changes of coatings and assess the degree of wear on the coating surface. Challenge: Optical sensors are easily damaged by seawater erosion and ultraviolet radiation. Solution: Use highly corrosion-resistant materials and add a housing to protect the sensor.

[0094] Environmental temperature and humidity sensor: Continuously monitor the temperature and humidity of the blade surface and evaluate the weather resistance of the coating. Challenge: Extreme conditions in the offshore environment may affect the sensor. Solution: Select high-performance and high-durability sensors and add a housing to prevent erosion by seawater and salt spray.

[0095] Using multiple high-precision optical sensors arranged in the upper coating on the surface of the blade, located in the fourth preset area (such as the easily worn part of the blade surface coating, the area susceptible to ultraviolet radiation, etc.), based on the principles of optical reflection, scattering and absorption, the glossiness and color changes of the upper coating on the surface of the blade are monitored in real time to obtain the wear status data of the blade surface coating;

[0096] High-precision optical sensors are sensors with highly accurate measurement capabilities. In the application of offshore wind turbine blade corrosion protection, high-precision optical sensors can monitor the gloss and color changes of blade coatings in real time by being embedded in the upper coating. With the help of image recognition technology, the sensor can perform intelligent diagnosis and repair suggestions to ensure the good condition of the coating.

[0097] Working principle: The working principle of high-precision optical sensors usually involves optical reflection, scattering and absorption. A high-precision optical sensor is embedded in the upper coating of the blade, which emits a beam of light or receives external light from the surface of the blade. Through changes in light reflection, scattering and absorption, the sensor can sense the glossiness and color changes of the coating surface.

[0098] Data transmission process: High-precision optical sensors are usually equipped with data transmission modules, which can transmit the collected data to the data acquisition unit or cloud server by wired or wireless means. In the case of offshore wind turbine blade corrosion protection, since the blades are located in an offshore environment far away from land, wireless transmission technology such as wireless sensor network (WSN) or Internet of Things (IoT) technology is usually selected.

[0099] The data transmission process is as follows:

[0100] Data collection: High-precision optical sensors monitor the glossiness and color changes of the blade coating surface in real time and collect relevant data. Data collection can be completed through the data processing unit inside the sensor.

[0101] Data Coding: The collected data may be analog or digital signals and need to be encoded and formatted for transmission and storage.

[0102] Wireless transmission: The sensor transmits the encoded data to the data acquisition unit or central controller through the built-in wireless module, such as Bluetooth, Wi-Fi, or other wireless communication technologies.

[0103] Data reception and processing: The data acquisition unit or central controller receives data from multiple sensors and integrates and processes them. Data processing may involve data decoding, correction, and outlier detection.

[0104] Data storage and analysis: The processed data is stored in a database or cloud server for subsequent data analysis and monitoring. Data analysis may use image recognition technology or other intelligent algorithms to diagnose coating conditions and provide repair suggestions.

[0105] Through the above working principles and data transmission process, high-precision optical sensors can provide real-time monitoring and intelligent diagnosis functions for offshore wind turbine blade corrosion protection, helping to ensure the quality and performance of the coating and protect the blade surface from corrosion and damage.

[0106] Utilize multiple environmental temperature and humidity sensors disposed in the upper coating layer on the blade surface to monitor the second temperature data and the second humidity data of the blade surface in real time.

[0107] like Figure 2 As shown, Figure 2 Schematic diagram of sensor location.

[0108] Based on the above embodiments, this embodiment describes step S104 in detail:

[0109] De-noising, filtering and correction of the monitored data:

[0110] De-noising: De-noising is performed on the collected raw data to remove random noise and interference signals in the data. Digital filtering techniques such as low-pass filtering, high-pass filtering, and band-pass filtering algorithms can be used to select appropriate filter parameters according to the frequency characteristics of the sensor data to filter out high-frequency noise and low-frequency interference. For example, for stress data collected by an adaptive stress sensor, a low-pass filter is used to filter out high-frequency noise caused by blade vibration and retain the low-frequency effective signal of stress.

[0111] Filtering: Further filter the data to smooth the data curve and improve the stability of the data. You can use algorithms such as moving average filtering, median filtering, Kalman filtering, and adaptive filtering algorithms. For example, for the data collected by the ambient temperature and humidity sensor, use the moving average filtering algorithm to average the data over a period of time, eliminate short-term fluctuations in the data, and obtain a stable temperature and humidity change trend.

[0112] Adaptive filtering algorithm is a type of filter that can automatically adjust the filter parameters according to the characteristics of the signal to achieve better filtering effect. Adaptive filtering algorithm is widely used in the field of signal processing, especially for removing noise from signals, filtering interference from signals, or extracting specific frequency components from signals.

[0113] Among them, the most common adaptive filtering algorithm is the infinite impulse response (IIR) filtering algorithm. The IIR filter is a recursive filter with good frequency response characteristics and high computational efficiency.

[0114] The advantage of IIR filter is that it can achieve a narrower cutoff frequency bandwidth at the same filter order compared to Finite Impulse Response (FIR) filter. At the same time, due to the recursive structure, IIR filter has high computational efficiency and is suitable for real-time signal processing and embedded system applications.

[0115] It should be noted that the adaptive filtering algorithm needs to be designed and optimized according to the specific application scenario and signal characteristics. Designing a suitable IIR filter requires considering factors such as cutoff frequency, filter order, filter type (such as low-pass, high-pass, band-pass, etc.), and filter stability and error. In addition, attention should also be paid to the filter order and computational complexity to ensure that performance and resource requirements are met in practical applications.

[0116] To achieve the above objectives, the adaptive filter of the present invention includes forward coefficients and feedback coefficients. By adaptively adjusting these coefficients, the frequency response and filtering characteristics of the filter are optimized, making it more suitable for the complex and changeable operation scenarios of offshore wind farms. The adaptive filtering algorithm of the present invention mainly includes the following steps:

[0117] Step 1: Collect the original signal as the input of the filter.

[0118] Step 2: Perform wavelet transform on the input signal to obtain wavelet coefficients.

[0119] Step 3: Select the appropriate filter type (such as low-pass, high-pass, band-pass, etc.) based on signal characteristics and filtering requirements.

[0120] Step 4: Initialize the forward and feedback coefficients of the filter.

[0121] Step 5: Perform time-frequency analysis on the wavelet coefficients to extract the time-frequency characteristics of the signal.

[0122] Step 6: Compare the difference between the extracted features and the expected features through error calculation.

[0123] Step 7: Adaptively adjust the forward coefficient and feedback coefficient of the filter according to the error size.

[0124] Step 8: Repeat steps 5 to 7 until the output characteristics of the filter meet the preset performance requirements.

[0125] The adaptive filtering algorithm of the present invention introduces methods such as wavelet transform and time-frequency analysis on the basis of traditional filtering methods, which can more accurately capture the time-frequency characteristics of the signal. In addition, by adaptively adjusting the coefficients of the filter, better signal feature extraction and analysis effects can be achieved, and the performance stability and accuracy of the filter are improved.

[0126] Correction processing: Correction processing is performed on sensor data to eliminate the sensor's system error and zero drift. According to the sensor's calibration parameters and calibration curve, linear or nonlinear correction is performed on the collected data. For example, for a multifunctional corrosion sensor, according to the calibration relationship between corrosion current and corrosion rate obtained in the calibration laboratory, the actual monitored corrosion current data is corrected to obtain accurate corrosion rate data.

[0127] Perform time domain feature extraction, frequency domain feature extraction and wavelet transform feature extraction on the preprocessed data:

[0128] Time domain feature extraction: Extract time domain features from preprocessed data, such as mean, variance, root mean square value, peak value, kurtosis, etc. These features can reflect the statistical characteristics and change trends of data in the time dimension. For example, for the stress data of the adaptive stress sensor, the average stress value over a period of time is calculated to reflect the average stress of the blade during the period of time; the variance of the stress data is calculated to reflect the degree of stress fluctuation. The larger the variance, the more unstable the force on the blade.

[0129] Frequency domain feature extraction: Perform frequency domain analysis on the data and extract frequency domain features, such as spectrum peak, spectrum center, bandwidth, power spectrum density, etc. Through methods such as Fourier transform or wavelet transform, the time domain signal is converted into a frequency domain signal, and the energy distribution of the data on different frequency components is analyzed. For example, for the stress data caused by blade vibration, the spectrum of the stress signal is obtained through Fourier transform, and the natural frequency and forced vibration frequency of the blade are identified. The frequency corresponding to the spectrum peak is the main vibration frequency of the blade. The power spectrum density can reflect the energy of different frequency components, so as to determine whether there is an abnormal vibration mode of the blade.

[0130] Wavelet transform feature extraction: Use wavelet transform to perform multi-scale analysis on data and extract wavelet domain features. Wavelet transform can analyze signals in both time domain and frequency domain at the same time and has good time-frequency localization characteristics. Select appropriate wavelet basis functions, perform wavelet decomposition on sensor data, and obtain wavelet coefficients at different scales. For example, for coating gloss and color change data collected by high-precision optical sensors, Daubechies wavelet or Haar wavelet is used for wavelet transform to extract detail features and trend features of data at different scales. Detail features can reflect microscopic changes on the coating surface, such as fine wear marks, corrosion spots, etc.; trend features can reflect the overall change trend of the coating, such as the gradual decrease in gloss and the gradual darkening of color.

[0131] like Figure 3 , Figure 3 Schematic diagram of data collection and preprocessing.

[0132] Based on the pre-processed first corrosion state data and the second corrosion state data of the blade surface, combined with the extracted feature data, the corrosion state level of the blade is predicted according to the corrosion state assessment model:

[0133] According to the data collected by the multifunctional corrosion sensor and the corrosion sensor, combined with the time domain, frequency domain and wavelet domain features obtained by feature extraction, the corrosion state of the blade surface is evaluated. A corrosion state evaluation model can be established, such as a classification model based on a support vector machine (SVM) or an artificial neural network (ANN). The feature vector is input into the model, and the model outputs the corrosion level of the blade, such as slight corrosion, moderate corrosion, severe corrosion, etc. For example, when the corrosion current density monitored by the corrosion sensor exceeds a certain threshold, and the detailed features extracted by the wavelet transform show obvious corrosion spots on the coating surface, the model determines that the blade is in a moderate corrosion state and anti-corrosion measures need to be taken in time.

[0134] Based on the pre-processed first stress state data and second stress state data of the blade surface, according to the stress-strain relationship model, combined with the blade structure model and load conditions, the stress distribution is predicted, and the stress concentration area is predicted based on the extracted characteristic data:

[0135] The stress state of the blade surface is evaluated using the data collected by the adaptive stress sensor and the stress sensor. The stress-strain relationship model can be used to convert the strain value into a stress value through the calibration coefficient according to the strain value measured by the sensor, and then analyze the stress distribution in combination with the structural model and load conditions of the blade. At the same time, the vibration mode of the blade is analyzed using the frequency domain characteristics to determine whether there is a stress concentration area. For example, when the adaptive stress sensor monitors that the stress value at the root of the blade exceeds a certain proportion of the design allowable stress, and the frequency domain analysis finds that the blade has an abnormal vibration frequency in this area, it is judged that there is stress concentration at the root of the blade, which may lead to structural fatigue damage, and structural reinforcement or adjustment of operating parameters is required.

[0136] Assuming that the strain value measured by the sensor is ε, the strain value is converted to stress σ through the calibration coefficient k. The formula of a simple linear relationship can be used:

[0137] σ=k*ε

[0138] Where k is the calibration coefficient, which is obtained according to the sensor type and calibration experiment. (On this basis, a dual-channel calibration coefficient k1 and k2 can be constructed, and a root mean square error standard coefficient k = sqrt() can be constructed)

[0139] It should be pointed out that this is only a simple example of a linear relationship. The actual situation may be more complicated and a more accurate stress calculation formula needs to be fitted based on the characteristics of the sensor and calibration data.

[0140] Because it is a stress calculation of multiple sensors, the root mean square calculation formula can be used. We need to consider the impact of multiple stress values ​​(calculated by multiple sensors, such as 3 or 4). The root mean square is an indicator to measure the degree of dispersion in the data set and can be used to describe the average size of multiple stress values.

[0141] Root mean square stress can more comprehensively reflect the differences and discreteness between multiple stress values. Therefore, in practical engineering and physical applications, root mean square stress is often used to evaluate the stability and safety of the system. The stress calculation value obtained in this way will be more accurate.

[0142] Based on the pre-treated blade surface coating wear state data, the coating wear area, peeling area and aging degree are predicted according to the coating state evaluation model:

[0143] According to the data collected by the high-precision optical sensor, the wear degree and weather resistance of the blade coating are evaluated. A coating status evaluation model can be established, such as a model based on image recognition technology. The coating image data collected by the optical sensor is input into the model. The model analyzes the texture, color, glossiness and other characteristics of the image to identify the wear area, peeling area, aging degree, etc. of the coating. For example, when the optical sensor monitors that the glossiness of the coating has dropped to a certain level, and the image recognition model identifies large areas of peeling marks on the surface of the coating, it is judged that the coating has been severely damaged and needs to be repaired or repainted.

[0144] Multi-sensor fusion algorithm is a method that comprehensively utilizes the data of multiple sensors to obtain more accurate and comprehensive information. In this invention, we will combine the wavelet transform and adaptive filter methods to perform multi-sensor fusion to achieve more accurate extraction and analysis of signal features.

[0145] The algorithm process is as follows:

[0146] Data collection: First, multiple sensors are used to collect raw signal data, each of which may provide different information. For example, for offshore wind turbine blade corrosion protection, multiple sensors can be used to obtain data such as temperature, humidity, and vibration on the blade surface.

[0147] Wavelet transform: Perform wavelet transform on the raw data collected by each sensor to convert the signal from the time domain to the wavelet domain. By selecting an appropriate wavelet function, the time-frequency characteristics of the signal can be extracted and the wavelet coefficients of each sensor can be obtained.

[0148] Adaptive filter: For each sensor’s wavelet coefficient, an adaptive filter is used for signal processing. The adaptive filter can automatically adjust the filter parameters according to the signal characteristics to achieve better filtering effects. The wavelet coefficients of each sensor are adaptively filtered to obtain the filtered wavelet coefficients.

[0149] Feature fusion: The filtered wavelet coefficients are fused from multiple sensors. Simple weighted summation, average value, etc. can be used, or more complex fusion algorithms such as Kalman filtering can be used. The fused wavelet coefficients represent the characteristics of the integrated information from multiple sensors.

[0150] Inverse wavelet transform: Perform inverse wavelet transform on the fused wavelet coefficients to restore the signal from the wavelet domain to the time domain. The signal obtained by inverse wavelet transform represents the characteristic analysis result of integrated multi-sensor.

[0151] Feature analysis: Perform feature analysis on the signal obtained by inverse wavelet transform. Feature indicators of interest can be extracted, such as corrosion degree, blade health status, etc.

[0152] Through the above multi-sensor fusion algorithm, the status of offshore wind turbine blades can be monitored and evaluated more comprehensively and accurately. At the same time, by using methods such as wavelet transform and adaptive filter, the information of sensors can be fully utilized to extract important features of signals, thereby achieving more effective control and maintenance of blade corrosion protection.

[0153] Based on the above embodiments, this embodiment describes step S105 in detail:

[0154] According to the blade design parameters, operating experience and historical data, set the warning thresholds for corrosion, stress and coating status:

[0155] According to the blade design parameters, operating experience and historical data, the warning thresholds of corrosion, stress and coating status are set. The warning thresholds can be divided into the first-level warning threshold and the second-level warning threshold. When the monitoring data or evaluation results exceed the first-level warning threshold, a warning signal is issued to remind the operation and maintenance personnel to pay attention to the blade status; when it exceeds the second-level warning threshold, an emergency warning signal is issued to require the operation and maintenance personnel to take immediate measures.

[0156] When the blade status assessment result exceeds the corresponding warning threshold, a warning signal is generated:

[0157] When the blade status assessment result exceeds the warning threshold, a warning signal is generated. The warning signal can include text messages, sound alarms, color changes and other forms, through the remote monitoring platform or mobile phone.

[0158] The present invention relates to the field of offshore wind turbine blade anti-corrosion, and provides a solution for applying intelligent sensor technology to blade anti-corrosion. This technical solution embeds multifunctional corrosion sensors, adaptive stress sensors, and high-precision optical sensors in the bottom, middle, and upper coatings, and combines them with a cloud system to achieve real-time monitoring and early warning of blade corrosion, stress status, and coating conditions, greatly improving the anti-corrosion performance and maintenance efficiency of offshore wind turbine blades.

[0159] The embodiment of the present invention further provides a device for monitoring the blade status of an offshore wind turbine; the specific device may include:

[0160] The blade surface bottom layer monitoring module is used to monitor the first corrosion state data of the blade surface, the thickness data of the anti-corrosion bottom layer on the blade surface, and the adhesion state data between the bottom layer on the blade surface and the substrate in real time by using the bottom layer sensor arranged on the bottom layer coating on the blade surface;

[0161] The blade surface middle layer monitoring module is used to monitor the first stress state data of the blade surface, the second corrosion state data of the blade surface, the second stress state data of the blade surface, the first temperature data and the first humidity data of the blade surface in real time by using the middle layer sensor arranged on the middle layer coating of the blade surface;

[0162] The upper layer monitoring module on the blade surface is used to monitor the wear state data of the blade surface coating and the second temperature data and the second humidity data of the blade surface in real time by using the upper layer sensor arranged on the upper layer coating on the blade surface;

[0163] The blade surface condition assessment module is used to pre-process and extract features from the monitored data, and to assess the blade surface corrosion condition, blade surface stress condition, and blade surface coating condition;

[0164] The early warning module is used to generate early warning signals according to the evaluation results.

[0165] The offshore wind turbine blade status monitoring device of this embodiment is used to implement the aforementioned offshore wind turbine blade status monitoring method. Therefore, the specific implementation method of the offshore wind turbine blade status monitoring device can be seen in the embodiment part of the offshore wind turbine blade status monitoring method above. For example, the blade surface bottom layer monitoring module, the blade surface middle layer monitoring module, the blade surface upper layer monitoring module, the blade surface status evaluation module, and the early warning module are respectively used to implement steps S101, S102, S103, S104 and S105 in the above-mentioned offshore wind turbine blade status monitoring method. Therefore, its specific implementation method can refer to the description of the corresponding each part of the embodiment, which will not be repeated here.

[0166] A specific embodiment of the present invention further provides an offshore wind turbine blade status monitoring device, comprising: a memory for storing a computer program; and a processor for implementing the steps of the above-mentioned offshore wind turbine blade status monitoring method when executing the computer program.

[0167] A specific embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned method for monitoring the condition of blades of an offshore wind turbine are implemented.

[0168] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0169] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0170] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0171] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0172] Obviously, the above embodiments are merely examples for the purpose of clear explanation and are not intended to limit the implementation methods. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived therefrom are still within the scope of protection of the present invention.

Claims

1. A method for monitoring the blade status of an offshore wind turbine, characterized in that: include: Using the bottom layer sensor arranged on the bottom layer coating on the blade surface, the first corrosion state data on the blade surface, the thickness data of the anti-corrosion bottom layer on the blade surface and the adhesion state data between the bottom layer on the blade surface and the substrate are monitored in real time; Using a middle layer sensor disposed on the middle layer coating on the blade surface, real-time monitoring is performed on the first stress state data on the blade surface, the second corrosion state data on the blade surface, the second stress state data on the blade surface, the first temperature data and the first humidity data on the blade surface; Using an upper layer sensor disposed on the upper layer coating on the blade surface, the wear state data of the blade surface coating and the second temperature data and the second humidity data of the blade surface are monitored in real time; Preprocess and extract features of the monitored data, and evaluate the corrosion status, stress status and coating status of the blade surface; Generate early warning signals based on the evaluation results.

2. The method for monitoring the blade status of an offshore wind turbine according to claim 1, characterized in that: The method of using a bottom layer sensor disposed on the bottom layer coating on the blade surface to monitor the first corrosion state data on the blade surface, the thickness data of the anti-corrosion bottom layer on the blade surface, and the adhesion state data between the bottom layer on the blade surface and the substrate in real time includes: Using multiple multifunctional corrosion sensors evenly distributed in the bottom coating on the blade surface, according to electrochemical technology, real-time monitoring of the electrochemical characteristic change data in the bottom coating on the blade surface is performed to obtain the first corrosion state data of the blade surface; Using multiple anti-corrosion bottom layer thickness sensors installed at key locations under the bottom layer coating on the blade surface, the thickness data of the bottom layer coating on the blade surface is collected in real time based on non-contact measurement technology to obtain the thickness data of the anti-corrosion bottom layer on the blade surface; By using multiple bottom layer adhesion sensors installed at key positions where the bottom layer on the blade surface and the blade substrate are combined, the adhesion state data between the bottom layer on the blade surface and the blade substrate are monitored in real time based on the resistance strain principle or the acoustic principle.

3. The method for monitoring the blade status of an offshore wind turbine according to claim 1, characterized in that: The method of using a middle layer sensor disposed on the middle layer coating on the blade surface to monitor the first stress state data on the blade surface, the second corrosion state data on the blade surface, the second stress state data on the blade surface, the first temperature data and the first humidity data on the blade surface in real time includes: Using a plurality of adaptive stress sensors disposed in a middle layer coating on the surface of the blade and located in a first preset area, the first stress state data on the surface of the blade is monitored in real time according to the resistance strain principle; Using a plurality of corrosion sensors disposed in the middle layer coating on the blade surface and located in the second preset area, the corrosion products and corrosion rate on the blade surface are detected in real time according to electrochemical or optical principles to obtain second corrosion state data on the blade surface; Using a plurality of stress sensors disposed in the middle layer coating on the blade surface and located in a third preset area, the second stress state data on the blade surface is monitored in real time according to the principle of fiber grating or piezoelectric ceramics; A plurality of environmental temperature and humidity sensors arranged in the middle coating layer on the surface of the blade are used to monitor the first temperature data and the first humidity data on the surface of the blade in real time.

4. The method for monitoring the blade status of an offshore wind turbine according to claim 1, characterized in that: The method of using the upper layer sensor disposed on the upper layer coating on the blade surface to monitor the wear state data of the blade surface coating and the second temperature data and the second humidity data of the blade surface in real time comprises: Using a plurality of optical sensors disposed in the upper coating on the surface of the blade and located in the fourth preset area, the glossiness and color changes of the upper coating on the surface of the blade are monitored in real time according to the principles of optical reflection, scattering and absorption, so as to obtain the wear state data of the coating on the surface of the blade; The second temperature data and the second humidity data of the blade surface are monitored in real time by using a plurality of environmental temperature and humidity sensors arranged in the upper coating layer on the blade surface.

5. The method for monitoring the status of offshore wind turbine blades according to claim 1, characterized in that: The preprocessing and feature extraction of the monitored data includes: De-noising, filtering and correction of the monitored data; The preprocessed data is subjected to time domain feature extraction, frequency domain feature extraction and wavelet transform feature extraction.

6. The method for monitoring the status of offshore wind turbine blades according to claim 1, characterized in that: The blade surface corrosion status assessment, blade surface stress status assessment and blade surface coating status assessment include: Based on the pre-processed first corrosion state data and the second corrosion state data of the blade surface, and in combination with the extracted characteristic data, according to the corrosion state assessment model, the corrosion state level of the blade is predicted; Based on the preprocessed first stress state data and the second stress state data of the blade surface, according to the stress-strain relationship model, combined with the blade structure model and load conditions, the stress distribution is predicted, and the stress concentration area is predicted according to the extracted characteristic data; Based on the wear state data of the blade surface coating after pretreatment, the wear area, peeling area and aging degree of the coating are predicted according to the coating state evaluation model.

7. The method for monitoring the status of offshore wind turbine blades according to claim 1, characterized in that: Generating an early warning signal according to the evaluation result comprises: Set warning thresholds for corrosion, stress, and coating status based on blade design parameters, operating experience, and historical data; When the status evaluation result of the blade exceeds the corresponding warning threshold, a warning signal is generated.

8. An offshore wind turbine blade status monitoring device, characterized in that: include: The blade surface bottom layer monitoring module is used to monitor the first corrosion state data of the blade surface, the thickness data of the anti-corrosion bottom layer on the blade surface, and the adhesion state data between the bottom layer on the blade surface and the substrate in real time by using the bottom layer sensor arranged on the bottom layer coating on the blade surface; The blade surface middle layer monitoring module is used to monitor the first stress state data of the blade surface, the second corrosion state data of the blade surface, the second stress state data of the blade surface, the first temperature data and the first humidity data of the blade surface in real time by using the middle layer sensor arranged on the middle layer coating of the blade surface; The upper layer monitoring module on the blade surface is used to monitor the wear state data of the blade surface coating and the second temperature data and the second humidity data of the blade surface in real time by using the upper layer sensor arranged on the upper layer coating on the blade surface; The blade surface condition assessment module is used to pre-process and extract features from the monitored data, and to assess the blade surface corrosion condition, blade surface stress condition, and blade surface coating condition; The early warning module is used to generate early warning signals according to the evaluation results.

9. An offshore wind turbine blade status monitoring device, characterized in that: include: Memory for storing computer programs; A processor is used to implement the steps of a method for monitoring the condition of an offshore wind turbine blade as claimed in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for monitoring the condition of an offshore wind turbine blade as claimed in any one of claims 1 to 7 are implemented.

Images