Method and system for monitoring generator displacement in a wind turbine generator

Abstract

The application provides a kind of wind turbine generator unit generator displacement monitoring method and system, method includes: determining the first displacement data of each generator base in wind turbine generator unit;Extract the abnormal features in first displacement data, establish feature data set;The feature data set is preprocessed, and the data to be analyzed is obtained;Based on feature data set and the data to be analyzed, the displacement state of each generator base in wind turbine generator unit is analyzed, and state analysis data is obtained;Based on feature data set, the data to be analyzed and state analysis data, generate monitoring early warning instruction.The scheme provided by the application carries out abnormal detection on the first displacement data of generator base by the way of feature extraction, preprocessing and state analysis in the data processing link, and abnormal early warning is carried out in time by the way of generating monitoring early warning instruction, which can accurately and reliably realize effective monitoring of generator displacement in wind turbine generator unit, and ensure the safe and stable operation of wind turbine generator unit.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of wind power generation technology, and in particular to a method and system for monitoring displacement of a generator in a wind turbine. BACKGROUND

[0002] During operation of the wind turbine, the generator is affected by long-term vibration of the nacelle, which can cause large vibration of the front and rear bearings of the generator, resulting in displacement of the generator base, and further affecting normal operation of the wind turbine. In order to detect potential problems of the wind turbine in advance, it is crucial to monitor the operating state of the generator in real time.

[0003] In related art, a relevant sensor is usually installed on the generator base to detect displacement of the generator base. Due to the data processing link in the later stage, whether the displacement data exceeds the upper limit of safety is used to artificially judge whether the generator base has serious displacement. The accuracy and reliability of the displacement monitoring link are insufficient, and thus it is difficult to ensure safe and stable operation of the wind turbine.

[0004] Therefore, the conventional displacement monitoring scheme has the problems of insufficient accuracy and reliability, and it is difficult to ensure safe and stable operation of the wind turbine. SUMMARY

[0005] The present application provides a method and system for monitoring displacement of a generator in a wind turbine, to solve the problem of insufficient accuracy and reliability of the conventional displacement monitoring scheme, and to ensure safe and stable operation of the wind turbine.

[0006] In one aspect, the present application provides a method for monitoring displacement of a generator in a wind turbine, comprising:

[0007] determining first displacement data of each generator base in the wind turbine;

[0008] extracting abnormal features in the first displacement data to establish a feature data set;

[0009] preprocessing the feature data set to obtain analysis data;

[0010] analyzing the displacement state of each generator base in the wind turbine based on the feature data set and the analysis data to obtain state analysis data;

[0011] generating a monitoring and warning instruction based on the feature data set, the analysis data and the state analysis data.

[0012] According to the method for monitoring displacement of a generator in a wind turbine provided by the present application, the first displacement data of each generator base in the wind turbine is determined, comprising:

[0013] Determine the displacement monitoring device corresponding to each generator base in the generator set;

[0014] Obtain the installation position information and device attribute information of each displacement monitoring device;

[0015] Based on the installation position information and the device attribute information, a monitoring device array is established;

[0016] Obtain the displacement measured value of the generator base collected by the monitoring device array;

[0017] The displacement measured value is summarized to obtain the first displacement data of each generator base in the generator set.

[0018] According to the wind turbine generator set provided by the present application, the displacement monitoring device corresponding to each generator base in the generator set is determined, which includes:

[0019] Obtain the demand information of the generator set;

[0020] Extract the target demand related to the generator base in the demand information;

[0021] Retrieve the target monitoring device matching the target demand from the preset demand-device database;

[0022] The target monitoring device is used as the displacement monitoring device corresponding to each generator base in the generator set.

[0023] According to the wind turbine generator set provided by the present application, the displacement monitoring device corresponding to each generator base in the generator set is determined, which includes:

[0024] Retrieve the target preprocessing strategy matching the feature data set from the preset feature-method database;

[0025] According to the target preprocessing strategy, the feature data set is preprocessed to obtain the analysis data.

[0026] According to the wind turbine generator set provided by the present application, the displacement monitoring device corresponding to each generator base in the generator set is determined, which includes:

[0027] Extract the target screening factor corresponding to the feature data set from the preset feature-factor control table;

[0028] Retrieve the state analysis strategy matching the target screening factor from the preset factor-method database;

[0029] According to the state analysis strategy, a displacement state of each generator base in the generator set is analyzed based on the to-be-analyzed data, and a state analysis result is obtained.

[0030] A displacement state matched with the state analysis result is extracted from a preset result-state correspondence table, and state analysis data is obtained.

[0031] According to the wind turbine generator set generator displacement monitoring method provided by the application, based on the feature data set, the to-be-analyzed data and the state analysis data, a monitoring early warning instruction is generated, including:

[0032] A target prediction model matched with the feature data set is called from a preset feature-model database;

[0033] The to-be-analyzed data is input into the target prediction model, and displacement prediction data output by the target prediction model is obtained;

[0034] A displacement prediction state corresponding to the displacement prediction data is determined;

[0035] The displacement prediction data, the displacement prediction state and the state analysis data are input into a preset early warning database for data matching, and an early warning matching result is obtained;

[0036] A target instruction corresponding to the early warning matching result is extracted from a preset result-instruction correspondence table;

[0037] The target instruction is taken as the monitoring early warning instruction.

[0038] According to the wind turbine generator set generator displacement monitoring method provided by the application, after the monitoring early warning instruction is generated, the method further includes:

[0039] Based on the monitoring early warning instruction, the positions of each generator base in the generator set are adjusted.

[0040] According to the wind turbine generator set generator displacement monitoring method provided by the application, based on the monitoring early warning instruction, the positions of each generator base in the generator set are adjusted, including:

[0041] The monitoring early warning instruction is parsed, and an instruction parsing package is obtained;

[0042] Factor matching is performed on parsed content in the instruction parsing package, a matching factor corresponding to each parsed content in the instruction parsing package is obtained, and a matching factor set is constructed;

[0043] An equipment adjustment strategy corresponding to the matching factor set is extracted from a preset factor-strategy correspondence table;

[0044] According to the device adjustment strategy, the positions of the generator bases in the generator set are adjusted.

[0045] According to the present application, the method for monitoring the displacement of the generator in the wind turbine generator set further comprises the following steps after adjusting the positions of the generator bases in the generator set:

[0046] determining second displacement data of the generator bases in the generator set after adjustment;

[0047] determining standard position data of the generator bases in the generator set;

[0048] comparing the standard position data with the second displacement data to obtain position difference data;

[0049] based on the position difference data, calibrating the positions of the generator bases in the generator set after adjustment.

[0050] In another aspect, the present application further provides a monitoring system for the displacement of the generator in the wind turbine generator set, comprising:

[0051] a data acquisition module for determining first displacement data of the generator bases in the generator set;

[0052] a feature extraction module for extracting abnormal features in the first displacement data and establishing a feature data set;

[0053] a preprocessing module for preprocessing the feature data set to obtain to-be-analyzed data;

[0054] a state analysis module for analyzing the displacement state of the generator bases in the generator set based on the feature data set and the to-be-analyzed data to obtain state analysis data;

[0055] a monitoring and early warning module for generating monitoring and early warning instructions based on the feature data set, the to-be-analyzed data and the state analysis data.

[0056] The present invention provides a method and system for monitoring generator displacement in wind turbine units. This method involves: determining the first displacement data of each generator base within the generator unit; extracting abnormal features from the first displacement data to establish a feature dataset; preprocessing the feature dataset to obtain data to be analyzed; analyzing the displacement state of each generator base within the generator unit based on the feature dataset and the data to be analyzed to obtain state analysis data; and generating monitoring and early warning commands based on the feature dataset, the data to be analyzed, and the state analysis data. Because the data processing stage employs feature extraction, preprocessing, and state analysis to detect anomalies in the first displacement data of the generator bases, and generates monitoring and early warning commands to provide timely anomaly warnings, it can accurately and reliably achieve effective monitoring of generator displacement in wind turbine units. This solves the problems of insufficient accuracy and reliability in traditional displacement monitoring schemes, ensuring the safe and stable operation of wind turbine units. Attached Figure Description

[0057] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0058] Figure 1 This is a flowchart illustrating the method for monitoring generator displacement in a wind turbine provided in an embodiment of the present invention;

[0059] Figure 2 This is a schematic diagram of the structure of the generator displacement monitoring system in a wind turbine provided in an embodiment of the present invention;

[0060] Figure 3 This is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention. Detailed Implementation

[0061] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0062] The following is combined with Figures 1 to 3 This invention describes the detailed scheme of the method and system for monitoring generator displacement in a wind turbine provided in the embodiments of the present invention.

[0063] Figure 1is a flowchart of a monitoring method for generator displacement in a wind turbine provided by an embodiment of the present application.

[0064] As shown in Figure 1 The monitoring method for generator displacement in a wind turbine provided by an embodiment of the present application can be executed by a computer or a server with data transceiving and processing capabilities, and the method mainly includes the following steps:

[0065] Step 110: Determine first displacement data of each generator base in the wind turbine.

[0066] In this embodiment, the first displacement data can be collected by displacement monitoring devices pre-installed at preset position points in the wind turbine.

[0067] Step 120: Extract abnormal features in the first displacement data and establish a feature data set.

[0068] It can be understood that abnormal features are mainly used to represent data features that deviate from the normal range in the first displacement data. After all abnormal features are summarized, a feature data set can be obtained.

[0069] In actual applications, a feature database storing various abnormal features and meanings of abnormal features can be pre-established, so that each data feature in the first displacement data can be matched with the abnormal features in the feature database, and then the abnormal features in the first displacement data can be accurately extracted.

[0070] Step 130: Preprocess the feature data set to obtain data to be analyzed.

[0071] In actual applications, the preprocessing link is mainly used to improve the data quality of the data in the feature data set, so as to provide accurate and reliable data basis for the subsequent data analysis link.

[0072] Step 140: Based on the feature data set and the data to be analyzed, analyze the displacement state of each generator base in the wind turbine to obtain state analysis data.

[0073] In this embodiment, the state analysis link mainly analyzes the displacement state of each generator base in the wind turbine, and the state analysis data can represent the position deviation of the generator base.

[0074] Step 150: Based on the feature data set, the data to be analyzed, and the state analysis data, generate a monitoring and early warning instruction.

[0075] It can be understood that the monitoring and early warning instruction can present the displacement state of the generator base to the user in the form of early warning information, so as to timely remind the user to adjust or maintain the generator base, so as to ensure the stable and safe operation of the wind turbine.

[0076] The scheme provided by the embodiment of the application can monitor the displacement of the generator base in real time, discover abnormal displacement of the generator base in time, generate a monitoring and early warning instruction according to the abnormal displacement, and thus ensure normal operation of the generator set, and help improve the power generation efficiency and system stability of the entire wind power generation system.

[0077] In an embodiment, the first displacement data of each generator base in the generator set is determined, including:

[0078] Firstly, the displacement monitoring device corresponding to each generator base in the generator set is determined.

[0079] In a specific implementation, the displacement monitoring device corresponding to each generator base in the generator set is determined, specifically including:

[0080] Firstly, the demand information of the generator set is acquired.

[0081] It can be understood that the demand information specifically refers to the demand information of the generator set or the power generation system, and in the embodiment, the demand information specifically can include the demand of monitoring the condition of the generator base, the demand of monitoring the running state of the system, and the demand of early warning and alarm, etc.

[0082] Then, the target demand related to the generator base in the demand information is extracted.

[0083] In the embodiment, the target demand includes but is not limited to the demand of displacement, temperature, vibration, etc. of the generator.

[0084] Next, the target monitoring device matched with the target demand is called from the preset demand-device database.

[0085] In the embodiment, the demand-device database is a database pre-constructed and storing the corresponding relationship between the demand related to the generator base and the displacement monitoring device.

[0086] Finally, the target monitoring device is taken as the displacement monitoring device corresponding to each generator base in the generator set.

[0087] In the embodiment, the displacement monitoring device can be a sliding distance sensor installed on the generator base. The sliding distance sensor adopts laser ranging and is installed on the X-axis, Y-axis and Z-axis of the generator base, wherein two position points are arranged on the X-axis, two position points are arranged on the Y-axis, and one position point is arranged on the Z-axis, so that five-point measurement of the sliding amount can be realized.

[0088] It can be found that by obtaining the demand information of the generator set, the target demand related to the generator base is parsed, and then the matching target monitoring device is selected in the preset demand-equipment database, so that the target monitoring device can be accurately matched according to the demand information of the generator set and the target demand of the generator base, ensuring the accuracy of the monitoring data. At the same time, through the demand and equipment matching mode, the displacement monitoring device can be ensured to be consistent with the demand, and the problem of low monitoring accuracy caused by information mismatch can be reduced.

[0089] Secondly, the installation position information and the equipment attribute information of each displacement monitoring device are obtained.

[0090] In this embodiment, the installation position information refers to the information of the position point of the displacement monitoring device, and the equipment attribute information includes equipment model, manufacturer, installation date and other equipment identifiers, which are used to identify and manage the displacement monitoring device.

[0091] Thirdly, a monitoring device array is established based on the installation position information and the equipment attribute information.

[0092] The monitoring device array specifically refers to a data matrix constructed according to the installation position information and the equipment attribute information of each displacement monitoring device, which is used to monitor the displacement condition of each generator base in the generator set in real time.

[0093] Fourthly, the displacement measured value of the generator base collected by the monitoring device array is obtained.

[0094] In this embodiment, the displacement measured value refers to the actual value of each generator base in the running process collected by the monitoring device array in real time, including but not limited to the displacement degree, temperature, vibration and other information of the generator.

[0095] Fifthly, the displacement measured value is summarized to obtain the first displacement data of each generator base in the generator set.

[0096] In actual application, the measurement results of the slip distance sensor will be collected in real time into the controller in the nacelle of the generator set. The controller will sample and filter the measurement results in the form of analog input point signal, and output to the data analysis software in the central control room. The data analysis software will display the displacement measured value in real time, and support functions such as historical displacement data viewing and abnormal parameter alarm, so as to realize the maintenance and repair based on the running state of the wind turbine generator set.

[0097] In an embodiment, the feature data set is preprocessed to obtain the data to be analyzed, specifically including:

[0098] Firstly, the target preprocessing strategy matched with the feature data set is called from the preset feature-method database.

[0099] In this embodiment, various abnormal features and corresponding preprocessing strategies are pre-stored in the feature-method database. In actual application, the preprocessing strategies can be data cleaning, data normalization, and other preprocessing schemes.

[0100] Then, the feature data set is pre-processed according to the target preprocessing strategy to obtain the to-be-analyzed data.

[0101] Through the feature extraction, preprocessing, and state analysis links, an automated data analysis process is realized, which can accurately analyze the displacement data and judge the displacement state of the generator base, discover problems in time and facilitate subsequent corresponding measures, reduce errors caused by human intervention, and improve data analysis efficiency.

[0102] In an embodiment, based on the feature data set and the to-be-analyzed data, the displacement states of each generator base in the generator set are analyzed to obtain state analysis data, specifically including:

[0103] Firstly, the target screening factor corresponding to the feature data set is extracted from the pre-set feature-factor correspondence table.

[0104] In this embodiment, the feature-factor correspondence table stores the correspondence between each screening factor and abnormal feature, thereby providing effective data basis for the conversion process of abnormal features to screening factors.

[0105] Secondly, the state analysis strategy matched with the target screening factor is called from the pre-set factor-method database.

[0106] In this embodiment, the factor-method database pre-stores the matching relationship between each screening factor and the state analysis strategy.

[0107] Thirdly, based on the to-be-analyzed data, the displacement states of each generator base in the generator set are analyzed according to the state analysis strategy to obtain the state analysis result.

[0108] It can be understood that the state analysis result can represent the displacement amount of the generator base, that is, the specific numerical value of the displacement deviation.

[0109] Fourthly, the displacement state matched with the state analysis result is extracted from the pre-set result-state correspondence table to obtain the state analysis data.

[0110] It can be understood that the result-state correspondence table stores the correspondence between different state analysis results and displacement states. Specifically, according to the numerical interval where the state analysis result is located, multiple displacement states can be demarcated, and the correspondence between the state analysis result in different intervals and the displacement state can be established.

[0111] In this embodiment, the displacement state can represent the degree and state of displacement of the generator base, and can specifically include normal, slight displacement, severe displacement, and the like.

[0112] The present application can convert abnormal features into screening factors through the steps of factor acquisition, method matching, and state analysis, and can further select appropriate analysis methods and finally convert the analysis results into specific displacement states. Through factor acquisition and method matching, accurate analysis of the data to be analyzed is achieved, the possibility of misjudgment is reduced, and it is convenient for operation and maintenance personnel to understand and take corresponding measures.

[0113] In an embodiment, based on the feature data set, the data to be analyzed, and the state analysis data, a monitoring and early warning instruction is generated, specifically including:

[0114] Firstly, a target prediction model matched with the feature data set is called from a preset feature-model database.

[0115] In this embodiment, the feature-model database pre-stores the matching relationship between abnormal features and prediction models.

[0116] In actual application, the prediction model can be a deep learning model pre-trained through sample data, such as a neural network model.

[0117] Secondly, the data to be analyzed is input into the target prediction model to obtain displacement prediction data output by the target prediction model.

[0118] It can be understood that since the target prediction model has been pre-trained through sample data, the data to be analyzed can be directly input into the target prediction model in the actual application, so that the displacement prediction data is directly output by the target prediction model. In this embodiment, the displacement prediction data is similar to the state analysis result, and is a specific numerical value that can represent the displacement condition.

[0119] Thirdly, a displacement prediction state corresponding to the displacement prediction data is determined.

[0120] In this embodiment, in order to facilitate the staff to check, the present application converts the displacement prediction data into a corresponding displacement prediction state, such as normal, slight displacement, and need to be handled.

[0121] Fourthly, the displacement prediction data, the displacement prediction state, and the state analysis data are input into a preset early warning database for data matching to obtain an early warning matching result.

[0122] In this embodiment, the early warning database pre-stores the matching relationship between the displacement prediction data, the displacement prediction state, and the state analysis data and the early warning matching result, and the early warning matching result can represent different early warning levels, such as low-level early warning, medium-level early warning, high-level early warning, and the like.

[0123] The fifth step is to extract the target instruction corresponding to the early warning matching result from the preset result-instruction correspondence table.

[0124] In the embodiment, the result-instruction correspondence table pre-stores the correspondence between different early warning matching results and early warning instructions, and the early warning instruction is the specific early warning content corresponding to the early warning matching result.

[0125] The sixth step is to take the target instruction as the monitoring early warning instruction.

[0126] Therefore, the generator base displacement condition can be monitored in real time, problems can be found in time, the monitoring early warning instruction can be generated according to the displacement prediction condition and the state analysis condition, the user is reminded to take corresponding measures, and the generator set can be ensured to operate safely and stably.

[0127] In an embodiment, after the monitoring early warning instruction is generated, the above method can further include:

[0128] Based on the monitoring early warning instruction, the positions of the generator bases in the generator set are adjusted.

[0129] In a specific implementation, based on the monitoring early warning instruction, the positions of the generator bases in the generator set are adjusted, specifically including:

[0130] The first step is to analyze the monitoring early warning instruction to obtain an instruction analysis package.

[0131] It can be understood that the instruction analysis package is an analysis data package corresponding to the analyzed monitoring early warning instruction, contains the instruction content after the analysis, and can be used for subsequent processing.

[0132] The second step is to perform factor matching on the analysis content in the instruction analysis package to obtain a matching factor corresponding to each analysis content in the instruction analysis package, and construct a matching factor set.

[0133] In the embodiment, the factor matching link is mainly used to simplify the analysis content in the instruction analysis package and determine the early warning root cause, that is, the matching factor is mainly used to represent the root cause information related to the analysis content.

[0134] The third step is to extract the device adjustment strategy corresponding to the matching factor set from the preset factor-strategy correspondence table.

[0135] It can be understood that the factor-root cause correspondence table pre-stores the correspondence between the matching factor and the device adjustment strategy.

[0136] The fourth step is to adjust the positions of the generator bases in the generator set according to the device adjustment strategy.

[0137] After the adjustment, the positions of the generator bases in the generator set are restored to near normal state, thereby relieving the generator displacement problem in the generator set in a timely intervention manner, and facilitating stable and safe operation of the generator set.

[0138] In an embodiment, after the adjustment of the positions of the generator bases in the generator set, the method can further include:

[0139] Firstly, second displacement data of the generator bases in the generator set after the adjustment are determined.

[0140] It should be noted that the determination manner of the second displacement data is basically the same as that of the first displacement data, which is not repeated here.

[0141] Secondly, standard position data of the generator bases in the generator set are determined.

[0142] In this embodiment, firstly, device attribute information of the displacement monitoring device on the generator base after the adjustment is obtained, and brake demand information of the generator is obtained, and then the standard position data of the generator base that matches is retrieved in the standard database according to the device attribute information and the brake demand information.

[0143] It can be understood that the standard database pre-stores the corresponding relationship between the device attribute information and the brake demand information and the standard position data of the generator base.

[0144] Thirdly, the standard position data and the second displacement data are compared to obtain position difference data.

[0145] It can be understood that the position difference data can represent the deviation between the second displacement data and the standard position data.

[0146] Fourthly, the positions of the generator bases in the generator set after the adjustment are calibrated based on the position difference data.

[0147] In this embodiment, the positions of the generator bases in the generator set after the adjustment are calibrated based on the position difference data, specifically including:

[0148] The position difference data is input into a preset deviation correction analysis model for deviation correction analysis, and a corresponding target calibration strategy is obtained in a preset result-calibration strategy table based on a deviation correction analysis result;

[0149] The positions of the generator bases after the adjustment are calibrated based on the target calibration strategy, and calibration position data is generated.

[0150] In one specific implementation, the position difference data is input into a preset deviation rectification analysis model for deviation rectification analysis, and a corresponding target calibration strategy is obtained in a preset result-calibration strategy table based on the deviation rectification analysis result, specifically including:

[0151] Firstly, the position difference data is analyzed to obtain position variation data of the adjusted generator base at a plurality of preset position points.

[0152] Secondly, the position variation data is feature extracted, and a key feature set is constructed.

[0153] Thirdly, a deviation rectification analysis model matching the key feature set is selected from a model database.

[0154] Fourthly, format information of the deviation rectification analysis model is obtained, and the position variation data is format converted based on the format information to obtain format conversion data.

[0155] The position data after the format conversion, i.e., the format conversion data, is more in line with the data format requirements of the subsequent deviation rectification analysis model, thereby providing an effective data basis for inputting the data into the deviation rectification analysis model in the next step.

[0156] Fifthly, the format conversion data is input into the deviation rectification analysis model for deviation rectification analysis, and axial offset analysis results and radial offset analysis results of the generator base are obtained respectively.

[0157] In this embodiment, the axial offset analysis results include axial offset coefficients corresponding to each row of preset position points on the generator base, and the radial offset analysis results include radial offset coefficients corresponding to each column of preset position points on the generator base.

[0158] Specifically, the axial offset coefficient corresponding to the i-th row of preset position points on the generator base and the radial offset coefficient corresponding to the j-th column of preset position points on the generator base can be expressed as follows:

[0159] (1)

[0160] wherein, represents the axial offset coefficient corresponding to the i-th row of preset position points on the generator base; represents the radial offset coefficient corresponding to the j-th column of preset position points on the generator base; represents the number of the i-th row of preset position points on the generator base; represents the number of the j-th column of preset position points on the generator base; represents the number of the i-th row of preset position points on the generator base; represents the number of the j-th column of preset position points on the generator base; represents the number of the i-th row of preset position points on the generator base; represents the number of the j-th column of preset position points on the generator base; represents the number of the i-th row of preset position points on the generator base;​​ row displacement measured value corresponding to the preset position point in the first row represents the standard position value corresponding to the preset position point in the first row row displacement measured value corresponding to the preset position point in the first row represents the deviation calculation weight coefficient corresponding to the preset position point in the first row row displacement deviation adjustment coefficient corresponding to the preset position point in the first row represents the displacement measured value at the preset position point in the first row row displacement deviation adjustment coefficient corresponding to the preset position point in the first row represents the displacement measured value at the preset position point in the first row row displacement deviation adjustment coefficient corresponding to the preset position point in the first row represents the displacement measured value at the preset position point in the first row row displacement deviation adjustment coefficient corresponding to the preset position point in the first row represents the displacement measured value at the preset position point in the first row row displacement deviation adjustment coefficient corresponding to the preset position point in the first row represents the displacement measured value at the preset position point in the first row row displacement deviation adjustment coefficient corresponding to the preset position point in the first row

[0161] Sixth, the axial offset analysis result and the radial offset analysis result are comprehensively analyzed to obtain a correction analysis result.

[0162] It can be understood that the correction analysis result is mainly used to represent the post-processing result of the axial offset analysis result and the radial offset analysis result, and further, the correction analysis result can be obtained after data preprocessing and data summarization of the axial offset analysis result and the radial offset analysis result.

[0163] Seventh, based on the correction analysis result, a corresponding target calibration strategy is obtained in a preset result-calibration strategy table.

[0164] In some embodiments, in order to ensure the effectiveness of the calibration link, after position calibration, the calibration result can be further verified. Specifically, the calibration position data and the standard position data can be compared and analyzed, the comparison and analysis result meeting the preset threshold condition is determined as a verification qualified state, and the calibration process of the generator base is ended.

[0165] The method for monitoring generator displacement in a wind turbine provided by the embodiment of the present application can ensure normal and stable operation of the wind turbine by monitoring displacement data of the generator base, analyzing the displacement state of the generator and generating a monitoring and early warning instruction, and then selecting a suitable generator maintenance strategy according to the monitoring and early warning instruction. Meanwhile, the present application can not only accurately analyze the position change of the generator base, but also match a corresponding calibration strategy according to the deviation correction analysis result, so as to realize calibration and optimization of the generator, improve the accuracy and efficiency of calibration, ensure that the position of the generator base after adjustment meets the requirements, and further improve the performance and reliability of the generator.

[0166] Based on the same general inventive concept, the present application also protects a monitoring system for generator displacement in a wind turbine. The monitoring system for generator displacement in a wind turbine provided by the present application is described below, and the monitoring system for generator displacement in a wind turbine described below can be mutually referred to the monitoring method for generator displacement in a wind turbine described above.

[0167] As shown in Figure 2 The monitoring system for generator displacement in a wind turbine provided by the embodiment of the present application specifically comprises:

[0168] The data acquisition module 210 is configured to determine the first displacement data of each generator base in the wind turbine.

[0169] The feature extraction module 220 is configured to extract abnormal features in the first displacement data and establish a feature data set.

[0170] The preprocessing module 230 is configured to preprocess the feature data set to obtain to-be-analyzed data.

[0171] The state analysis module 240 is configured to analyze the displacement state of each generator base in the wind turbine based on the feature data set and the to-be-analyzed data, and obtain state analysis data.

[0172] The monitoring and early warning module 250 is configured to generate a monitoring and early warning instruction based on the feature data set, the to-be-analyzed data and the state analysis data.

[0173] The monitoring system for generator displacement in a wind turbine provided by the embodiment of the present application can adopt feature extraction, preprocessing and state analysis to detect abnormalities in the first displacement data of the generator base in cooperation with the feature extraction module, the preprocessing module, the state analysis module and the monitoring and early warning module, and can timely perform abnormal early warning through the monitoring and early warning instruction, so as to accurately and reliably realize effective monitoring of the generator displacement in the wind turbine, solve the problems of insufficient accuracy and reliability of the traditional displacement monitoring scheme, and ensure safe and stable operation of the wind turbine.

[0174] Regarding the system in the above embodiments, the specific ways in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated further here.

[0175] Figure 3 This is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention.

[0176] like Figure 3 As shown, the electronic device may include a processor 310, a communication interface 320, a memory 330, and a communication bus 340, wherein the processor 310, the communication interface 320, and the memory 330 communicate with each other through the communication bus 340. The processor 310 can call logical instructions in the memory 330 to execute the generator displacement monitoring method in the wind turbine provided in the above embodiments. The method includes: determining the first displacement data of each generator base in the generator set; extracting abnormal features from the first displacement data to establish a feature dataset; preprocessing the feature dataset to obtain data to be analyzed; analyzing the displacement state of each generator base in the generator set based on the feature dataset and the data to be analyzed to obtain state analysis data; and generating a monitoring and early warning instruction based on the feature dataset, the data to be analyzed, and the state analysis data.

[0177] Furthermore, the logical instructions in the aforementioned memory 330 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0178] In another aspect, the present application also provides a computer program product comprising a computer program, which can be stored on a non-transitory computer readable storage medium, and the computer program is executable by a processor to enable a computer to perform the method for monitoring displacement of a generator in a wind turbine provided by any of the above embodiments, which comprises: determining first displacement data of each generator base in the wind turbine; extracting abnormal features in the first displacement data to establish a feature data set; pre-processing the feature data set to obtain to-be-analyzed data; analyzing displacement states of each generator base in the wind turbine based on the feature data set and the to-be-analyzed data to obtain state analysis data; and generating a monitoring and early warning instruction based on the feature data set, the to-be-analyzed data, and the state analysis data.

[0179] In another aspect, the present application also provides a non-transitory computer readable storage medium having a computer program stored thereon, which is executable by a processor to implement the method for monitoring displacement of a generator in a wind turbine provided by any of the above embodiments, which comprises: determining first displacement data of each generator base in the wind turbine; extracting abnormal features in the first displacement data to establish a feature data set; pre-processing the feature data set to obtain to-be-analyzed data; analyzing displacement states of each generator base in the wind turbine based on the feature data set and the to-be-analyzed data to obtain state analysis data; and generating a monitoring and early warning instruction based on the feature data set, the to-be-analyzed data, and the state analysis data.

[0180] The device embodiments described above are merely illustrative, wherein the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, i.e., can be located in one place or distributed on multiple network units. Part or all of the modules can be selected to achieve the purpose of the present embodiment scheme according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0181] From the above description of the embodiments, those skilled in the art can clearly understand that the embodiments can be implemented by means of software plus necessary general hardware platforms, and of course can also be implemented by hardware. Based on such understanding, the above technical solutions can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiments.

[0182] It should be pointed out finally that the above embodiments are only used to illustrate the technical solutions of the present application, but not to limit the same; and although the present application has been described in detail with reference to the foregoing embodiments, it should be appreciated by those skilled in the art that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features thereof can be replaced equivalently; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for monitoring generator displacement in a wind turbine unit, characterized in that, include: Determine the first displacement data of each generator base within the generator set; Extract abnormal features from the first displacement data and establish Feature dataset; The feature dataset is preprocessed to obtain the data to be analyzed; Based on the feature dataset and the data to be analyzed, the displacement state of each generator base in the generator set is analyzed to obtain state analysis data. Based on the feature dataset, the data to be analyzed, and the status analysis data, a monitoring and early warning instruction is generated. Based on the monitoring and early warning instructions, the positions of each generator base in the generator set are adjusted; Determine the second displacement data of each generator base in the generator set after adjustment; determine the standard position data of each generator base in the generator set. The standard position data is compared with the second displacement data to obtain position difference data; The position difference data is analyzed to obtain the position change data of the generator base at multiple preset position points after adjustment; features are extracted from the position change data, and a key feature set is constructed. Select a correction analysis model that matches the key feature set from the model database; obtain the format information of the correction analysis model, and perform format conversion on the position change data based on the format information to obtain format-converted data; The format-converted data is input into the correction analysis model for correction analysis, and the axial offset analysis results and radial offset analysis results of the generator base are obtained respectively. The axial offset analysis results include the axial offset coefficients corresponding to the preset position points of each row on the generator base, and the radial offset analysis results include the radial offset coefficients corresponding to the preset position points of each column on the generator base.

2. The method for monitoring generator displacement in a wind turbine according to claim 1, characterized in that, Determine the first displacement data of each generator base within the generator set, including: Determine the displacement monitoring equipment corresponding to each generator base within the generator set; Obtain the installation location information and device attribute information of each displacement monitoring device; Based on the installation location information and the device attribute information, a monitoring device array is established; Obtain the measured displacement value of the generator base collected by the monitoring equipment array; The measured displacement values ​​are summarized to obtain the first displacement data of each generator base in the generator set.

3. The method for monitoring generator displacement in a wind turbine according to claim 2, characterized in that, Identify the displacement monitoring equipment corresponding to each generator base within the generator set, including: Obtain generator set demand information; Extract the target requirements related to the generator base from the requirement information; Retrieve target monitoring equipment that matches the target requirements from the preset requirements-equipment database; The target monitoring device is used as the displacement monitoring device for each generator base in the generator set.

4. The method for monitoring generator displacement in a wind turbine according to claim 1, characterized in that, The feature dataset is preprocessed to obtain the data to be analyzed, including: Retrieve the target preprocessing strategy that matches the feature dataset from the preset feature-method database; The feature dataset is preprocessed according to the target preprocessing strategy to obtain the data to be analyzed.

5. The method for monitoring generator displacement in a wind turbine according to claim 1, characterized in that, Based on the feature dataset and the data to be analyzed, the displacement state of each generator base within the generator set is analyzed to obtain state analysis data, including: Extract the target screening factors corresponding to the feature dataset from the preset feature-factor lookup table; Retrieve state analysis strategies that match the target screening factors from a pre-defined factor-method database; Based on the data to be analyzed, the displacement state of each generator base in the generator set is analyzed according to the state analysis strategy to obtain the state analysis results. The displacement states that match the state analysis results are extracted from the preset result-state lookup table to obtain state analysis data.

6. The method for monitoring generator displacement in a wind turbine according to claim 1, characterized in that, Based on the feature dataset, the data to be analyzed, and the status analysis data, a monitoring and early warning instruction is generated, including: Retrieve the target prediction model that matches the feature dataset from the preset feature-model database; The data to be analyzed is input into the target prediction model to obtain the displacement prediction data output by the target prediction model; Determine the displacement prediction state corresponding to the displacement prediction data; The displacement prediction data, displacement prediction status, and status analysis data are input into a preset early warning database for data matching to obtain early warning matching results. Extract the target instruction corresponding to the warning matching result from the preset result-instruction lookup table; The target instruction will be used as a monitoring and early warning instruction.

7. The method for monitoring generator displacement in a wind turbine according to claim 1, characterized in that, Based on the aforementioned monitoring and early warning instructions, the positions of each generator base within the generator set are adjusted, including: The monitoring and early warning commands are parsed to obtain command parsing packets; Factor matching is performed on the parsed content in the instruction parsing package to obtain the matching factor corresponding to each parsed content in the instruction parsing package, and a matching factor set is constructed. Extract the device adjustment strategy corresponding to the matching factor set from the preset factor-strategy lookup table; The positions of each generator base within the generator set are adjusted according to the aforementioned equipment adjustment strategy.

8. A monitoring system for generator displacement in a wind turbine unit, characterized in that, include: The data acquisition module is used to determine the first displacement data of each generator base in the generator set; The feature extraction module is used to extract abnormal features from the first displacement data and establish a feature dataset; The preprocessing module is used to preprocess the feature dataset to obtain the data to be analyzed; The state analysis module is used to analyze the displacement state of each generator base in the generator set based on the feature dataset and the data to be analyzed, and to obtain state analysis data. The monitoring and early warning module is used to generate monitoring and early warning instructions based on the feature dataset, the data to be analyzed, and the status analysis data. The system is also used for: adjusting the position of each generator base in the generator set based on the monitoring and early warning command; determining the second displacement data of each generator base in the generator set after adjustment; determining the standard position data of each generator base in the generator set; comparing the standard position data with the second displacement data to obtain position difference data; parsing the position difference data to obtain the position change data of the adjusted generator base at multiple preset position points; extracting features from the position change data and constructing a key feature set. Select a correction analysis model that matches the key feature set from the model database; obtain the format information of the correction analysis model, and perform format conversion on the position change data based on the format information to obtain format-converted data; The format-converted data is input into the correction analysis model for correction analysis, and the axial offset analysis results and radial offset analysis results of the generator base are obtained respectively. The axial offset analysis results include the axial offset coefficients corresponding to the preset position points of each row on the generator base, and the radial offset analysis results include the radial offset coefficients corresponding to the preset position points of each column on the generator base.

Images