Fan installation monitoring method, device and equipment based on bolt axial stress measurement

Abstract

The disclosure provides a fan installation monitoring method, device and equipment based on bolt axial stress measurement, which comprises collecting historical bolt axial stress data in the fan installation process to obtain a historical bolt data set, wherein the historical bolt data set comprises a normal bolt data set and an abnormal bolt data set; based on the normal bolt data set, a network training database is built; based on the abnormal bolt data set, a bolt damage data evaluation model is built; according to the network training database and the bolt damage data evaluation model, a bolt axial force monitoring model of the fan installation process is built, and a first mapping relationship is determined; and according to the first mapping relationship, the fan installation process is dynamically monitored. Through the disclosure, the fan installation process can be effectively monitored based on the key connection position, the installation quality and stability of the fan are improved, and a strong technical basis is provided for the installation, maintenance, modification and supervision of related parts.

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence technology, and in particular to a method, apparatus and equipment for monitoring wind turbine installation based on bolt axial stress measurement. Background Technology

[0002] Bolts are the most common and critical force transmission connection components in wind turbine generator sets. They are often used for pitch bearing connections, tower flange connections, or other structural connection components. Bolts bear axial force, bending moment, lateral force, and torque. The stability of bolts is directly related to the safe operation of wind turbine generator sets. Once a bolt breaks or falls off, it should be inspected or maintained in a timely manner.

[0003] Among related technologies, monitoring the installation process of wind turbines is particularly important. This is usually achieved by increasing the intensity of inspections and shortening the inspection cycle.

[0004] In this approach, inspections consume a lot of time and manpower, the timeliness of the inspection and monitoring results is poor, and it is impossible to maintain or improve the solution in a timely manner when installation problems occur, thus failing to effectively monitor the quality and stability of the wind turbine installation. Summary of the Invention

[0005] This disclosure aims to at least partially address one of the technical problems in the related art.

[0006] Therefore, the purpose of this disclosure is to propose a method, device and equipment for monitoring the installation of wind turbines based on bolt axial stress measurement, which can effectively monitor the wind turbine installation process based on key connection parts, improve the installation quality and stability of wind turbines, and provide strong technical basis for the installation, maintenance, modification and supervision of related components.

[0007] The wind turbine installation monitoring method based on bolt axial stress measurement proposed in the first aspect of this disclosure includes: collecting historical bolt axial stress data during the wind turbine installation process to obtain a historical bolt data set, wherein the historical bolt data set includes a normal bolt data set and an abnormal bolt data set; building a network training database based on the normal bolt data set; building a bolt damage data evaluation model based on the abnormal bolt data set; building a bolt axial force monitoring model for the wind turbine installation process according to the network training database and the bolt damage data evaluation model, and determining a first mapping relationship; and dynamically monitoring the wind turbine installation process according to the first mapping relationship.

[0008] The wind turbine installation monitoring method based on bolt axial stress measurement proposed in the first aspect of this disclosure collects historical bolt axial stress data during the wind turbine installation process to obtain a historical bolt data set, which includes a normal bolt data set and an abnormal bolt data set. Then, based on the normal bolt data set, a network training database is built; based on the abnormal bolt data set, a bolt damage data evaluation model is built; subsequently, based on the network training database and the bolt damage data evaluation model, a bolt axial force monitoring model for the wind turbine installation process is built, and a first mapping relationship is determined. Based on the first mapping relationship, the wind turbine installation process is dynamically monitored. Since the bolt axial force monitoring model is built based on the historical bolt data set, and the first mapping relationship is determined using this model, the wind turbine installation process can be effectively monitored based on key connection points, improving the installation quality and stability of the wind turbine and providing strong technical support for the installation, maintenance, modification, and supervision of related components.

[0009] The wind turbine installation monitoring device based on bolt axial stress measurement according to the second aspect of this disclosure includes: a data acquisition module for acquiring historical bolt axial stress data during the wind turbine installation process to obtain a historical bolt data set, wherein the historical bolt data set includes a normal bolt data set and an abnormal bolt data set; a first construction module for constructing a network training database based on the normal bolt data set; a second construction module for constructing a bolt damage data evaluation model based on the abnormal bolt data set; a third construction module for constructing a bolt axial force monitoring model for the wind turbine installation process based on the network training database and the bolt damage data evaluation model, and determining a first mapping relationship; and a monitoring module for dynamically monitoring the wind turbine installation process according to the first mapping relationship.

[0010] The wind turbine installation monitoring device based on bolt axial stress measurement proposed in the second aspect of this disclosure collects historical bolt axial stress data during the wind turbine installation process to obtain a historical bolt data set, which includes a normal bolt data set and an abnormal bolt data set. Then, based on the normal bolt data set, a network training database is built; based on the abnormal bolt data set, a bolt damage data evaluation model is built; subsequently, based on the network training database and the bolt damage data evaluation model, a bolt axial force monitoring model for the wind turbine installation process is built, and a first mapping relationship is determined. Based on the first mapping relationship, the wind turbine installation process is dynamically monitored. Because the bolt axial force monitoring model is built based on the historical bolt data set, and the first mapping relationship is determined using this model, the wind turbine installation process can be dynamically monitored based on key connection points, improving the installation quality and stability of the wind turbine and providing strong technical support for the installation, maintenance, modification, and supervision of related components.

[0011] A third aspect of this disclosure provides an electronic device, comprising: 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, the instructions being executed by the at least one processor to enable the at least one processor to perform the wind turbine installation monitoring method based on bolt axial stress measurement according to the first aspect of this disclosure.

[0012] In a fourth aspect, this disclosure provides a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute a wind turbine installation monitoring method based on bolt axial stress measurement, as described in the first aspect of this disclosure.

[0013] In a fifth aspect, this disclosure provides a computer program product, including a computer program that, when executed by a processor, implements the wind turbine installation monitoring method based on bolt axial stress measurement according to the first aspect of this disclosure.

[0014] Additional aspects and advantages of this disclosure will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this disclosure. Attached Figure Description

[0015] The above and / or additional aspects and advantages of this disclosure will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, in which:

[0016] Figure 1 This is a schematic flowchart of a fan installation monitoring method based on bolt axial stress measurement according to an embodiment of this disclosure;

[0017] Figure 2 This is a schematic flowchart of a fan installation monitoring method based on bolt axial stress measurement, proposed in another embodiment of this disclosure.

[0018] Figure 3 This is a schematic flowchart of a fan installation monitoring method based on bolt axial stress measurement, proposed in another embodiment of this disclosure.

[0019] Figure 4 This is a schematic flowchart of a fan installation monitoring method based on bolt axial stress measurement, proposed in another embodiment of this disclosure.

[0020] Figure 5 This is a schematic diagram of the structure of a fan installation monitoring device based on bolt axial stress measurement according to an embodiment of this disclosure;

[0021] Figure 6 This is a schematic diagram of the structure of a fan installation monitoring device based on bolt axial stress measurement according to another embodiment of this disclosure;

[0022] Figure 7 A block diagram of an exemplary electronic device suitable for implementing embodiments of the present disclosure is shown. Detailed Implementation

[0023] Embodiments of this disclosure are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are used only to explain this disclosure, and should not be construed as limiting this disclosure. Rather, embodiments of this disclosure include all variations, modifications, and equivalents falling within the spirit and scope of the appended claims.

[0024] Figure 1 This is a schematic flowchart of a fan installation monitoring method based on bolt axial stress measurement, as proposed in one embodiment of this disclosure.

[0025] It should be noted that the execution subject of the wind turbine installation monitoring method based on bolt axial stress measurement in this embodiment is a wind turbine installation monitoring device based on bolt axial stress measurement. This device can be implemented by software and / or hardware. The device can be configured in an electronic device, which may include, but is not limited to, a terminal, a server, etc.

[0026] like Figure 1 As shown, the wind turbine installation monitoring method based on bolt axial stress measurement includes:

[0027] S101: Collect historical bolt axial stress data during the wind turbine installation process to obtain a historical bolt data set, which includes a normal bolt data set and an abnormal bolt data set.

[0028] Among them, the historical bolt axial stress data is the data information about the bolt axial stress collected during the wind turbine installation process. Multiple historical bolt axial stress data sets constitute the historical bolt data set, which includes the normal bolt data set and the abnormal bolt data set.

[0029] The normal bolt data set is a set of data from the historical bolt data set that represents the axial stress data of historical bolts during normal installation.

[0030] The abnormal bolt data set is a set of data from the historical bolt data set that represents the axial stress data of historical bolts during abnormal installation. The abnormal bolt data set may include environmental anomaly data and fault anomaly data. The actual bolt axial stress data may contain various other dimensional parameter data, and no uniqueness limit is imposed here.

[0031] In this embodiment of the disclosure, collecting historical bolt axial stress data during the wind turbine installation process can be achieved by building a wind turbine installation monitoring system and setting up a data acquisition unit within the system to collect historical bolt axial stress data. Alternatively, historical bolt axial stress data can be obtained from a network or from pre-existing historical data. Or, any other possible implementation method can be used to collect historical bolt axial stress data during the wind turbine installation process, without any limitation.

[0032] In this embodiment of the disclosure, after collecting historical bolt axial stress data during the wind turbine installation process, the historical bolt axial stress data can be divided into normal bolt data and abnormal bolt data, and normal bolt data set and abnormal bolt data set can be generated respectively to obtain historical bolt data set.

[0033] In other words, the embodiments of this disclosure support the collection of historical bolt axial stress data during the wind turbine installation process to obtain a historical bolt data set, thereby ensuring the authenticity and objectivity of the data.

[0034] In this embodiment of the disclosure, after collecting historical bolt axial stress data during the wind turbine installation process and obtaining a historical bolt data set, subsequent steps can be triggered.

[0035] S102: Build a network training database based on a normal bolt dataset.

[0036] The network training database is a database used for network training. This network training process can be neural network training, or, for example, deep learning network training, without any restrictions.

[0037] In some embodiments, building a network training database can be achieved by classifying a set of normal bolt data, configuring reference labels, and optimizing the data distribution of the normal bolt data set by setting reference labels, thereby obtaining the network training database.

[0038] In other embodiments, building a network training database can also involve preprocessing the normal bolt data set (such as data transformation, data integration, data cleaning, etc.) to obtain the network training database based on the preprocessed data set.

[0039] Of course, any possible implementation can be used to process normal bolt datasets and build a network training database; there are no restrictions on this.

[0040] S103: Based on the abnormal bolt data set, build a bolt damage data evaluation model.

[0041] The bolt damage data assessment model is a data model that evaluates abnormal bolt data and analyzes the abnormal state of bolts. The abnormal state of bolts can be bolt breakage or bolt loosening, etc., without any restrictions.

[0042] In this embodiment of the disclosure, the abnormal bolt data set may be classified, a comparison label may be configured, and a bolt damage data evaluation model may be built by setting the comparison label. Alternatively, the abnormal bolt data set may be preprocessed (such as data transformation, data integration, data cleaning, etc.) to build a bolt damage data evaluation model based on the preprocessed data set. There is no limitation on this.

[0043] S104: Based on the network training database and bolt damage data evaluation model, build a bolt axial force monitoring model for the wind turbine installation process and determine the first mapping relationship.

[0044] Among them, the bolt axial force monitoring model is a model used to monitor the axial stress of bolts. It can perform monitoring tasks during the installation of wind turbines and obtain the monitoring results of the axial stress of bolts.

[0045] The mapping relationship between the axial stress of the bolt and the characteristic parameter information during the installation process of the wind turbine can be called the first mapping relationship. It can be understood that if the axial stress of the bolt is in a normal state, the installation process of the wind turbine is also in a normal state. If the axial stress of the bolt is in an abnormal state, the bolt damage situation corresponding to the abnormal state can be determined according to the bolt damage data evaluation model, without any restrictions.

[0046] Among them, the characteristic parameter information refers to the characteristic parameters corresponding to each state during the installation of the wind turbine, such as the characteristic parameter information corresponding to the normal state and the characteristic parameter information corresponding to the abnormal state. There are no restrictions on this.

[0047] The features in the feature parameter information can be specific, such as the material properties of the bolt and the connected parts, stiffness, friction, bolt preload, external load, ambient temperature, etc., and there are no restrictions on them.

[0048] In this embodiment, the normal state of the bolt corresponds to the network training database, and the abnormal state of the bolt corresponds to the bolt damage data evaluation model. The models for determining the normal state and the abnormal state of the bolt can be merged to build a bolt axial force monitoring model for the wind turbine installation process, providing a model basis for determining the state of the bolt.

[0049] In this embodiment of the disclosure, model data processing can be performed based on the bolt axial force monitoring model to determine the characteristic parameter information corresponding to the bolt axial stress, and the characteristic parameter information can be matched with the bolt axial stress to determine the first mapping relationship. Alternatively, data information in the bolt axial force monitoring model can be extracted and the first mapping relationship can be determined based on the actual process of wind turbine installation. Alternatively, any other possible implementation method can be used to determine the first mapping relationship, without any limitation.

[0050] S105: Based on the first mapping relationship, dynamically monitor the wind turbine installation process.

[0051] In this embodiment of the disclosure, the mapping conditions between the axial stress of the bolt and the characteristic parameter information of the fan can be determined according to the first mapping relationship.

[0052] For example, when the axial stress is N, the characteristic parameter information corresponding to the axial stress N is determined according to the first mapping relationship, and the installation status of the wind turbine indicated by the characteristic parameter information is determined, so as to dynamically monitor the wind turbine installation process.

[0053] In this embodiment, historical bolt axial stress data during the wind turbine installation process is collected to obtain a historical bolt data set, which includes normal bolt data sets and abnormal bolt data sets. Then, a network training database is built based on the normal bolt data set, and a bolt damage data evaluation model is built based on the abnormal bolt data set. Subsequently, a bolt axial force monitoring model for the wind turbine installation process is built based on the network training database and the bolt damage data evaluation model, and a first mapping relationship is determined. Based on this first mapping relationship, the wind turbine installation process is dynamically monitored. Since the bolt axial force monitoring model is built based on the historical bolt data set, and the first mapping relationship is determined using this model, the wind turbine installation process can be effectively monitored based on key connection points, improving the installation quality and stability of the wind turbine and providing strong technical support for the installation, maintenance, modification, and supervision of related components.

[0054] Figure 2 This is a schematic flowchart of a fan installation monitoring method based on bolt axial stress measurement, proposed in another embodiment of this disclosure.

[0055] like Figure 2 As shown, the wind turbine installation monitoring method based on bolt axial stress measurement includes:

[0056] S201: Collect historical bolt axial stress data during the wind turbine installation process to obtain a historical bolt data set, which includes a normal bolt data set and an abnormal bolt data set.

[0057] For a detailed description of S201, please refer to the above embodiments, which will not be repeated here.

[0058] S202: Perform data preprocessing on the normal bolt dataset and use the preprocessed data as standard training data.

[0059] The standard training data is data obtained from a normal bolt dataset through data preprocessing.

[0060] In this embodiment of the disclosure, data preprocessing of the normal bolt dataset can be performed by dividing the data in the normal bolt dataset into parameters and performing frequency statistics on parameters of the same type to obtain standard training data. Alternatively, data transformation, data statistics, or other preprocessing methods can be used to process the data in the normal bolt dataset to obtain standard training data. Or, any other possible implementation method can be used to preprocess the normal bolt dataset and use the preprocessed data as standard training data. There are no restrictions on this.

[0061] Understandably, there is no single preprocessing scheme, and the specific processing scheme can be determined based on the actual changes in parameters.

[0062] S203: Perform deep analysis on the standard training data to generate analytical data, which includes bolt connection structure data, bolt preload data, and wind speed environmental data.

[0063] Among them, the analytical data is the data information obtained after the standard training data has been processed by deep analysis. The analytical data includes bolt connection structure data, bolt preload data, and wind speed environmental data.

[0064] Among them, bolt connection structure data refers to the data information of the structure connected by bolts, such as various types of connections, such as butt joints, lap joints, and T-joints, without any restrictions.

[0065] Among them, bolt preload data is used to represent the preload information of the bolt during connection.

[0066] Among them, wind speed environmental data refers to data such as wind speed and wind force in the area where the wind turbine is located.

[0067] In this embodiment of the disclosure, various deep parsing processing methods can be used to process standard training data to obtain parsed data.

[0068] In this embodiment of the disclosure, clustering operations can be performed on the standard training data to obtain the data dimensions of the standard training data. The data dimensions can be bolt connection structure data, bolt preload data, wind speed environmental data, etc., in order to obtain analytical data.

[0069] In some embodiments, clustering operations on standard training data can be performed by determining a clustering algorithm model and using that model to perform clustering operations on the standard training data; alternatively, clustering operations can be performed on the standard training data using artificial intelligence clustering methods; or, the standard training data can be subjected to deep analysis processing based on any other possible implementation method to generate analytical data, without any limitation.

[0070] S204: Perform weight analysis on the bolt connection structure data, bolt preload data, and wind speed environmental data respectively to determine the first influence weight corresponding to the bolt connection structure data, the second influence weight corresponding to the bolt preload data, and the third influence weight corresponding to the wind speed environmental data.

[0071] The first influencing weight is the weight information corresponding to the bolt connection structure data; the second influencing weight is the weight information corresponding to the bolt preload data; and the third influencing weight is the weight information corresponding to the wind speed environmental data.

[0072] In this embodiment of the disclosure, the installation status of the wind turbine can be analyzed, and a first influence weight corresponding to the bolt connection structure data, a second influence weight corresponding to the bolt preload data, and a third influence weight corresponding to the wind speed environment data can be configured according to the actual situation.

[0073] Optionally, in this embodiment of the disclosure, weight analysis is performed on the bolt connection structure data, bolt preload data, and wind speed environmental data to determine the first influence weight corresponding to the bolt connection structure data, the second influence weight corresponding to the bolt preload data, and the third influence weight corresponding to the wind speed environmental data. This can be achieved by constructing a weight allocation expert system, inputting the bolt connection structure data, bolt preload data, and wind speed environmental data into the weight allocation expert system sequentially, training the weight allocation, and obtaining the training results of the weight allocation expert system. The training results include the first influence weight corresponding to the bolt connection structure data, the second influence weight corresponding to the bolt preload data, and the third influence weight corresponding to the wind speed environmental data.

[0074] The sum of the weights of the first influence weight, the second influence weight, and the third influence weight is 1. The weight allocation expert system is used to allocate specific weight ratios.

[0075] Of course, in this embodiment of the invention, relevant personnel can also directly configure the influence weights of the bolt connection structure data, the bolt preload data, and the wind speed environmental data, without any limitation.

[0076] S205: Using the first influence weight, the second influence weight, and the third influence weight as reference identification information, train the standard training data to generate normal bolt axial force data distribution information.

[0077] Among them, the data information that is identified by weighting the data volume can be called the comparison identification information.

[0078] In this embodiment of the disclosure, the first influence weight, the second influence weight, and the third influence weight can be directly used as the comparison identification information, or they can be combined with other weight information as the comparison identification information, and there is no limitation on this.

[0079] In this embodiment of the disclosure, after determining the reference identification information, standard training data can be trained to generate normal bolt axial force data distribution information.

[0080] S206: Based on the comparison identification information and the distribution information of normal bolt axial force data, a network training database is built.

[0081] In this embodiment, data distribution information corresponding to the axial force of each normal bolt can be obtained. The data distribution information satisfies the weight allocation result in the comparison identification information. Then, based on the comparison identification information and the data distribution information of the normal bolt axial force, a network training database is built, ensuring the effectiveness and rationality of the data distribution of the network training database.

[0082] S207: Based on the abnormal bolt data set, build a bolt damage data assessment model.

[0083] S208: Based on the network training database and bolt damage data evaluation model, build a bolt axial force monitoring model for the wind turbine installation process and determine the first mapping relationship.

[0084] S209: Based on the first mapping relationship, dynamically monitor the wind turbine installation process.

[0085] The descriptions of S207-S209 can be found in the above embodiments, and will not be repeated here.

[0086] In this embodiment, since a bolt axial force monitoring model is built based on historical bolt data sets, and the first mapping relationship is determined using this model, the wind turbine installation process is dynamically monitored. This enables effective monitoring of the wind turbine installation process based on key connection points, improving the installation quality and stability of the wind turbine. It also provides strong technical support for the installation, maintenance, modification, and supervision of related components. Because the network training database is built based on the comparison identification information and the distribution information of normal bolt axial force data, the rationality of the influence weights of various data in the network training database can be guaranteed, making the data in the network training database more applicable to actual scenarios and ensuring the effectiveness and objectivity of the data distribution in the network training database.

[0087] Figure 3 This is a schematic flowchart of a fan installation monitoring method based on bolt axial stress measurement, proposed in another embodiment of this disclosure.

[0088] like Figure 3 As shown, the wind turbine installation monitoring method based on bolt axial stress measurement includes:

[0089] S301: Collect historical bolt axial stress data during the wind turbine installation process to obtain a historical bolt data set, which includes a normal bolt data set and an abnormal bolt data set.

[0090] S302: Build a network training database based on a normal bolt dataset.

[0091] For a detailed description of S301-S302, please refer to the above embodiments, which will not be repeated here.

[0092] S303: Based on the abnormal bolt data set, determine the fault category set of the abnormal bolt data, where the fault category set includes the fault log.

[0093] The set of bolt failure types during wind turbine installation can be called the failure category set. The failure category set can specifically include failure types such as bolt breakage and bolt loosening, without any restrictions.

[0094] It is understandable that abnormal conditions of bolts can be caused by a variety of reasons, such as bolt breakage due to overload, bolt loosening due to insufficient preload, bolt breakage will reduce the axial stress of the bolt, and in severe cases, the axial stress of the bolt will be zero. Bolt loosening will also reduce the axial stress of the bolt.

[0095] In this embodiment of the disclosure, based on the abnormal bolt data set, the abnormal bolt data set is classified into data categories by corresponding to multiple abnormal states of the bolts with the abnormal bolt data set, and the fault category set of each abnormal bolt data is determined. The number of abnormal categories of each abnormal bolt data can correspond to the number of abnormal categories of multiple abnormal states of the bolt.

[0096] S304: Perform full-cycle tracking of fault logs and generate a full-cycle fault data set.

[0097] The full-cycle fault data set is the set of fault data that has been tracked throughout the entire lifecycle.

[0098] In this embodiment of the disclosure, a recording unit can be configured in the wind turbine installation monitoring system to obtain log information during the wind turbine installation and operation process, and extract fault logs from the log information. For example, a fault identifier can be configured for the fault log, and the fault log can be directly exported from the operation log through the fault identifier. There are no restrictions on this.

[0099] Understandably, the faults are phased and varied. For example, in the initial stage of installation, the bolt preload may be insufficient, causing the bolts to loosen, but there may be instances where the axial stress of the bolts reaches the standard threshold range. Full-cycle tracking refers to the full-cycle tracking of data corresponding to the fault states. By performing full-cycle tracking on the fault logs corresponding to the fault category set, a full-cycle fault data set is obtained. This full-cycle fault data set can include all fault parameter data from the initial installation stage to real-time.

[0100] S305: Based on the full-cycle fault data set, a bolt damage data evaluation model is built.

[0101] In this embodiment of the disclosure, a bolt damage data evaluation model is built based on a full-cycle fault data set. This can be done by determining the fault data of the bolt, then determining the bolt damage data evaluation corresponding to the fault data, and building the bolt damage data evaluation model based on the bolt fault data and the corresponding bolt damage data evaluation.

[0102] Optionally, the following steps are taken: first abnormal bolt data is obtained from the abnormal bolt data set; manufacturing data acquisition and processing is performed on the first abnormal bolt data to determine the first yield strength; based on the first yield strength, stress analysis is performed on the first abnormal bolt data under multiple different external loads to generate bolt damage distribution information; correlation analysis is performed on different external loads and bolt damage distribution information to determine the initial external load-bolt damage mapping relationship; based on the initial external load-bolt damage mapping relationship, the abnormal bolt data set is traversed to obtain the target external load-bolt damage mapping relationship; and a bolt damage data evaluation model is built based on the target external load-bolt damage mapping relationship.

[0103] Among them, the first abnormal bolt data is the basic data information corresponding to the abnormal bolt in the abnormal bolt data set. The first abnormal bolt data may include the preload data of the abnormal bolt, bolt connection structure data, etc., without any restrictions.

[0104] Manufacturing data acquisition and processing involves collecting manufacturing data for bolts. This manufacturing data includes information on the material properties, stiffness, and other characteristics of the bolts and the connected components. Specifically, manufacturing data can include, for example, the yield strength of the bolts.

[0105] Among them, the critical stress value for the yield of bolt material is the value at which the bolt continues to undergo significant plastic deformation even without increasing the load when the external load on the bolt reaches a certain limit. This value can be called the first yield limit.

[0106] In this embodiment of the disclosure, the stress information of the bolt is proportional to the deformation of the bolt. Based on the first yield limit, the data of the first abnormal bolt can be analyzed under different external loads to obtain the corresponding bolt damage distribution information. This bolt damage distribution information can be used to determine whether the bolt damage is less than the first yield limit. If it is less than the first yield limit, the bolt damage is determined. If it is greater than the first yield limit, it can be indicated that the bolt is damaged.

[0107] In this embodiment of the disclosure, correlation analysis is performed on different external loads and bolt damage distribution information to determine the initial external load-bolt damage mapping relationship. It can be understood that the bolt damage distribution can be determined in combination with the bolt deformation. That is to say, the bolt external load and bolt damage distribution information have a mapping, and this mapping can be called the initial external load-bolt damage mapping relationship.

[0108] In this embodiment of the disclosure, by traversing the abnormal bolt data set, the target external load-bolt damage mapping relationship can be obtained. The target external load-bolt damage mapping relationship is a standard mapping relationship used to represent the bolt external load and bolt damage. Based on the target external load-bolt damage mapping relationship, a bolt damage data evaluation model can be built.

[0109] In this embodiment of the disclosure, the bolt damage data evaluation model can combine the bolt damage status to determine the threshold alarm range of the bolt's axial stress, thereby ensuring the bolt's service life when the axial stress is stable.

[0110] Furthermore, for individual bolts, an experimental environment can be built based on the actual yield strength of the bolt during manufacturing. This allows for the study of applying a certain external load under different preload forces, analyzing the relationship between the external load force and bolt loosening damage, and establishing a direct mapping relationship between bolt loosening damage and the axial force of the acquired signal—that is, the initial external load-bolt damage mapping relationship. For example, in the initial installation phase, the bolt preload meets the bolt's axial stress standard. However, due to the external load force, after a period of use, the bolt undergoes a certain elastic deformation. When the bolt preload no longer meets the bolt's axial stress standard, leading to bolt loosening, a loosening warning is issued. After repair, the bolt loosening is corrected so that the bolt preload once again meets the bolt's axial stress standard. The deformation information of the bolt before and after repair corresponds to the bolt loosening damage data. By combining the bolt preload change data set with the bolt deformation information, a bolt loosening damage data model is established, which serves as a bolt damage data evaluation model.

[0111] S306: Extract abnormal features from the abnormal bolt data set to generate an abnormal feature set.

[0112] Among them, abnormal feature extraction is to obtain the characteristic parameters for determining bolt loosening damage. These characteristic parameters can be the material properties of the bolt and the connected parts, stiffness, friction, bolt preload, external load, ambient temperature, etc., without any restrictions.

[0113] In this embodiment of the disclosure, the abnormal bolt data set is subjected to abnormal feature extraction. This can be done by extracting abnormal features based on the identification markers pre-configured in the abnormal bolt data set, or by building an abnormal feature extraction model and extracting abnormal features from the abnormal bolt data set based on the abnormal feature extraction model through data recognition or other methods to generate an abnormal feature set. No limitation is imposed on this method.

[0114] S307: Based on the manufacturing data, perform feature removal on the abnormal feature set to generate an external influence feature set, where the manufacturing data is the basic information of the bolt and the connected parts.

[0115] Feature removal involves optimizing the relevant features generated by manufacturing data. For example, it removes the influence of elastic deformation caused by the material properties and stiffness of bolts and connected parts, thereby optimizing the set of abnormal features.

[0116] In this embodiment of the disclosure, feature information corresponding to manufacturing data can be removed based on the identification information to generate an external influence feature set. Alternatively, feature information corresponding to manufacturing data can be directly removed to generate an external influence feature set. Of course, any other possible implementation method can be used to remove features from the abnormal feature set to generate an external influence feature set, and there are no restrictions on this.

[0117] S308: Based on the set of external influence features, the target external load-bolt damage mapping relationship is corrected.

[0118] The correction process involves adjusting and optimizing the data, correcting the target external load-bolt damage mapping relationship, and merging and allocating weights to the data related to the target external load-bolt damage mapping relationship.

[0119] In this embodiment of the disclosure, the target external load-bolt damage mapping relationship is corrected based on the external influence feature set, which may be by redistributing the weight values ​​corresponding to the features in the external influence feature set.

[0120] For example, the external load force and bolt deformation in the characteristic parameters can be weighted in the first yield limit. The weight value corresponding to the bolt deformation is 0.7, and the weight value corresponding to the external load force is 0.3. The actual weight fusion allocation can be specifically determined by combining the correlation of bolt damage.

[0121] S309: Based on the network training database and bolt damage data evaluation model, build a bolt axial force monitoring model for the wind turbine installation process and determine the first mapping relationship.

[0122] S310: Dynamically monitor the wind turbine installation process based on the first mapping relationship.

[0123] For a detailed description of S309-S310, please refer to the above embodiments, which will not be repeated here.

[0124] In this embodiment, because a bolt axial force monitoring model is built based on historical bolt data sets, and this model is used to determine the first mapping relationship, the wind turbine installation process is dynamically monitored. This enables effective monitoring of the wind turbine installation process based on key connection points, improving the installation quality and stability of the wind turbine. It provides strong technical support for the installation, maintenance, modification, and supervision of related components. Because the bolt damage data evaluation model is built based on a full-cycle fault data set, it can perform full-cycle processing of the fault data set, ensuring the comprehensiveness, authenticity, and objectivity of the data. By traversing the abnormal bolt data set to obtain the target external load-bolt damage mapping relationship, and building a bolt damage data evaluation model based on this relationship, it can perform correlation analysis between external loads and bolt damage, effectively determining the threshold alarm range of the bolt's axial stress. Under stable axial stress conditions, this ensures the bolt's service life. Because the target external load-bolt damage mapping relationship is corrected based on an external influence feature set, it ensures that the target external load-bolt damage mapping relationship is more adapted to real-world usage scenarios, improving the authenticity and objectivity of the target external load-bolt damage mapping relationship.

[0125] Figure 4 This is a schematic flowchart of a fan installation monitoring method based on bolt axial stress measurement, proposed in another embodiment of this disclosure.

[0126] like Figure 4 As shown, the wind turbine installation monitoring method based on bolt axial stress measurement includes:

[0127] S401: Collect historical bolt axial stress data during the wind turbine installation process to obtain a historical bolt data set, which includes a normal bolt data set and an abnormal bolt data set.

[0128] S402: Build a network training database based on a normal bolt dataset.

[0129] S403: Based on the abnormal bolt data set, build a bolt damage data assessment model.

[0130] The descriptions of S401-S3403 can be found in the above embodiments, and will not be repeated here.

[0131] S404: Based on the network training database and bolt damage data evaluation model, build a bolt axial force monitoring model for the wind turbine installation process and obtain the first bolt data in the bolt data set.

[0132] The first bolt data includes the bolt's axial stress data and time data.

[0133] In this embodiment of the disclosure, the first bolt data can be determined from the bolt data set. Furthermore, the first bolt data in the bolt data set can be obtained by identifying the data information in the bolt data set based on the identification mark, or by building an identification network or identification system. There are no limitations on this.

[0134] S405: Filter the full-cycle axial force data of the first bolt data to determine the change information of the first full-cycle axial force data.

[0135] In this embodiment of the disclosure, a time-axial stress variation curve of the bolt can be constructed, and a coordinate system can be built with time as the horizontal axis and axial stress as the vertical axis. Thus, the full-cycle axial force data of the first bolt data can be filtered according to the time-axial stress variation curve.

[0136] It is understandable that the periodicity indicates that the time-axial stress variation curve has a certain data variation pattern. Based on this data variation pattern, the axial force data variation information for the first full cycle can be determined. For example, the data variation pattern can be directly used as the axial force data variation information for the first full cycle, or the data variation pattern can be processed to obtain the axial force data variation information for the first full cycle. There are no restrictions on this.

[0137] S406: Analyze the trend of axial force data changes during the first full cycle to determine the extreme value inflection point data.

[0138] Among them, the extreme value turning point data are the point data information where the trend of change in the axial force data changes in the first full cycle. There are multiple extreme value turning point data, which need to be determined in combination with the time node.

[0139] In this embodiment of the disclosure, the extreme inflection point can be the peak point of the change trend in the first full-cycle axial force data change information, which is used to indicate that the axial stress of the bolt has reached the peak. The change trend of the first full-cycle axial force data change information can be analyzed to determine multiple peak information from the change trend and directly used as extreme inflection point data. Alternatively, an analysis function can be set to process the curve corresponding to the first full-cycle axial force data change information based on the analysis function to determine multiple extreme inflection point data. There is no limitation on this.

[0140] S407: Using the extreme inflection point as the center point, calibrate the data before and after the center point to generate bolt data before and after the center point.

[0141] The time intervals between the bolt data before and after the center point are the same, and both the bolt data before and after the center point are pre-calibrated.

[0142] In this embodiment of the disclosure, the extreme inflection point can be used as the center point, a constant period position can be preset, and the data before and after the center point at the preset constant period position can be calibrated to obtain the bolt data before the center point and the bolt data after the center point.

[0143] S408: Based on the bolt data before the center point and the bolt data after the center point, determine the axial force characteristic mapping relationship of the first bolt data, and use the axial force characteristic mapping relationship as the first mapping relationship.

[0144] In this embodiment of the disclosure, the data characteristics corresponding to the bolt data before the center point and the bolt data after the center point may be different. Therefore, the characteristic parameters can be compared by combining the time nodes. The parameter information of multiple extreme inflection points of the time-axial stress change curve is traversed to construct the axial force characteristic mapping relationship of the first bolt data and use it as the first mapping relationship to provide technical support for realizing the mapping between axial stress change and characteristic parameters.

[0145] To elaborate further, the period represents a certain data variation pattern in the time-axial stress change curve. In the initial stage of installation, the bolt has not deformed, and the axial stress can reach its maximum value. As time goes by, the axial stress of the bolt decreases. When the axial stress can no longer meet the threshold of the bolt's axial stress, the bolt is repaired. After repair, due to the plastic deformation of the bolt, the axial stress can reach its peak value, which is the extreme value inflection point data. The axial stress of the bolt corresponding to the peak value is less than the axial stress of the bolt corresponding to the maximum value. Generally, the axial stress of the bolt determined by the peak value of the previous period is greater than the axial stress of the bolt determined by the peak value of the next period. Therefore, the axial force characteristic mapping relationship of the first bolt data can be determined based on the bolt data before the center point and the bolt data after the center point.

[0146] S409: Based on the first mapping relationship, dynamically monitor the wind turbine installation process.

[0147] For a detailed description of S409, please refer to the above embodiments, which will not be repeated here.

[0148] In this embodiment, since a bolt axial force monitoring model is built based on historical bolt data sets, and the first mapping relationship is determined using this model, the wind turbine installation process is dynamically monitored. This enables effective monitoring of the wind turbine installation process based on key connection points, improving the installation quality and stability of the wind turbine. It also provides strong technical support for the installation, maintenance, modification, and supervision of related components. Because the axial force characteristic mapping relationship of the first bolt data is determined based on the bolt data before and after the center point, and this axial force characteristic mapping relationship is used as the first mapping relationship, the mapping between axial stress changes and characteristic parameters can be effectively realized. The first mapping relationship can be accurately determined, and thus the stability of dynamic monitoring of the wind turbine installation process can be achieved based on the first mapping relationship.

[0149] Figure 5 This is a schematic diagram of the structure of a fan installation monitoring device based on bolt axial stress measurement according to an embodiment of this disclosure.

[0150] like Figure 5 As shown, in some embodiments, the wind turbine installation monitoring device 50 based on bolt axial stress measurement according to this disclosure includes:

[0151] The data acquisition module 501 is used to collect historical bolt axial stress data during the wind turbine installation process to obtain a historical bolt data set, which includes a normal bolt data set and an abnormal bolt data set.

[0152] The first module 502 is used to build a network training database based on a set of normal bolt data.

[0153] The second construction module 503 is used to build a bolt damage data evaluation model based on the abnormal bolt data set;

[0154] The third module 504 is used to build a bolt axial force monitoring model for the wind turbine installation process based on the network training database and bolt damage data evaluation model, and to determine the first mapping relationship; and

[0155] The monitoring module 505 is used to dynamically monitor the wind turbine installation process according to the first mapping relationship.

[0156] In some embodiments of this disclosure, such as Figure 6 As shown, Figure 6 This is a schematic diagram of a wind turbine installation monitoring device based on bolt axial stress measurement according to another embodiment of this disclosure, wherein the first assembly module 502 is specifically used for:

[0157] The normal bolt dataset was preprocessed, and the preprocessed data was used as standard training data.

[0158] The standard training data is subjected to deep analysis to generate analytical data, which includes bolt connection structure data, bolt preload data, and wind speed environmental data.

[0159] We conducted weight analysis on bolted connection structure data, bolt preload data, and wind speed environmental data to determine the first influence weight corresponding to bolted connection structure data, the second influence weight corresponding to bolt preload data, and the third influence weight corresponding to wind speed environmental data.

[0160] Using the first, second, and third influence weights as reference labels, the standard training data is trained to generate normal bolt axial force data distribution information.

[0161] A network training database was built based on the comparison identification information and the distribution information of normal bolt axial force data.

[0162] In some embodiments of this disclosure, such as Figure 6 As shown, the second assembly module 503 includes:

[0163] The determination submodule 5031 is used to determine the set of fault categories of abnormal bolt data based on the abnormal bolt data set, wherein the set of fault categories includes fault logs;

[0164] The tracing submodule 5032 is used to perform full-cycle tracing of fault logs and generate a full-cycle fault data set.

[0165] Submodule 5033 is built to construct a bolt damage data evaluation model based on a full-cycle fault data set.

[0166] In some embodiments of this disclosure, such as Figure 6 As shown, submodule 5033 is built, specifically for:

[0167] Obtain the first abnormal bolt data from the abnormal bolt data set;

[0168] The manufacturing data acquisition and processing of the first abnormal bolt data is performed to determine the first yield limit;

[0169] Based on the first yield limit, stress analysis is performed on the first abnormal bolt data under multiple different external load conditions to generate bolt damage distribution information;

[0170] Correlation analysis was performed on different external loads and bolt damage distribution information to determine the initial external load-bolt damage mapping relationship;

[0171] Based on the external load-bolt damage mapping relationship, the abnormal bolt data set is traversed to obtain the target external load-bolt damage mapping relationship;

[0172] Based on the target external load-bolt damage mapping relationship, a bolt damage data evaluation model is built.

[0173] In some embodiments of this disclosure, such as Figure 6 As shown, the device also includes:

[0174] Extraction module 506 is used to extract abnormal features from the abnormal bolt data set and generate an abnormal feature set;

[0175] Processing module 507 is used to remove abnormal features from the set of manufacturing data and generate an external influence feature set, wherein the manufacturing data consists of basic information about the bolts and the connected parts;

[0176] The correction module 508 is used to correct the target external load-bolt damage mapping relationship based on the set of external influence features.

[0177] In some embodiments of this disclosure, such as Figure 6 As shown, the third building module 504 is specifically used for:

[0178] Retrieve the data of the first bolt in the bolt data set;

[0179] The full-cycle axial force data of the first bolt is filtered to determine the change information of the first full-cycle axial force data.

[0180] Analyze the trend of axial force changes during the first full cycle to determine the extreme value inflection point data.

[0181] Using the extreme inflection point as the center point, the data before and after the center point are calibrated to generate bolt data before and after the center point;

[0182] Based on the bolt data before and after the center point, the axial force characteristic mapping relationship of the first bolt data is determined, and the axial force characteristic mapping relationship is used as the first mapping relationship.

[0183] It should be noted that the foregoing explanation of the embodiment of the wind turbine installation monitoring method based on bolt axial stress measurement also applies to the wind turbine installation monitoring device based on bolt axial stress measurement in this embodiment, and will not be repeated here.

[0184] In this embodiment, historical bolt axial stress data during the wind turbine installation process is collected to obtain a historical bolt data set, which includes normal bolt data sets and abnormal bolt data sets. Then, a network training database is built based on the normal bolt data set, and a bolt damage data evaluation model is built based on the abnormal bolt data set. Subsequently, a bolt axial force monitoring model for the wind turbine installation process is built based on the network training database and the bolt damage data evaluation model, and a first mapping relationship is determined. Based on this first mapping relationship, the wind turbine installation process is dynamically monitored. Since the bolt axial force monitoring model is built based on the historical bolt data set, and the first mapping relationship is determined using this model, the wind turbine installation process can be effectively monitored based on key connection points, improving the installation quality and stability of the wind turbine and providing strong technical support for the installation, maintenance, modification, and supervision of related components.

[0185] To implement some of the above embodiments, this disclosure also proposes an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the wind turbine installation monitoring method based on bolt axial stress measurement as proposed in the foregoing embodiments of this disclosure.

[0186] To implement some of the above embodiments, this disclosure also proposes a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the wind turbine installation monitoring method based on bolt axial stress measurement as proposed in the foregoing embodiments of this disclosure.

[0187] To implement some of the above embodiments, this disclosure also proposes a computer program product that, when executed by an instruction processor, performs a wind turbine installation monitoring method based on bolt axial stress measurement as proposed in the foregoing embodiments of this disclosure.

[0188] Figure 7 A block diagram of an exemplary electronic device suitable for implementing embodiments of the present disclosure is shown. Figure 7The electronic device 12 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0189] like Figure 7 As shown, the electronic device 12 is represented in the form of a general-purpose computing device. The components of the electronic device 12 may include, but are not limited to: one or more processors or processing units 16, system memory 28, and bus 18 connecting different system components (including system memory 28 and processing unit 16).

[0190] Bus 18 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. Examples of these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0191] Electronic device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by electronic device 12, including volatile and non-volatile media, removable and non-removable media.

[0192] Memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM) 30 and / or cache memory 32. Electronic device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write non-removable, non-volatile magnetic media (… Figure 7 Not shown; usually referred to as a "hard drive".

[0193] although Figure 7Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disc drive for reading and writing to a removable non-volatile optical disc (e.g., a compact disc read-only memory (CD-ROM), a digital video disc read-only memory (DVD-ROM), or other optical media) may be provided. In these cases, each drive may be connected to bus 18 via one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of this disclosure.

[0194] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 42 typically perform the functions and / or methods described in the embodiments of this disclosure.

[0195] Electronic device 12 can also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), and with one or more devices that enable a user to interact with electronic device 12, and / or with any device that enables electronic device 12 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed via input / output (I / O) interface 22. Furthermore, electronic device 12 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 20. As shown, network adapter 20 communicates with other modules of electronic device 12 via bus 18. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0196] The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, such as implementing the wind turbine installation monitoring method based on bolt axial stress measurement mentioned in the foregoing embodiments.

[0197] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0198] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

[0199] It should be noted that in the description of this disclosure, the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance. Furthermore, in the description of this disclosure, unless otherwise stated, "a plurality of" means two or more.

[0200] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of preferred embodiments of this disclosure includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the function involved, as will be understood by those skilled in the art to which embodiments of this disclosure pertain.

[0201] It should be understood that various parts of this disclosure can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0202] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0203] Furthermore, the functional units in the various embodiments of this disclosure can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0204] The storage media mentioned above can be read-only memory, disk, or optical disk, etc.

[0205] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this disclosure. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0206] Although embodiments of the present disclosure have been shown and described above, it is to be understood that the above embodiments are exemplary and should not be construed as limiting the present disclosure. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present disclosure.

Claims

1. A method for monitoring the installation of a wind turbine based on bolt axial stress measurement, characterized in that, The method includes: Historical bolt axial stress data during the installation process of the wind turbine are collected to obtain a historical bolt data set, which includes a normal bolt data set and an abnormal bolt data set. Based on the aforementioned normal bolt data set, a network training database is constructed, including: The normal bolt dataset is preprocessed, and the preprocessed data is used as standard training data. The standard training data is subjected to deep analysis to generate analytical data, which includes bolt connection structure data, bolt preload data, and wind speed environmental data. Weight analysis was performed on the bolt connection structure data, the bolt preload data, and the wind speed environmental data to determine the first influence weight corresponding to the bolt connection structure data, the second influence weight corresponding to the bolt preload data, and the third influence weight corresponding to the wind speed environmental data. Using the first influence weight, the second influence weight, and the third influence weight as reference identification information, the standard training data is trained to generate normal bolt axial force data distribution information; Based on the comparison identification information and the distribution information of normal bolt axial force data, the network training database is constructed; Based on the aforementioned abnormal bolt data set, a bolt damage data assessment model is constructed, including: Based on the abnormal bolt data set, a fault category set for the abnormal bolt data is determined, wherein the fault category set includes fault logs; The fault logs are tracked throughout the entire lifecycle to generate a full-lifecycle fault data set; Based on the aforementioned full-cycle fault data set, a bolt damage data assessment model is built, including: Obtain the first abnormal bolt data from the abnormal bolt data set; The manufacturing data acquisition and processing of the first abnormal bolt data is performed to determine the first yield limit; Based on the first yield limit, stress analysis is performed on the first abnormal bolt data under multiple different external load conditions to generate bolt damage distribution information. A correlation analysis is performed on the different external loads and the bolt damage distribution information to determine the initial external load-bolt damage mapping relationship; Based on the initial external load-bolt damage mapping relationship, the abnormal bolt data set is traversed to obtain the target external load-bolt damage mapping relationship; Based on the target external load-bolt damage mapping relationship, a bolt damage data evaluation model is constructed. Based on the network training database and the bolt damage data evaluation model, a bolt axial force monitoring model for the wind turbine installation process is built, and a first mapping relationship is determined; and The wind turbine installation process is dynamically monitored based on the first mapping relationship; The determination of the first mapping relationship includes: Obtain the first bolt data from the bolt data set; The full-cycle axial force data of the first bolt data is filtered to determine the change information of the first full-cycle axial force data. Analyze the trend of the first full-cycle axial force data to determine the extreme value inflection point data; Using the extreme inflection point as the center point, the data before and after the center point are calibrated to generate bolt data before the center point and bolt data after the center point. Based on the bolt data before the center point and the bolt data after the center point, the axial force feature mapping relationship of the first bolt data is determined, and the axial force feature mapping relationship is used as the first mapping relationship.

2. The method as described in claim 1, characterized in that, The method further includes: Anomaly features are extracted from the abnormal bolt data set to generate an abnormal feature set; Based on the manufacturing data, the abnormal feature set is subjected to feature removal to generate an external influence feature set, wherein the manufacturing data is the basic information of the bolt and the connected parts; Based on the set of external influence features, the target external load-bolt damage mapping relationship is corrected.

3. A fan installation monitoring device based on bolt axial stress measurement, characterized in that, The device includes: The data acquisition module is used to collect historical bolt axial stress data during the installation process of the wind turbine to obtain a historical bolt data set, wherein the historical bolt data set includes a normal bolt data set and an abnormal bolt data set; The first construction module is used to build a network training database based on the normal bolt data set; The first construction module is specifically used for: The normal bolt dataset is preprocessed, and the preprocessed data is used as standard training data. The standard training data is subjected to deep analysis to generate analytical data, which includes bolt connection structure data, bolt preload data, and wind speed environmental data. Weight analysis was performed on the bolt connection structure data, the bolt preload data, and the wind speed environmental data to determine the first influence weight corresponding to the bolt connection structure data, the second influence weight corresponding to the bolt preload data, and the third influence weight corresponding to the wind speed environmental data. Using the first influence weight, the second influence weight, and the third influence weight as reference identification information, the standard training data is trained to generate normal bolt axial force data distribution information; Based on the comparison identification information and the distribution information of normal bolt axial force data, the network training database is constructed; The second construction module is used to build a bolt damage data evaluation model based on the abnormal bolt data set. The second construction module includes: The determination submodule is used to determine the set of fault categories of the abnormal bolt data based on the abnormal bolt data set, wherein the set of fault categories includes fault logs; The tracking submodule is used to perform full-cycle tracking of the fault logs and generate a full-cycle fault data set. A submodule is built to construct a bolt damage data evaluation model based on the full-cycle fault data set. The aforementioned construction submodule is specifically used for: Obtain the first abnormal bolt data from the abnormal bolt data set; The manufacturing data acquisition and processing of the first abnormal bolt data is performed to determine the first yield limit; Based on the first yield limit, stress analysis is performed on the first abnormal bolt data under multiple different external load conditions to generate bolt damage distribution information. A correlation analysis is performed on the different external loads and the bolt damage distribution information to determine the initial external load-bolt damage mapping relationship; Based on the initial external load-bolt damage mapping relationship, the abnormal bolt data set is traversed to obtain the target external load-bolt damage mapping relationship; Based on the target external load-bolt damage mapping relationship, a bolt damage data evaluation model is constructed. The third module is used to build a bolt axial force monitoring model for the wind turbine installation process based on the network training database and the bolt damage data evaluation model, and to determine the first mapping relationship; and The monitoring module is used to dynamically monitor the wind turbine installation process according to the first mapping relationship; The third construction module is specifically used for: Obtain the first bolt data from the bolt data set; The full-cycle axial force data of the first bolt data is filtered to determine the change information of the first full-cycle axial force data. Analyze the trend of the first full-cycle axial force data to determine the extreme value inflection point data; Using the extreme inflection point as the center point, the data before and after the center point are calibrated to generate bolt data before the center point and bolt data after the center point. Based on the bolt data before the center point and the bolt data after the center point, the axial force feature mapping relationship of the first bolt data is determined, and the axial force feature mapping relationship is used as the first mapping relationship.

4. The apparatus as described in claim 3, characterized in that, The device further includes: The extraction module is used to extract abnormal features from the abnormal bolt data set and generate an abnormal feature set. The processing module is used to perform feature removal on the abnormal feature set based on the manufacturing data to generate an external influence feature set, wherein the manufacturing data is the basic information of the bolt and the connected parts; The correction module is used to correct the target external load-bolt damage mapping relationship based on the set of external influence features.

5. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the wind turbine installation monitoring method based on bolt axial stress measurement as described in any one of claims 1-2.

6. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to execute the wind turbine installation monitoring method based on bolt axial stress measurement as described in any one of claims 1-2.

Images