Intelligent monitoring method and system for corrosion resistance test of wind power blade

Abstract

The invention relates to the technical field of wind power blades, in particular to an intelligent monitoring method and system for a corrosion resistance test of a wind power blade, and the method comprises the steps: coating the surface of the blade with an intelligent coating containing tiny sensing particles; the method comprises the following steps: dividing a wind power blade into a plurality of monitoring areas, and arranging sensing nodes in each monitoring area; based on a sliding window and threshold detection, performing multi-level screening on the resistance and temperature curve of each monitoring area, and marking the monitoring area with abnormal curve fluctuation; whether corrosion traces exist or not is judged through spectral analysis, and whether the marked monitoring area has a real corrosion risk or not is determined; and according to multiple screening and optical monitoring results, a corrosion state map is generated, and dynamic updating is performed based on periodic monitoring. According to the invention, the problems of response lag, high labor cost and lack of real-time performance of a traditional corrosion monitoring method are effectively solved, the real-time performance and accuracy of monitoring are improved, the labor cost is reduced, and the safe operation of the wind turbine generator is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of wind turbine blades, and in particular to an intelligent monitoring method and system for a wind turbine blade corrosion resistance test. Background Art

[0002] Wind turbine blades face harsh environmental conditions during operation, such as strong winds, high humidity and salt spray. These factors can easily lead to corrosion and aging of blade materials. Corrosion will not only significantly reduce the mechanical properties and service life of wind turbine blades, but may also cause failures, affecting the overall operating efficiency of wind turbines and resulting in additional maintenance costs and downtime.

[0003] Traditional corrosion monitoring methods usually rely on regular manual inspections or the use of traditional monitoring equipment. This method has problems such as delayed response, high cost and lack of real-time performance, making it difficult to detect potential corrosion problems in a timely manner. Summary of the invention

[0004] The present invention provides an intelligent monitoring method and system for wind turbine blade corrosion resistance testing, thereby effectively solving the problems pointed out in the background technology.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is: An intelligent monitoring method for a wind turbine blade corrosion test, comprising: Applying a smart coating containing tiny sensing particles on the blade surface, the smart coating generates a response signal in the corrosion area; Divide the wind turbine blade into several monitoring areas, and arrange sensor nodes in each monitoring area, wherein the sensor nodes are connected to the coating and periodically collect parameters of the monitoring area; Based on sliding window and threshold detection, the resistance and temperature curves of each monitoring area are screened at multiple levels, and the monitoring area with abnormal curve fluctuations is marked; Scan the marked monitoring area, and determine whether there are traces of corrosion through spectral analysis to determine whether there is a real corrosion risk in the marked monitoring area; Based on the multiple screening and optical monitoring results, a corrosion status map is generated and dynamically updated based on periodic monitoring.

[0006] Furthermore, based on the sliding window and threshold detection, the resistance and temperature curves of each monitoring area are screened at multiple levels, including: Compare the collected resistance and temperature data with the set normal threshold value, and if the data exceeds the normal range, mark the monitoring area as an abnormal monitoring area; Applying a sliding window algorithm to the data of each monitoring area to calculate the average value of resistance and temperature within a set window size; Compare the collected data with the sliding window mean, and if the current value deviates from the mean by more than a preset percentage, mark the monitoring area as a potential anomaly; Calculating the change rate of the resistance and temperature in each monitoring area within a certain time interval, if the change rate continues to increase and exceeds a preset threshold, marking the monitoring area as a continuous change abnormality; Based on the screening results, the status of the monitoring area is comprehensively marked. If the monitoring area shows abnormalities in all tests, it will be marked as a key abnormal area.

[0007] Furthermore, the response signal is used to identify and locate the corrosion area based on the real-time perception of the resistance or temperature change caused by the particles in the coating to the corrosion.

[0008] Furthermore, the wind turbine blades are divided into several monitoring areas, including: According to the design drawings and actual structures of wind turbine blades, the structural distribution and physical characteristics of each area are obtained; Analyze the corrosion risk of each area of ​​the blade based on the structural characteristics analysis results and historical corrosion data, and identify high-risk areas; According to the identified high-risk area, the distribution density of the monitoring area is determined, and the wind turbine blades are divided into monitoring areas.

[0009] Further, the marked monitoring area is scanned, and whether there are traces of corrosion is determined by spectral analysis to determine whether there is a real corrosion risk in the marked monitoring area, including: Scan the marked majority of monitoring areas to obtain spectral data of the corrosion area; Extracting features from the spectral data, identifying possible corrosion characteristic bands, and distinguishing specific corrosion signals in the monitoring area through a corrosion characteristic spectral library; Based on the spectrum analysis results, the corrosion mode and corrosion risk level of the corrosion traces in the monitoring area are determined by comparing with the baseline spectrum of the normal area.

[0010] Furthermore, possible corrosion characteristic bands are identified and judged through machine learning models.

[0011] Furthermore, feature extraction is performed on the spectral data to identify possible corrosion feature bands, and specific corrosion signals of the monitoring area are identified through a corrosion feature spectral library, including: The collected spectral data are de-noised using a filtering algorithm; Through feature extraction and selection algorithms, the spectrum curve is analyzed to extract the bands related to corrosion characteristics; The extracted characteristic band is compared with the established corrosion characteristic spectrum library to determine whether a specific corrosion signal exists. The corrosion characteristic spectrum library contains standard spectrum data of different types of corrosion.

[0012] Further, based on the multiple screening and optical monitoring results, a corrosion state map is generated and dynamically updated based on periodic monitoring, including: Collect comprehensive data obtained from multiple screening and optical monitoring in each monitoring area to obtain a multidimensional data set; Based on visualization technology, the comprehensive data in the multidimensional data set is mapped to the structural model of the wind turbine blade to create an initial corrosion state map; The parameter data collected periodically are compared with the initial corrosion state map, and the comparison analysis results are fed back to the initial corrosion state map.

[0013] An intelligent monitoring system for wind turbine blade corrosion resistance test, the system comprising: An intelligent coating module is used to coat the blade surface with an intelligent coating containing tiny sensing particles, which generates a response signal in the corrosion area; A sensor node deployment module divides the wind turbine blade into a number of monitoring areas and deploys sensor nodes in each of the monitoring areas. The sensor nodes are connected to the coating and perform periodic parameter collection on the monitoring areas. The abnormal monitoring area marking module performs multi-level screening of the resistance and temperature curves of each monitoring area based on sliding window and threshold detection, and marks the monitoring area with abnormal curve fluctuations; The corrosion risk judgment module scans the marked monitoring area and judges whether there are corrosion traces through spectral analysis to determine whether there is a real corrosion risk in the marked monitoring area; The dynamic monitoring and updating module generates a corrosion state map according to the multiple screening and optical monitoring results, and performs dynamic updates based on periodic monitoring.

[0014] Furthermore, the corrosion risk judgment module includes: A spectral data acquisition unit scans the marked majority of monitoring areas to acquire spectral data of the corrosion area; A specific signal identification unit extracts features from the spectral data, identifies possible corrosion characteristic bands, and identifies specific corrosion signals in the monitoring area through a corrosion characteristic spectral library; The corrosion information determination unit determines the corrosion mode and corrosion risk level of the corrosion traces in the monitoring area based on the spectrum analysis result and by comparing the result with the reference light skin in the normal area.

[0015] The technical solution of the present invention can achieve the following technical effects: It effectively solves the problems of delayed response, high labor costs and lack of real-time performance in traditional corrosion monitoring methods, improves the real-time and accuracy of monitoring, reduces labor costs, and ensures the safe operation of wind turbines. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 A schematic diagram of a flow chart of an intelligent monitoring method for a wind turbine blade corrosion resistance test; Figure 2 A schematic diagram of the process for multi-level screening in each monitoring area; Figure 3 A schematic diagram of the process of dividing a wind turbine blade into several monitoring areas; Figure 4 Schematic diagram of the process to determine whether there is a real corrosion risk in the marked monitoring area; Figure 5 A schematic diagram of the process for identifying corrosion characteristic bands and distinguishing specific corrosion signals; Figure 6 Schematic diagram of the process for generating a corrosion state map and dynamically updating it. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0020] Embodiment 1 like Figure 1 As shown, the present invention provides an intelligent monitoring method for wind turbine blade corrosion resistance test, the method comprising: S1: A smart coating containing tiny sensing particles is applied to the blade surface, and the smart coating generates a response signal in the corrosion area; Specifically, by coating the surface of wind turbine blades with a smart coating, early monitoring of corrosion can be achieved. The tiny sensing particles in the smart coating can generate response signals when corrosion occurs, and can detect abnormalities in the early stages of corrosion.

[0021] S2: Divide the wind turbine blade into several monitoring areas, and arrange sensor nodes in each monitoring area. The sensor nodes are connected to the coating and periodically collect parameters of the monitoring area. Specifically, this step provides more accurate corrosion detection data by zoning monitoring of each area of ​​the wind turbine blade. The blade is divided into several monitoring areas, and sensor nodes are arranged in each monitoring area. This can effectively cover different parts of the blade, allowing the system to capture the changes in resistance, temperature and other parameters in detail in each area. Through the connection between the sensor node and the coating and the periodic parameter collection, it can detect abnormalities in specific areas in the early stages of corrosion, ensure monitoring accuracy, and provide efficient and reliable basic data for zoning analysis and early warning of corrosion status.

[0022] S3: Based on sliding window and threshold detection, the resistance and temperature curves of each monitoring area are screened at multiple levels, and the monitored areas with abnormal curve fluctuations are marked; Specifically, through the sliding window and threshold detection method, the resistance and temperature data of each monitoring area are screened at multiple levels to identify early anomalies and corrosion trends. The sliding window and threshold detection can smooth data fluctuations, eliminate occasional noise, and capture significant data deviations. When the resistance or temperature curve of the monitoring area fluctuates abnormally and exceeds the normal threshold, the system automatically marks the monitoring area as an abnormal area. This process helps the system locate potential corrosion areas in real time, providing precise targets for subsequent in-depth analysis and preventive maintenance, making corrosion monitoring more timely and accurate.

[0023] S4: Scan the marked monitoring area and determine whether there are traces of corrosion through spectral analysis to determine whether there is a real corrosion risk in the marked monitoring area; Specifically, spectral analysis is used to confirm whether there is a real corrosion risk in the marked monitoring area, thereby improving the accuracy of corrosion identification. By scanning and analyzing spectral data, it is possible to verify whether anomalies in resistance or temperature screening are related to actual corrosion, eliminate false alarms, and identify the specific type and severity of corrosion.

[0024] S5: Based on multiple screening and optical monitoring results, a corrosion status map is generated and dynamically updated based on periodic monitoring.

[0025] Specifically, by generating and dynamically updating the corrosion status map, the corrosion status and risk distribution of each monitoring area of ​​the wind turbine blade can be intuitively displayed. According to the results of multiple screening and optical monitoring, the corrosion status map can convert real-time monitoring data into visual information, helping operation and maintenance personnel to clearly understand the distribution, severity and development trend of corrosion. Through periodic data updates, the map can reflect the latest corrosion status and realize continuous monitoring of corrosion risks. This provides a reliable basis for maintenance decisions and resource allocation, and improves the safety and efficiency of wind turbine operation.

[0026] The present invention effectively solves the problems of delayed response, high labor cost and lack of real-time performance in traditional corrosion monitoring methods, improves the real-time performance and accuracy of monitoring, reduces labor costs, and ensures the safe operation of wind turbines.

[0027] As a preferred embodiment of the above, Figure 2 As shown in the figure, based on sliding window and threshold detection, the resistance and temperature curves of each monitoring area are screened at multiple levels, including: A10: Compare the collected resistance and temperature data with the set normal threshold value. If the data exceeds the normal range, the monitoring area is marked as an abnormal monitoring area. A20: Apply the sliding window algorithm to the data of each monitoring area and calculate the mean value of resistance and temperature within the set window size; A30: Compare the collected data with the sliding window mean. If the current value deviates from the mean by more than a preset percentage, the monitoring area is marked as a potential anomaly. A40: Calculate the change rate of resistance and temperature in each monitoring area within a certain time interval. If the change rate continues to increase and exceeds the preset threshold, the monitoring area is marked as a continuous change abnormality; A50: Based on the screening results, the status of the monitoring area is comprehensively marked. If the monitoring area shows abnormalities in all tests, it will be marked as a key abnormal area.

[0028] Specifically, the system compares the collected resistance and temperature data with the preset normal range threshold. If the data exceeds the normal threshold, the monitoring area is marked as an "abnormal monitoring area" as a preliminary screening for further analysis; within the set window size, the sliding window algorithm is applied to the data of each monitoring area to calculate the mean of the resistance and temperature of the area. This calculation can smooth the short-term fluctuations of the data and provide a stable baseline value for subsequent deviation detection; the real-time collected data is compared with the sliding window mean. If the current value deviates from the mean by more than a preset percentage (such as 15%), the monitoring area is marked as "potential abnormality". This step helps detect significant data deviations and identifies early signs of potential corrosion; the rate of change of resistance and temperature in the monitoring area within a fixed time interval is calculated. If the rate continues to increase and exceeds the set threshold, the monitoring area is marked as "continuous change abnormality". This test identifies the area of ​​continuous corrosion development and provides a reference for long-term corrosion trends; the above multi-level screening results are combined to determine the corrosion status of the monitoring area. If a monitoring area shows abnormalities in multiple detection items, it will be marked as a "key abnormal area" for priority monitoring and preventive maintenance.

[0029] As a preferred embodiment of the above embodiment, the response signal is based on real-time sensing of the resistance or temperature change caused by corrosion of particles in the coating, and is used to identify and locate the corrosion area.

[0030] Specifically, the response signal is based on tiny sensing particles embedded in the coating. These particles are highly sensitive to resistance or temperature changes caused by corrosion. When corrosion occurs, the physical or chemical properties of the particles change, causing significant changes in the resistance or temperature of the coating. The sensing node detects these changes in real time to form a response signal. By monitoring the intensity and distribution of the response signal, the location and extent of corrosion can be identified and the corrosion area can be accurately located.

[0031] As a preferred embodiment of the above, Figure 3 As shown, the wind turbine blades are divided into several monitoring areas, including: B10: Based on the design drawing and actual structure of the wind turbine blade, the structural distribution and physical characteristics of each area are obtained; B20: Analyze the corrosion risk of each area of ​​the blade based on the structural characteristics analysis results and historical corrosion data, and identify high-risk areas; B30: Based on the identified high-risk areas, determine the distribution density of the monitoring area and divide the wind turbine blades into monitoring areas.

[0032] Specifically, first, according to the design drawings and actual structure of the wind turbine blades, the detailed distribution and physical characteristics of each area of ​​the blade are obtained, such as the thickness, material composition, stress distribution, etc. of the blade. This information provides basic data for the subsequent division of monitoring areas, so that the monitoring area settings can better adapt to the actual force and structural requirements of the blades; based on the results of the structural characteristic analysis and combined with the historical corrosion data accumulated in the actual operation of the blades, the corrosion risk of each area is evaluated. For example, the leading edge, root and other areas exposed to high wind speed, humidity or salt spray are more prone to corrosion. Through this analysis, high-risk areas can be identified so that monitoring resources can be allocated preferentially; based on the identified high-risk areas, the distribution density of the monitoring area is determined, and more dense sensor nodes are arranged in high corrosion risk areas to improve monitoring accuracy and real-time performance. For low-risk areas, the monitoring density can be appropriately reduced to optimize resource allocation. Finally, the blades are reasonably divided into monitoring areas based on the results of the risk assessment.

[0033] As a preferred embodiment of the above, Figure 4 As shown, step S4 is to scan the marked monitoring area and determine whether there are traces of corrosion through spectral analysis to determine whether there is a real corrosion risk in the marked monitoring area, including: S41: Scanning the marked majority of monitoring areas to obtain spectral data of the corrosion area; S42: extracting features from the spectral data, identifying possible corrosion characteristic bands, and identifying specific corrosion signals in the monitoring area through the corrosion characteristic spectral library; S43: Based on the spectral analysis results, the corrosion pattern and corrosion risk level of the corrosion traces in the monitoring area are determined by comparing with the baseline spectrum of the normal area.

[0034] Specifically, first, perform multi-spectral or hyperspectral scanning on the marked monitoring areas to capture detailed spectral data in the area. The scanning covers multiple bands such as ultraviolet, visible light and infrared to ensure that the complete spectral characteristics that may be caused by corrosion can be obtained; feature extraction is performed on the acquired spectral data. These characteristic bands may show changes in reflectivity, absorption peaks or specific spectral forms. The extracted corrosion characteristic bands are then compared with the preset corrosion characteristic spectral library. Through pattern recognition technology, it is determined whether there are specific corrosion signs in the spectral signal, thereby confirming the corrosion state of the monitoring area; based on the comparison results of spectral analysis, the marked monitoring area is compared with the baseline spectrum of the normal area. By analyzing the changes in the corrosion characteristic bands, the system can determine the type of corrosion (such as pitting corrosion, uniform corrosion, etc.) and the severity of corrosion. Finally, according to the spectral differences and corrosion characteristics, the monitoring area is divided into different corrosion risk levels to provide a basis for subsequent maintenance and protection measures.

[0035] As a preferred embodiment of the above embodiment, possible corrosion characteristic bands are identified and judged through a machine learning model.

[0036] As a preferred embodiment of the above, Figure 5 As shown, step S42, feature extraction is performed on the spectral data to identify possible corrosion feature bands, and specific corrosion signals in the monitoring area are identified through the corrosion feature spectral library, including: S421: using a filtering algorithm to perform noise removal on the collected spectral data; S422: Analyze the spectrum curve and extract the bands related to the corrosion characteristics through feature extraction and selection algorithm; S423: Compare the extracted characteristic band with the established corrosion characteristic spectrum library to determine whether there is a specific corrosion signal, and the corrosion characteristic spectrum library contains standard spectrum data of different types of corrosion.

[0037] Specifically, the process of identifying possible corrosion characteristic bands and judging them through machine learning models includes the following steps. First, the collected spectral data is preprocessed, including denoising, normalization, and spectral correction to ensure the accuracy and consistency of the data; then, the most representative bands in the spectral data are identified using feature extraction algorithms (such as principal component analysis PCA or feature band selection algorithms), which contain key information related to corrosion, such as specific reflection peaks or absorption peaks; after the characteristic bands are identified, specific data features related to corrosion are extracted from them, such as peak position, peak intensity, absorptivity, etc., and these features are standardized so that the machine learning model can better understand and process the data. After the processed feature data is input into the pre-trained machine learning model, the model will analyze and judge these data. The model can use algorithms such as support vector machine (SVM), random forest or convolutional neural network (CNN), and select according to the complexity of the corrosion characteristics and the characteristics of the data set. The machine learning model will determine whether there is corrosion feature in the spectral signal by analyzing the feature data. The model uses the patterns learned during the training process to compare the detected band features with the existing corrosion samples, so as to accurately determine the type of corrosion and the possibility of its existence; finally, based on the output results of the machine learning model, the type and severity of corrosion are judged, and the extracted characteristic bands are compared with the established corrosion characteristic spectrum library to determine whether there is a specific corrosion signal. The corrosion characteristic spectrum library contains standard spectral data of different types of corrosion, covering common corrosion types and their corresponding spectral features, such as absorption peak position, reflectivity and other characteristic information. During the comparison process, the system matches the extracted characteristic bands with the standard spectral data in the spectral library, calculates the similarity between the two, and determines whether the spectral signal conforms to a known corrosion type. If the spectral morphology of the characteristic band matches the standard spectrum in the library, the system determines that there is a specific type of corrosion in the monitoring area and further analyzes its severity. This comparison process can accurately identify different types of corrosion with the help of standard data of different types of corrosion in the spectral library, providing an accurate basis for the classification of corrosion types and risk level assessment.

[0038] As a preferred embodiment of the above, Figure 6 As shown, step S5 generates a corrosion state map based on multiple screening and optical monitoring results, and dynamically updates it based on periodic monitoring, including: S51: Collect the comprehensive data obtained from multiple screening and optical monitoring in each monitoring area to obtain a multidimensional data set; S52: Based on visualization technology, the comprehensive data in the multidimensional data set is mapped to the structural model of the wind turbine blade to create an initial corrosion state map; S53: comparing the periodically collected parameter data with the initial corrosion state map, and feeding back the comparison analysis results to the initial corrosion state map.

[0039] Specifically, first, the comprehensive data such as resistance, temperature and spectrum obtained in multiple screening and optical monitoring of each monitoring area are collected to form a multidimensional data set, which contains the corrosion status information of different time points and each monitoring area, providing a comprehensive basis for subsequent analysis; then, based on visualization technology, the data in the multidimensional data set is mapped to the structural model of the wind turbine blade to create an initial corrosion state map. In the map, the corrosion degree and risk level of each monitoring area are intuitively represented by the change of color or symbol (such as green, yellow, red), thus presenting an overall view of the corrosion state of the blade, which is convenient for rapid identification and positioning of high-risk areas. Finally, according to the parameter data collected periodically in the future, the new data is compared with the initial corrosion state map, and the trend of change or deterioration of the corrosion state is analyzed. The results of the comparative analysis are fed back to the initial map to automatically update the map content to ensure that the map reflects the latest corrosion state. Through this dynamically updated corrosion state map, the real-time corrosion information of the blade can be accurately provided, providing a basis for maintenance decisions and ensuring the timeliness and effectiveness of corrosion monitoring.

[0040] Embodiment 2 Based on the same inventive concept as the intelligent monitoring method for wind turbine blade corrosion test in the aforementioned embodiment, the present invention also provides an intelligent monitoring system for wind turbine blade corrosion test, the system comprising: Smart coating module: a smart coating containing tiny sensing particles is applied to the blade surface. The smart coating generates a response signal in the corrosion area. The sensor node layout module divides the wind turbine blade into several monitoring areas and arranges sensor nodes in each monitoring area. The sensor nodes are connected to the coating and periodically collect parameters of the monitoring area. The abnormal monitoring area marking module performs multi-level screening of the resistance and temperature curves of each monitoring area based on sliding windows and threshold detection, and marks the monitoring areas with abnormal curve fluctuations; The corrosion risk judgment module scans the marked monitoring area and determines whether there are traces of corrosion through spectral analysis to determine whether there is a real corrosion risk in the marked monitoring area; The dynamic monitoring update module generates a corrosion status map based on multiple screening and optical monitoring results, and dynamically updates it based on periodic monitoring.

[0041] The above-mentioned monitoring system in the present invention can effectively realize the intelligent monitoring method of the wind turbine blade corrosion resistance test, and the technical effects that can be achieved are as described in the above-mentioned embodiments, which will not be repeated here.

[0042] As a preferred embodiment of the above, the corrosion risk judgment module includes: A spectral data acquisition unit scans the marked majority of monitoring areas to acquire spectral data of the corrosion area; The specific signal identification unit extracts features from the spectral data, identifies possible corrosion characteristic bands, and identifies specific corrosion signals in the monitoring area through the corrosion characteristic spectral library; The corrosion information determination unit determines the corrosion pattern and corrosion risk level of the corrosion traces in the monitoring area based on the spectral analysis results and compares them with the reference light skin in the normal area.

[0043] Similarly, the above-mentioned optimization schemes for the system can also respectively achieve the optimization effects corresponding to the method in Example 1, which will not be repeated here.

[0044] Although the present application has been described in conjunction with specific features and embodiments thereof, it is apparent that various modifications and combinations may be made thereto without departing from the spirit and scope of the present application. Accordingly, this specification and the accompanying drawings are merely exemplary illustrations of the present application as defined herein, and are deemed to have covered any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these modifications and variations.

Claims

1. An intelligent monitoring method for wind turbine blade corrosion resistance test, characterized in that: include: Applying a smart coating containing tiny sensing particles on the blade surface, the smart coating generates a response signal in the corrosion area; Divide the wind turbine blade into several monitoring areas, and arrange sensor nodes in each monitoring area, wherein the sensor nodes are connected to the coating and periodically collect parameters of the monitoring area; Based on sliding window and threshold detection, the resistance and temperature curves of each monitoring area are screened at multiple levels, and the monitoring area with abnormal curve fluctuations is marked; Scan the marked monitoring area, and determine whether there are traces of corrosion through spectral analysis to determine whether there is a real corrosion risk in the marked monitoring area; Based on the multiple screening and optical monitoring results, a corrosion status map is generated and dynamically updated based on periodic monitoring.

2. The intelligent monitoring method for wind turbine blade corrosion resistance test according to claim 1 is characterized in that: Based on sliding window and threshold detection, the resistance and temperature curves of each monitoring area are screened at multiple levels, including: Compare the collected resistance and temperature data with the set normal threshold value, and if the data exceeds the normal range, mark the monitoring area as an abnormal monitoring area; Applying a sliding window algorithm to the data of each monitoring area to calculate the average value of resistance and temperature within a set window size; Compare the collected data with the sliding window mean, and if the current value deviates from the mean by more than a preset percentage, mark the monitoring area as a potential anomaly; Calculating the change rate of the resistance and temperature in each monitoring area within a certain time interval, if the change rate continues to increase and exceeds a preset threshold, marking the monitoring area as a continuous change abnormality; Based on the screening results, the status of the monitoring area is comprehensively marked. If the monitoring area shows abnormalities in all tests, it will be marked as a key abnormal area.

3. The intelligent monitoring method for wind turbine blade corrosion resistance test according to claim 1 is characterized in that: The response signal is based on real-time sensing of the resistance or temperature changes caused by corrosion by particles in the coating, and is used to identify and locate the corrosion area.

4. The intelligent monitoring method for wind turbine blade corrosion resistance test according to claim 1 is characterized in that: Wind turbine blades are divided into several monitoring areas, including: According to the design drawings and actual structures of wind turbine blades, the structural distribution and physical characteristics of each area are obtained; Analyze the corrosion risk of each area of ​​the blade based on the structural characteristics analysis results and historical corrosion data, and identify high-risk areas; According to the identified high-risk area, the distribution density of the monitoring area is determined, and the wind turbine blades are divided into monitoring areas.

5. The intelligent monitoring method for wind turbine blade corrosion resistance test according to claim 1 is characterized in that: Scan the marked monitoring area and determine whether there are traces of corrosion through spectral analysis to determine whether there is a real corrosion risk in the marked monitoring area, including: Scan the marked majority of monitoring areas to obtain spectral data of the corrosion area; Extracting features from the spectral data, identifying possible corrosion characteristic bands, and distinguishing specific corrosion signals in the monitoring area through a corrosion characteristic spectral library; Based on the spectrum analysis results, the corrosion mode and corrosion risk level of the corrosion traces in the monitoring area are determined by comparing with the baseline spectrum of the normal area.

6. The intelligent monitoring method for wind turbine blade corrosion resistance test according to claim 5 is characterized in that: Identify possible corrosion characteristic bands and make judgments through machine learning models.

7. The intelligent monitoring method for wind turbine blade corrosion resistance test according to claim 5 is characterized in that: Extracting features from the spectral data, identifying possible corrosion characteristic bands, and identifying specific corrosion signals in the monitoring area through a corrosion characteristic spectral library, including: The collected spectral data are de-noised using a filtering algorithm; Through feature extraction and selection algorithms, the spectrum curve is analyzed to extract the bands related to corrosion characteristics; The extracted characteristic band is compared with the established corrosion characteristic spectrum library to determine whether a specific corrosion signal exists. The corrosion characteristic spectrum library contains standard spectrum data of different types of corrosion.

8. The intelligent monitoring method for wind turbine blade corrosion resistance test according to claim 1 is characterized in that: Based on the multiple screening and optical monitoring results, a corrosion status map is generated and dynamically updated based on periodic monitoring, including: Collect comprehensive data obtained from multiple screening and optical monitoring in each monitoring area to obtain a multidimensional data set; Based on visualization technology, the comprehensive data in the multidimensional data set is mapped to the structural model of the wind turbine blade to create an initial corrosion state map; The parameter data collected periodically are compared with the initial corrosion state map, and the comparison analysis results are fed back to the initial corrosion state map.

9. An intelligent monitoring system for wind turbine blade corrosion resistance test, characterized in that: The system comprises: An intelligent coating module is used to coat the blade surface with an intelligent coating containing tiny sensing particles, which generates a response signal in the corrosion area; A sensor node deployment module divides the wind turbine blade into a number of monitoring areas and deploys sensor nodes in each of the monitoring areas. The sensor nodes are connected to the coating and perform periodic parameter collection on the monitoring areas. The abnormal monitoring area marking module performs multi-level screening of the resistance and temperature curves of each monitoring area based on sliding window and threshold detection, and marks the monitoring area with abnormal curve fluctuations; The corrosion risk judgment module scans the marked monitoring area and judges whether there are corrosion traces through spectral analysis to determine whether there is a real corrosion risk in the marked monitoring area; The dynamic monitoring and updating module generates a corrosion state map according to the multiple screening and optical monitoring results, and performs dynamic updates based on periodic monitoring.

10. The intelligent monitoring system for wind turbine blade corrosion test according to claim 9, characterized in that: The corrosion risk judgment module includes: A spectral data acquisition unit scans the marked majority of monitoring areas to acquire spectral data of the corrosion area; A specific signal identification unit extracts features from the spectral data, identifies possible corrosion characteristic bands, and identifies specific corrosion signals in the monitoring area through a corrosion characteristic spectral library; The corrosion information determination unit determines the corrosion mode and corrosion risk level of the corrosion traces in the monitoring area based on the spectrum analysis result and by comparing the result with the reference light skin in the normal area.

Images