Active vibration avoidance method and system for yaw system based on air pressure gradient sensing

Abstract

The present invention discloses a method and system for actively avoiding vibrations in a yaw system based on air pressure gradient sensing, which relates to the field of wind power control technology. The method and system include: performing distributed continuous air pressure monitoring on the yaw system through a distributed air pressure sensor to obtain distributed air pressure gradient data; performing data conversion on first air pressure gradient data in the distributed air pressure gradient data to obtain a first vibration signal; performing feature analysis on a target vibration signal obtained by integrating the first vibration signal to obtain a target vibration avoidance strategy; and activating a vibration avoidance mechanism to actively avoid vibrations in accordance with the target vibration avoidance strategy. The present invention solves the technical problem that the prior art cannot effectively identify vibrations of the yaw system caused by wind-induced disturbances. By constructing a distributed air pressure sensing and vibration signal analysis mechanism, an active vibration avoidance strategy is generated and executed, achieving the technical effect of improving the vibration recognition accuracy and active vibration avoidance control capability of the yaw system.

Description

Technical Field

[0001] The present invention relates to the field of wind power control technology, and in particular to a method and system for actively avoiding vibration of a yaw system based on air pressure gradient sensing. Background Art

[0002] During wind turbine operation, the yaw system must continuously adjust the nacelle's orientation based on changing wind direction to ensure the blades face the incoming wind and capture maximum wind energy. However, under conditions of sudden changes in wind speed or localized airflow disturbances, the yaw system is susceptible to irregular wind loads, resulting in periodic or sudden vibrations. Traditional monitoring methods rely on structural stress or angular velocity sensors, which struggle to detect early changes in airflow disturbances. This results in a delayed response to the yaw system's vibration state, making accurate identification and effective control difficult. Summary of the Invention

[0003] The present application provides a method and system for active vibration avoidance of a yaw system based on air pressure gradient sensing, which is used to solve the technical problem that the existing technology cannot effectively identify the vibration of the yaw system caused by wind disturbances.

[0004] In view of the above problems, the present application provides a method and system for active vibration avoidance of a yaw system based on air pressure gradient sensing.

[0005] In a first aspect of the present application, a method for active vibration avoidance of a yaw system based on air pressure gradient sensing is provided, the method comprising:

[0006] Distributed continuous air pressure monitoring is performed on the yaw system through distributed air pressure sensors to obtain distributed air pressure gradient data; data conversion is performed on the first air pressure gradient data in the distributed air pressure gradient data to obtain a first vibration signal; feature analysis is performed on the target vibration signal obtained by fusing the first vibration signal to obtain a target vibration avoidance strategy; and the vibration avoidance mechanism is activated to actively execute the target vibration avoidance strategy.

[0007] A second aspect of the present application provides an active vibration avoidance system for a yaw system based on air pressure gradient sensing, the system comprising:

[0008] A monitoring module is used to perform distributed continuous air pressure monitoring on the yaw system through a distributed air pressure sensor to obtain distributed air pressure gradient data; a data conversion module is used to perform data conversion on the first air pressure gradient data in the distributed air pressure gradient data to obtain a first vibration signal; a feature analysis module is used to perform feature analysis on the target vibration signal obtained by fusing the first vibration signal to obtain a target vibration avoidance strategy; and a vibration avoidance module is used to activate the vibration avoidance mechanism to actively execute the target vibration avoidance strategy.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] This application uses distributed pressure sensors to perform distributed continuous pressure monitoring on the yaw system to obtain distributed pressure gradient data; performs data conversion on the first pressure gradient data in the distributed pressure gradient data to obtain a first vibration signal; performs feature analysis on the target vibration signal obtained by integrating the first vibration signal to obtain a target vibration avoidance strategy; and activates a vibration avoidance mechanism to actively implement the target vibration avoidance strategy. This invention solves the technical problem that existing technologies cannot effectively identify yaw system vibrations caused by wind-induced disturbances. By constructing a distributed pressure sensing and vibration signal analysis mechanism, it generates and executes an active vibration avoidance strategy, achieving the technical effect of improving the yaw system vibration identification accuracy and active vibration avoidance control capabilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0012] Figure 1 A schematic flow chart of a method for active vibration avoidance of a yaw system based on air pressure gradient sensing provided in an embodiment of the present application;

[0013] Figure 2 Schematic diagram of the structure of the active vibration avoidance system of the yaw system based on pressure gradient sensing provided in an embodiment of the present application.

[0014] Description of reference numerals: monitoring module 11 , data conversion module 12 , feature analysis module 13 , vibration avoidance module 14 . DETAILED DESCRIPTION

[0015] This application provides a method and system for active vibration avoidance of the yaw system based on air pressure gradient sensing, aiming to solve the technical problem that the existing technology cannot effectively identify the vibration of the yaw system caused by wind disturbances. By constructing a distributed air pressure sensing and vibration signal analysis mechanism, an active vibration avoidance strategy is generated and executed, thereby achieving the technical effect of improving the vibration identification accuracy and active vibration avoidance control capability of the yaw system.

[0016] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only some of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0017] It should be noted that any variations of the terms "include" and "have" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products or devices.

[0018] Example 1, as Figure 1 As shown, the present application provides a method for active vibration avoidance of a yaw system based on air pressure gradient sensing, the method comprising:

[0019] Step S100: performing distributed continuous air pressure monitoring on the yaw system through distributed air pressure sensors to obtain distributed air pressure gradient data.

[0020] In this embodiment, a yaw system key component set is first assembled, identifying key structural areas such as the nacelle tail, blade roots, and tower top. Distributed pressure sensors are then deployed at these key locations to enable continuous data collection from multiple points in the yaw system. During operation, the distributed pressure sensors continuously monitor the yaw system's pressure, generating distributed pressure gradient data.

[0021] Furthermore, in the method provided in the embodiment of the application, distributed continuous air pressure monitoring of the yaw system is performed by using a distributed air pressure sensor to obtain distributed air pressure gradient data, and the method further includes:

[0022] A set of key parts of the yaw system is formed, and the distributed air pressure sensors are respectively deployed in the key part sets; distributed continuous air pressure monitoring of the yaw system is performed by the distributed air pressure sensors to obtain the distributed air pressure gradient data; wherein the key part set includes at least the tail of the nacelle, the root of the blade and the top of the tower.

[0023] In this embodiment, based on the stress characteristics of the yaw system under wind-induced loads, sensitive areas of the structural vibration response are pre-selected as monitoring points to establish a key location set. This key location set includes at least the nacelle aft (an area prone to turbulence after windflow bypasses it), the blade root (the connection point that receives the blade rotational torque and transmits it to the main shaft), and the tower top (the location where the overall structural vibration response is concentrated), comprehensively covering the main areas of wind pressure disturbance. Subsequently, using a fixed-point installation method, multiple distributed air pressure sensors are deployed at each of these key locations, forming a spatially distributed sensing array.

[0024] During operation, each distributed pressure sensor continuously collects real-time pressure data at its location with a unified sampling cycle, forming a distributed continuous pressure monitoring mechanism for the yaw system. After time-synchronizing the collected multi-point pressure data, a pressure differential calculation method is used to perform spatial differential calculations on the pressure values ​​between any two key locations, constructing the pressure gradient between each pair of monitoring points. Ultimately, by integrating the calculation results from all node pairs, distributed pressure gradient data is generated, reflecting the intensity and direction of wind pressure disturbances.

[0025] Step S200: performing data conversion on first pressure gradient data in the distributed pressure gradient data to obtain a first vibration signal.

[0026] In this embodiment, first, a first pressure gradient data set is randomly selected from the distributed pressure gradient data, and a corresponding first pressure time series is constructed based on the first pressure gradient data. Then, any adjacent pressure group is extracted from the first pressure time series, and the corresponding arbitrary pressure amplitude is calculated. Finally, a first vibration signal is generated based on the correspondence between the arbitrary pressure amplitude and the arbitrary time zone.

[0027] Furthermore, in the method provided in the embodiment of the application, performing data conversion on the first pressure gradient data in the distributed pressure gradient data to obtain the first vibration signal further includes:

[0028] A first air pressure time series is obtained based on the first air pressure gradient data; any adjacent air pressure groups in the first air pressure time series are extracted, and any air pressure amplitudes of the any adjacent air pressure groups are calculated; and the first vibration signal is formed based on the correspondence between the any air pressure amplitudes and any time zones.

[0029] In this embodiment, a time series reconstruction method is first used to sort and align the first pressure gradient data according to their sampling time sequence, thereby constructing a first pressure time series that reflects the continuous changes in the pressure gradient data within the monitoring period. Subsequently, a sliding window method is used to extract any adjacent pressure groups within the first pressure time series. Specifically, pressure data pairs of two adjacent sampling points are extracted at fixed time intervals, and their numerical differences are calculated using a difference calculation method to obtain the arbitrary pressure amplitudes for each group of adjacent pressure groups.

[0030] Then, combined with the time segment mapping rule, each of the above pressure amplitudes is mapped to a fixed-length time segment according to its corresponding sampling timestamp, establishing an association between the amplitude and the time segment. This time segment mapping rule organizes the pressure amplitudes into non-overlapping time windows, ensuring a structured representation of the amplitude sequence in the time domain, thereby generating an amplitude-time zone mapping relationship table.

[0031] Finally, based on the established mapping relationship, the interval reconstruction method is adopted to integrate the air pressure amplitudes of each segment in sequence according to the time segment order, and reconstruct the first vibration signal with time continuity and disturbance feature expression ability.

[0032] Furthermore, in the method provided in the embodiment of the application, before performing feature analysis on the target vibration signal obtained by fusing the first vibration signal to obtain the target vibration avoidance strategy, the method further includes:

[0033] The predetermined weight distribution of the key part set is read; and the first vibration signal is weightedly fused in combination with the predetermined weight distribution to obtain the target vibration signal.

[0034] In an embodiment of the present application, a parameter configuration reading method is first used to extract predetermined weight distribution parameters corresponding to key monitoring parts from a preset configuration. The parameters are pre-set by technical experts, and each key part, such as the tail of the cabin, the root of the blade, and the top of the tower, corresponds to a weight coefficient with a fixed value.

[0035] The first vibration signals from each key location are then time-aligned based on a unified timeline. Combined with the pre-determined weights, a weighted superposition method is used for fusion calculation. Specifically, at each sampling moment, the instantaneous amplitude of each first vibration signal is multiplied by its corresponding weight coefficient and summed to form a new amplitude point. This method is repeated throughout the entire sampling period, constructing a vibration response sequence with continuous time characteristics. Through this weighted fusion process, the target vibration signal is ultimately obtained.

[0036] Step S300: performing feature analysis on a target vibration signal obtained by fusing the first vibration signal to obtain a target vibration avoidance strategy.

[0037] In this embodiment, the target vibration signal, obtained by fusing the first vibration signal, is first subjected to feature analysis. This involves collecting its time and frequency domain features, and constructing a signal feature set based on these features. This signal feature set is then used as a traversal constraint to filter the vibration avoidance database and obtain a target vibration avoidance data set that matches the feature set. A vibration suppression effectiveness evaluation plan is then introduced, and an optimization analysis is performed on the target vibration avoidance data set to determine the optimal vibration avoidance strategy. Finally, based on the optimal vibration avoidance strategy, a corresponding target vibration avoidance strategy is generated.

[0038] Furthermore, in the method provided in the embodiment of the application, feature analysis is performed on the target vibration signal obtained by fusing the first vibration signal to obtain a target vibration avoidance strategy, and the method further includes:

[0039] The time domain features of the target vibration signal are collected; the features of the target vibration spectrum obtained by converting the target vibration signal are collected to obtain the frequency domain features; a signal feature set is formed based on the time domain features and the frequency domain features, and the signal feature set is used as a traversal constraint to traverse and filter the vibration avoidance database to obtain a target vibration avoidance data group; a vibration suppression effect evaluation plan is introduced to perform optimization analysis on the target vibration avoidance data group to obtain an optimal vibration avoidance strategy; and the target vibration avoidance strategy is determined based on the optimal vibration avoidance strategy.

[0040] In the present embodiment, a statistical feature extraction method is first used to process the target vibration signal, extracting its time series response characteristics, including maximum amplitude, root mean square value, crest factor, and variance, thereby obtaining time domain features. The target vibration signal is then converted from the time domain to the frequency domain using a fast Fourier transform method. Its spectral structure is analyzed, and frequency distribution characteristics such as dominant frequency, frequency amplitude, spectral center of gravity, and bandwidth are extracted to obtain frequency domain features.

[0041] Next, a feature vector concatenation method is used to sequentially combine the extracted time-domain and frequency-domain features to construct a unified multidimensional vector, resulting in a signal feature set. The signal feature set is then used as a traversal constraint to traverse and filter the vibration avoidance database. The vibration avoidance database is a pre-constructed dataset containing multiple sets of historical vibration features and corresponding vibration avoidance strategies. During this traversal and filtering process, a similarity calculation method is used to extract the first vibration avoidance data set from the database. The Euclidean distance method is then used to calculate the numerical similarity between the first feature set in this data set and the current signal feature set, which serves as the first similarity. If the first similarity is less than the set similarity limit (i.e., the similarity is sufficiently high), the first vibration avoidance data set is added to the target vibration avoidance data set. This method traverses the entire database, ultimately yielding the target vibration avoidance data set.

[0042] After obtaining the target vibration avoidance data set, a vibration suppression effectiveness evaluation plan is introduced to perform an optimization analysis on the target vibration avoidance data set. Specifically, a single-group scoring method is used to evaluate the first data set within the target vibration avoidance data set. This data set contains the first offset vibration energy (which measures the degree to which vibration energy is absorbed or neutralized) and the first energy decay rate (which reflects the rate of decrease in vibration amplitude over time). Based on these two indicators, the first vibration suppression coefficient for this data set is calculated. Next, using the vibration suppression coefficient as the optimization target, the strategy with the largest vibration suppression coefficient is selected from all target vibration avoidance data sets to optimize and determine the optimal vibration avoidance strategy.

[0043] Finally, based on the control parameters contained in the optimal vibration avoidance strategy, the parameter analysis method is used to extract the execution content, including the control mode, adjustment amplitude and response time, to determine the target vibration avoidance strategy for execution.

[0044] Furthermore, in the method provided in the embodiment of the application, a signal feature set is formed based on the time domain features and the frequency domain features, and the signal feature set is used as a traversal constraint to traverse and filter the vibration avoidance database to obtain a target vibration avoidance data set, further comprising:

[0045] Extracting a first vibration isolation data group from the vibration isolation database; obtaining a first similarity between the signal feature set and a first feature set in the first vibration isolation data group; and adding the first vibration isolation data group to the target vibration isolation data group if the first similarity reaches a predetermined similarity limit.

[0046] In the embodiment of the present application, a data reading method is first used to select any set of vibration isolation data from the vibration isolation database as a first vibration isolation data set. The first vibration isolation data set includes a first feature set for describing the vibration state of the set, and the first feature set is composed of time domain features and frequency domain features obtained from historical extraction.

[0047] After obtaining the first vibration isolation data set, the Euclidean distance method is used to calculate the similarity between the signal feature set generated by the current target vibration signal and the first feature set in the first vibration isolation data set. Specifically, the two feature vectors are mapped one-to-one by dimension, and the difference is calculated item by item. The difference is then squared, summed, and squared to obtain the first similarity between the two in the feature space.

[0048] The calculated first similarity is then compared with a similarity limit preset by technical experts. If the first similarity is less than or equal to the similarity limit, it indicates that the vibration isolation data set has sufficient feature consistency with the current vibration state, and the first vibration isolation data set is added to the target vibration isolation data set.

[0049] By repeating the above process, each set of data in the vibration avoidance database is read, similarity is calculated, limit judgment and strategy screening are performed in turn, until the entire vibration avoidance database is traversed, and finally the construction of the target vibration avoidance data group is completed.

[0050] Furthermore, in the method provided in the embodiment of the application, after forming a signal feature set based on the time domain features and the frequency domain features, the method further includes:

[0051] The target vibration signal is segmented to obtain a segmentation result; an arbitrary signal component in the segmentation result is extracted, and an information ratio of the arbitrary signal component to the target vibration signal is obtained, which is recorded as an arbitrary ratio; with the maximum arbitrary ratio as the goal, a target signal component is screened and obtained; a target feature set of the target signal component is obtained, and the target feature set is added to the signal feature set.

[0052] In an embodiment of the present application, a fixed window segmentation method is first used to segment the target vibration signal. According to a pre-set time window length and sliding step size, a traversal operation is performed on the target vibration signal to divide the complete signal into multiple continuous, non-overlapping or partially overlapping signal components, thereby obtaining a segmentation result.

[0053] After obtaining the segmentation results, each signal component is analyzed using a signal energy ratio calculation method. This method quantifies the intensity of the disturbance information carried by each component by calculating the ratio of the energy of the signal component (usually the sum of the squared amplitudes) to the overall energy of the target vibration signal. Specifically, an energy calculation is performed on each signal component, recorded as the local energy value, and the same calculation is performed on the entire target vibration signal to obtain the total energy value. The information content ratio of each signal component is then calculated, that is, the ratio of the local energy value to the total energy value, recorded as the arbitrary ratio.

[0054] Then, the maximum value screening method is used to select the signal component corresponding to the largest value among all information ratios as the most representative target signal component in the current state.

[0055] After selecting the target signal component, feature extraction methods are used to analyze it in the time and frequency domains. Specifically, statistical parameter calculations (such as maximum value, root mean square, and variance) are used to obtain time domain features, while fast Fourier transforms are used to extract frequency domain features such as dominant frequency, frequency amplitude, and spectral distribution. Together, these features form the target feature set corresponding to that component.

[0056] Finally, the feature splicing method is used to merge the obtained target feature set into the original signal feature set.

[0057] Furthermore, in the method provided in the embodiment of the application, a vibration suppression effect evaluation plan is introduced to perform optimization analysis on the target vibration avoidance data set to obtain the optimal vibration avoidance strategy, and the method further includes:

[0058] Obtain a first data group in the target vibration avoidance data group; evaluate and analyze the first data group according to the vibration suppression effect evaluation plan to obtain a first vibration suppression coefficient; and optimize to obtain the optimal vibration avoidance strategy with the goal of maximizing the first vibration suppression coefficient; wherein the first data group includes at least a first offsetting vibration energy and a first energy attenuation rate.

[0059] In this embodiment, a sequential reading method is first used to sequentially extract a set of records from the target vibration isolation data set as a first data set. The first data set includes vibration isolation control parameters under historical vibration conditions and corresponding effect evaluation indicators, including at least a first offset vibration energy and a first energy attenuation rate.

[0060] After obtaining the first data group, its effect is analyzed according to the built-in vibration suppression effect evaluation plan. Specifically, the first offset vibration energy is first normalized, and a normalized interval is constructed based on the maximum and minimum values ​​in all data groups in the current target vibration avoidance data group, and the value is compressed to between 0 and 1. The first energy attenuation rate is then subjected to the same normalization process to make it comparable under the same numerical scale. For example, if the offset vibration energy in the first data group is 2400 units, which is between the maximum value of 3000 units and the minimum value of 1500 units, its normalized value is 0.6; if the energy attenuation rate is 60%, which is between the maximum value of 80% and the minimum value of 40%, the normalized value is 0.5. After completing the normalization process, the weighted summation method is used to fuse the first offset vibration energy and the first energy attenuation rate to form the first vibration suppression coefficient used to evaluate the effectiveness of the current strategy. The first vibration suppression coefficient is used to comprehensively reflect the vibration suppression performance of the first data group, wherein the weights of the first offset vibration energy and the first energy attenuation rate are preset by technical experts according to application requirements (e.g., the offset vibration energy weight is 0.6, and the energy attenuation rate weight is 0.4).

[0061] Using this first vibration suppression coefficient as the performance target, the system then iterates through the remaining data sets within the target vibration avoidance data set, performing the same normalization and vibration suppression coefficient calculation on each data set. Using a maximum value comparison method, the data set with the highest current vibration suppression coefficient is continuously updated. After the traversal is complete, the control parameter set with the highest vibration suppression coefficient is ultimately selected as the optimal vibration avoidance strategy for the current vibration state.

[0062] Step S400: activating the vibration isolation mechanism to actively implement the target vibration isolation strategy.

[0063] In an embodiment of the present application, when actively implementing a target vibration avoidance strategy, key control parameters, namely speed and braking force, are first extracted from the optimal vibration avoidance strategy. The vibration avoidance mechanism is then activated to actively implement the target vibration avoidance strategy. Specifically, the extracted speed command is transmitted to the yaw drive motor, causing it to adjust the yaw motion speed according to the strategy requirements. Simultaneously, the braking force parameter is transmitted to the yaw brake, causing it to apply the specified damping at the corresponding moment. In this way, the vibration avoidance mechanism achieves dynamic response and active control of the target vibration avoidance strategy, thereby suppressing vibration of the yaw system under wind-induced disturbances.

[0064] Furthermore, in the method provided in the embodiment of the application, activating the vibration isolation mechanism to actively implement the target vibration isolation strategy further includes:

[0065] Extracting the rotational speed and braking force in the optimal vibration avoidance strategy; controlling the rotational speed and braking force through the vibration avoidance mechanism to achieve active vibration avoidance; wherein, the yaw drive motor in the vibration avoidance mechanism controls the rotational speed, and the yaw brake in the vibration avoidance mechanism controls the braking force.

[0066] In an embodiment of the present application, the corresponding control parameters are first extracted from the optimal vibration avoidance strategy, including the rotational speed for adjusting the yaw response and the braking force for applying damping. The vibration avoidance mechanism is then activated and the extracted parameters are sent to the corresponding execution unit. The vibration avoidance mechanism includes two components, a yaw drive motor and a yaw brake, which respectively undertake the execution control tasks of the rotational speed and the braking force. Specifically, the yaw drive motor adjusts the movement speed of the yaw structure according to the rotational speed parameter to achieve dynamic adjustment of the vibration response process; the yaw brake applies mechanical resistance to the key parts of the structure according to the braking force parameter, thereby suppressing the abnormal amplitude caused by the disturbance. Through the coordinated operation of the yaw drive motor and the yaw brake, the execution of the target vibration avoidance strategy is completed, and finally real-time intervention and active vibration avoidance control of the structural vibration are achieved.

[0067] In the embodiments of the present application, in summary, the embodiments of the present application have at least the following technical effects:

[0068] This application uses distributed pressure sensors to perform distributed continuous pressure monitoring on the yaw system to obtain distributed pressure gradient data; performs data conversion on the first pressure gradient data in the distributed pressure gradient data to obtain a first vibration signal; performs feature analysis on the target vibration signal obtained by integrating the first vibration signal to obtain a target vibration avoidance strategy; and activates a vibration avoidance mechanism to actively implement the target vibration avoidance strategy. This invention solves the technical problem that existing technologies cannot effectively identify yaw system vibrations caused by wind-induced disturbances. By constructing a distributed pressure sensing and vibration signal analysis mechanism, it generates and executes an active vibration avoidance strategy, achieving the technical effect of improving the yaw system vibration identification accuracy and active vibration avoidance control capabilities.

[0069] The second embodiment is based on the same inventive concept as the method for active vibration avoidance of the yaw system based on pressure gradient sensing in the above embodiment. Figure 2 As shown, the present application provides an active vibration isolation system for a yaw system based on air pressure gradient sensing. The system and method embodiments in the present application are based on the same inventive concept. The system includes:

[0070] The monitoring module 11 is used to perform distributed continuous air pressure monitoring on the yaw system through a distributed air pressure sensor to obtain distributed air pressure gradient data; the data conversion module 12 is used to perform data conversion on the first air pressure gradient data in the distributed air pressure gradient data to obtain a first vibration signal; the feature analysis module 13 is used to perform feature analysis on the target vibration signal obtained by fusing the first vibration signal to obtain a target vibration avoidance strategy; the vibration avoidance module 14 is used to activate the vibration avoidance mechanism to actively execute the target vibration avoidance strategy.

[0071] Furthermore, the system is also used to implement the following functions:

[0072] A set of key parts of the yaw system is formed, and the distributed air pressure sensors are respectively deployed in the key part sets; distributed continuous air pressure monitoring of the yaw system is performed by the distributed air pressure sensors to obtain the distributed air pressure gradient data; wherein the key part set includes at least the tail of the nacelle, the root of the blade and the top of the tower.

[0073] Furthermore, the system is also used to implement the following functions:

[0074] A first air pressure time series is obtained based on the first air pressure gradient data; any adjacent air pressure groups in the first air pressure time series are extracted, and any air pressure amplitudes of the any adjacent air pressure groups are calculated; and the first vibration signal is formed based on the correspondence between the any air pressure amplitudes and any time zones.

[0075] Furthermore, the system is also used to implement the following functions:

[0076] The predetermined weight distribution of the key part set is read; and the first vibration signal is weightedly fused in combination with the predetermined weight distribution to obtain the target vibration signal.

[0077] Furthermore, the system is also used to implement the following functions:

[0078] The time domain features of the target vibration signal are collected; the features of the target vibration spectrum obtained by converting the target vibration signal are collected to obtain the frequency domain features; a signal feature set is formed based on the time domain features and the frequency domain features, and the signal feature set is used as a traversal constraint to traverse and filter the vibration avoidance database to obtain a target vibration avoidance data group; a vibration suppression effect evaluation plan is introduced to perform optimization analysis on the target vibration avoidance data group to obtain an optimal vibration avoidance strategy; and the target vibration avoidance strategy is determined based on the optimal vibration avoidance strategy.

[0079] Furthermore, the system is also used to implement the following functions:

[0080] Extracting a first vibration isolation data group from the vibration isolation database; obtaining a first similarity between the signal feature set and a first feature set in the first vibration isolation data group; and adding the first vibration isolation data group to the target vibration isolation data group if the first similarity reaches a predetermined similarity limit.

[0081] Furthermore, the system is also used to implement the following functions:

[0082] The target vibration signal is segmented to obtain a segmentation result; an arbitrary signal component in the segmentation result is extracted, and an information ratio of the arbitrary signal component to the target vibration signal is obtained, which is recorded as an arbitrary ratio; with the maximum arbitrary ratio as the goal, a target signal component is screened and obtained; a target feature set of the target signal component is obtained, and the target feature set is added to the signal feature set.

[0083] Furthermore, the system is also used to implement the following functions:

[0084] Obtain a first data group in the target vibration avoidance data group; evaluate and analyze the first data group according to the vibration suppression effect evaluation plan to obtain a first vibration suppression coefficient; and optimize to obtain the optimal vibration avoidance strategy with the goal of maximizing the first vibration suppression coefficient; wherein the first data group includes at least a first offsetting vibration energy and a first energy attenuation rate.

[0085] Furthermore, the system is also used to implement the following functions:

[0086] Extracting the rotational speed and braking force in the optimal vibration avoidance strategy; controlling the rotational speed and braking force through the vibration avoidance mechanism to achieve active vibration avoidance; wherein, the yaw drive motor in the vibration avoidance mechanism controls the rotational speed, and the yaw brake in the vibration avoidance mechanism controls the braking force.

[0087] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0088] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

[0089] This specification and drawings are merely illustrative of the present application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Obviously, those skilled in the art may make various modifications and variations to this application without departing from the scope of this application. Thus, this application is intended to include such modifications and variations as fall within the scope of this application and its equivalents.

Claims

1. The active vibration avoidance method of the yaw system based on air pressure gradient sensing is characterized by: include: Distributed continuous air pressure monitoring of the yaw system is performed through distributed air pressure sensors to obtain distributed air pressure gradient data; performing data conversion on first pressure gradient data in the distributed pressure gradient data to obtain a first vibration signal; Performing feature analysis on a target vibration signal obtained by fusing the first vibration signal to obtain a target vibration avoidance strategy; The vibration isolation mechanism is activated to actively implement the target vibration isolation strategy.

2. The method for active vibration avoidance of a yaw system based on air pressure gradient sensing according to claim 1, characterized in that: The distributed pressure sensor is used to monitor the yaw system's distributed and continuous pressure to obtain distributed pressure gradient data, including: Assembling a set of key parts of the yaw system, and respectively arranging the distributed air pressure sensors in the set of key parts; Performing distributed continuous air pressure monitoring on the yaw system by using the distributed air pressure sensor to obtain the distributed air pressure gradient data; The key parts set includes at least the tail of the nacelle, the root of the blade and the top of the tower.

3. The active vibration avoidance method for a yaw system based on air pressure gradient sensing according to claim 1, characterized in that: Performing data conversion on first pressure gradient data in the distributed pressure gradient data to obtain a first vibration signal includes: obtaining a first air pressure time series based on the first air pressure gradient data; Extracting any adjacent air pressure group in the first air pressure time series, and calculating any air pressure amplitude of the any adjacent air pressure group; The first vibration signal is generated based on the correspondence between the arbitrary air pressure amplitude and the arbitrary time zone.

4. The method for active vibration avoidance of a yaw system based on air pressure gradient sensing as claimed in claim 2, characterized in that: Before performing feature analysis on the target vibration signal obtained by fusing the first vibration signal to obtain a target vibration avoidance strategy, the method includes: Reading a predetermined weight distribution of the key part set; The first vibration signal is weightedly fused in combination with the predetermined weight distribution to obtain the target vibration signal.

5. The method for active vibration avoidance of a yaw system based on air pressure gradient sensing according to claim 1, characterized in that: Performing feature analysis on a target vibration signal obtained by fusing the first vibration signal to obtain a target vibration avoidance strategy, including: Collecting and obtaining the time domain characteristics of the target vibration signal; collecting features of a target vibration spectrum obtained by converting the target vibration signal to obtain frequency domain features; A signal feature set is formed based on the time domain features and the frequency domain features, and the signal feature set is used as a traversal constraint to traverse and filter the vibration avoidance database to obtain a target vibration avoidance data set; Introducing a vibration suppression effect evaluation plan to perform optimization analysis on the target vibration avoidance data set to obtain an optimal vibration avoidance strategy; The target vibration avoidance strategy is determined according to the optimal vibration avoidance strategy.

6. The method for active vibration avoidance of a yaw system based on air pressure gradient sensing as claimed in claim 5, characterized in that: A signal feature set is formed based on the time domain features and the frequency domain features, and the signal feature set is used as a traversal constraint to traverse and filter the vibration avoidance database to obtain a target vibration avoidance data set, including: extracting a first vibration isolation data group from the vibration isolation database; Obtaining a first similarity between the signal feature set and a first feature set in the first vibration isolation data set; If the first similarity reaches a predetermined similarity limit, the first vibration isolation data set is added to the target vibration isolation data set.

7. The method for active vibration avoidance of a yaw system based on air pressure gradient sensing as claimed in claim 5, characterized in that: After forming a signal feature set based on the time domain features and the frequency domain features, the method further includes: Segmenting the target vibration signal to obtain a segmentation result; Extracting an arbitrary signal component from the segmentation result, and obtaining an information ratio between the arbitrary signal component and the target vibration signal, which is recorded as an arbitrary ratio; Taking the maximum of the arbitrary ratio as the goal, screening to obtain the target signal component; A target feature set of the target signal component is obtained, and the target feature set is added to the signal feature set.

8. The method for active vibration avoidance of a yaw system based on air pressure gradient sensing as claimed in claim 5, characterized in that: The vibration suppression effect evaluation plan is introduced to perform optimization analysis on the target vibration avoidance data set to obtain the optimal vibration avoidance strategy, including: Acquiring a first data group in the target vibration isolation data group; evaluating and analyzing the first data group according to the vibration suppression effect evaluation plan to obtain a first vibration suppression coefficient; Taking the first vibration suppression coefficient as the maximum as the goal, optimizing and obtaining the optimal vibration avoidance strategy; The first data group includes at least a first offset vibration energy and a first energy attenuation rate.

9. The method for active vibration avoidance of a yaw system based on air pressure gradient sensing as claimed in claim 8, characterized in that: Activating the vibration avoidance mechanism to actively execute the target vibration avoidance strategy includes: Extracting the rotation speed and braking force in the optimal vibration avoidance strategy; The rotation speed and braking force are controlled by the vibration-isolating mechanism to achieve active vibration-isolating; Wherein, the yaw drive motor in the vibration isolation mechanism controls the rotation speed, and the yaw brake in the vibration isolation mechanism controls the braking force.

10. The active vibration avoidance system of the yaw system based on air pressure gradient sensing is characterized by: The system is used to perform the active vibration avoidance method for a yaw system based on air pressure gradient sensing as described in any one of claims 1 to 9, and the system includes: A monitoring module is used to perform distributed continuous air pressure monitoring on the yaw system through distributed air pressure sensors to obtain distributed air pressure gradient data; a data conversion module, configured to perform data conversion on first pressure gradient data in the distributed pressure gradient data to obtain a first vibration signal; A feature analysis module, configured to perform feature analysis on a target vibration signal obtained by fusing the first vibration signal to obtain a target vibration avoidance strategy; The vibration avoidance module is used to activate the vibration avoidance mechanism to actively implement the target vibration avoidance strategy.

Images