Non-intrusive optical fiber fan health monitoring method and system

Abstract

The invention provides a non-intrusive optical fiber fan health monitoring method and system.The health monitoring method specifically comprises the steps that a non-intrusive optical fiber sensing array is arranged at a preset part of fan equipment, and the optical fiber sensing array comprises an optical fiber grating sensor array; a first optical fiber sensing grid is built based on the optical fiber grating sensor array, the first optical fiber sensing grid covers the multiple draught fan devices and is used for continuously monitoring a first parameter set of the covered draught fan devices, and a first monitoring data set is generated. The beneficial effects of the invention are that through the arrangement of the optical fiber sensing grids, the multiple fan devices deployed in the same area can be synchronously monitored according to the parameters such as the load capacity, the deformation condition, the operation temperature and the vibration condition, and the monitoring errors generated by the fan devices in the same area due to the influence of environmental factors and the like can be corrected; the health state of the fan equipment can be accurately monitored, and the false alarm condition is avoided.

Description

Technical Field

[0001] This disclosure belongs to the field of digital signal processing technology, and in particular relates to a non-invasive fiber optic wind turbine health monitoring method and system. Background Technology

[0002] Wind power, as a clean and renewable energy source, has broad development prospects, and the installed capacity of wind turbines has been growing rapidly in recent years. With the increase in installed wind power capacity and the lengthening of turbine operating time, reducing the failure rate of wind turbines and improving the effective monitoring of their operational health have become urgent problems to be solved.

[0003] Monitoring methods based on fiber optic sensors (FOS) involve installing fiber optic sensors on wind turbine equipment and transmitting data to a remote control center for processing and analysis via fiber optic communication. This enables continuous, high-precision health monitoring of the wind turbine equipment. However, due to the complexity of signal processing and the susceptibility of non-invasive fiber optic sensors to interference from environmental or other external factors, health monitoring of the wind turbine equipment may result in inaccuracies and false alarms. Summary of the Invention

[0004] In view of this, the present disclosure aims to propose a non-invasive fiber optic wind turbine health monitoring method and system, which can realize accurate monitoring and analysis of the operating conditions and health status of wind turbine equipment.

[0005] The first aspect of this disclosure provides a non-invasive fiber optic wind turbine health monitoring method, which specifically includes: setting up a non-invasive fiber optic sensor array at a preset location on the wind turbine equipment, the fiber optic sensor array including a fiber Bragg grating sensor array; constructing a first fiber optic sensor grid based on the fiber Bragg grating sensor array, the first fiber optic sensor grid covering multiple wind turbine equipment, for continuously monitoring a first set of parameters of the covered wind turbine equipment, generating a first monitoring dataset; obtaining a first synchronous monitoring error of the covered wind turbine equipment based on the first monitoring data corresponding to different wind turbine equipment in the first monitoring dataset, and correcting a first monitoring index of the wind turbine equipment based on the first synchronous monitoring error; and determining the health monitoring status of the wind turbine equipment by comparing the first monitoring dataset and the corrected first monitoring index.

[0006] In one possible implementation of the first aspect described above, the first set of parameters includes at least one or any combination of multiple of the monitoring point stress parameters, monitoring point temperature parameters, monitoring point deformation parameters, and monitoring point vibration parameters of the wind turbine equipment.

[0007] In one possible implementation of the first aspect described above, the fiber optic sensing array includes a microelectromechanical system (MEMS) fiber optic sensor array; this non-invasive fiber optic wind turbine health monitoring method may further include: constructing a second fiber optic sensing grid based on the MEMS fiber optic sensor array, the second fiber optic sensing grid covering multiple wind turbine devices, for continuously monitoring a second set of parameters of the covered wind turbine devices, generating a second monitoring dataset; obtaining a second synchronous monitoring error of the covered wind turbine devices based on the second monitoring data corresponding to different wind turbine devices in the second monitoring dataset, and correcting the second monitoring index of the wind turbine devices based on the second synchronous monitoring error; and determining the health monitoring status by comparing the second monitoring dataset and the corrected second monitoring index, and / or synchronously comparing the first monitoring dataset and the corrected first monitoring index.

[0008] In one possible implementation of the first aspect described above, the second set of parameters includes at least one or any combination of monitoring point vibration parameters, monitoring point noise parameters, and monitoring point air gap parameters.

[0009] In one possible implementation of the first aspect above, the wind turbine equipment covered by the second fiber optic sensing grid is the same as the wind turbine equipment covered by the first fiber optic sensing grid; this non-invasive fiber optic wind turbine health monitoring method may further include: obtaining the environmental system monitoring error of the wind turbine equipment covered by the second fiber optic sensing grid through a first preset neural network model based on the first synchronous monitoring error and the second synchronous monitoring error; correcting the first monitoring data and / or the second monitoring data based on the environmental system monitoring error; and determining the health monitoring status by comparing the second monitoring dataset and the corrected second monitoring indicator, and / or simultaneously comparing the first monitoring dataset and the corrected first monitoring indicator.

[0010] In one possible implementation of the first aspect above, the first synchronous monitoring error of the covered wind turbine equipment is obtained based on the first monitoring data corresponding to different wind turbine equipment in the first monitoring dataset, including the following steps: obtaining the deviation between the first monitoring data and the first monitoring index corresponding to each wind turbine equipment covered by the first fiber optic sensing grid; based on the deviation, obtaining the system monitoring deviation and / or environmental monitoring deviation of the wind turbine equipment covered by the first fiber optic sensing grid based on the second preset neural network model; and generating the first synchronous monitoring error based on the preset weighting coefficients and the system monitoring deviation and / or environmental monitoring deviation.

[0011] In one possible implementation of the first aspect above, determining the health monitoring status of the wind turbine equipment by comparing the first monitoring dataset and the corrected first monitoring index includes the following steps: obtaining a set of deviation monitoring data that deviates from the corrected first monitoring index; obtaining a set of prior deviation data that has the highest similarity to the set of deviation monitoring data based on a preset prior experience library, and taking the equipment status corresponding to the prior deviation data set as the health monitoring status of the wind turbine equipment; wherein, the prior experience library is obtained based on the historical monitoring data and / or prior monitoring knowledge of the wind turbine equipment corresponding to the first fiber optic sensing grid.

[0012] In one possible implementation of the first aspect above, when the similarity between the prior deviation data set with the highest similarity and the deviation monitoring data set is lower than a first preset threshold, a corresponding field monitoring work order is generated based on the deviation monitoring data set; based on the feedback results of the field monitoring work order, the health monitoring status of the wind turbine equipment is obtained, and the health monitoring status is used as update data to update the prior experience base.

[0013] The second aspect of this disclosure provides a non-invasive fiber optic wind turbine health monitoring system, which specifically includes: a deployment unit for setting up a non-invasive fiber optic sensor array at a preset location on the wind turbine equipment, the fiber optic sensor array including a fiber Bragg grating sensor array; a data monitoring unit for building a first fiber optic sensor grid based on the fiber Bragg grating sensor array, the first fiber optic sensor grid covering multiple wind turbine equipment, for continuously monitoring a first set of parameters of the covered wind turbine equipment, and generating a first monitoring dataset; an error correction unit for obtaining a first synchronous monitoring error of the covered wind turbine equipment based on the first monitoring data corresponding to different wind turbine equipment in the first monitoring dataset, and correcting a first monitoring index of the wind turbine equipment based on the first synchronous monitoring error; and a health monitoring unit for determining the health monitoring status of the wind turbine equipment by comparing the first monitoring dataset and the corrected first monitoring index.

[0014] In one possible view of the second aspect described above, the fiber optic sensing array includes a microelectromechanical system (MEMS) fiber optic sensor array; the data monitoring unit is further configured to build a second fiber optic sensing grid based on the MEMS fiber optic sensor array, the second fiber optic sensing grid covering multiple wind turbine devices, for continuously monitoring a second set of parameters of the covered wind turbine devices, generating a second monitoring dataset; the error correction unit is further configured to obtain a second synchronous monitoring error of the covered wind turbine devices based on the second monitoring data corresponding to different wind turbine devices in the second monitoring dataset, and to correct the second monitoring index of the wind turbine devices based on the second synchronous monitoring error; and the health monitoring unit is further configured to compare the second monitoring dataset and the corrected second monitoring index, and / or synchronously compare the first monitoring dataset and the corrected first monitoring index to determine the health monitoring status.

[0015] Compared to existing technologies, the non-invasive fiber optic wind turbine health monitoring method and system provided in this disclosure have the following beneficial effects: It can simultaneously monitor parameters such as load capacity, deformation, operating temperature, and vibration of multiple wind turbines deployed in the same area through the setting of a fiber optic sensor grid. It can also correct monitoring errors caused by environmental factors affecting wind turbines in the same area, enabling accurate monitoring of the wind turbine's health status and avoiding false alarms. Furthermore, the fiber optic sensing devices provided in this disclosure support non-embedded installation methods, making them easy to deploy at desired locations on wind turbines. They can also be replaced promptly when malfunctions occur, effectively ensuring continuous and accurate monitoring of the wind turbine's health status, and thus have significant potential for widespread application. Attached Figure Description

[0016] The accompanying drawings, which form part of this disclosure, are used to provide a further understanding of this disclosure. The illustrative embodiments of this disclosure and their descriptions are used to explain this disclosure and do not constitute an undue limitation of this disclosure. In the drawings: Figure 1 This is a flowchart illustrating a non-invasive fiber optic wind turbine health monitoring method according to an embodiment of this disclosure.

[0017] Figure 2 This is a schematic diagram of a process for obtaining the first synchronous monitoring error according to an embodiment of this disclosure.

[0018] Figure 3 This is a schematic diagram illustrating a process for obtaining health monitoring information according to an embodiment of this disclosure.

[0019] Figure 4 This is a flowchart illustrating another non-invasive fiber optic wind turbine health monitoring method according to an embodiment of this disclosure.

[0020] Figure 5 This is a schematic diagram of the structure of a non-invasive fiber optic wind turbine health monitoring system according to an embodiment of this disclosure. Detailed Implementation

[0021] To more clearly illustrate the technical solutions of the embodiments in this specification, the embodiments will be described in detail below with reference to the accompanying drawings. Obviously, the content described below are some examples or embodiments of this specification. For those skilled in the art, without creative effort, the technical solutions or means disclosed in this specification can be applied to other scenarios based on this technical content.

[0022] Figure 1 This is a flowchart illustrating a data acquisition and processing method for bone injury assessment according to an embodiment of this disclosure, which may specifically include: Step 101: Install a non-invasive fiber optic sensor array at a predetermined location on the wind turbine equipment. In some embodiments, the fiber optic sensor array may include a fiber Bragg grating sensor array. In some embodiments, those skilled in the art can deploy the fiber optic sensor array at various key locations on the wind turbine equipment according to actual needs, and this is not limited thereto.

[0023] Step 102: Construct a first fiber optic sensing grid based on a fiber optic grating sensor array, wherein the first fiber optic sensing grid covers multiple wind turbine devices and is used to continuously monitor the first set of parameters of the covered wind turbine devices to generate a first monitoring dataset.

[0024] In some embodiments, a fiber Bragg grating sensor array can be connected to a laser source and an analytical spectrometer via optical fiber to form a first fiber optic sensing grid. This first fiber optic sensing grid can cover fiber Bragg grating sensor arrays mounted on multiple wind turbines located in the same area, enabling collaborative analysis of the health status of multiple wind turbines in the same area during subsequent continuous monitoring. In some embodiments, the laser source can be a laser generator capable of producing narrowband laser signals, outputting corresponding laser signals according to the needs of different fiber Bragg grating sensor arrays; this is not limited to any particular source. In some embodiments, the analytical spectrometer is a device capable of performing spectral analysis on the reflection signal corresponding to the narrowband laser signal provided by the laser generator, obtaining a corresponding first parameter set based on the specific monitoring functions implemented by different fiber Bragg grating sensor arrays.

[0025] In some embodiments, the first parameter set may specifically include at least one or any combination of multiple monitoring point parameters, monitoring point temperature parameters, monitoring point deformation parameters, and monitoring point vibration parameters corresponding to the covered multiple wind turbine devices. In some specific setup examples, the fiber grating sensor array may consist of multiple fiber Brillouin scattering (FBG) sensors, specifically including strain FBG sensors, temperature FBG sensors, deformation FBG sensors, and vibration FBG sensors. The strain FBG sensors may be installed on the blade structure of the wind turbine device for continuous monitoring of the stress parameters of the blades during operation; the temperature FBG sensors may be installed on the blade structure and / or tower structure of the wind turbine device for continuous monitoring of the temperature parameters of the blades and / or tower during operation. In some specific setup examples, the fiber grating sensor array may also include a crack FBG sensor, installed at the base of the wind turbine device for continuous monitoring of whether cracks have appeared in the base of the wind turbine device. In some specific setup examples, the fiber grating sensor array may also include a load FBG sensor for continuous monitoring of the operating load of the wind turbine device. In some embodiments, those skilled in the art can deploy fiber optic sensor arrays at various key locations of the wind turbine equipment according to actual needs, without limitation. In some embodiments, by deploying multiple non-invasive fiber Bragg grating sensors on the surface of the wind turbine equipment to form a fiber Bragg grating sensor array, it is possible to achieve a monitoring range corresponding to the wind turbine load sensing within the range [-1500]. 1500 The monitoring range of the fan vibration sensor is within the range of [-5g, 5g], with an error accuracy of less than or equal to 0.5% of the full scale. The monitoring range of the fan bolt force sensor is within the range of [400KN, 800KN], with an error accuracy of less than or equal to 2.5% of the full scale, which can support accurate monitoring of the health status of fan equipment.

[0026] Step 103: Based on the first monitoring data corresponding to different wind turbine equipment in the first monitoring dataset, obtain the first synchronous monitoring error of the covered wind turbine equipment, and correct the first monitoring index of the wind turbine equipment based on the first synchronous monitoring error. It is understandable that for multiple wind turbine equipment covered by the first fiber optic sensing grid, they can be centrally deployed in the same external environment area, requiring additional exclusion of external interference factors during the sensing and monitoring process. Specifically, Figure 2 This is a schematic flowchart illustrating an embodiment of the present disclosure for obtaining a first synchronous monitoring error, which may specifically include: Step 103a: Obtain the deviation between the first monitoring data and the first monitoring index corresponding to each wind turbine equipment covered by the first fiber optic sensing grid.

[0027] Step 103b: Based on the deviation, obtain the system monitoring deviation and / or environmental monitoring deviation of the wind turbine equipment covered by the first fiber optic sensing grid based on the second preset neural network model. In some embodiments, the system monitoring deviation may be due to the non-invasive fiber optic sensor, such as the fiber optic sensor experiencing reading deviation or failure under extreme external environments; the environmental monitoring deviation may be caused by the external environment of the wind turbine equipment, such as high temperature environment, strong wind environment, ground vibration environment caused by large herds of livestock grazing nearby, etc. In some embodiments, the above system monitoring deviation and environmental monitoring deviation are obtained based on the pre-trained neural network model, which can reflect the real monitoring influencing factors in the area where the wind turbine equipment is installed. Those skilled in the art can also obtain the above system monitoring deviation and environmental monitoring deviation through other feasible technical means, which are not limited here.

[0028] Step 103c: Generate the first synchronous monitoring error based on the preset weighting coefficients and the system monitoring deviation and / or environmental monitoring deviation. It is understood that the preset weighting coefficients can be adjusted according to actual conditions. For example, if the monitoring readings of one or more sensors in the fiber optic sensor array deviate significantly from those of other sensors, a single or multiple sensor malfunction may occur. In this case, the weighting coefficients corresponding to the system monitoring deviation can be adjusted adaptively. Similarly, if the fan equipment operates in certain extremely harsh environments, the weighting coefficients corresponding to the environmental monitoring deviation can be adjusted adaptively; this is not limited here.

[0029] Step 104: By comparing the first monitoring dataset with the corrected first monitoring indicator, determine the health monitoring status of the wind turbine equipment. It is understood that by accurately obtaining the first monitoring dataset and the corrected first monitoring indicator, the health monitoring status of the wind turbine equipment can be analyzed and determined. In some embodiments, the technical solution provided in this disclosure supports the analysis of hundreds of monitoring data points per second within the monitoring window, enabling accurate acquisition of the actual health status of the wind turbine equipment in a timely manner. Specifically, Figure 3 This is a schematic diagram of a process for obtaining health monitoring information according to an embodiment of this disclosure, which may specifically include: Step 104a: Obtain the deviation monitoring data set of the first monitoring indicator after deviation correction. It is understood that the corrected first monitoring indicator reflects the actual standard monitoring indicator. If the collected monitoring parameters deviate from the corrected first monitoring indicator, it indicates that the wind turbine equipment may be facing abnormal conditions such as malfunctions. These monitoring parameters can be uniformly included in the deviation monitoring data set for further analysis.

[0030] Step 104b: Based on a preset prior experience library, obtain the prior deviation data set with the highest similarity to the deviation monitoring data set, and use the equipment status corresponding to the prior deviation data set as the health monitoring status of the wind turbine equipment. In some embodiments, the prior experience library is obtained based on the historical monitoring data and / or prior monitoring knowledge of the wind turbine equipment corresponding to the first fiber optic sensing grid. It is understood that the historical monitoring data of the wind turbine equipment corresponding to the first fiber optic sensing grid can be used as prior experience to compare the current monitoring status of the wind turbine equipment; when there is limited prior experience, prior monitoring knowledge provided by professionals can also be used as a supplement, such as when the load on the wind turbine blades exceeds the standard monitoring range by 30%, it indicates that the wind turbine blades may be facing abnormal conditions such as objects hanging on them, and timely investigation is required, etc., which is not limited here.

[0031] In some embodiments, further, when the similarity between the prior deviation data set with the highest similarity and the deviation monitoring data set is lower than a first preset threshold, it indicates that the actual situation corresponding to the current deviation monitoring data set is not included in the prior experience base. In this case, a corresponding on-site monitoring work order can be generated based on the deviation monitoring data set, and maintenance personnel can be arranged to conduct manual on-site situation analysis and monitoring work order feedback. Based on the feedback results of the on-site monitoring work order, the health monitoring status of the wind turbine equipment can be obtained, and the health monitoring status can be used as update data to update the prior experience base. In some embodiments, considering that the wind turbine equipment deployment site is relatively remote, a corresponding on-site monitoring work order can be generated only when the actual situation corresponding to the current deviation monitoring data set is not included in the prior experience base, and the deviation amplitude corresponding to the deviation monitoring data set is greater than a second preset threshold. A deviation amplitude greater than the second preset threshold indicates that the monitoring data of the wind turbine equipment deviates significantly from the normal value. In this case, it is more reasonable to generate and dispatch a manual on-site monitoring work order, which is not limited here.

[0032] In some embodiments, the fiber optic sensing array may include not only a fiber Bragg grating sensor array but also a microelectromechanical system (MEMS) fiber optic sensor array. In some specific configuration examples, the MEMS fiber optic sensor array may consist of multiple MEMS fiber optic sensors, which may specifically include vibration MEMS sensors, noise MEMS sensors, air gap MEMS sensors, etc., without limitation. Figure 4 This is a flowchart illustrating another non-invasive fiber optic wind turbine health monitoring method according to an embodiment of this disclosure, which may specifically include: Step 401: Construct a second fiber optic sensing grid based on a microelectromechanical system (MEMS) fiber optic sensor array. This second fiber optic sensing grid covers multiple wind turbine devices and is used to continuously monitor a second set of parameters for the covered wind turbine devices, generating a second monitoring dataset. In some embodiments, the second set of parameters may include at least one or any combination of monitoring point vibration parameters, monitoring point noise parameters, and monitoring point air gap parameters. In some embodiments, the specific implementation of step 401 can refer to the specific implementation of step 102 in the foregoing embodiments, and is not limited here.

[0033] Step 402: Based on the second monitoring data corresponding to different wind turbine equipment in the second monitoring dataset, obtain the second synchronous monitoring error of the covered wind turbine equipment, and correct the second monitoring index of the wind turbine equipment based on the second synchronous monitoring error. In some embodiments, the specific implementation of step 402 can refer to the specific implementation of step 103 in the foregoing embodiments, and is not limited here.

[0034] Step 403: Compare the second monitoring dataset with the corrected second monitoring indicator, and / or simultaneously compare the first monitoring dataset with the corrected first monitoring indicator to determine the health monitoring status. In some embodiments, the specific implementation of step 403 can refer to the specific implementation of step 104 in the foregoing embodiments, the difference being that a second monitoring dataset and a second monitoring indicator are newly introduced in the process of analyzing and determining the health monitoring status. In some embodiments, the second monitoring indicator also corresponds to a corresponding prior experience base, which is not limited here.

[0035] In some embodiments, the wind turbine equipment covered by the second fiber optic sensing grid is the same as that covered by the first fiber optic sensing grid, meaning the coverage area of ​​the second fiber optic sensing grid is the same as that of the first fiber optic sensing grid. Since the coverage areas of the first and second fiber optic sensing grids are the same, the obtained first and second synchronous monitoring errors also exhibit a certain similarity, reflecting the same environmental interference factors. Therefore, based on the first and second synchronous monitoring errors, the environmental system monitoring error of the wind turbine equipment covered by the second fiber optic sensing grid can be obtained through a first preset neural network model. This environmental system monitoring error reflects the natural environmental influencing factors at the wind turbine equipment's location at the monitoring time, such as high temperature, strong winds, and ground vibration. In some embodiments, the first and / or second monitoring data can be corrected based on the environmental system monitoring error, and the health monitoring status can be determined by comparing the second monitoring dataset with the corrected second monitoring index, and / or simultaneously comparing the first monitoring dataset with the corrected first monitoring index; this is not limited here.

[0036] Figure 5This is a schematic diagram of a non-invasive fiber optic wind turbine health monitoring system according to an embodiment of this disclosure, which specifically includes: The deployment unit 501 is used to set up a non-invasive fiber optic sensing array at a preset location on the wind turbine equipment, wherein the fiber optic sensing array may include a fiber optic grating sensor array.

[0037] The data monitoring unit 502 is used to build a first fiber optic sensing grid based on a fiber optic grating sensor array, wherein the first fiber optic sensing grid covers multiple wind turbine devices, and is used to continuously monitor a first set of parameters of the covered wind turbine devices to generate a first monitoring dataset.

[0038] The error correction unit 503 is used to obtain the first synchronous monitoring error of the covered wind turbine equipment based on the first monitoring data corresponding to different wind turbine equipment in the first monitoring dataset, and to correct the first monitoring index of the wind turbine equipment based on the first synchronous monitoring error.

[0039] The health monitoring unit 504 is used to determine the health monitoring status of the wind turbine equipment by comparing it with the first monitoring dataset and the corrected first monitoring indicators.

[0040] It is understood that the functions performed by the deployment units 501 to the health monitoring units 504 are the same as the actions performed in the aforementioned steps 101 to 104, and will not be described in detail here.

[0041] In some embodiments, the fiber optic sensing array may further include a microelectromechanical system (MEMS) fiber optic sensor array. Correspondingly, in some embodiments, the data monitoring unit 502 may also be used to build a second fiber optic sensing grid based on the MEMS fiber optic sensor array, the second fiber optic sensing grid covering multiple wind turbine devices, for continuous monitoring of a second set of parameters of the covered wind turbine devices, generating a second monitoring dataset; the error correction unit 503 may also be used to obtain a second synchronous monitoring error of the covered wind turbine devices based on the second monitoring data corresponding to different wind turbine devices in the second monitoring dataset, and to correct the second monitoring index of the wind turbine devices based on the second synchronous monitoring error; the health monitoring unit 504 may also be used to compare the second monitoring dataset with the corrected second monitoring index, and / or synchronously compare the first monitoring dataset with the corrected first monitoring index, to determine the health monitoring status. Those skilled in the art can set the functional modules of the non-invasive fiber optic wind turbine health monitoring system according to actual needs, and no limitations are imposed here.

[0042] In summary, the technical solution provided in this disclosure enables the synchronous monitoring of multiple wind turbines deployed in the same area, including parameters such as load capacity, deformation, operating temperature, and vibration, through the setup of a fiber optic sensor grid. It also corrects for monitoring errors caused by environmental factors affecting the wind turbines in the same area, allowing for accurate monitoring of the wind turbines' health status and preventing false alarms. Furthermore, the fiber optic sensing equipment provided in this disclosure supports a non-embedded setup, facilitating easy deployment at desired locations on the wind turbines. It also allows for timely replacement of faulty fiber optic sensors, effectively ensuring continuous and accurate monitoring of the wind turbines' health, and thus has significant potential for widespread application.

[0043] The above description, in conjunction with specific preferred embodiments, provides a further detailed explanation of this disclosure and should not be construed as limiting the specific implementation of this disclosure to these descriptions. For those skilled in the art, various simple deductions or substitutions can be made without departing from the concept of this disclosure, and all such modifications and substitutions should be considered within the scope of protection of this disclosure.

Claims

1. A non-invasive method for monitoring the health of fiber optic wind turbines, characterized in that, include: A non-invasive fiber optic sensing array is installed at a predetermined location on the wind turbine equipment. The fiber optic sensing array includes a fiber optic grating sensor array. A first fiber optic sensing grid is constructed based on the fiber optic grating sensor array. The first fiber optic sensing grid covers multiple wind turbine devices and is used to continuously monitor a first set of parameters of the covered wind turbine devices to generate a first monitoring dataset. Based on the first monitoring data corresponding to different wind turbine equipment in the first monitoring dataset, the first synchronous monitoring error of the covered wind turbine equipment is obtained, and the first monitoring index of the wind turbine equipment is corrected based on the first synchronous monitoring error. By comparing the first monitoring dataset with the corrected first monitoring indicator, the health monitoring status of the wind turbine equipment is determined.

2. The method according to claim 1, characterized in that, The first set of parameters includes at least one or any combination of multiple of the monitoring point stress parameters, monitoring point temperature parameters, monitoring point deformation parameters, and monitoring point vibration parameters of the wind turbine equipment.

3. The method according to claim 1, characterized in that, The fiber optic sensing array includes a microelectromechanical system fiber optic sensor array. The method further includes: building a second fiber optic sensing grid based on the microelectromechanical system fiber optic sensor array, the second fiber optic sensing grid covering multiple wind turbine devices, for continuously monitoring a second set of parameters of the covered wind turbine devices, and generating a second monitoring dataset; Based on the second monitoring data corresponding to different wind turbine equipment in the second monitoring dataset, the second synchronous monitoring error of the covered wind turbine equipment is obtained, and the second monitoring index of the wind turbine equipment is corrected based on the second synchronous monitoring error; and The health monitoring status is determined by comparing the second monitoring dataset with the corrected second monitoring indicator, and / or simultaneously comparing the first monitoring dataset with the corrected first monitoring indicator.

4. The method according to claim 3, characterized in that, The second set of parameters includes at least one or any combination of multiple monitoring point vibration parameters, monitoring point noise parameters, and monitoring point air gap parameters.

5. The method according to claim 3, characterized in that, The wind turbine equipment covered by the second fiber optic sensing grid is the same as the wind turbine equipment covered by the first fiber optic sensing grid; The method further includes: Based on the first synchronous monitoring error and the second synchronous monitoring error, the environmental system monitoring error of the wind turbine equipment covered by the second optical fiber sensing grid is obtained through the first preset neural network model. The first monitoring data and / or the second monitoring data are corrected based on the monitoring error of the environmental system. The health monitoring status is determined by comparing the second monitoring dataset with the corrected second monitoring indicator, and / or simultaneously comparing the first monitoring dataset with the corrected first monitoring indicator.

6. The method according to claim 1, characterized in that, The step of obtaining the first synchronous monitoring error of the covered wind turbine equipment based on the first monitoring data corresponding to different wind turbine equipment in the first monitoring dataset includes the following steps: Obtain the deviation between the first monitoring data and the first monitoring index for each wind turbine device covered by the first optical fiber sensing grid; Based on the aforementioned deviation, the system monitoring deviation and / or environmental monitoring deviation of the wind turbine equipment covered by the first fiber optic sensing grid are obtained based on the second preset neural network model. The first synchronous monitoring error is generated based on preset weighting coefficients and the system monitoring deviation and / or environmental monitoring deviation.

7. The method according to claim 1, characterized in that, The process of determining the health monitoring status of the wind turbine equipment by comparing the first monitoring dataset with the corrected first monitoring indicator includes the following steps: Obtain a set of deviation monitoring data that deviates from the corrected first monitoring indicator; Based on a preset prior experience library, a prior deviation data set with the highest similarity to the deviation monitoring data set is obtained, and the equipment status corresponding to the prior deviation data set is used as the health monitoring status of the wind turbine equipment. The prior experience base is obtained based on the historical monitoring data and / or prior monitoring knowledge of the wind turbine equipment corresponding to the first optical fiber sensing grid.

8. The method according to claim 7, characterized in that, When the similarity between the prior deviation data set with the highest similarity and the deviation monitoring data set is lower than a first preset threshold, a corresponding on-site monitoring work order is generated based on the deviation monitoring data set. Based on the feedback results of the on-site monitoring work orders, the health monitoring status of the wind turbine equipment is obtained, and the health monitoring status is used as update data to update the prior experience base.

9. A non-invasive fiber optic wind turbine health monitoring system, characterized in that, include: A deployment unit is used to install a non-invasive fiber optic sensing array at a preset location on the wind turbine equipment. The fiber optic sensing array includes a fiber optic grating sensor array. The data monitoring unit is used to build a first fiber optic sensing grid based on the fiber optic grating sensor array, the first fiber optic sensing grid covering multiple wind turbine devices, and to continuously monitor a first set of parameters of the covered wind turbine devices to generate a first monitoring dataset. An error correction unit is used to obtain the first synchronous monitoring error of the covered wind turbine equipment based on the first monitoring data corresponding to different wind turbine equipment in the first monitoring dataset, and to correct the first monitoring index of the wind turbine equipment based on the first synchronous monitoring error. A health monitoring unit is used to determine the health monitoring status of the wind turbine equipment by comparing it with the first monitoring dataset and the corrected first monitoring indicators.

10. The system according to claim 9, characterized in that, The fiber optic sensing array includes a microelectromechanical system fiber optic sensor array. The data monitoring unit is also used to build a second fiber optic sensing grid based on the microelectromechanical system fiber optic sensor array. The second fiber optic sensing grid covers multiple wind turbine devices and is used to continuously monitor the second set of parameters of the covered wind turbine devices to generate a second monitoring dataset. The error correction unit is further configured to obtain the second synchronous monitoring error of the covered wind turbine equipment based on the second monitoring data corresponding to different wind turbine equipment in the second monitoring dataset, and to correct the second monitoring index of the wind turbine equipment based on the second synchronous monitoring error; as well as The health monitoring unit is also used to compare the second monitoring dataset with the corrected second monitoring indicator, and / or simultaneously compare the first monitoring dataset with the corrected first monitoring indicator to determine the health monitoring status.

Images