Fan bearing pre-tightening force adjusting method, device and equipment and storage medium

Abstract

The invention discloses a draught fan bearing pre-tightening force adjusting method, device and equipment and a storage medium, and relates to the technical field of wind power. The method comprises the steps that current operation parameters of a wind turbine generator are collected and preprocessed, and draught fan working condition data are obtained; determining a current bearing wear state of a fan bearing of the wind turbine generator according to the fan working condition data; the current bearing abrasion state and the fan working condition data are input into a preset bearing adjusting model, the target pre-tightening force of the fan bearing is obtained, and the preset bearing adjusting model is obtained by training a neural network model through a mapping database; the mapping database comprises a mapping relationship between the bearing wear state of the fan bearing and the optimal pre-tightening force under various working conditions; and adjusting the fan bearing based on the target pre-tightening force. Compared with an existing mode depending on fixed pre-tightening force or regular shutdown inspection, the method can respond to complex working conditions of the fan bearing in real time, and the service life of the fan bearing is prolonged.

Description

Technical Field

[0001] This application relates to the field of wind power technology, and in particular to a method, device, equipment and storage medium for adjusting the preload of wind turbine bearings. Background Technology

[0002] As a key component of wind turbine units, wind turbine bearings are subjected to highly dynamic loads and complex working environments. In the operation of wind turbine units, in order to ensure that the main shaft bearings can withstand highly dynamic wind loads and complex torques, it is generally necessary to apply and precisely set the initial preload during the assembly stage.

[0003] During wind turbine operation, when faced with actual conditions such as fluctuating wind speed and alternating loads, wind speed and load are dynamic parameters that change continuously and randomly. Their coupling effect will change the internal clearance of the bearing in real time and accelerate the wear process. Traditional methods that rely on fixed preload or periodic shutdown for inspection are difficult to respond to these dynamic changes, resulting in the bearing being in a suboptimal preload state for a long time, making it difficult to maintain the bearing's best performance and greatly reducing its service life. Summary of the Invention

[0004] The main objective of this application is to provide a method, device, equipment, and storage medium for adjusting the preload of wind turbine bearings, aiming to solve the technical problem that traditional fixed preload is difficult to adapt to the complex working conditions of wind turbine bearings, resulting in reduced performance.

[0005] To achieve the above objectives, this application proposes a method for adjusting the preload of a wind turbine bearing, the method comprising: Collect the current operating parameters of the wind turbine and preprocess the current operating parameters to obtain wind turbine operating condition data; The current bearing wear condition of the wind turbine bearing of the wind turbine unit is determined based on the wind turbine operating condition data; The current bearing wear state and the wind turbine operating condition data are input into the preset bearing adjustment model to obtain the target preload of the wind turbine bearing. The preset bearing adjustment model is obtained by training a neural network model through a mapping database. The mapping database includes the mapping relationship between the bearing wear state and the optimal preload of the wind turbine bearing under various operating conditions. The fan bearing is adjusted based on the target preload.

[0006] In one embodiment, the step of determining the current bearing wear state of the wind turbine bearing based on the wind turbine operating condition data includes: The initial clearance and sample vibration spectrum of the wind turbine under low load operating conditions after installation are obtained, and the current vibration spectrum is extracted from the wind turbine operating data; Using the sample vibration spectrum as a benchmark, the current vibration spectrum is compared to obtain the residual feature vector; Based on the residual feature vector, it is determined whether the wind turbine bearing of the wind turbine unit deviates from the initial clearance; When the wind turbine bearing deviates from the initial clearance, the current bearing wear state of the wind turbine bearing is determined based on the residual feature vector.

[0007] In one embodiment, the step of obtaining the initial clearance and sample vibration spectrum of the wind turbine under low-load operating conditions after installation includes: Obtain sample operating parameters of the wind turbine, which are the operating parameters of the wind turbine under low load operating conditions after installation; Extract the sample vibration spectrum and sample bearing displacement data of the wind turbine generator's motor bearing from the sample operating parameters; Feature extraction is performed on the vibration spectrum of the sample to obtain the bearing vibration fundamental frequency, and feature extraction is performed on the bearing displacement data of the sample to obtain the static offset of the shaft center trajectory; The initial clearance of the motor bearing is determined based on the bearing's fundamental vibration frequency and the static offset of the shaft center trajectory.

[0008] In one embodiment, before the step of collecting the current operating parameters of the wind turbine, the method further includes: Set corresponding simulated bearing wear states for the wind turbine bearings under various operating conditions of the wind turbine, and simulate the wind turbine based on the simulated bearing wear states; During the simulation, a multi-objective genetic algorithm was used to optimize the preload of the wind turbine bearing under the corresponding operating conditions, thereby obtaining the optimal preload of the wind turbine bearing. A mapping database is constructed based on the simulated bearing wear states corresponding to the various working conditions and the corresponding optimal preload values. The preset neural network model is trained based on the mapping database to obtain the preset bearing adjustment model.

[0009] In one embodiment, the step of optimizing the preload of the wind turbine bearing under corresponding operating conditions using a multi-objective genetic algorithm to obtain the optimal preload of the wind turbine bearing includes: Based on the simulated bearing wear state and corresponding operating condition data, a candidate population of preload force is constructed. With the maximum preload as the optimization objective, the candidate population of preload is iteratively optimized using a multi-objective genetic algorithm to obtain the Pareto optimal solution set; The optimal preload of the wind turbine bearing under various operating conditions is selected from the Pareto optimal solution set.

[0010] In one embodiment, a hydraulic actuator, a force sensor, and a controller are provided outside the wind turbine bearing, and the controller is connected to the hydraulic actuator and the force sensor respectively. The step of adjusting the wind turbine bearing based on the target preload includes: The target preload force is sent to the controller to generate an adjustment command; Based on the adjustment command, the hydraulic actuator is controlled to apply an axial force to the fan bearing in order to adjust the adjusting ring of the fan bearing; The net axial clamping force borne by the adjusting ring is collected by the force sensor; Compare the net axial clamping force with the target preload force; If the net axial clamping force is lower than the target preload, the process returns to the step of applying axial force to the fan bearing using the controlled hydraulic actuator until the net axial clamping force reaches the target preload, at which point the hydraulic actuator is controlled to stop applying the axial force.

[0011] In one embodiment, the step of collecting the current operating parameters of the wind turbine and preprocessing the current operating parameters to obtain wind turbine operating condition data includes: The SCADA system reads the current operating parameters of the wind turbine. Various sensors are installed in various parts of the wind turbine, and the SCADA system collects data through these sensors. The current operating parameters are time-aligned according to the timestamp of the SCADA system to obtain the time-series operating parameters; Based on the time-series operating parameters, a scatter plot of wind speed and power of the wind turbine is drawn, and the upper and lower envelopes of the scatter plot of wind speed and power are constructed using the quantile regression method. Isolated scatter points outside the upper and lower envelopes are identified as outliers and removed from the wind speed and power scatter plot to obtain the wind turbine operating data.

[0012] Furthermore, to achieve the above objectives, this application also proposes a wind turbine bearing preload adjustment device, the device comprising: The data processing module is used to collect the current operating parameters of the wind turbine and preprocess the current operating parameters to obtain wind turbine operating condition data. The wear status module is used to determine the current bearing wear status of the wind turbine bearings of the wind turbine unit based on the wind turbine operating condition data. The preload module is used to input the current bearing wear state and the wind turbine operating condition data into the preset bearing adjustment model to obtain the target preload of the wind turbine bearing. The preset bearing adjustment model is obtained by training a neural network model through a mapping database. The mapping database includes the mapping relationship between the bearing wear state and the optimal preload of the wind turbine bearing under various operating conditions. The bearing adjustment module is used to adjust the fan bearing based on the target preload.

[0013] In addition, to achieve the above objectives, this application also proposes a wind turbine bearing preload adjustment device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the wind turbine bearing preload adjustment method described above.

[0014] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the wind turbine bearing preload adjustment method described above.

[0015] One or more technical solutions proposed in this application have at least the following technical effects: The wind turbine bearing preload adjustment method of this application includes: collecting the current operating parameters of the wind turbine unit and preprocessing the current operating parameters to obtain wind turbine operating condition data; determining the current bearing wear state of the wind turbine bearing of the wind turbine unit based on the wind turbine operating condition data; inputting the current bearing wear state and the wind turbine operating condition data into a preset bearing adjustment model to obtain the target preload of the wind turbine bearing, wherein the preset bearing adjustment model is obtained by training a neural network model through a mapping database, and the mapping database includes the mapping relationship between the bearing wear state and the optimal preload of the wind turbine bearing under various operating conditions; and adjusting the wind turbine bearing based on the target preload.

[0016] This application first collects and preprocesses the current operating parameters of the wind turbine to obtain wind turbine operating condition data. Then, based on this data, it determines the current bearing wear state. The current bearing wear state and the wind turbine operating condition data are then input into a preset bearing adjustment model obtained by training a neural network model through a mapping database. This yields the target preload of the wind turbine bearing, which is then adjusted. Compared to existing methods that rely on fixed preload or periodic shutdowns for inspection, this application dynamically adjusts the target preload by acquiring real-time wind turbine operating condition data and bearing wear state. This allows for real-time response to complex operating conditions of the wind turbine bearing, reducing bearing wear and thus extending its service life. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart illustrating Embodiment 1 of the wind turbine bearing preload adjustment method of this application; Figure 2 This is a flowchart illustrating Embodiment 2 of the wind turbine bearing preload adjustment method of this application; Figure 3 This is a flowchart illustrating Embodiment 3 of the wind turbine bearing preload adjustment method of this application; Figure 4 This is a block diagram of the module structure of the fan bearing preload adjustment device according to an embodiment of this application; Figure 5 This is a schematic diagram of the hardware operating environment involved in the wind turbine bearing preload adjustment device in the embodiments of this application.

[0020] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0021] To make the above-mentioned objectives, features, and advantages of this application more apparent and understandable, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this application, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0022] The main solution of this application is: as a key component of wind turbine units, wind turbine bearings bear high dynamic loads and complex working environments. In the operation scenario of wind turbine units, in order to ensure that wind turbine bearings can withstand high dynamic wind loads and complex torques, it is generally necessary to apply and accurately set the initial preload force during the assembly stage.

[0023] During wind turbine operation, when faced with actual conditions such as fluctuating wind speed and alternating loads, wind speed and load are dynamic parameters that change continuously and randomly. Their coupling effect will change the internal clearance of the bearing in real time and accelerate the wear process. Traditional methods that rely on fixed preload or periodic shutdown for inspection are difficult to respond to these dynamic changes, resulting in the bearing being in a suboptimal preload state for a long time, making it difficult to maintain the bearing's best performance and greatly reducing its service life.

[0024] To address the aforementioned issues, this application provides a method for adjusting the preload of wind turbine bearings. First, the current operating parameters of the wind turbine are collected and preprocessed to obtain wind turbine operating condition data. Then, based on this data, the current bearing wear state is determined. Next, the current bearing wear state and the wind turbine operating condition data are input into a preset bearing adjustment model obtained by training a neural network model using a mapping database. The target preload of the wind turbine bearing is then obtained and adjusted. Compared to existing methods that rely on fixed preload or periodic shutdowns for inspection, this application allows for dynamic target preload adjustment by acquiring real-time wind turbine operating condition data and bearing wear state. This enables real-time response to complex operating conditions of the wind turbine bearings, reducing bearing wear and thus extending their service life.

[0025] It should be noted that the executing entity of this application embodiment can be a computing service device with data processing and program running functions, such as a personal computer, control center, server, etc., or an electronic device capable of realizing the above functions, a wind turbine bearing preload adjustment device for executing the wind turbine bearing preload adjustment method of this application, etc. This embodiment does not limit this. The following uses a wind turbine bearing preload adjustment device (hereinafter referred to as the device) as an example to describe this embodiment and the following embodiments.

[0026] Based on this, this application proposes a wind turbine bearing preload adjustment method according to the first embodiment, referring to... Figure 1 , Figure 1 This is a flowchart illustrating an embodiment of the wind turbine bearing preload adjustment method of this application. In this embodiment, the wind turbine bearing preload adjustment method may include steps S10 to S40: Step S10: Collect the current operating parameters of the wind turbine and preprocess the current operating parameters to obtain wind turbine operating condition data.

[0027] It should be noted that the current operating parameters can be various parameters of the wind turbine during its actual operation at the current moment, reflecting the current operating status of the wind turbine. For example, data such as wind speed, power, rotational speed, and dynamic load spectrum of the gearbox (such as radial force, axial force, and bending moment) are not limited in this embodiment.

[0028] It should also be noted that, in order to improve the quality and availability of the current operating parameters, data preprocessing can be performed on the current operating parameters, such as timestamp alignment, data cleaning (e.g., removing noise, outliers, etc.), and data filtering (e.g., eliminating interference signals), to obtain wind turbine operating condition data, so that data analysis can be performed more accurately in the future.

[0029] In actual use, the equipment can collect the current operating parameters of the wind turbine in real time, and then perform preprocessing such as timestamp alignment, data cleaning, and data filtering on the current operating parameters to obtain wind turbine operating condition data.

[0030] Furthermore, in order to obtain the aforementioned wind turbine operating condition data, in this embodiment, the step of collecting the current operating parameters of the wind turbine and preprocessing the current operating parameters to obtain the wind turbine operating condition data includes: reading the current operating parameters of the wind turbine through a SCADA system, wherein various sensors are configured at various locations on the wind turbine, and the SCADA system collects data through the various sensors; performing time-series alignment of the current operating parameters according to the timestamp of the SCADA system to obtain time-series operating parameters; plotting a scatter plot of wind speed and power of the wind turbine based on the time-series operating parameters, and constructing the upper and lower envelopes of the scatter plot of wind speed and power using quantile regression; identifying isolated scatter points outside the upper and lower envelopes as outliers, and removing the outliers from the scatter plot of wind speed and power to obtain the wind turbine operating condition data.

[0031] Understandably, a SCADA (Supervisory Control And Data Acquisition) system is a computer system used in the wind power generation field to monitor, collect data, and remotely control the operating status of wind turbines in real time. Through a SCADA system, data from sensors located throughout the wind turbine can be collected.

[0032] For example, you can set it to collect the current operating parameters every hour and store the current operating parameters in a specified folder on the device in CSV format.

[0033] The various sensors can be installed in different parts of the wind turbine to sense and measure various physical quantities. For example, wind speed sensors measure wind speed; speed sensors measure the rotational speed of the generator shaft or blades; and power sensors measure the output power of the wind turbine. These sensors convert the measured physical quantities into electrical signals, which are then transmitted to the SCADA system for processing via wired networks (such as Ethernet) or wireless networks (such as ZigBee, LoRa, etc.).

[0034] It is also understandable that a timestamp is a time stamp attached to the current running parameters to record the specific time when the current running parameters were generated.

[0035] Specifically, since the various operating parameters collected by the SCADA system may be collected at different times, the device can adjust these current operating parameters collected at different times to a unified time series based on the timestamp to obtain time-series operating parameters, thus ensuring the time-series accuracy of the data.

[0036] It should be understood that a wind speed vs. power scatter plot can be a graph that plots wind speed and power data from time-series operating parameters as scatter points on a plane coordinate system, with wind speed as the x-axis and power as the y-axis. Quantile regression is a data-based quantile modeling method that can construct regression curves at different quantile levels, i.e., construct the upper and lower envelopes of the wind speed vs. power scatter plot, to accurately describe the boundary relationship between wind speed and power, unaffected by extreme values.

[0037] The upper and lower envelopes can be two curves constructed using quantile regression, located above and below the wind speed versus power scatter plot. The upper envelope represents the upper limit of power that can be achieved at a given wind speed; the lower envelope represents the lower limit of power that can be achieved at a given wind speed. The region between the upper and lower envelopes reflects the reasonable range of wind speed and power variation for wind turbines under normal operating conditions.

[0038] It should be noted that isolated scatter points are those located outside the upper and lower envelopes in the wind speed and power scatter plot. These points represent data that does not conform to the wind speed-power relationship under normal operating conditions, and may be due to abnormal data points caused by sensor malfunctions, data acquisition errors, or abnormal operation of the wind turbine. The presence of these points may interfere with the analysis of the normal operating conditions of the wind turbine, therefore they need to be removed from the data to improve its accuracy and reliability.

[0039] Since this embodiment collects data through a SCADA system and uses timestamps for time-series alignment, the accuracy and consistency of the data's timing can be guaranteed. By using quantile regression to construct upper and lower envelopes and removing outliers, noise and erroneous data can be effectively removed, thereby improving the quality of wind turbine operating data.

[0040] Step S20: Determine the current bearing wear status of the wind turbine bearing of the wind turbine unit based on the wind turbine operating condition data.

[0041] It should be noted that wind turbine bearings are key components of wind turbine units, installed inside the unit, and their main function is to support rotating parts (such as blades and main shaft). Because wind turbine bearings bear high dynamic loads and operate in complex environments, their performance directly affects the normal operation and service life of the wind turbine unit, thus requiring real-time adjustment.

[0042] It should also be noted that the current bearing wear condition is used to characterize the degree of wear of the wind turbine bearing at the current moment. For example, it can be described by indicators such as wear amount, wear rate, and wear type. This embodiment does not limit this.

[0043] In practical use, the equipment can extract features from the wind turbine operating data, such as using the time-frequency domain features of the vibration signal in the wind turbine operating data (such as envelope spectrum and wavelet energy entropy) for analysis to determine the current bearing wear state of the wind turbine bearing.

[0044] Step S30: Input the current bearing wear state and the wind turbine operating condition data into the preset bearing adjustment model to obtain the target preload of the wind turbine bearing. The preset bearing adjustment model is obtained by training a neural network model through a mapping database. The mapping database includes the mapping relationship between the bearing wear state and the optimal preload of the wind turbine bearing under various operating conditions.

[0045] Step S40: Adjust the fan bearing based on the target preload.

[0046] Understandably, the preset bearing adjustment model can be a model obtained by training a neural network model through a mapping database. This model can determine the target preload of the wind turbine bearing based on the current bearing wear state and wind turbine operating data. During the training process of this preset bearing adjustment model, it can learn the mapping relationship between the bearing wear state and the optimal preload under various operating conditions and make accurate predictions based on the input real-time data.

[0047] The mapping database can be a database containing the mapping relationship between bearing wear state and optimal preload of wind turbine bearings under various operating conditions, providing data support for the training of the preset bearing adjustment model, enabling the neural network model to learn the inherent law between bearing wear and preload under different operating conditions.

[0048] It is also understandable that the target preload can be the value of the optimal preload state of the wind turbine bearing under the current actual operating conditions. If the wind turbine bearing is under this target preload, the performance and service life of the bearing can be improved.

[0049] In actual use, the equipment can input the current bearing wear status and fan operating condition data obtained above into a preset bearing adjustment model, and the model directly outputs the target preload of the fan bearing. Then, based on the obtained target preload, the hydraulic system is used to adjust the actual preload of the fan bearing to ensure that the actual preload of the fan bearing reaches the target preload, thus ensuring that the bearing operates in optimal condition.

[0050] Furthermore, in order to adjust the aforementioned wind turbine bearing, in this embodiment, a hydraulic actuator, a force sensor, and a controller are provided outside the wind turbine bearing, and the controller is connected to the hydraulic actuator and the force sensor respectively. The step of adjusting the wind turbine bearing based on the target preload includes: sending the target preload to the controller to generate an adjustment command; controlling the hydraulic actuator to apply an axial force to the wind turbine bearing based on the adjustment command to adjust the adjusting ring of the wind turbine bearing; collecting the net axial clamping force borne by the adjusting ring through the force sensor; comparing the net axial clamping force with the target preload; if the net axial clamping force is lower than the target preload, returning to the step of controlling the hydraulic actuator to apply an axial force to the wind turbine bearing until the net axial clamping force reaches the target preload, and controlling the hydraulic actuator to stop applying the axial force.

[0051] Understandably, a hydraulic actuator is a device that uses hydraulic energy to generate linear motion or torque. During the adjustment of the wind turbine bearing, the hydraulic actuator is connected to the bearing and, according to the controller's instructions, pushes a piston with pressurized oil, thereby applying axial force to the bearing. The force sensor, on the other hand, is a device that converts force signals into measurable electrical signals. It is installed near the adjusting ring of the bearing to collect the net axial clamping force on the adjusting ring in real time. The controller is the core control component of the wind turbine bearing adjustment process and is connected to both the hydraulic actuator and the force sensor.

[0052] The adjusting ring is a crucial component in the wind turbine bearing structure used to adjust the bearing's axial clearance and preload. It is typically located on the outer or inner ring of the bearing. Net axial clamping force refers to the net pressure exerted on the adjusting ring along the axial direction during actual operation. By controlling the position and force applied to the adjusting ring, the axial preload of the bearing can be altered.

[0053] In practical use, the wind turbine bearing has an adjusting ring on its outer side that can be driven by a hydraulic actuator. Simultaneously, the wind turbine bearing is equipped with a hydraulic actuator, a force sensor, and a controller, which is connected to both the hydraulic actuator and the force sensor. The equipment outputs the target preload force to the controller, which generates an adjustment command based on this target preload force. The controller then sends this adjustment command to the hydraulic actuator, controlling it to apply axial force to the wind turbine bearing to adjust the adjusting ring. Simultaneously, the force sensor collects the net axial clamping force on the adjusting ring; if the net axial clamping force is lower than the target preload force, the hydraulic actuator continues to apply axial force to the wind turbine bearing until the target preload force is reached. This forms a closed-loop control system, ensuring that the wind turbine bearing preload reaches the target value, thereby improving the bearing's operating accuracy.

[0054] This application provides a method for adjusting the preload of a wind turbine bearing. First, the current operating parameters of the wind turbine are collected and preprocessed to obtain wind turbine operating condition data. Then, based on this data, the current bearing wear state is determined. Next, the current bearing wear state and the wind turbine operating condition data are input into a preset bearing adjustment model obtained by training a neural network model using a mapping database. The target preload of the wind turbine bearing is then obtained and adjusted. Compared to existing methods that rely on fixed preload or periodic shutdowns for inspection, this application allows for dynamic target preload adjustment by acquiring real-time wind turbine operating condition data and bearing wear state. This enables real-time response to complex operating conditions of the wind turbine bearing, reducing bearing wear and thus extending its service life.

[0055] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to the above embodiment can be referred to the above description, and will not be repeated hereafter. On this basis, a second embodiment of the dialogue method of this application is proposed, please refer to... Figure 2 , Figure 2 This is a flowchart illustrating Embodiment 2 of the wind turbine bearing preload adjustment method of this application. To determine the current bearing wear state, as described above... Figure 2 As shown, in this embodiment, the step of determining the current bearing wear state of the wind turbine bearing based on the wind turbine operating data may include: Step S21: Obtain the initial clearance and sample vibration spectrum of the wind turbine under low load operating conditions after installation, and extract the current vibration spectrum from the wind turbine operating data.

[0056] It should be noted that low-load operating conditions refer to the operating conditions under which the wind turbine is subjected to relatively small loads. Under these conditions, the forces and vibrations experienced by the various components of the wind turbine are relatively small, the operating state is relatively stable, and more accurate basic data can be obtained.

[0057] It should also be noted that the initial clearance can be the initial gap between the various components of the wind turbine bearing under low-load operating conditions. The sample vibration spectrum can be a spectrum obtained by spectral analysis of vibration signals collected by vibration sensors under low-load operating conditions, used to characterize the vibration characteristics of the wind turbine during normal operation. The current vibration spectrum can be a spectrum extracted from wind turbine operating condition data reflecting the vibration characteristics of the wind turbine under the current operating state.

[0058] Furthermore, in order to obtain the aforementioned initial clearance and sample vibration spectrum, in this embodiment, the step of obtaining the initial clearance and sample vibration spectrum of the wind turbine under low-load operating conditions after installation includes: obtaining sample operating parameters of the wind turbine, wherein the sample operating parameters are the operating parameters of the wind turbine under low-load operating conditions after installation; extracting the sample vibration spectrum and sample bearing displacement data of the motor bearing of the wind turbine from the sample operating parameters; performing feature extraction on the sample vibration spectrum to obtain the bearing vibration fundamental frequency, and performing feature extraction on the sample bearing displacement data to obtain the static offset of the shaft center trajectory; and determining the initial clearance of the motor bearing based on the bearing vibration fundamental frequency and the static offset of the shaft center trajectory.

[0059] Understandably, the sample operating parameters can be a series of operating data recorded under low-load operating conditions after the wind turbine is installed. The operating parameters obtained at this time are closer to the initial ideal operating state of the equipment. The sample bearing displacement data can be the position change data of various components of the motor bearing obtained by displacement sensors under low-load operating conditions, used to characterize the displacement of the bearing during operation.

[0060] It is also understandable that the bearing vibration fundamental frequency can be a characteristic frequency related to the motor bearing structure extracted from the sample vibration spectrum. Different bearing fault types (such as inner ring faults, rolling element faults, etc.) will generate specific fundamental frequency components and their harmonics in the vibration spectrum. The static offset of the shaft center trajectory represents the degree of static offset of the motor shaft center relative to its ideal center position during operation, reflecting the deviation that exists in the bearing during operation.

[0061] Specifically, under stable operating conditions of low load and constant speed, sample operating parameters of the wind turbine can be collected to extract sample vibration spectrum and sample bearing displacement data of the wind turbine bearing. Then, the amplitude and phase characteristics of the bearing vibration fundamental frequency and its harmonics in the sample vibration spectrum can be analyzed. Combined with the static offset of the shaft center trajectory of the bearing displacement data, the initial clearance and its confidence interval with the highest fit to all observed data can be calculated by using the bearing stiffness-clearance relationship curve established in advance through simulation or calibration experiments.

[0062] Because this embodiment obtains sample operating parameters of the wind turbine under low load operating conditions, and extracts the bearing vibration fundamental frequency and shaft center trajectory static offset from the sample vibration spectrum and sample bearing displacement data respectively, and comprehensively utilizes these two key characteristic parameters to determine the initial clearance of the motor bearing, it can more accurately reflect the initial state of the bearing.

[0063] Step S22: Using the sample vibration spectrum as a benchmark, compare it with the current vibration spectrum to obtain the residual feature vector.

[0064] The residual feature vector can be obtained by subtracting the amplitude of the current vibration spectrum from that of the sample vibration spectrum at each frequency point, using the sample vibration spectrum as the reference value. The difference at each frequency point reflects the change of the current vibration spectrum relative to the sample vibration spectrum.

[0065] Step S23: Based on the residual feature vector, determine whether the wind turbine bearing of the wind turbine unit deviates from the initial clearance.

[0066] Step S24: When the wind turbine bearing deviates from the initial clearance, determine the current bearing wear state of the wind turbine bearing based on the residual feature vector.

[0067] In practical implementation, after obtaining the aforementioned residual feature vector, the device can use an unsupervised model (such as a single-class support vector machine or autoencoder trained based on residual features) to determine whether the wind turbine bearing has deviated from its initial clearance. If an anomaly is detected, the residual feature vector is input into a supervised machine learning classifier (such as a gradient boosting tree model trained with high-level vibration diagnosis results as labels), and the output is a discrete wear level (such as normal, slight wear, moderate wear, severe wear, etc., which are not limited in this embodiment) as the current bearing wear state of the wind turbine bearing.

[0068] In conjunction with the foregoing, the technical solution provided in this application embodiment uses the initial clearance and sample vibration spectrum of the wind turbine after installation as a benchmark, and compares the current vibration spectrum with it to obtain the residual feature vector. This allows for timely detection of changes in wind turbine bearing clearance and abnormal vibration characteristics, thereby improving the availability of the wind turbine.

[0069] Based on the first and / or second embodiments of this application, in the third embodiment of this application, the content that is the same as or similar to that in embodiments one and two above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 3 , Figure 3 This is a flowchart illustrating Embodiment 3 of the wind turbine bearing preload adjustment method of this application. To obtain the aforementioned preset bearing adjustment model, as shown... Figure 3As shown, in this embodiment, before the step of collecting the current operating parameters of the wind turbine, the following steps are also included: Step S01: Set corresponding simulated bearing wear states for the wind turbine bearings under various operating conditions of the wind turbine unit, and simulate the wind turbine unit according to the simulated bearing wear states.

[0070] It should be noted that various operating conditions refer to the different working conditions and states faced by wind turbines during actual operation, such as shutdown, startup, rated operation, full load, cut-out, transient load (gusts, emergency stop), etc. This embodiment does not limit these conditions.

[0071] It should also be noted that the simulated bearing wear condition is achieved by artificially setting the degree and type of wear that the wind turbine bearing may experience under different operating conditions during the simulation process. For example, simulating different forms of wear such as scratches, pitting, and fatigue spalling on the bearing surface, as well as different degrees of wear.

[0072] Step S02: During the simulation, the preload of the wind turbine bearing under the corresponding working conditions is optimized by a multi-objective genetic algorithm to obtain the optimal preload of the wind turbine bearing.

[0073] Understandably, multi-objective genetic algorithms are intelligent algorithms used to solve optimization problems, specifically to find the optimal preload of wind turbine bearings under different operating conditions.

[0074] In practical use, the equipment can utilize computer software and models to simulate the operation of wind turbine generators under set simulated bearing wear conditions. First, in the simulation environment, different simulated bearing wear conditions are set for the bearings (e.g., by changing parameters such as clearance and contact surface roughness), and batch simulations are performed within a parameter space covering all operating conditions. For each combination of simulated bearing wear conditions and operating conditions, a multi-objective genetic algorithm can be used to find the preload that optimizes bearing performance indicators (e.g., minimizing maximum contact stress, ensuring roller slippage is below a threshold, etc.; this embodiment does not impose such limitations).

[0075] Furthermore, in order to obtain the aforementioned optimal preload, in this embodiment, the step of optimizing the preload of the wind turbine bearing under corresponding operating conditions using a multi-objective genetic algorithm to obtain the optimal preload of the wind turbine bearing includes: constructing a candidate population of preload based on the simulated bearing wear state and corresponding operating condition data; using the maximum preload as the optimization objective, iteratively optimizing the candidate population of preload using a multi-objective genetic algorithm to obtain a Pareto optimal solution set; and selecting the optimal preload of the wind turbine bearing under various operating conditions from the Pareto optimal solution set.

[0076] Understandably, the candidate population of preload forces can be a set of preload force values ​​generated during the preload force optimization process based on simulated bearing wear conditions and corresponding operating data. The Pareto optimal solution set is crucial in multi-objective optimization problems where, due to potential conflicts and constraints between objectives, it's difficult to find a solution that simultaneously optimizes all objectives. In wind turbine bearing preload force optimization, the Pareto optimal solution set encompasses the optimal preload force combination considering multiple performance indicators under different operating conditions and wear states.

[0077] In practical implementation, the equipment can be optimized through iterative evolution. Based on the simulated bearing wear state and corresponding operating condition data, a candidate population for preload can be constructed. Then, with the maximum preload as the optimization objective, a multi-objective genetic algorithm is used to iteratively optimize the candidate population. Individuals are sorted, selected, crossovered, and mutated according to their fitness across multiple objectives, resulting in a new candidate population for preload. This process is repeated cyclically, causing the population as a whole to evolve towards simultaneously improving all objectives. Finally, after the algorithm converges, it outputs a Pareto optimal solution set, where each solution represents an optimal trade-off among multiple competing objectives. Finally, based on the current primary maintenance objective (such as service life or efficiency), the most suitable preload value can be selected from this solution set as the optimal preload for the wind turbine bearing under various operating conditions for subsequent model training.

[0078] Because this embodiment constructs a candidate population of preload force and performs iterative optimization, it can fully consider the diversity of simulated bearing wear state and working condition data, and search in a larger solution space, avoiding the problem of local optima, thereby improving the reliability of preload force optimization.

[0079] Step S03: Construct a mapping database based on the simulated bearing wear state corresponding to each type of working condition and the corresponding optimal preload value.

[0080] Step S04: Train the preset neural network model based on the mapping database to obtain the preset bearing adjustment model.

[0081] It should be noted that the mapping database is a database that stores the relationship between the simulated bearing wear state under various working conditions and the corresponding optimal preload value, and it is the basis for subsequent training of neural network models.

[0082] In actual training, the equipment can construct a large-scale state-operating condition-optimal preload mapping database based on the simulated bearing wear states and corresponding optimal preloads for the various operating conditions described above. Then, based on this mapping database, the wear state and key operating conditions are used as input features, and the obtained optimal preload is used as the target label. A neural network model is then trained to learn the nonlinear mapping from complex states to optimal decisions. By continuously adjusting the connection weights between neurons in the neural network model during training, the model can accurately predict the corresponding optimal preload based on the input operating conditions and bearing wear states.

[0083] This embodiment simulates wear conditions for wind turbine bearings under different operating conditions and then uses a multi-objective genetic algorithm to find the optimal preload, ensuring the bearing operates at its best under various real-world conditions. A mapping database is then constructed based on this database, and a neural network model is trained on it. This allows the pre-defined bearing adjustment model to learn the relationship between various operating conditions, bearing wear states, and the optimal preload, enabling accurate prediction of the optimal preload under different conditions and improving the model's accuracy.

[0084] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the wind turbine bearing preload adjustment method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0085] This application also provides a fan bearing preload adjustment device; please refer to... Figure 4 , Figure 4 This is a block diagram of the module structure of the wind turbine bearing preload adjustment device according to an embodiment of this application; in this embodiment, the wind turbine bearing preload adjustment device includes: The data processing module 401 is used to collect the current operating parameters of the wind turbine and preprocess the current operating parameters to obtain wind turbine operating condition data. Wear status module 402 is used to determine the current bearing wear status of the wind turbine bearing of the wind turbine unit based on the wind turbine operating condition data; The preload module 403 is used to input the current bearing wear state and the wind turbine operating condition data into the preset bearing adjustment model to obtain the target preload of the wind turbine bearing. The preset bearing adjustment model is obtained by training a neural network model through a mapping database. The mapping database includes the mapping relationship between the bearing wear state and the optimal preload of the wind turbine bearing under various operating conditions. The bearing adjustment module 404 is used to adjust the fan bearing based on the target preload.

[0086] This application first collects and preprocesses the current operating parameters of the wind turbine to obtain wind turbine operating condition data. Then, based on this data, it determines the current bearing wear state. The current bearing wear state and the wind turbine operating condition data are then input into a preset bearing adjustment model obtained by training a neural network model using a mapping database. This yields the target preload of the wind turbine bearing, which is then adjusted. Compared to existing methods that rely on fixed preload or periodic shutdowns for inspection, this application dynamically adjusts the target preload by acquiring real-time wind turbine operating condition data and bearing wear state. This allows for real-time response to complex operating conditions of the wind turbine bearing, reducing bearing wear and thus extending its service life.

[0087] In one implementation, the wear status module 402 is further configured to acquire the initial clearance and sample vibration spectrum of the wind turbine under low-load operating conditions after installation, and to extract the current vibration spectrum from the wind turbine operating data; compare the current vibration spectrum with the sample vibration spectrum as a reference value to obtain a residual feature vector; determine whether the wind turbine bearing of the wind turbine deviates from the initial clearance based on the residual feature vector; and determine the current bearing wear status of the wind turbine bearing based on the residual feature vector if the wind turbine bearing deviates from the initial clearance.

[0088] In one implementation, the wear status module 402 is further configured to acquire sample operating parameters of the wind turbine, which are the operating parameters of the wind turbine under low-load operating conditions after installation; extract sample vibration spectrum and sample bearing displacement data of the motor bearing of the wind turbine from the sample operating parameters; perform feature extraction on the sample vibration spectrum to obtain the bearing vibration fundamental frequency, and perform feature extraction on the sample bearing displacement data to obtain the static offset of the shaft center trajectory; and determine the initial clearance of the motor bearing based on the bearing vibration fundamental frequency and the static offset of the shaft center trajectory.

[0089] In one implementation, the preload module 403 is further configured to set corresponding simulated bearing wear states for the wind turbine bearings under various operating conditions of the wind turbine unit, and to simulate the wind turbine unit based on the simulated bearing wear states. During the simulation, a multi-objective genetic algorithm is used to optimize the preload of the wind turbine bearing under the corresponding operating conditions to obtain the optimal preload of the wind turbine bearing. A mapping database is constructed based on the simulated bearing wear states corresponding to various operating conditions and the corresponding optimal preload values. A preset neural network model is trained based on the mapping database to obtain a preset bearing adjustment model.

[0090] In one implementation, the preload module 403 is further configured to construct a preload candidate population based on the simulated bearing wear state and corresponding operating condition data; to iteratively optimize the preload candidate population using a multi-objective genetic algorithm with the maximum preload as the optimization objective, thereby obtaining a Pareto optimal solution set; and to select the optimal preload of the wind turbine bearing under various operating conditions from the Pareto optimal solution set.

[0091] In one implementation, the bearing adjustment module 404 is further configured to send the target preload to the controller to generate an adjustment command; based on the adjustment command, control the hydraulic actuator to apply an axial force to the wind turbine bearing to adjust the adjusting ring of the wind turbine bearing; collect the net axial clamping force borne by the adjusting ring through the force sensor; compare the net axial clamping force with the target preload; if the net axial clamping force is lower than the target preload, return to the step of controlling the hydraulic actuator to apply an axial force to the wind turbine bearing until the net axial clamping force reaches the target preload, and control the hydraulic actuator to stop applying the axial force.

[0092] In one implementation, the data processing module 401 is further configured to read the current operating parameters of the wind turbine through a SCADA system. Various sensors are configured at various locations on the wind turbine, and the SCADA system collects data through these sensors. The current operating parameters are time-series aligned according to the timestamps of the SCADA system to obtain time-series operating parameters. A scatter plot of wind speed and power of the wind turbine is plotted based on the time-series operating parameters, and the upper and lower envelopes of the scatter plot are constructed using quantile regression. Isolated scatter points outside the upper and lower envelopes are identified as outliers, and these outliers are removed from the scatter plot to obtain wind turbine operating condition data.

[0093] Other embodiments or specific implementations of the wind turbine bearing preload adjustment device of this application can be found in the above-described method embodiments, and will not be repeated here.

[0094] The wind turbine bearing preload adjustment device provided in this application, employing the wind turbine bearing preload adjustment method described in the above embodiments, can solve the technical problem that traditional fixed preload is difficult to adapt to the complex operating conditions of wind turbine bearings, leading to performance degradation. Compared with the prior art, the beneficial effects of the wind turbine bearing preload adjustment device provided in this application are the same as those of the wind turbine bearing preload adjustment method provided in the above embodiments, and other technical features in the wind turbine bearing preload adjustment device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0095] This application provides a wind turbine bearing preload adjustment device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform the wind turbine bearing preload adjustment method in the above embodiments.

[0096] The following is for reference. Figure 5 , Figure 5 This is a schematic diagram of the hardware operating environment involved in the wind turbine bearing preload adjustment device in the embodiments of this application. It shows a structural schematic diagram suitable for implementing the wind turbine bearing preload adjustment device in the embodiments of this application. The wind turbine bearing preload adjustment device in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, personal digital assistants (PDAs), tablet computers (PADs), portable media players (PMPs), vehicle terminals (e.g., vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The wind turbine bearing preload adjustment device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0097] like Figure 5As shown, the wind turbine bearing preload adjustment device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory 1002 or a program loaded from a storage device 1003 into a random access memory 1004. The random access memory 1004 also stores various programs and data required for the operation of the wind turbine bearing preload adjustment device. The processing unit 1001, the read-only memory 1002, and the random access memory 1004 are interconnected via a bus 1005. An input / output interface 1006 is also connected to the bus. Typically, the following systems can be connected to the input / output interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the wind turbine bearing preload adjustment device to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows wind turbine bearing preload adjustment devices with various systems, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0098] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from read-only memory 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0099] The wind turbine bearing preload adjustment device provided in this application, employing the wind turbine bearing preload adjustment method described in the above embodiments, can solve the technical problem that traditional fixed preload is difficult to adapt to the complex operating conditions of wind turbine bearings, leading to performance degradation. Compared with the prior art, the beneficial effects of the wind turbine bearing preload adjustment device provided in this application are the same as those of the wind turbine bearing preload adjustment method provided in the above embodiments, and other technical features of this wind turbine bearing preload adjustment device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0100] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0101] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0102] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the wind turbine bearing preload adjustment method in the above embodiments.

[0103] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, radio frequency (RF), etc., or any suitable combination thereof.

[0104] The aforementioned computer-readable storage medium may be included in the wind turbine bearing preload adjustment device; or it may exist independently and not assembled into the wind turbine bearing preload adjustment device.

[0105] The aforementioned computer-readable storage medium carries one or more programs. When these programs are executed by the wind turbine bearing preload adjustment device, the wind turbine bearing preload adjustment device performs the following actions: collects the current operating parameters of the wind turbine unit and preprocesses the current operating parameters to obtain wind turbine operating condition data; determines the current bearing wear state of the wind turbine bearing based on the wind turbine operating condition data; inputs the current bearing wear state and the wind turbine operating condition data into a preset bearing adjustment model to obtain the target preload of the wind turbine bearing. The preset bearing adjustment model is obtained by training a neural network model using a mapping database, which includes the mapping relationship between the bearing wear state and the optimal preload of the wind turbine bearing under various operating conditions; and adjusts the wind turbine bearing based on the target preload.

[0106] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0107] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0108] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0109] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described wind turbine bearing preload adjustment method. This solves the technical problem that traditional fixed preload methods are difficult to adapt to the complex operating conditions of wind turbine bearings, leading to performance degradation. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the wind turbine bearing preload adjustment method provided in the above embodiments, and will not be repeated here.

[0110] The above description is only a part of the embodiments of this application and does not limit the scope of protection of this application. All equivalent structural transformations made under the technical concept of this application and using the content of this application specification and drawings, or direct / indirect applications in other related technical fields, are included in the scope of protection of this application.

Claims

1. A method of adjusting a pre-tightening force of a bearing of a fan, characterized by, The method comprises: collecting current operating parameters of a wind turbine and preprocessing the current operating parameters to obtain wind turbine working condition data; determining a current bearing wear state of a wind turbine bearing of the wind turbine according to the wind turbine working condition data; inputting the current bearing wear state and the wind turbine working condition data into a preset bearing adjustment model to obtain a target pre-tightening force of the wind turbine bearing, the preset bearing adjustment model being obtained by training a neural network model through a mapping database, the mapping database comprising a mapping relationship between bearing wear states and optimal pre-tightening forces of the wind turbine bearing under various working conditions; adjusting the wind turbine bearing based on the target pre-tightening force.

2. The method of claim 1, wherein, The step of determining the current bearing wear state of the wind turbine bearing of the wind turbine according to the wind turbine working condition data comprises: obtaining an initial clearance and a sample vibration spectrum of the wind turbine under a low-load operating condition after installation of the wind turbine, and extracting a current vibration spectrum from the wind turbine working condition data; comparing the current vibration spectrum with the sample vibration spectrum as a reference value to obtain a residual feature vector; determining whether the wind turbine bearing deviates from the initial clearance according to the residual feature vector; in the case where the wind turbine bearing deviates from the initial clearance, determining the current bearing wear state of the wind turbine bearing according to the residual feature vector.

3. The method of claim 2, wherein, The step of obtaining the initial clearance and the sample vibration spectrum of the wind turbine under a low-load operating condition after installation of the wind turbine comprises: obtaining sample operating parameters of the wind turbine, the sample operating parameters being operating parameters of the wind turbine under a low-load operating condition after installation of the wind turbine; extracting sample vibration spectrum and sample bearing displacement data of a motor bearing of the wind turbine from the sample operating parameters; extracting a bearing vibration fundamental frequency from the sample vibration spectrum and a static offset of an axis trajectory from the sample bearing displacement data; determining an initial clearance of the motor bearing according to the bearing vibration fundamental frequency and the static offset of the axis trajectory.

4. The method of claim 1, wherein, Before the step of collecting current operating parameters of a wind turbine, the method further comprises: setting corresponding simulated bearing wear states for wind turbine bearings under various working conditions of the wind turbine, and simulating the wind turbine according to the simulated bearing wear states; in the simulation process, optimizing the pre-tightening force of the wind turbine bearing under the corresponding working condition through a multi-objective genetic algorithm to obtain an optimal pre-tightening force of the wind turbine bearing; constructing a mapping database according to the simulated bearing wear states corresponding to the various working conditions and the corresponding optimal pre-tightening force values; training a preset neural network model based on the mapping database to obtain a preset bearing adjustment model.

5. The method of claim 4, wherein, The step of optimizing the pre-tightening force of the wind turbine bearing under the corresponding working condition through a multi-objective genetic algorithm to obtain an optimal pre-tightening force of the wind turbine bearing comprises: constructing a pre-tightening force candidate population according to the simulated bearing wear states and the corresponding working condition data; Taking the maximum pre-tightening force as an optimization target, the pre-tightening force candidate population is iteratively optimized by a multi-objective genetic algorithm to obtain a Pareto optimal solution set; The optimal pre-tightening force of the fan bearing under various working conditions is selected from the Pareto optimal solution set.

6. The method of any one of claims 1 to 5, wherein, The fan bearing is externally provided with a hydraulic actuator, a force sensor and a controller, and the controller is connected with the hydraulic actuator and the force sensor respectively; The step of adjusting the fan bearing based on the target pre-tightening force comprises: The target pre-tightening force is sent to the controller to generate an adjustment instruction; Based on the adjustment instruction, the hydraulic actuator is controlled to apply an axial force to the fan bearing to adjust the adjustment ring of the fan bearing; The net axial compression force borne by the adjustment ring is collected by the force sensor; The net axial compression force is compared with the target pre-tightening force; If the net axial compression force is lower than the target pre-tightening force, the step of controlling the hydraulic actuator to apply an axial force to the fan bearing is returned to be executed until the net axial compression force reaches the target pre-tightening force, and the hydraulic actuator is controlled to stop applying the axial force.

7. The method of any one of claims 1 to 5, wherein, The step of collecting the current operating parameters of the wind turbine generator and preprocessing the current operating parameters to obtain fan working condition data comprises: The current operating parameters of the wind turbine generator are read by a SCADA system, various sensors are configured at various positions of the wind turbine generator, and the SCADA system collects data through the various sensors; The current operating parameters are time-series aligned according to the time stamp of the SCADA system to obtain time-series operating parameters; The wind speed and power scatter plot of the wind turbine generator is drawn according to the time-series operating parameters, and the upper and lower envelope lines of the wind speed and power scatter plot are constructed by using quantile regression method; Isolated scatter points outside the upper and lower envelope lines are taken as abnormal points, and the abnormal points are removed from the wind speed and power scatter plot to obtain fan working condition data.

8. A fan bearing pre-load adjustment device, characterized by, The device comprises: a data processing module for collecting the current operating parameters of the wind turbine generator and preprocessing the current operating parameters to obtain fan working condition data; a wear state module for determining the current bearing wear state of the fan bearing of the wind turbine generator according to the fan working condition data; a pre-tightening force module for inputting the current bearing wear state and the fan working condition data into a pre-set bearing adjustment model to obtain the target pre-tightening force of the fan bearing, wherein the pre-set bearing adjustment model is obtained by training a neural network model through a mapping database, and the mapping database comprises the mapping relationship between the bearing wear state and the optimal pre-tightening force of the fan bearing under various working conditions; a bearing adjustment module for adjusting the fan bearing based on the target pre-tightening force.

9. A fan bearing pre-load adjustment apparatus, characterized by, The device comprises a memory, a processor and a computer program stored on the memory and executable on the processor, and the computer program is configured to implement the steps of the fan bearing pre-tightening force adjustment method according to any one of claims 1 to 7.

10. A storage medium, characterized by The storage medium is a computer readable storage medium, and the storage medium stores a computer program. The computer program is executed by a processor to implement the steps of the fan bearing pre-tightening force adjusting method in any one of claims 1 to 7.

Images