Fan tower drum deformation real-time monitoring and early warning system, method and equipment based on Internet of Things safety

Abstract

The invention provides a fan tower drum deformation real-time monitoring and early warning system, method and equipment based on Internet of Things safety, and relates to the technical field of wind power generation. The system comprises a sensor module used for collecting deformation data of a fan tower, and the deformation data comprises strain data, inclination data, micro-strain data, vibration data, wind load spectrum and temperature and humidity parameters of distributed optical fibers; the data analysis and early warning module is used for inputting the standard deformation data into the deformation prediction model and outputting a deformation prediction value; inputting the standard deformation data into a health assessment unit to obtain a health score; and sending red early warning information under the condition that the variable quantity of the deformation predicted value within the target duration is greater than a first threshold value and / or the health score is less than a second threshold value. According to the method, composite early warning is carried out through the abnormal modes of the associated multiple parameters, and the health condition of the fan tower can be judged more accurately.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of wind power generation, in particular, to a wind turbine tower deformation real-time monitoring and early warning system, method and device based on Internet of Things security. BACKGROUND

[0002] Wind turbine tower deformation monitoring is an important means to ensure the safe and stable operation of wind turbines by using various sensors and measurement techniques to monitor and evaluate the deformation of wind turbine towers in real time or periodically. After analyzing the monitoring data, stress abnormalities, cracks or fatigue damage can be identified, thereby providing early warning and taking maintenance measures, which is crucial for the safety of wind farms and the service life of wind turbines.

[0003] However, the related art wind turbine tower deformation monitoring has the following deficiencies: traditional point sensors can only obtain discrete point deformation data and cannot reflect the global strain distribution of the tower; it relies on manual inspection and post-disposal, lacks early risk identification capability; the data acquisition, analysis and decision-making modules operate in isolation and cannot form a closed-loop management link. SUMMARY

[0004] Embodiments of the present application provide a wind turbine tower deformation real-time monitoring and early warning system based on Internet of Things security, aiming to overcome the above problems or at least partially solve the above problems.

[0005] The first aspect of the embodiments of the present application provides a wind turbine tower deformation real-time monitoring and early warning system based on Internet of Things security, comprising: a sensor module for collecting deformation data of a wind turbine tower, the deformation data including strain data of a distributed optical fiber, inclination data, micro-strain data, vibration data, wind load spectrum and temperature and humidity parameters; a data acquisition and transmission module for preliminarily processing the deformation data to obtain preliminarily processed deformation data; a data processing and storage module for preprocessing the preliminarily processed deformation data to obtain standard deformation data, adding corresponding metadata tags to each parameter in the standard deformation data, and storing the standard deformation data; a data analysis and early warning module for inputting the standard deformation data into a deformation prediction model to output a deformation prediction value, inputting the standard deformation data into a health assessment unit to obtain a health score, and sending a red early warning information in the case that the change amount of the deformation prediction value is greater than a first threshold value within a target time length and / or the health score is less than a second threshold value. A system management and maintenance module is configured to manage and maintain the sensor module, the data acquisition and transmission module, the data processing and storage module, and the data analysis and early warning module, and to fix the operation records of the user on each module through the blockchain technology.

[0006] In an alternative embodiment, the sensor module comprises a distributed optical fiber sensor, an inclination sensor, a micro strain gauge, a three-axis vibration sensor, an ultrasonic anemometer, and a temperature and humidity sensor.

[0007] In an alternative embodiment, the data acquisition and transmission module comprises an edge computing node and a secure communication unit. The edge computing node is configured to eliminate high-frequency noise of each parameter in the deformation data and compress the strain data of the distributed optical fiber to obtain edge pre-processed deformation data. The secure communication unit integrates a hardware encryption chip, which is configured to encrypt the edge pre-processed deformation data to obtain the preliminary processed deformation data, and transmit the preliminary processed deformation data to the data processing and storage module based on the LoRa spread spectrum technology.

[0008] In an alternative embodiment, the data processing and storage module comprises a data receiving and preprocessing submodule and a distributed storage and management submodule. The data receiving and preprocessing submodule is configured to preprocess the preliminary processed deformation data through a first processing algorithm to obtain the standard deformation data, and add corresponding metadata tags to each parameter in the standard deformation data; the first processing algorithm at least includes data cleaning, outlier processing, vibration data spectrum reconstruction, and time alignment processing. The distributed storage and management submodule is configured to perform a hierarchical storage strategy according to the data value density to store the standard deformation data.

[0009] In an alternative embodiment, the data analysis and early warning module comprises a deformation analysis and prediction submodule, a digital twin health assessment submodule, and a multi-level early warning and decision support submodule. The deformation analysis and prediction submodule is configured to train an initial deformation prediction model according to historical deformation data and tower material attribute data, and update the model parameters of the initial deformation prediction model according to a strain energy density constrained physical information loss function to obtain a trained deformation prediction model. The digital twin health assessment submodule is configured to input the standard deformation data into a health assessment unit to obtain a health score; the health assessment unit is configured to calculate strain, stress and stiffness values of each part of the tower drum according to a three-dimensional geometric model of the tower drum and the standard deformation data, and compare the values with corresponding tower drum material attribute data, and obtain the health score according to a comparison result; The multi-level early warning and decision support submodule is configured to send red early warning information when a variation of the deformation prediction value in a target time length is greater than a first threshold value, and / or when the health score is less than a second threshold value.

[0010] In an optional implementation, the deformation analysis and prediction submodule is further configured to: extract vibration spectrum features in the vibration data by fast Fourier transform, and identify a vibration main frequency and harmonic components according to the vibration spectrum features; generate a strain thermodynamic map of the fan tower drum according to the vibration main frequency, the harmonic components and strain data of the distributed optical fiber; and obtain a real-time deformation rate by differential calculation according to the tilt data; The multi-level early warning and decision support submodule is further configured to send orange early warning information when there is a continuous abnormal area in the strain thermodynamic map and an offset of the vibration main frequency is greater than a third threshold value, and send yellow early warning information when the real-time deformation rate is greater than a fourth threshold value; the yellow early warning information has a lower level than the orange early warning information, and the orange early warning information has a lower level than the red early warning information.

[0011] In an optional implementation, the digital twin health assessment submodule further includes and is configured to: input the standard deformation data of the key components into a material fatigue damage accumulation model to obtain a structural cumulative damage degree of the key components; and calculate a remaining use cycle of the key components according to the structural cumulative damage degree of the key components and a damage growth rate; the material fatigue damage accumulation model is configured to input the standard deformation data of the key components and output the structural cumulative damage degree of the key components.

[0012] In an optional implementation, the multi-level early warning and decision support submodule is further configured to: calculate a risk index of the fan tower drum according to the standard deformation data; dynamically adjust a decision threshold value according to a season and a geological condition of an area where the fan tower drum is located; send early warning processing information when the risk index is greater than the decision threshold value, and generate a maintenance scheme by matching a historical similar event based on a case library according to the standard deformation data.

[0013] The second aspect of the embodiment of the application provides a wind turbine tower deformation real-time monitoring and early warning method based on Internet of Things security, and the method comprises the following steps: Collecting deformation data of the wind turbine tower, wherein the deformation data comprises strain data, inclination data, micro-strain data, vibration data, wind load spectrum and temperature and humidity parameters of the distributed optical fiber; Performing preliminary processing on the deformation data to obtain preliminary processed deformation data; Performing preprocessing on the preliminary processed deformation data to obtain standard deformation data, adding corresponding metadata tags to each parameter in the standard deformation data, and storing the standard deformation data; Inputting the standard deformation data into a deformation prediction model to output a deformation prediction value, inputting the standard deformation data into a health assessment unit to obtain a health score, and sending red early warning information in the case that a change amount of the deformation prediction value is greater than a first threshold value within a target time length and / or the health score is less than a second threshold value.

[0014] The third aspect of the embodiment of the application provides an electronic device, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, and the computer program is executed by the processor to realize the wind turbine tower deformation real-time monitoring and early warning method based on Internet of Things security according to the second aspect of the application.

[0015] The fourth aspect of the embodiment of the application provides a computer readable storage medium, and the computer readable storage medium stores a computer program, and the computer program is executed by a processor to realize the wind turbine tower deformation real-time monitoring and early warning method based on Internet of Things security according to the second aspect of the application.

[0016] In the fan tower cylinder deformation real-time monitoring and early warning system based on Internet of Things security provided in the application, the strain data of the distributed optical fiber collected by the sensor module can reflect the strain distribution information of the tower cylinder, and the deformation condition of the tower cylinder can be more comprehensively mastered. The data analysis and early warning module obtains the health score and deformation prediction value of the fan tower cylinder according to the processed standard deformation data. When the change amount of the deformation prediction value is greater than the first threshold value, and / or the health score is less than the second threshold value, a red early warning is triggered. The double-threshold early warning form can more accurately judge the health condition of the fan tower cylinder and reduce false positives. The system management and maintenance module manages and maintains the entire system to ensure the normal operation of each module. At the same time, the operation records of users on each module are fixed through the blockchain technology, which improves the security and traceability of the system and further promotes the collaborative work between each module. The collaborative work between each module forms a closed-loop management link from data collection, transmission, processing to analysis and early warning, changes the passive mode of traditional operation and maintenance relying on manual experience and lagging response, and finally achieves the dual goals of safety control of the tower cylinder structure throughout the life cycle and collaborative optimization of economic benefits of the wind farm. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the application, the following will briefly introduce the drawings needed to be used in the description of the embodiments of the application. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can be obtained by those skilled in the art without creating labor intensity.

[0018] Figure 1 is a structural schematic diagram of a fan tower cylinder deformation real-time monitoring and early warning system based on Internet of Things security provided by an embodiment of the application; Figure 2 is a detailed structural schematic diagram of a fan tower cylinder deformation real-time monitoring and early warning system based on Internet of Things security provided by an embodiment of the application; Figure 3 is a structural schematic diagram of a data processing and storage module of a fan tower cylinder deformation real-time monitoring and early warning system based on Internet of Things security provided by an embodiment of the application; Figure 4 is a structural schematic diagram of a data analysis and early warning module of a fan tower cylinder deformation real-time monitoring and early warning system based on Internet of Things security provided by an embodiment of the application; Figure 5 is a step flow chart of a fan tower cylinder deformation real-time monitoring and early warning method based on Internet of Things security provided by an embodiment of the application; Figure 6 is a schematic diagram of an electronic device provided by an embodiment of the application. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of the present application.

[0020] In the drawings, the size of a constituent element, the thickness of a layer, or a region may be exaggerated for the sake of clarity in some cases. Therefore, any one of the implementations of the present disclosure is not necessarily limited to the size shown in the drawings. The shapes and the sizes of the components shown in the drawings do not reflect the actual ones. Furthermore, the drawings schematically show ideal examples, and any one of the implementations of the present disclosure is not limited to the shapes or numerical values shown in the drawings.

[0021] Referring to Figure 1 , Figure 1 FIG. 1 is a structural schematic diagram of a wind turbine tower deformation real-time monitoring and early warning system based on Internet of Things security according to an embodiment of the present application. As shown in FIG. 1, the system includes a sensor module 101, a data acquisition and transmission module 102, a data processing and storage module 103, a data analysis and early warning module 104, and a system management and maintenance module 105. Figure 1

[0022] The sensor module 101 is configured to acquire deformation data of the wind turbine tower, and the deformation data includes strain data of the distributed optical fiber, inclination data, micro-strain data, vibration data, wind load spectrum, and temperature and humidity parameters.

[0023] In the embodiment, the sensor module acquires deformation data of the wind turbine tower through various sensors, and the deformation data includes strain data of the distributed optical fiber, inclination data, micro-strain data, vibration data, wind load spectrum, and temperature and humidity parameters. The sensor module comprehensively acquires deformation-related data of the wind turbine tower, realizes whole-life cycle monitoring coverage from local damage to overall instability, and provides strong data support for subsequent data analysis and early warning.

[0024] ​Specifically, the sensor module includes: a distributed optical fiber sensor, an inclination sensor, a micro strain gauge, a three-axis vibration sensor, an ultrasonic anemometer, and a temperature and humidity sensor. The distributed optical fiber sensor adopts a distributed optical fiber sensing technology, tightly winds a single-mode optical fiber in a spiral path on the outer wall of the tower drum, analyzes the axial and tangential strain distribution in real time through the Brillouin scattering effect, can detect changes of ±2 micro-strain level per meter spatial resolution, eliminates the interference of thermal expansion and contraction through a temperature compensation algorithm, and obtains the strain data of the distributed optical fiber in the whole domain. The inclination sensor measures the inclination angle changes of each height section of the tower drum by the laser interference principle to obtain the inclination data, and the accuracy reaches 0.001 degrees. The micro strain gauge is attached to the stress concentration area such as the welding seam of the tower drum by using a metal foil structure, and the micro strain value is inversely calculated through the resistance change rate to obtain the micro strain data. The three-axis vibration sensor is built-in MEMS chip, which can collect vibration signals in the frequency band of 0.1-2 kHz to obtain vibration data. The ultrasonic anemometer and the temperature and humidity sensor are used to synchronously collect the wind load spectrum and temperature and humidity parameters outside the tower drum.

[0025] The data acquisition and transmission module 102 is configured to perform preliminary processing on the deformation data to obtain preliminary processed deformation data.

[0026] In this embodiment, the data acquisition and transmission module can perform preliminary processing on the deformation data by using filtering algorithms, wavelet compression technology, etc. to obtain preliminary processed deformation data. By performing preliminary processing on the deformation data, the efficiency of subsequent data processing can be improved, and the network transmission pressure can be reduced.

[0027] The data processing and storage module 103 is configured to perform preprocessing on the preliminary processed deformation data to obtain standard deformation data, add corresponding metadata tags to each parameter in the standard deformation data, and store the standard deformation data.

[0028] In this embodiment, the data processing and storage module can preprocess the preliminary processed deformation data by using data cleaning, time alignment processing, etc. to convert it into high-quality information flow for analysis, i.e., to obtain standard deformation data. For each piece of data of each parameter in the standard deformation data, a timestamp, a sensor ID (device label), a position coordinate, a calibration coefficient, etc. are added as metadata tags to construct a traceable data bloodline system. Then, the standard deformation data is stored. By deeply processing the collected data through the data processing and storage module, the data is converted into high-quality information flow for analysis, which facilitates subsequent data analysis and early warning; through the metadata tags, the original data collection scene can be traced back, improving the readability and manageability of the data; and data storage provides a guarantee for long-term preservation and subsequent analysis of the data.

[0029] The data analysis and early warning module 104 is configured to input the standard deformation data into a deformation prediction model to output a deformation prediction value, input the standard deformation data into a health assessment unit to obtain a health score, and send a red early warning information in a case where a variation of the deformation prediction value in a target time length is greater than a first threshold value and / or the health score is less than a second threshold value.

[0030] In the embodiment, the evidence theory fusion algorithm is used to eliminate the environmental noise interference of the standard deformation data. For example, the tilt data in the standard deformation data is spatiotemporally aligned with the strain data of the distributed optical fiber to distinguish the real deformation from the temporary deviation caused by strong wind. The standard deformation data is input into a deformation prediction model to output a deformation prediction value. The deformation prediction model is configured to input the standard deformation data and output the deformation prediction value. The deformation prediction value is a quantitative index of the future deformation state of the tower calculated by a machine learning model. Generally, the standard deformation data is collected by various sensors for a long time (e.g., 72 hours) to facilitate the model to predict the deformation prediction value corresponding to a target time length (e.g., the next 24 hours). The variation of the deformation prediction value is the difference between the deformation prediction values at different time points in the target time length. For example, the target time length is the next 24 hours, and the difference between the deformation prediction values at the start time and the end time in the next 24 hours is calculated to obtain the variation of the deformation prediction value. The variation of the deformation prediction value is compared with the first threshold value. If the variation of the deformation prediction value is greater than the first threshold value, a red early warning information is sent. The first threshold value is set in advance according to the safety standard of the wind turbine tower and the actual operation experience.

[0031] In the embodiment, the standard deformation data is input into a health assessment unit to obtain a health score. The health assessment unit is configured to calculate the health score of the tower according to the standard deformation data. The health score is a dynamic numerical index quantifying the overall safety state of the tower structure. The health score is compared with the second threshold value. If the health score is less than the second threshold value, a red early warning information is sent. The second threshold value is set in advance according to the safety standard of the wind turbine tower and the actual operation experience. By analyzing the deformation prediction value and the health score in real time, the accelerated deterioration trend of the deformation and the overall safety state of the tower structure can be captured. The composite early warning can be performed by associating the abnormal patterns of multiple parameters to more accurately judge the health condition of the wind turbine tower, reduce false positives, and take maintenance measures in time to avoid accidents.

[0032] The system management and maintenance module 105 is configured to manage and maintain the sensor module, the data acquisition and transmission module, the data processing and storage module, and the data analysis and early warning module, and fix the operation records of the user on each module by using the block chain technology.

[0033] In this embodiment, the system management and maintenance module manages and maintains each module to ensure the normal operation of each module, and fixes the operation records of the user on each module through the blockchain technology, thereby improving the security and traceability of the system. Specifically, the system management and maintenance module is internally provided with a user permission subunit, a device monitoring unit, a log audit engine, and a remote upgrade unit. The user permission subunit implements dynamic role access control: only authorized personnel can perform device debugging, parameter adjustment, and other operations; 12 levels of operation permissions of data browsing, parameter modification, early warning disposal, etc. are divided according to the job level of the operation and maintenance personnel, and double identity authentication is realized in combination with iris recognition and device fingerprint technology. The device monitoring unit establishes a sensor health file: the sensor and other devices are monitored, 23 device indexes such as real-time tracking of power supply voltage, signal-to-noise ratio, and communication packet loss rate are tracked, and a maintenance work order can be automatically triggered when the device index is abnormal, for example, a maintenance work order is automatically triggered when the strain gauge temperature drift exceeds the threshold. The log audit engine fixes the operation records by using the blockchain technology: the events such as device debugging, early warning response, and parameter adjustment are encrypted and chained according to the time stamp, and the reverse traceability of any operation within a preset time period (such as six months) is supported. The remote upgrade unit builds a double-partition safe start mechanism: the integrity of the firmware package is verified through digital signature, the algorithm model of the edge node is updated without sensing under the premise of maintaining business continuity; through automatic inspection and defensive maintenance strategy, the running state of each module is monitored in real time, and maintenance strategies are executed when potential problems are found, such as automatically triggering a maintenance work order, remotely upgrading the algorithm model, etc.

[0034] In the fan tower cylinder deformation real-time monitoring and early warning system based on Internet of Things security provided in the application, the strain data of the distributed optical fiber collected by the sensor module can reflect the strain distribution information of the whole tower cylinder, and the deformation condition of the tower cylinder can be more comprehensively mastered. The data analysis and early warning module obtains the health score and deformation prediction value of the fan tower cylinder according to the processed standard deformation data, triggers a red early warning when the change amount of the deformation prediction value is greater than a first threshold value and / or the health score is less than a second threshold value, and the double-threshold early warning form can more accurately judge the health condition of the fan tower cylinder and reduce false positives. The system management and maintenance module manages and maintains the whole system to ensure the normal operation of each module, at the same time, the operation records of the user on each module are fixed through the blockchain technology, thereby improving the security and traceability of the system, and further promoting the collaborative work between each module. The collaborative work between each module forms a closed-loop management link from data collection, transmission, processing to analysis and early warning, changes the passive mode of relying on manual experience and lagging response in traditional operation and maintenance, and finally achieves the dual goals of safe management and control of the tower cylinder structure throughout the life cycle and collaborative optimization of economic benefits of the wind farm.

[0035] Reference Figure 2 , Figure 2This is a detailed structural diagram of a wind turbine tower deformation real-time monitoring and early warning system based on Internet of Things security proposed in one embodiment of this application. Figure 2 As shown, the system includes: a sensor module 101, a data acquisition and transmission module 102, a data processing and storage module 103, a data analysis and early warning module 104 and a system management and maintenance module 105; the data acquisition and transmission module 102 includes: an edge computing node and a secure communication unit; the data processing and storage module 103 includes: a data reception and preprocessing submodule and a distributed storage and management submodule; the data analysis and early warning module 104 includes: a deformation analysis and prediction submodule, a digital twin health assessment submodule and a multi-level early warning and decision support submodule.

[0036] In this embodiment, the data output end of the sensor module is directly connected to the edge computing node input end of the data acquisition and transmission module via an industrial-grade shielded cable. The output end of the secure communication unit of the data acquisition and transmission module establishes two-way communication with the cloud data receiving interface of the data processing and storage module via an encrypted wireless channel. The standardized data output end of the data processing and storage module is connected to the real-time computing engine of the data analysis and early warning module via a high-throughput API interface; the multi-level early warning instruction output end of the data analysis and early warning module is interconnected with the log audit and early warning distribution interface of the system management and maintenance module via a blockchain gateway, pushing the red shutdown instruction to the wind turbine master control system in real time and synchronously writing the event log to the distributed ledger. The configuration management end of the system management and maintenance module issues control instructions to the calibration parameter interface of the sensor module, the encryption policy loading interface of the data acquisition and transmission module, the storage policy control interface of the data processing and storage module, and the data analysis and early warning module via the RESTful protocol, forming a closed-loop control link.

[0037] In one embodiment, the present application further provides a wind turbine tower deformation real-time monitoring and early warning system based on IoT security. In this system, the data acquisition and transmission module 102 specifically includes: an edge computing node and a secure communication unit: The edge computing node is used to eliminate high-frequency noise of various parameters in the deformation data and compress the strain data of the distributed optical fiber to obtain edge preprocessed deformation data; The secure communication unit integrates a hardware encryption chip for encrypting the deformation data after edge preprocessing to obtain the initially processed deformation data, and transmits the initially processed deformation data to the data processing and storage module based on LoRa spread spectrum technology.

[0038] In this embodiment, the edge computing node can carry an industrial-grade ARM processor, deploy an adaptive filtering algorithm to eliminate high-frequency noise of each parameter in the deformation data, and use wavelet compression technology to reduce the volume of strain data of the distributed optical fiber by more than 70%, obtaining the edge preprocessed deformation data. The secure communication unit integrates a hardware encryption chip, which can encrypt the edge preprocessed deformation data using the SM4 algorithm to obtain the preliminary processed deformation data. End-to-end encryption of data stream is realized, and data is encrypted at the sending end and decrypted after reaching the cloud (data processing and storage module). The secure communication unit uses LoRa spread spectrum technology to enhance the anti-interference ability of remote transmission, and designs a dual-channel redundancy mechanism to cope with sudden signal interruption, and then transmits the preliminary processed deformation data to the data processing and storage module. The data acquisition and transmission module reduces the cloud load through edge preprocessing, and ensures the reliable transmission of massive data in complex industrial environments through encryption and anti-destroying design.

[0039] In this embodiment, the data acquisition and transmission module deploys a buffer and temporarily stores data of a target duration (such as nearly 24 hours) through an edge-cloud collaborative caching mechanism to cope with network interruption, and can dynamically adjust the transmission priority according to the warning level. For example, when the distributed optical fiber sensor detects a sudden increase in local strain, the upload rate of data in the region is automatically increased to ensure that critical information reaches the cloud in real time. The data acquisition and transmission module implements data transmission between the data processing and storage module based on a data relay station when uploading data. The data relay station is deployed at the commanding heights of the wind farm, equipped with a high-gain directional antenna and a solar power supply system, and constructs a Mesh ad hoc network to realize relay transmission of data of multiple towers within a radius of 10 kilometers, and diagnoses the network node health status in real time through a heartbeat packet monitoring mechanism.

[0040] In one embodiment, referring to Figure 3 The application also provides a structural diagram of a data processing and storage module of a wind turbine tower deformation real-time monitoring and early warning system based on Internet of Things security. As Figure 3 shown, in the system, the data processing and storage module 103 specifically includes a data receiving and preprocessing submodule 201 and a distributed storage and management submodule 202: The data receiving and preprocessing submodule 201 is configured to preprocess the preliminary processed deformation data by using a first processing algorithm to obtain the standard deformation data, and add corresponding metadata tags to each parameter in the standard deformation data; the first processing algorithm at least includes data cleaning, outlier processing, vibration data spectrum reconstruction, and time alignment processing.

[0041] In this embodiment, the data receiving and preprocessing submodule pre-processes the deformation data after preliminary processing by a first processing algorithm to obtain standard deformation data, and adds corresponding metadata tags to each parameter in the standard deformation data. The first processing algorithm includes data cleaning, outlier processing, vibration data spectrum reconstruction, time alignment processing, etc. Specifically, data cleaning: this module deploys a data cleaning engine to repair missing data segments caused by sensor network disconnection or hardware failure through a time series interpolation algorithm. Outlier processing: dynamic threshold technology is used to identify outliers, and outliers are processed, for example, the reasonable fluctuation range of the inclination data is adjusted adaptively in combination with the environmental wind speed change to avoid misjudgment of the deformation state due to extreme weather. Vibration data spectrum reconstruction: the noise filtering layer integrates wavelet transform and Kalman filtering to reconstruct the spectrum of electromagnetic interference and mechanical resonance noise in the high-frequency vibration signal in the vibration data, and to retain the effective frequency band reflecting the structural damage. Time alignment processing: a unified timestamp alignment protocol is established to convert multi-source heterogeneous data such as distributed fiber strain data, angle sequence of inclination data, and spectrum matrix of vibration data into standardized time series data stream. The collected data is deeply processed to convert it into high-quality information stream for analysis, facilitating subsequent data analysis and early warning.

[0042] The distributed storage and management submodule 202 is configured to perform a hierarchical storage strategy according to data value density to store the standard deformation data.

[0043] In this embodiment, the distributed storage and management submodule is based on a hybrid architecture and performs a hierarchical storage strategy according to data value density to store standard deformation data. The hybrid architecture is a three-level storage architecture, including a real-time stream processing layer, a time series database, and cold storage. The real-time stream processing layer uses Apache Kafka and InfluxDB in combination to accept the writing of ten thousand concurrent sensor data with microsecond-level delay, and can quickly store and query real-time data (such as vibration spectrum in vibration data in standard deformation data). The time series database is based on the TDengine engine, and stores standard deformation data by time window and device label for sharding and compression, providing millisecond-level response for cross-year trend query functions, for example, quickly retrieving the seasonal deformation fluctuation curve of a certain wind turbine. The cold storage is a distributed file storage pool based on Hadoop HDFS, which uses the Snappy compression algorithm to convert low-frequency data into low-cost archive files, while retaining the ability to quickly retrieve by geographic location (position coordinates) and timestamp. According to the hierarchical storage strategy based on data value density, data in standard deformation data with high access frequency can be retained in the memory database in the real-time stream processing layer, and data in standard deformation data with low access frequency can be migrated to cold storage, and non-active data copies can be dynamically cleaned up through the LRU algorithm. Through the hybrid architecture and the hierarchical storage strategy, the needs of different data access frequencies are met, and the storage cost and access efficiency are effectively balanced.

[0044] In this embodiment, the distributed storage and management submodule establishes indexes for the stored data through a multi-dimensional index engine, such as establishing a feature hash index for the vibration spectrum in vibration data, to achieve efficient data retrieval. In addition, through an intelligent data partitioning strategy, the tower position coordinates and collection timestamps are jointly encoded to achieve geographic fence query optimization, for example, quickly extracting deformation records of all wind turbines in the northwest region of a certain wind farm during a typhoon passage. Through the multi-dimensional index engine, indexes are established for the stored data, which facilitates operators to quickly obtain the required information, and efficient data retrieval is achieved; the intelligent data partitioning strategy provides more accurate and efficient query methods for operators, which helps to quickly locate and analyze data in a specific region and time period.

[0045] In one embodiment, referring to Figure 4 The present application also provides a structural diagram of a data analysis and warning module of a wind turbine tower deformation real-time monitoring and early warning system based on Internet of Things security. As shown in Figure 4 The data analysis and warning module 104 specifically includes a deformation analysis and prediction submodule 301, a digital twin health assessment submodule 302, and a multi-level early warning and decision support submodule 303: The shape change analysis and prediction submodule 301 is configured to train an initial shape change prediction model according to historical shape change data and tower drum material attribute data, and update model parameters of the initial shape change prediction model according to a strain energy density constraint physical information loss function, to obtain a trained shape change prediction model.

[0046] In this embodiment, a large amount of historical shape change data is obtained from a distributed storage and management submodule in the data processing and storage module, and attribute information of the tower drum material, including elastic modulus, yield strength, Poisson's ratio, etc., is obtained through laboratory material testing and consulting relevant technical documents. The shape change prediction model to be trained can capture the change rule of the shape change data over time through a long short-term memory neural network. The historical shape change data is divided into a training set, a validation set and a test set according to a ratio of 70%, 15% and 15%. The training set is input into the shape change prediction model to be trained for training, and the attribute data of the tower drum material is embedded in the neural network training process. A back propagation algorithm and an optimizer (such as Adam and SGD) are used to update the parameters of the model to minimize the strain energy density constraint physical information loss function, until the performance of the model on the training set and the validation set reaches a satisfactory result, and finally a trained shape change prediction model is obtained. By introducing a physical constraint mechanism, the inherent properties of the tower drum material, such as the elastic modulus and the yield strength, are embedded in the neural network training process. The loss function is constructed through the strain energy density equation, so that the prediction result conforms to the laws of material mechanics, improves the prediction reliability under extreme working conditions, and can more accurately predict the shape change value of the wind turbine tower drum.

[0047] The formula of the strain energy density constraint physical information loss function is: L total = αL data + βL physics Wherein, L data is a data-driven loss term; L physics is a physical constraint term; and α and β are weighting coefficients. L data is calculated by the mean square error of the predicted shape change value and the measured value; and L physics is constructed through the strain energy density equation, and is specifically defined as a double-point integral of the material elastic modulus, the strain tensor and the stress tensor. The elastic modulus is obtained through laboratory material testing, and a temperature compensation coefficient is introduced to correct the environmental thermal effect; the strain tensor is calculated and generated from the axial and tangential strain components measured by the distributed optical fiber sensor; and the stress tensor is mapped according to the generalized Hooke's law and the strain tensor. The weighting coefficient is adaptively adjusted according to the prediction confidence. When the sensor data quality decreases, the physical constraint weight is automatically enhanced. The weighting coefficient dynamically balances the data fitting and the compliance with the physical law, so that the prediction result still conforms to the basic laws of material mechanics under data loss or noise interference.

[0048] In the training phase of the model, the model parameters can also be updated by setting a prediction result dynamic calibration unit. The prediction result dynamic calibration module monitors the prediction deviation in real time. When the actual deformation value deviates from the predicted value by more than a preset threshold, the online learning process is automatically triggered, the model parameters are updated by using a sliding time window strategy, and the prediction uncertainty is quantified by using a Monte Carlo random neuron discarding technology to mark a high-risk interval for manual review. By updating the model parameters by using the sliding time window strategy, the model is prevented from excessively relying on historical data, the model can focus on the current data features and change trend, and the accuracy and generalization ability of the model are improved.

[0049] The digital twin health assessment sub-module 302 is configured to input the standard deformation data into a health assessment unit to obtain a health score. The health assessment unit is configured to calculate the strain, stress and stiffness values of each part of the tower drum according to the tower drum three-dimensional geometric model and the standard deformation data, and compare the values with the corresponding tower drum material attribute data, and obtain the health score according to the comparison result. In this embodiment, the health assessment unit is based on a tower drum three-dimensional geometric model established by a finite element method, and integrates a material attribute database. The material attribute database stores the mechanical performance parameters (tower drum material attribute data) of the materials used in the tower drum, such as elastic modulus, Poisson's ratio, yield strength, etc. These parameters are the basis for finite element analysis and can reflect the mechanical behavior of the materials. The standard deformation data is input into the tower drum three-dimensional geometric unit to obtain simulation results reflecting the actual operating state of the tower drum. The health assessment unit calculates the strain, stress and stiffness values of each part of the tower drum according to the tower drum three-dimensional geometric model and the standard deformation data, and compares the values with the corresponding tower drum material attribute data to evaluate the structural integrity index scores of different regions. For example, if the stress of a certain region exceeds the yield strength of the material, the structural integrity index score of the region is lower. According to the structural integrity index scores of different regions, the overall structural integrity index score of the tower drum is obtained, i.e., the health score. The tower drum three-dimensional geometric model can continuously calibrate the model parameters by using a Kalman filtering algorithm, for example, compare the sudden increase in local strain captured by the distributed optical fiber sensor with the simulation results, automatically correct the structural stiffness degradation coefficient, so that the simulation results of the model are closer to the actual situation, and the accuracy of the model is improved.

[0050] In this embodiment, the digital twin health assessment sub-module collects and organizes common failure modes of the fan tower and their corresponding damage characteristics to establish a failure mode knowledge base. For example, bolt loosening can cause changes in tower vibration frequency, and weld cracking can exhibit a specific crack propagation pattern on the strain thermogram. The correspondence between these typical damage characteristics and failure modes is stored in the knowledge base, providing a basis for subsequent fault diagnosis. The Bayesian causal reasoning engine in the digital twin health assessment sub-module can calculate the probability distribution of each failure hypothesis based on the information in the failure mode knowledge base, and accurately locate the positions of hidden dangers such as bolt loosening and weld cracking by analyzing the probabilities of different failure hypotheses. For example, if the vibration spectrum shows a significant shift at a certain specific frequency, the Bayesian causal reasoning engine will determine that it is likely caused by bolt loosening based on the knowledge base and calculate the probability of this failure hypothesis to provide accurate fault location information for maintenance personnel.

[0051] The multi-level warning and decision support sub-module 303 is configured to send red warning information when the change in the deformation prediction value within the target time period is greater than a first threshold value and / or when the health score is less than a second threshold value.

[0052] In this embodiment, the change in the deformation prediction value within the target time period is compared with the first threshold value, and the health score is compared with the second threshold value. Red warning information is sent when the change in the deformation prediction value within the target time period is greater than the first threshold value and / or when the health score is less than the second threshold value. By correlating abnormal patterns of multiple parameters for composite warning, the health status of the fan tower can be more accurately judged, false positives can be reduced, and maintenance measures can be taken in a timely manner to prevent accidents.

[0053] In one embodiment, the present application also provides a wind turbine tower deformation real-time monitoring and warning system based on Internet of Things security. In this system, the deformation analysis and prediction sub-module 301 is further configured to: extract vibration spectrum features from the vibration data by fast Fourier transform, and identify the vibration main frequency and harmonic components based on the vibration spectrum features; generate a strain thermogram of the wind turbine tower based on the vibration main frequency, the harmonic components, and the strain data of the distributed optical fiber; and obtain the real-time deformation rate by differential calculation based on the inclination data; The multi-level warning and decision support sub-module is further configured to send orange warning information when there is a continuous abnormal area in the strain thermogram and the vibration main frequency deviates by more than a third threshold value; and send yellow warning information when the real-time deformation rate is greater than a fourth threshold value. The level of the yellow warning information is lower than that of the orange warning information, and the level of the orange warning information is lower than that of the red warning information.

[0054] In this embodiment, the deformation analysis and prediction submodule can use fast Fourier transform to extract vibration frequency spectrum features in the vibration data; by analyzing the vibration frequency spectrum features, the vibration main frequency and harmonic components in the vibration frequency spectrum features are identified; based on the Brillouin optical time domain analysis technology, the strain data of the distributed optical fiber are analyzed, and combined with the vibration main frequency and harmonic components, a strain thermal map covering the full circumference of the tower drum is generated, and the spatial resolution can reach millimeter level. The differential calculation is performed on the inclination data, that is, the ratio of the change amount of the inclination angle at adjacent time and the time interval is calculated to obtain the real-time deformation rate. The strain thermal map can intuitively show the strain distribution of the wind turbine tower drum at different positions, so as to quickly understand the stress concentration area and potential dangerous position of the tower drum; the high-risk area can be visualized through the strain thermal map, which can guide the artificial inspection path planning; the real-time deformation rate can reflect the deformation trend of the tower drum, and if the deformation rate is too large, it may indicate that the foundation of the tower drum is unstable or the structure has serious problems.

[0055] In this embodiment, the multi-level early warning and decision support submodule sends an orange early warning information when there is a continuous abnormal area in the strain thermal map and the shift of the vibration main frequency is greater than a third threshold. The continuous area refers to the adjacent or similar positions on the tower drum structure, and the strain value presents similar abnormal characteristics, while the shift of the vibration main frequency may indicate a change in structural characteristics. When the real-time deformation rate is greater than a fourth threshold, a yellow early warning information is sent. The level of the yellow early warning information is lower than that of the orange early warning information, and the level of the orange early warning information is lower than that of the red early warning information. The event log is fixed by the blockchain technology, and the hierarchical instructions are pushed to the local sound and light alarm, the operation and maintenance mobile terminal and the emergency management platform in synchronization, to ensure the timeliness and non-tamperability of the early warning information transmission. By setting different levels of early warning information, the health status of the tower drum can be warned in stages according to the severity, so that the operation and maintenance personnel can take targeted measures. The levels of orange and yellow early warnings are lower than that of red early warning, but higher than that of normal state, which can timely remind the operation and maintenance personnel to pay attention to the health status of the tower drum.

[0056] In one embodiment, the application also provides a wind turbine tower deformation real-time monitoring and early warning system based on Internet of Things security, in which the digital twin health assessment submodule 302 is further used for: inputting the standard deformation data corresponding to the key components into a material fatigue damage accumulation model to obtain the structural cumulative damage degree of the key components; and calculating the residual service life of the key components according to the structural cumulative damage degree and the damage growth rate of the key components; the material fatigue damage accumulation model is used for inputting the standard deformation data corresponding to the key components and outputting the structural cumulative damage degree of the key components.

[0057] In this embodiment, a material fatigue damage accumulation model based on a dynamic damage accumulation factor formula is constructed to build a physical mechanism. The material fatigue damage accumulation model is used to input the standard deformation data corresponding to the key component, and output the structural cumulative damage degree of the key component. According to the historical structural cumulative damage degree of the key component in the past period of time, the damage growth rate of the key component is determined. Based on the critical damage degree of the key component (which can be determined by a material fracture test), according to the structural cumulative damage degree and the damage growth rate of the key component, the remaining service period of the key component is calculated. By calculating the remaining service period of the key component, the maintenance personnel can reasonably arrange the maintenance plan of the key component and determine the best repair or replacement time.

[0058] The expression formula of the dynamic damage accumulation factor is:

[0059] wherein, D total is the structural cumulative damage degree, i.e. the dynamic damage accumulation factor, which is used to quantify the fatigue aging degree of the component; n i is the actual stress cycle number, which is obtained by statistical vibration data; N i is the material standard fatigue life, which is determined by laboratory S-N curve table lookup; σ eq is the equivalent alternating stress amplitude, which is calculated by strain data and rainflow counting method; m is the material strain hardening index; T k is the real-time temperature value, which is obtained by a temperature and humidity sensor; T ref is the reference temperature under the standard test environment; σ i is the stress reference value under the standard test environment. The formula avoids prediction deviation under complex working conditions by introducing a temperature stress coupling correction term, which helps to improve the life assessment accuracy.

[0060] In one embodiment, the application also provides a wind turbine tower deformation real-time monitoring and early warning system based on Internet of Things security. In the system, the multi-level early warning and decision support submodule 303 is further used to: calculate the risk index of the wind turbine tower according to the standard deformation data; dynamically adjust the decision threshold according to the season and the geological conditions of the area where the wind turbine tower is located; in the case where the risk index is greater than the decision threshold, send the early warning processing information, and generate a maintenance scheme by matching historical similar events based on a case library according to the standard deformation data.

[0061] In this embodiment, the risk index of the fan tower drum is calculated according to the standard deformation data by a dynamic risk index fusion formula. Considering that the weather conditions such as the size of wind in different seasons and the change of wind direction are different, the influence on the fan tower drum is also different; the geological conditions (such as soil type, underground water level, etc.) of the region where the fan tower drum is located will affect the stability of the tower drum foundation. Therefore, according to the season and the geological conditions of the region where the fan tower drum is located, the decision threshold is dynamically adjusted, for example, in winter or in the region with poor geological conditions, the external environmental risk is higher, and the warning needs to be triggered more sensitively, and the decision threshold is appropriately reduced. When the risk index is greater than the decision threshold, the warning processing information is sent, and the standard deformation data is matched with the historical similar events based on the case library to generate a maintenance scheme. The case library stores the processing cases of similar deformation conditions of the fan tower drum in the past, including fault reasons, processing methods, processing effects and other information. Through a similarity algorithm, the current deformation data is matched with the cases in the case library to find the most similar historical event. Then, according to the processing scheme of the matched historical event, the actual situation of the current fan tower drum is combined to generate a maintenance scheme, and the maintenance scheme includes the optimal maintenance path and resource allocation. The effect of different treatment measures can be simulated in the three-dimensional geometric model of the tower drum, for example, the feasibility of the tower stress relief scheme is verified by adjusting the fan load distribution. By dynamically adjusting the decision threshold, the false alarm problem of the single threshold warning under complex working conditions is avoided, and the reliability and effectiveness of the warning are improved; the maintenance scheme is generated based on the matching of the historical similar events in the case library, which provides specific processing suggestions for the operation and maintenance personnel, improves the maintenance efficiency and quality, and reduces the operation and maintenance cost.

[0062] The dynamic risk index fusion formula is:

[0063] Wherein, R is the dynamic risk index; Δd is the real-time deformation rate, which is calculated by the difference of inclination data; μ d is the mean value of historical deformation rate, which is obtained by statistical monitoring data in the past year; A e is the area of abnormal strain region detected by the distributed optical fiber sensor, A c is the total area of the tower drum section; Δf is the vibration main frequency offset, f0 is the natural frequency of the tower drum; v is the current wind speed, v max is the maximum wind resistance speed of the fan design; P f is the structure failure probability, that is, the probability of failure (such as collapse, fracture, excessive deformation, etc.) of the fan tower drum under given load and environmental conditions; λ1, λ2, λ3 are weight coefficients of deformation, strain and vibration factors respectively, which are dynamically adjusted according to the season and the geological conditions; γ is the environmental coupling coefficient, which is used to strengthen the risk sensitivity under extreme weather. The formula improves the risk judgment accuracy through multi-dimensional parameter fusion and nonlinear weighting mechanism.

[0064] Based on the same inventive concept, an embodiment of the present application provides a wind turbine tower deformation real-time monitoring and early warning method based on Internet of Things security. Figure 5 is a step flow chart of the wind turbine tower deformation real-time monitoring and early warning method based on Internet of Things security provided by an embodiment of the present application, as Figure 5 shown, the method comprises: Step S51: collecting deformation data of the wind turbine tower, the deformation data comprising strain data, inclination data, micro-strain data, vibration data, wind load spectrum and temperature and humidity parameters of the distributed optical fiber; Step S52: performing preliminary processing on the deformation data to obtain the deformation data after preliminary processing; Step S53: preprocessing the deformation data after preliminary processing to obtain standard deformation data, and adding corresponding metadata tags to each parameter in the standard deformation data; storing the standard deformation data; Step S54: inputting the standard deformation data into a deformation prediction model to output a deformation prediction value; inputting the standard deformation data into a health assessment unit to obtain a health score; in the case that the change amount of the deformation prediction value is greater than a first threshold value within a target time length, and / or in the case that the health score is less than a second threshold value, sending a red early warning information.

[0065] Based on the same inventive concept, an embodiment of the present application provides an electronic device, referring to Figure 6 , Figure 6 is a schematic diagram of an electronic device according to an embodiment of the present application. As Figure 6 shown, the electronic device 100 comprises a memory 110 and a processor 120, the memory 110 and the processor 120 are in communication connection through a bus, the memory 110 stores a computer program, the computer program can run on the processor 120, and then realize the steps in the wind turbine tower deformation real-time monitoring and early warning method based on Internet of Things security described in the above embodiments of the present application.

[0066] Based on the same inventive concept, the present disclosure further provides a computer readable storage medium, when the instructions in the computer readable storage medium are executed by the processor of the computer device, the computer device can execute the steps in the wind turbine tower deformation real-time monitoring and early warning method based on Internet of Things security described in the above embodiments of the present application.

[0067] Each embodiment in the specification is described in a progressive manner, and each embodiment focuses on the difference from other embodiments. The same and similar parts between each embodiment can be referred to each other.

[0068] Those skilled in the art will appreciate that embodiments of the application can be readily used as software, hardware, or a combination of software and hardware. In one embodiment, the application can be implemented in software and / or firmware. In particular, the application forms part of the software and / or firmware of a terminal device. The software and / or firmware can be executed on a processor-based platform.

[0069] Embodiments of the application are described herein with reference to the drawings, in which are shown flowcharts and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the application. It will be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processing device, or other programmable data processing terminal devices to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal devices, create means for implementing the functions specified in the flowcharts and / or block diagrams block or blocks. Figure 1 one or more functions specified by one or more blocks Figure 1 one or more blocks.

[0070] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing terminal devices to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the function specified in the flowcharts and / or block diagrams block or blocks. Figure 1 one or more functions specified by one or more blocks Figure 1 one or more blocks.

[0071] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal devices to cause a series of operational steps to be performed on the computer or other programmable terminal devices to produce a computer-implemented process such that the instructions which execute on the computer or other programmable terminal devices provide steps for implementing the functions specified in the flowcharts and / or block diagrams block or blocks. Figure 1 one or more functions specified by one or more blocks Figure 1 one or more blocks.

[0072] While preferred embodiments of the application have been described, modifications and alterations thereto will occur to those skilled in the art upon reading the preceding description. In particular, it is apparent that those skilled in the art will be able to devise many embodiments that, although not explicitly described herein, embody the principles of the application and, as such, are within the spirit and scope of the application. Accordingly, it is not intended that the application be limited, except as by the appended claims.

[0073] Finally, it is to be understood that the phraseology or terminology such as "first" and "second" etc. used herein is merely intended to differentiate one entity or operation from another entity or operation, without necessarily requiring or implying any actual such relationship or order between such entities or operations. Moreover, the terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by "comprises... a" does not, without more constraints, exclude the existence of additional identical elements in the process, method, article, or apparatus that comprises the element.

[0074] The above provides a kind of based on the safety of Internet of Things fan tower cylinder deformation real-time monitoring and early warning system, method and equipment, the principle and implementation of the present application are described in this paper by applying specific examples, the above example is only for helping to understand the method of the present application and its core idea;For the general technical personnel in the art, according to the idea of the present application, there will be changes in specific implementation and application range, as described above, the content of the specification should not be understood as the limitation of the present application.

Claims

1. An Internet of Things security-based fan tower drum deformation real-time monitoring and early warning system, characterized in that, The system comprises: a sensor module for collecting deformation data of a fan tower drum, the deformation data comprising strain data of a distributed optical fiber, inclination data, micro-strain data, vibration data, wind load spectrum and temperature and humidity parameters; a data acquisition and transmission module for preliminarily processing the deformation data to obtain preliminarily processed deformation data; a data processing and storage module for preprocessing the preliminarily processed deformation data to obtain standard deformation data, adding corresponding metadata tags to each parameter in the standard deformation data, and storing the standard deformation data; a data analysis and early warning module for inputting the standard deformation data into a deformation prediction model to output a deformation prediction value, inputting the standard deformation data into a health assessment unit to obtain a health score, and sending a red early warning information in a case where a change amount of the deformation prediction value is greater than a first threshold value within a target time length and / or the health score is less than a second threshold value; a system management and maintenance module for managing and maintaining the sensor module, the data acquisition and transmission module, the data processing and storage module, and the data analysis and early warning module, and fixing user operation records of each module through a blockchain technology.

2. The wind turbine tower deformation real-time monitoring and early warning system based on the Internet of Things safety according to claim 1, characterized in that, The sensor module comprises a distributed optical fiber sensor, an inclination sensor, a micro-strain gauge, a three-axis vibration sensor, an ultrasonic anemometer and a temperature and humidity sensor.

3. The wind turbine tower deformation real-time monitoring and early warning system based on the Internet of Things safety according to claim 1, characterized in that, The data acquisition and transmission module comprises an edge computing node and a secure communication unit; The edge computing node is configured to eliminate high-frequency noise of each parameter in the deformation data and compress strain data of the distributed optical fiber to obtain edge preprocessed deformation data; The secure communication unit integrates a hardware encryption chip and is configured to encrypt the edge preprocessed deformation data to obtain the preliminarily processed deformation data, and transmit the preliminarily processed deformation data to the data processing and storage module based on LoRa spread spectrum technology.

4. The wind turbine tower deformation real-time monitoring and early warning system based on the Internet of Things safety according to claim 1, characterized in that, The data processing and storage module comprises a data receiving and preprocessing submodule and a distributed storage and management submodule; The data receiving and preprocessing submodule is configured to preprocess the preliminarily processed deformation data through a first processing algorithm to obtain the standard deformation data and add corresponding metadata tags to each parameter in the standard deformation data, and the first processing algorithm at least comprises data cleaning, outlier processing, vibration data spectrum reconstruction and time alignment processing; The distributed storage and management submodule is configured to perform a hierarchical storage strategy according to data value density to store the standard deformation data.

5. The wind turbine tower deformation real-time monitoring and early warning system based on the Internet of Things safety according to claim 1, characterized in that, The data analysis and early warning module comprises a deformation analysis and prediction submodule, a digital twin health assessment submodule and a multi-level early warning and decision support submodule; The deformation analysis and prediction submodule is configured to train an initial deformation prediction model according to historical deformation data and tower drum material attribute data, and update model parameters of the initial deformation prediction model according to a strain energy density constrained physical information loss function to obtain the trained deformation prediction model. The digital twin health assessment submodule is configured to input the standard deformation data into a health assessment unit to obtain a health score; the health assessment unit is configured to calculate strain, stress, and stiffness values of each part of the tower tube according to a three-dimensional geometric model of the tower tube and the standard deformation data, and compare the values with corresponding tower tube material attribute data, and obtain a health score according to a comparison result; The multi-level early warning and decision support submodule is configured to send red early warning information when a change amount of the deformation prediction value is greater than a first threshold value within a target time length, and / or when the health score is less than a second threshold value.

6. The wind turbine tower deformation real-time monitoring and early warning system based on the Internet of Things safety according to claim 5, characterized in that, The deformation analysis and prediction submodule is further configured to: extract vibration spectrum features in the vibration data through fast Fourier transform, and identify a vibration main frequency and a harmonic component according to the vibration spectrum features; generate a strain thermal map of the fan tower tube according to the vibration main frequency, the harmonic component, and strain data of the distributed optical fiber; and obtain a real-time deformation rate through differential calculation according to the tilt data; The multi-level early warning and decision support submodule is further configured to send orange early warning information when there is a continuous abnormal area in the strain thermal map and an offset of the vibration main frequency is greater than a third threshold value; send yellow early warning information when the real-time deformation rate is greater than a fourth threshold value; the level of the yellow early warning information is lower than that of the orange early warning information, and the level of the orange early warning information is lower than that of the red early warning information.

7. The wind turbine tower deformation real-time monitoring and early warning system based on the Internet of Things safety according to claim 5, characterized in that, The digital twin health assessment submodule further includes: input the standard deformation data corresponding to the key components into a material fatigue damage accumulation model to obtain a structural cumulative damage degree of the key components; and calculate a remaining use cycle of the key components according to the structural cumulative damage degree of the key components and a damage growth rate; the material fatigue damage accumulation model is configured to input the standard deformation data corresponding to the key components and output a structural cumulative damage degree of the key components.

8. The wind turbine tower deformation real-time monitoring and early warning system based on the Internet of Things safety according to claim 5, characterized in that, The multi-level early warning and decision support submodule is further configured to: calculate a risk index of the fan tower tube according to the standard deformation data; dynamically adjust a decision threshold value according to a season and a geological condition of an area where the fan tower tube is located; send early warning processing information when the risk index is greater than the decision threshold value, and generate a maintenance scheme by matching a historical similar event based on a case library according to the standard deformation data.

9. A wind turbine tower deformation real-time monitoring and early warning method based on Internet of Things security, characterized in that, The method includes: collecting deformation data of a fan tower tube, the deformation data including strain data, tilt data, micro-strain data, vibration data, wind load spectrum, and temperature and humidity parameters of a distributed optical fiber; preliminarily processing the deformation data to obtain preliminarily processed deformation data; preprocessing the preliminarily processed deformation data to obtain standard deformation data, and adding corresponding metadata tags to each parameter in the standard deformation data; and storing the standard deformation data; The standard deformation data is input into a deformation prediction model to output a deformation prediction value, and is input into a health assessment unit to obtain a health score. Red alert information is sent in a case where a change amount of the deformation prediction value is greater than a first threshold value within a target time length, and / or in a case where the health score is less than a second threshold value.

10. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The computer program is executed by the processor to implement the fan tower drum deformation real-time monitoring and early warning method based on Internet of Things security according to claim 9.

Images